Copyright (C) 1995-2024 FinalWire Ltd. All rights reserved. aida_bench64.dll build: 4.7.912.8 Dec 20 2024 12:30:07 Arch:X64 CPUCount:8 NUMA:0 Freq: 2419.14MHz Priority:080 OS:6.3.22631 Memory: 8086296KB AllocGran:0x00010000 P:0x00001000 LP:0x0000000000200000 Memory To Test:32768KB 4K DTLB:1024 2M DTLB:512 1G DTLB:512 CLFlush:64 ProcMask: 0x00000000000000ff Features: X86,TSC,X87,CMOV,MMX,SSE,SSE2,SSE3,AMD64,SSSE3,ABM,SSE4.1,SSE4.2,POPCNT,LAHF,CMPX8,CMPX16,AESNI,CLMUL,AVX,FMA3,MOVBE,F16C,HTT,RDRAND,FSGSBASE,BMI,CLFLUSH,X2APIC,TSCINV,RDTSCP,3DNOWPREF,LNOP,AVX2,BMI2,ERMS,PSE,RDSEED,ADX,SMAP,PAGE1GB,PT,SHA,AVX512F,AVX512CD,CLFLUSHOPT,RDT_A,AVX512DQ,AVX512BW,AVX512VL,AVX512_IFMA,AVX512_VBMI,CLWB,PKU,UMIP,RDPID,AVX512_VPOPCNTDQ,AVX512_VBMI2,AVX512_VNNI,AVX512_BITALG,VAES,GFNI,VPCLMULQDQ,AVX512_VP2INTERSECT,MOVDIRI,MOVDIR64B,KEYLOCK,WIDE_KL,FSRM, CPU#000 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#000 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#000 AffMask: 0x0000000000000001 CPU#000 PhysMask:0x00000000000000ff CPU#000 APIC_ID:0x00000000 Phys_ID:000 Core_ID:00 SMT_ID:00 CPU#000 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000003 CPU#000 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000003 CPU#000 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:0000000000000003, non-inclusive CPU#000 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#000 L1I 4K TLB: 128 entries, 8 way, SMask:0000000000000003 CPU#000 L1I 2M TLB: 16 entries, 8 way, SMask:0000000000000003 CPU#000 L1D 4K TLB(loads): 64 entries, 4 way, SMask:0000000000000003 CPU#000 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000003 CPU#000 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000003 CPU#000 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000003 CPU#000 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#000 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#001 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#001 AffMask: 0x0000000000000002 CPU#001 PhysMask:0x00000000000000ff CPU#001 APIC_ID:0x00000001 Phys_ID:000 Core_ID:00 SMT_ID:01 CPU#001 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000003 CPU#001 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000003 CPU#001 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:0000000000000003, non-inclusive CPU#001 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#001 L1I 4K TLB: 128 entries, 8 way, SMask:0000000000000003 CPU#001 L1I 2M TLB: 16 entries, 8 way, SMask:0000000000000003 CPU#001 L1D 4K TLB(loads): 64 entries, 4 way, SMask:0000000000000003 CPU#001 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000003 CPU#001 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000003 CPU#001 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000003 CPU#001 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#002 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#002 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#002 AffMask: 0x0000000000000004 CPU#002 PhysMask:0x00000000000000ff CPU#002 APIC_ID:0x00000002 Phys_ID:000 Core_ID:01 SMT_ID:00 CPU#002 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:000000000000000c CPU#002 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:000000000000000c CPU#002 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:000000000000000c, non-inclusive CPU#002 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#002 L1I 4K TLB: 128 entries, 8 way, SMask:000000000000000c CPU#002 L1I 2M TLB: 16 entries, 8 way, SMask:000000000000000c CPU#002 L1D 4K TLB(loads): 64 entries, 4 way, SMask:000000000000000c CPU#002 L1D 2M TLB(loads): 32 entries, 4 way, SMask:000000000000000c CPU#002 L1D 1G TLB(loads): 8 entries, full, SMask:000000000000000c CPU#002 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:000000000000000c CPU#002 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#002 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#003 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#003 AffMask: 0x0000000000000008 CPU#003 PhysMask:0x00000000000000ff CPU#003 APIC_ID:0x00000003 Phys_ID:000 Core_ID:01 SMT_ID:01 CPU#003 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:000000000000000c CPU#003 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:000000000000000c CPU#003 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:000000000000000c, non-inclusive CPU#003 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#003 L1I 4K TLB: 128 entries, 8 way, SMask:000000000000000c CPU#003 L1I 2M TLB: 16 entries, 8 way, SMask:000000000000000c CPU#003 L1D 4K TLB(loads): 64 entries, 4 way, SMask:000000000000000c CPU#003 L1D 2M TLB(loads): 32 entries, 4 way, SMask:000000000000000c CPU#003 L1D 1G TLB(loads): 8 entries, full, SMask:000000000000000c CPU#003 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:000000000000000c CPU#003 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#004 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#004 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#004 AffMask: 0x0000000000000010 CPU#004 PhysMask:0x00000000000000ff CPU#004 APIC_ID:0x00000004 Phys_ID:000 Core_ID:02 SMT_ID:00 CPU#004 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000030 CPU#004 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000030 CPU#004 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:0000000000000030, non-inclusive CPU#004 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#004 L1I 4K TLB: 128 entries, 8 way, SMask:0000000000000030 CPU#004 L1I 2M TLB: 16 entries, 8 way, SMask:0000000000000030 CPU#004 L1D 4K TLB(loads): 64 entries, 4 way, SMask:0000000000000030 CPU#004 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000030 CPU#004 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000030 CPU#004 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000030 CPU#004 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000030 CPU#004 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000030 CPU#005 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#005 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#005 AffMask: 0x0000000000000020 CPU#005 PhysMask:0x00000000000000ff CPU#005 APIC_ID:0x00000005 Phys_ID:000 Core_ID:02 SMT_ID:01 CPU#005 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000030 CPU#005 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000030 CPU#005 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:0000000000000030, non-inclusive CPU#005 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#005 L1I 4K TLB: 128 entries, 8 way, SMask:0000000000000030 CPU#005 L1I 2M TLB: 16 entries, 8 way, SMask:0000000000000030 CPU#005 L1D 4K TLB(loads): 64 entries, 4 way, SMask:0000000000000030 CPU#005 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000030 CPU#005 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000030 CPU#005 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000030 CPU#005 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000030 CPU#005 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000030 CPU#006 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#006 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#006 AffMask: 0x0000000000000040 CPU#006 PhysMask:0x00000000000000ff CPU#006 APIC_ID:0x00000006 Phys_ID:000 Core_ID:03 SMT_ID:00 CPU#006 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:00000000000000c0 CPU#006 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:00000000000000c0 CPU#006 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:00000000000000c0, non-inclusive CPU#006 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#006 L1I 4K TLB: 128 entries, 8 way, SMask:00000000000000c0 CPU#006 L1I 2M TLB: 16 entries, 8 way, SMask:00000000000000c0 CPU#006 L1D 4K TLB(loads): 64 entries, 4 way, SMask:00000000000000c0 CPU#006 L1D 2M TLB(loads): 32 entries, 4 way, SMask:00000000000000c0 CPU#006 L1D 1G TLB(loads): 8 entries, full, SMask:00000000000000c0 CPU#006 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:00000000000000c0 CPU#006 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:00000000000000c0 CPU#006 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:00000000000000c0 CPU#007 Vendor: GenuineIntel Family: 6 Model: 8c Stepping: 1 CoreType:0x200806c1 CPU#007 Type: "11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz" CPU#007 AffMask: 0x0000000000000080 CPU#007 PhysMask:0x00000000000000ff CPU#007 APIC_ID:0x00000007 Phys_ID:000 Core_ID:03 SMT_ID:01 CPU#007 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:00000000000000c0 CPU#007 L1D cache: 48KB, 64 byte cache line, 12 way, SMask:00000000000000c0 CPU#007 L2 cache: 1280KB, 64 byte cache line, 20 way, SMask:00000000000000c0, non-inclusive CPU#007 L3 cache: 8192KB, 64 byte cache line, 8 way, SMask:00000000000000ff, non-inclusive CPU#007 L1I 4K TLB: 128 entries, 8 way, SMask:00000000000000c0 CPU#007 L1I 2M TLB: 16 entries, 8 way, SMask:00000000000000c0 CPU#007 L1D 4K TLB(loads): 64 entries, 4 way, SMask:00000000000000c0 CPU#007 L1D 2M TLB(loads): 32 entries, 4 way, SMask:00000000000000c0 CPU#007 L1D 1G TLB(loads): 8 entries, full, SMask:00000000000000c0 CPU#007 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:00000000000000c0 CPU#007 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:00000000000000c0 CPU#007 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:00000000000000c0 Instruction Latency: Used CPUs: 1 ProcMask: 0x0000000000000008 0 X86 :NOP L: [no true dep.] T: 0.12ns= 0.290c 1 X86 :0x66 NOP L: [no true dep.] T: 0.09ns= 0.210c 2 X86 : 2x 0x66 NOP L: [no true dep.] T: 0.09ns= 0.211c 3 X86 : 3x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.267c 4 X86 : 4x 0x66 NOP L: [no true dep.] T: 0.12ns= 0.300c 5 X86 : 5x 0x66 NOP L: [no true dep.] T: 0.15ns= 0.362c 6 X86 : 6x 0x66 NOP L: [no true dep.] T: 0.13ns= 0.322c 7 X86 : 7x 0x66 NOP L: [no true dep.] T: 0.15ns= 0.373c 8 X86 : 8x 0x66 NOP L: [no true dep.] T: 0.22ns= 0.541c 9 X86 : 9x 0x66 NOP L: [no true dep.] T: 0.15ns= 0.370c 10 X86 :10x 0x66 NOP L: [no true dep.] T: 0.10ns= 0.232c 11 X86 :11x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.261c 12 X86 :12x 0x66 NOP L: [no true dep.] T: 0.14ns= 0.337c 13 X86 :13x 0x66 NOP L: [no true dep.] T: 0.19ns= 0.463c 14 X86 :14x 0x66 NOP L: [no true dep.] T: 0.22ns= 0.526c 15 SSE2 :PAUSE L: [no true dep.] T: 58.01ns= 140.337c 16 X86 :MOV r8, imm8 L: 0.42ns= 1.01c T: 0.11ns= 0.259c 17 X86 :MOV r16, imm16 L: 0.45ns= 1.10c T: 0.38ns= 0.926c 18 X86 :MOV r32, imm32 L: 0.10ns= 0.25c T: 0.11ns= 0.256c 19 AMD64 :MOV r64, imm64 L: 0.26ns= 0.63c T: 0.26ns= 0.635c 20 X86 :MOV r8, r8 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 21 X86 :MOV r16, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 22 X86 :MOV r32, r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 23 AMD64 :MOV r64, r64 L: 0.42ns= 1.01c T: 0.11ns= 0.276c 24 X86 :MOV r8, [m8] L: 2.50ns= 6.05c T: 0.21ns= 0.505c 25 X86 :MOV r16, [m16] L: 2.50ns= 6.05c T: 0.21ns= 0.505c 26 X86 :MOV r32, [m32] L: 2.08ns= 5.04c T: 0.21ns= 0.505c 27 AMD64 :MOV r64, [m64] L: 2.08ns= 5.04c T: 0.21ns= 0.505c 28 X86 :MOV [m8], r8 L: [memory dep.] T: 0.21ns= 0.505c 29 X86 :MOV [m16], r16 L: [memory dep.] T: 0.21ns= 0.505c 30 X86 :MOV [m32], r32 L: [memory dep.] T: 0.21ns= 0.505c 31 X86 :MOV [m32 + 2], r32 L: [memory dep.] T: 0.21ns= 0.498c 32 AMD64 :MOV [m64], r64 L: [memory dep.] T: 0.21ns= 0.505c 33 AMD64 :MOV [m64 + 4], r64 L: [memory dep.] T: 0.21ns= 0.498c 34 X86 :MOV r8,[m8]+MOV [m8],r8 L: 0.42ns= 1.01c T: 0.29ns= 0.708c 35 X86 :MOV r16,[m16]+MOV [m16],r16 L: 5.01ns= 12.13c T: 0.29ns= 0.708c 36 X86 :MOV r32,[m32]+MOV [m32],r32 L: 0.20ns= 0.50c T: 0.29ns= 0.707c 37 AMD64 :MOV r64,[m64]+MOV [m64],r64 L: 0.20ns= 0.50c T: 0.33ns= 0.809c 38 SSE2 :MOVNTI [m32], r32 L: [memory dep.] T: 3.28ns= 3.279c 39 AMD64 :MOVNTI [m64], r64 L: [memory dep.] T: 3.13ns= 3.125c 40 CMOV :CMOVNZ r16, r16 L: 0.42ns= 1.01c T: 0.25ns= 0.613c 41 CMOV :CMOVNZ r32, r32 L: 0.42ns= 1.01c T: 0.23ns= 0.561c 42 AMD64 :CMOVNZ r64, r64 L: 0.42ns= 1.01c T: 0.23ns= 0.545c 43 X86 :MOVSX r16, r8 L: 0.42ns= 1.01c T: 0.12ns= 0.279c 44 X86 :MOVSX r32, r8 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 45 AMD64 :MOVSX r64, r8 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 46 X86 :MOVSX r32, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 47 AMD64 :MOVSX r64, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 48 AMD64 :MOVSXD r64, r32 L: 0.42ns= 1.01c T: 0.12ns= 0.290c 49 X86 :MOVZX r16, r8 L: 0.42ns= 1.01c T: 0.12ns= 0.279c 50 X86 :MOVZX r32, r8 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 51 AMD64 :MOVZX r64, r8 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 52 X86 :MOVZX r32, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 53 AMD64 :MOVZX r64, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 54 X86 :XCHG r8, r8 L: 0.86ns= 2.09c T: 0.42ns= 1.011c 55 X86 :XCHG r16, r16 L: 0.86ns= 2.08c T: 0.42ns= 1.011c 56 X86 :XCHG r32, r32 L: 0.86ns= 2.08c T: 0.42ns= 1.010c 57 AMD64 :XCHG r64, r64 L: 0.86ns= 2.08c T: 0.42ns= 1.010c 58 X86 :XCHG r1_8, r2_8 L: 0.64ns= 1.55c T: 0.84ns= 2.021c 59 X86 :XCHG r1_16, r2_16 L: 0.64ns= 1.55c T: 0.84ns= 2.021c 60 X86 :XCHG r1_32, r2_32 L: 0.64ns= 1.55c T: 0.84ns= 2.021c 61 AMD64 :XCHG r1_64, r2_64 L: 0.64ns= 1.55c T: 0.84ns= 2.021c 62 X86 :XCHG r8, [m8] L: 8.77ns= 21.22c T: 7.94ns= 19.200c 63 X86 :XCHG r16, [m16] L: 8.77ns= 21.22c T: 7.94ns= 19.200c 64 X86 :XCHG r32, [m32] L: 8.77ns= 21.22c T: 7.94ns= 19.200c 65 AMD64 :XCHG r64, [m64] L: 8.77ns= 21.22c T: 7.94ns= 19.200c 66 X86 :ADD r8, r8 L: 0.42ns= 1.01c T: 0.11ns= 0.260c 67 X86 :ADD r16, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 68 X86 :ADD r32, r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 69 AMD64 :ADD r64, r64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 70 X86 :ADD r1_8, r2_8 L: 0.42ns= 1.01c T: 0.11ns= 0.258c 71 X86 :ADD r1_16, r2_16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 72 X86 :ADD r1_32, r2_32 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 73 AMD64 :ADD r1_64, r2_64 L: 0.42ns= 1.01c T: 0.11ns= 0.261c 74 X86 :ADD r8, [m8] L: 2.50ns= 6.05c T: 0.21ns= 0.505c 75 X86 :ADD r16, [m16] L: 2.50ns= 6.05c T: 0.21ns= 0.505c 76 X86 :ADD r32, [m32] L: 2.50ns= 6.05c T: 0.21ns= 0.505c 77 AMD64 :ADD r64, [m64] L: 2.50ns= 6.05c T: 0.21ns= 0.505c 78 X86 :ADD [m8], r8 L: 3.17ns= 7.67c T: 0.39ns= 0.935c 79 X86 :ADD [m16], r16 L: 3.16ns= 7.64c T: 0.39ns= 0.944c 80 X86 :ADD [m32], r32 L: 3.17ns= 7.67c T: 0.42ns= 1.010c 81 X86 :ADD [m32 + 2], r32 L: 3.17ns= 7.66c T: 3.17ns= 7.672c 82 AMD64 :ADD [m64], r64 L: 3.16ns= 7.65c T: 0.40ns= 0.961c 83 AMD64 :ADD [m64 + 4], r64 L: 3.13ns= 7.58c T: 3.14ns= 7.587c 84 X86 :LOCK ADD [m8], r8 L: 8.77ns= 21.22c T: 7.94ns= 19.211c 85 X86 :LOCK ADD [m16], r16 L: 8.77ns= 21.22c T: 7.94ns= 19.202c 86 X86 :LOCK ADD [m32], r32 L: 8.77ns= 21.22c T: 7.94ns= 19.203c 87 X86 :LOCK ADD [m32 + 2], r32 L: 8.77ns= 21.22c T: 8.77ns= 21.219c 88 AMD64 :LOCK ADD [m64], r64 L: 8.77ns= 21.22c T: 7.94ns= 19.202c 89 AMD64 :LOCK ADD [m64 + 4], r64 L: 8.77ns= 21.22c T: 8.77ns= 21.219c 90 X86 :ADD r8, imm8 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 91 X86 :ADD r16, imm8 L: 0.42ns= 1.01c T: 0.11ns= 0.256c 92 X86 :ADD r32, imm8 L: 0.42ns= 1.01c T: 0.11ns= 0.254c 93 AMD64 :ADD r64, imm8 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 94 X86 :ADD r16, imm16 L: 1.38ns= 3.34c T: 1.39ns= 3.371c 95 X86 :ADD r32, imm32 L: 0.42ns= 1.01c T: 0.14ns= 0.349c 96 AMD64 :ADD r64, imm32 L: 0.42ns= 1.01c T: 0.16ns= 0.383c 97 X86 :ADD [m8], imm8 L: 3.15ns= 7.62c T: 0.40ns= 0.975c 98 X86 :ADD [m16], imm8 L: 3.15ns= 7.62c T: 0.41ns= 0.986c 99 X86 :ADD [m32], imm8 L: 3.14ns= 7.60c T: 0.40ns= 0.976c 100 AMD64 :ADD [m64], imm8 L: 3.13ns= 7.57c T: 0.41ns= 0.981c 101 X86 :ADD [m16], imm16 L: 3.13ns= 7.57c T: 1.30ns= 3.148c 102 X86 :ADD [m32], imm32 L: 3.15ns= 7.62c T: 0.40ns= 0.974c 103 AMD64 :ADD [m64], imm32 L: 3.15ns= 7.62c T: 0.40ns= 0.976c 104 X86 :ADD al, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 105 X86 :ADD ax, imm16 L: 1.36ns= 3.28c T: 1.36ns= 3.284c 106 X86 :ADD eax, imm32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 107 AMD64 :ADD rax, imm32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 108 X86 :SUB r8, r8 L: 0.42ns= 1.01c T: 0.11ns= 0.259c 109 X86 :SUB r16, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 110 X86 :SUB r32, r32 L: 0.08ns= 0.20c T: 0.09ns= 0.208c 111 AMD64 :SUB r64, r64 L: 0.08ns= 0.20c T: 0.09ns= 0.221c 112 X86 :SUB r1_8, r2_8 L: 0.42ns= 1.01c T: 0.11ns= 0.258c 113 X86 :SUB r1_16, r2_16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 114 X86 :SUB r1_32, r2_32 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 115 AMD64 :SUB r1_64, r2_64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 116 X86 :ADC r8, r8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 117 X86 :ADC r16, r16 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 118 X86 :ADC r32, r32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 119 AMD64 :ADC r64, r64 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 120 X86 :SBB r8, r8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 121 X86 :SBB r16, r16 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 122 X86 :SBB r32, r32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 123 AMD64 :SBB r64, r64 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 124 X86 :SBB r1_8, r2_8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 125 X86 :SBB r1_16, r2_16 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 126 X86 :SBB r1_32, r2_32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 127 AMD64 :SBB r1_64, r2_64 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 128 X86 :CMP r8, r8 L: [no true dep.] T: 0.11ns= 0.262c 129 X86 :CMP r16, r16 L: [no true dep.] T: 0.12ns= 0.299c 130 X86 :CMP r32, r32 L: [no true dep.] T: 0.11ns= 0.267c 131 AMD64 :CMP r64, r64 L: [no true dep.] T: 0.11ns= 0.276c 132 X86 :CMP r1_8, r2_8 L: [no true dep.] T: 0.11ns= 0.264c 133 X86 :CMP r1_16, r2_16 L: [no true dep.] T: 0.10ns= 0.253c 134 X86 :CMP r1_32, r2_32 L: [no true dep.] T: 0.12ns= 0.281c 135 AMD64 :CMP r1_64, r2_64 L: [no true dep.] T: 0.11ns= 0.277c 136 X86 :AND r8, r8 L: 0.42ns= 1.01c T: 0.11ns= 0.259c 137 X86 :AND r16, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 138 X86 :AND r32, r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 139 AMD64 :AND r64, r64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 140 X86 :AND r1_8, r2_8 L: 0.42ns= 1.01c T: 0.11ns= 0.258c 141 X86 :AND r1_16, r2_16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 142 X86 :AND r1_32, r2_32 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 143 AMD64 :AND r1_64, r2_64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 144 X86 :OR r8, r8 L: 0.42ns= 1.01c T: 0.11ns= 0.260c 145 X86 :OR r16, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 146 X86 :OR r32, r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 147 AMD64 :OR r64, r64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 148 X86 :OR r1_8, r2_8 L: 0.42ns= 1.01c T: 0.11ns= 0.258c 149 X86 :OR r1_16, r2_16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 150 X86 :OR r1_32, r2_32 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 151 AMD64 :OR r1_64, r2_64 L: 0.42ns= 1.01c T: 0.11ns= 0.261c 152 X86 :XOR r8, r8 L: 0.42ns= 1.01c T: 0.11ns= 0.259c 153 X86 :XOR r16, r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 154 X86 :XOR r32, r32 L: 0.08ns= 0.19c T: 0.09ns= 0.208c 155 AMD64 :XOR r64, r64 L: 0.08ns= 0.20c T: 0.09ns= 0.223c 156 X86 :XOR r1_8, r2_8 L: 0.42ns= 1.01c T: 0.11ns= 0.258c 157 X86 :XOR r1_16, r2_16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 158 X86 :XOR r1_32, r2_32 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 159 AMD64 :XOR r1_64, r2_64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 160 X86 :NEG r8 L: 0.42ns= 1.01c T: 0.11ns= 0.260c 161 X86 :NEG r16 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 162 X86 :NEG r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 163 AMD64 :NEG r64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 164 X86 :NOT r8 L: 0.42ns= 1.01c T: 0.11ns= 0.259c 165 X86 :NOT r16 L: 0.42ns= 1.01c T: 0.11ns= 0.263c 166 X86 :NOT r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 167 AMD64 :NOT r64 L: 0.42ns= 1.01c T: 0.11ns= 0.261c 168 X86 :TEST r8, r8 L: [no true dep.] T: 0.11ns= 0.262c 169 X86 :TEST r16, r16 L: [no true dep.] T: 0.10ns= 0.252c 170 X86 :TEST r32, r32 L: [no true dep.] T: 0.11ns= 0.266c 171 AMD64 :TEST r64, r64 L: [no true dep.] T: 0.11ns= 0.276c 172 X86 :TEST r1_8, r2_8 L: [no true dep.] T: 0.11ns= 0.265c 173 X86 :TEST r1_16, r2_16 L: [no true dep.] T: 0.10ns= 0.253c 174 X86 :TEST r1_32, r2_32 L: [no true dep.] T: 0.12ns= 0.281c 175 AMD64 :TEST r1_64, r2_64 L: [no true dep.] T: 0.11ns= 0.275c 176 X86 :BT r16, r16 L: [no true dep.] T: 0.31ns= 0.757c 177 X86 :BT r32, r32 L: [no true dep.] T: 0.32ns= 0.782c 178 AMD64 :BT r64, r64 L: [no true dep.] T: 0.31ns= 0.742c 179 X86 :BT r16, imm8 L: [no true dep.] T: 0.24ns= 0.588c 180 X86 :BT r32, imm8 L: [no true dep.] T: 0.31ns= 0.757c 181 AMD64 :BT r64, imm8 L: [no true dep.] T: 0.33ns= 0.791c 182 X86 :BTC r16, r16 L: 0.42ns= 1.01c T: 0.25ns= 0.615c 183 X86 :BTC r32, r32 L: 0.42ns= 1.01c T: 0.23ns= 0.563c 184 AMD64 :BTC r64, r64 L: 0.42ns= 1.01c T: 0.23ns= 0.546c 185 X86 :BTC r16, imm8 L: 0.42ns= 1.01c T: 0.22ns= 0.526c 186 X86 :BTC r32, imm8 L: 0.42ns= 1.01c T: 0.25ns= 0.613c 187 AMD64 :BTC r64, imm8 L: 0.42ns= 1.01c T: 0.30ns= 0.715c 188 X86 :BTR r16, r16 L: 0.42ns= 1.01c T: 0.25ns= 0.613c 189 X86 :BTR r32, r32 L: 0.42ns= 1.01c T: 0.23ns= 0.563c 190 AMD64 :BTR r64, r64 L: 0.42ns= 1.01c T: 0.23ns= 0.546c 191 X86 :BTR r16, imm8 L: 0.42ns= 1.01c T: 0.22ns= 0.526c 192 X86 :BTR r32, imm8 L: 0.42ns= 1.01c T: 0.25ns= 0.612c 193 AMD64 :BTR r64, imm8 L: 0.42ns= 1.01c T: 0.29ns= 0.701c 194 X86 :BTS r16, r16 L: 0.42ns= 1.01c T: 0.26ns= 0.617c 195 X86 :BTS r32, r32 L: 0.42ns= 1.01c T: 0.23ns= 0.562c 196 AMD64 :BTS r64, r64 L: 0.42ns= 1.01c T: 0.23ns= 0.546c 197 X86 :BTS r16, imm8 L: 0.42ns= 1.01c T: 0.22ns= 0.528c 198 X86 :BTS r32, imm8 L: 0.42ns= 1.01c T: 0.25ns= 0.616c 199 AMD64 :BTS r64, imm8 L: 0.42ns= 1.01c T: 0.29ns= 0.709c 200 X86 :SETC r8 L: 0.42ns= 1.01c T: 0.34ns= 0.820c 201 X86 :INC r8 L: 0.42ns= 1.01c T: 0.11ns= 0.260c 202 X86 :INC r16 L: 0.42ns= 1.01c T: 0.10ns= 0.252c 203 X86 :INC r32 L: 0.42ns= 1.01c T: 0.11ns= 0.255c 204 AMD64 :INC r64 L: 0.42ns= 1.01c T: 0.11ns= 0.262c 205 AMD64 :LEA r16, [r64 + r64] L: 0.83ns= 2.02c T: 0.39ns= 0.938c 206 AMD64 :LEA r32, [r64 + r64] L: 0.42ns= 1.01c T: 0.11ns= 0.275c 207 AMD64 :LEA r64, [r64 + r64] L: 0.42ns= 1.01c T: 0.10ns= 0.253c 208 AMD64 :LEA r16, [r64 + r64 + disp8] L: 0.83ns= 2.02c T: 0.38ns= 0.917c 209 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.42ns= 1.01c T: 0.11ns= 0.261c 210 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.42ns= 1.01c T: 0.12ns= 0.293c 211 AMD64 :LEA r16, [r64 + r64 * 8] L: 0.83ns= 2.02c T: 0.39ns= 0.944c 212 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 213 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 214 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 0.83ns= 2.02c T: 0.38ns= 0.926c 215 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 216 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 217 X86 :SHL r8, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 218 X86 :SHL r16, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 219 X86 :SHL r32, 1 L: 0.42ns= 1.02c T: 0.21ns= 0.505c 220 AMD64 :SHL r64, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 221 X86 :SHL r8, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 222 X86 :SHL r16, imm8 L: 0.42ns= 1.02c T: 0.21ns= 0.505c 223 X86 :SHL r32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 224 AMD64 :SHL r64, imm8 L: 0.42ns= 1.02c T: 0.23ns= 0.568c 225 X86 :SHL r8, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 226 X86 :SHL r16, cl L: 0.66ns= 1.59c T: 0.42ns= 1.010c 227 X86 :SHL r32, cl L: 0.46ns= 1.11c T: 0.42ns= 1.011c 228 AMD64 :SHL r64, cl L: 0.66ns= 1.60c T: 0.42ns= 1.011c 229 X86 :SHR r8, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 230 X86 :SHR r16, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 231 X86 :SHR r32, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 232 AMD64 :SHR r64, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 233 X86 :SHR r8, imm8 L: 0.42ns= 1.02c T: 0.21ns= 0.505c 234 X86 :SHR r16, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 235 X86 :SHR r32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 236 AMD64 :SHR r64, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 237 X86 :SHR r8, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 238 X86 :SHR r16, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 239 X86 :SHR r32, cl L: 0.46ns= 1.12c T: 0.42ns= 1.011c 240 AMD64 :SHR r64, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 241 X86 :SAR r8, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 242 X86 :SAR r16, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 243 X86 :SAR r32, 1 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 244 AMD64 :SAR r64, 1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 245 X86 :SAR r8, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 246 X86 :SAR r16, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 247 X86 :SAR r32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 248 AMD64 :SAR r64, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 249 X86 :SAR r8, cl L: 0.46ns= 1.11c T: 0.42ns= 1.010c 250 X86 :SAR r16, cl L: 0.46ns= 1.11c T: 0.42ns= 1.011c 251 X86 :SAR r32, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 252 AMD64 :SAR r64, cl L: 0.45ns= 1.09c T: 0.42ns= 1.010c 253 X86 :SHLD r1_16, r1_16, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 254 X86 :SHLD r1_32, r1_32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 255 AMD64 :SHLD r1_64, r1_64, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 256 X86 :SHLD r1_16, r1_16, cl L: 1.75ns= 4.24c T: 0.42ns= 1.011c 257 X86 :SHLD r1_32, r1_32, cl L: 1.76ns= 4.25c T: 0.42ns= 1.010c 258 AMD64 :SHLD r1_64, r1_64, cl L: 1.76ns= 4.25c T: 0.42ns= 1.010c 259 X86 :SHRD r1_16, r1_16, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 260 X86 :SHRD r1_32, r1_32, imm8 L: 0.42ns= 1.02c T: 0.23ns= 0.558c 261 AMD64 :SHRD r1_64, r1_64, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 262 X86 :SHRD r1_16, r1_16, cl L: 1.78ns= 4.32c T: 0.42ns= 1.010c 263 X86 :SHRD r1_32, r1_32, cl L: 1.75ns= 4.24c T: 0.42ns= 1.010c 264 AMD64 :SHRD r1_64, r1_64, cl L: 1.75ns= 4.23c T: 0.42ns= 1.010c 265 X86 :ROL r8, 1 L: 0.46ns= 1.12c T: 0.42ns= 1.010c 266 X86 :ROL r16, 1 L: 0.46ns= 1.12c T: 0.42ns= 1.011c 267 X86 :ROL r32, 1 L: 0.46ns= 1.11c T: 0.42ns= 1.010c 268 AMD64 :ROL r64, 1 L: 0.46ns= 1.12c T: 0.42ns= 1.011c 269 X86 :ROL r8, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 270 X86 :ROL r16, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 271 X86 :ROL r32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 272 AMD64 :ROL r64, imm8 L: 0.42ns= 1.02c T: 0.21ns= 0.505c 273 X86 :ROL r8, cl L: 0.65ns= 1.58c T: 0.42ns= 1.010c 274 X86 :ROL r16, cl L: 0.65ns= 1.58c T: 0.42ns= 1.010c 275 X86 :ROL r32, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 276 AMD64 :ROL r64, cl L: 0.46ns= 1.12c T: 0.42ns= 1.011c 277 X86 :ROR r8, 1 L: 0.46ns= 1.12c T: 0.42ns= 1.010c 278 X86 :ROR r16, 1 L: 0.45ns= 1.10c T: 0.42ns= 1.011c 279 X86 :ROR r32, 1 L: 0.46ns= 1.12c T: 0.42ns= 1.011c 280 AMD64 :ROR r64, 1 L: 0.46ns= 1.12c T: 0.42ns= 1.010c 281 X86 :ROR r8, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 282 X86 :ROR r16, imm8 L: 0.42ns= 1.02c T: 0.21ns= 0.505c 283 X86 :ROR r32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 284 AMD64 :ROR r64, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 285 X86 :ROR r8, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 286 X86 :ROR r16, cl L: 0.46ns= 1.12c T: 0.42ns= 1.011c 287 X86 :ROR r32, cl L: 0.46ns= 1.12c T: 0.42ns= 1.010c 288 AMD64 :ROR r64, cl L: 0.44ns= 1.08c T: 0.42ns= 1.010c 289 X86 :RCL r8, 1 L: 0.84ns= 2.02c T: 0.84ns= 2.021c 290 X86 :RCL r16, 1 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 291 X86 :RCL r32, 1 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 292 AMD64 :RCL r64, 1 L: 0.86ns= 2.08c T: 0.84ns= 2.021c 293 X86 :RCL r8, imm8 L: 2.77ns= 6.71c T: 2.36ns= 5.718c 294 X86 :RCL r16, imm8 L: 2.97ns= 7.18c T: 2.95ns= 7.141c 295 X86 :RCL r32, imm8 L: 2.97ns= 7.19c T: 2.95ns= 7.141c 296 AMD64 :RCL r64, imm8 L: 2.97ns= 7.18c T: 2.95ns= 7.141c 297 X86 :RCL r8, cl L: 2.77ns= 6.70c T: 2.36ns= 5.720c 298 X86 :RCL r16, cl L: 2.97ns= 7.18c T: 2.95ns= 7.142c 299 X86 :RCL r32, cl L: 2.97ns= 7.18c T: 2.95ns= 7.142c 300 AMD64 :RCL r64, cl L: 2.95ns= 7.13c T: 2.95ns= 7.142c 301 X86 :RCR r8, 1 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 302 X86 :RCR r16, 1 L: 0.86ns= 2.08c T: 0.84ns= 2.021c 303 X86 :RCR r32, 1 L: 0.83ns= 2.01c T: 0.84ns= 2.021c 304 AMD64 :RCR r64, 1 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 305 X86 :RCR r8, imm8 L: 3.43ns= 8.30c T: 2.79ns= 6.754c 306 X86 :RCR r16, imm8 L: 2.51ns= 6.08c T: 2.51ns= 6.072c 307 X86 :RCR r32, imm8 L: 2.53ns= 6.12c T: 2.51ns= 6.072c 308 AMD64 :RCR r64, imm8 L: 2.51ns= 6.08c T: 2.51ns= 6.073c 309 X86 :RCR r8, cl L: 3.42ns= 8.28c T: 2.78ns= 6.733c 310 X86 :RCR r16, cl L: 2.51ns= 6.08c T: 2.51ns= 6.069c 311 X86 :RCR r32, cl L: 2.51ns= 6.08c T: 2.51ns= 6.068c 312 AMD64 :RCR r64, cl L: 2.51ns= 6.08c T: 2.51ns= 6.070c 313 X86 :BSF r16, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.019c 314 X86 :BSF r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 315 AMD64 :BSF r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 316 X86 :BSR r16, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 317 X86 :BSR r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 318 AMD64 :BSR r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 319 X86 :BSWAP r32 L: 0.42ns= 1.01c T: 0.36ns= 0.863c 320 AMD64 :BSWAP r64 L: 0.83ns= 2.02c T: 0.42ns= 1.010c 321 MOVBE :MOVBE r16, [m16] L: 2.92ns= 7.06c T: 0.40ns= 0.973c 322 MOVBE :MOVBE r32, [m32] L: 2.50ns= 6.05c T: 0.38ns= 0.919c 323 MOVBE_X64 :MOVBE r64, [m64] L: 2.92ns= 7.07c T: 0.40ns= 0.973c 324 MOVBE :MOVBE [m16], r16 L: [memory dep.] T: 0.39ns= 0.955c 325 MOVBE :MOVBE [m32], r32 L: [memory dep.] T: 0.40ns= 0.977c 326 MOVBE_X64 :MOVBE [m64], r64 L: [memory dep.] T: 0.41ns= 0.990c 327 X86 :IMUL r16, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 328 X86 :IMUL r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 329 AMD64 :IMUL r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 330 X86 :IMUL r16, r16, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 331 X86 :IMUL r32, r32, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 332 AMD64 :IMUL r64, r64, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 333 X86 :IMUL r16, r16, imm16 L: 1.67ns= 4.04c T: 1.25ns= 3.018c 334 X86 :IMUL r32, r32, imm32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 335 AMD64 :IMUL r64, r64, imm32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 336 X86 :IMUL r8l al/eax upd L: 1.25ns= 3.02c T: 0.42ns= 1.010c 337 X86 :IMUL r16 ax/eax upd L: 1.70ns= 4.11c T: 0.62ns= 1.494c 338 X86 :IMUL r32 eax/eax upd L: 1.76ns= 4.26c T: 0.50ns= 1.218c 339 AMD64 :IMUL r64 rax/eax upd L: 1.25ns= 3.03c T: 0.42ns= 1.011c 340 X86 :MUL r8l al/eax upd L: 1.25ns= 3.02c T: 0.42ns= 1.010c 341 X86 :MUL r16 ax/eax upd L: 1.70ns= 4.11c T: 0.62ns= 1.493c 342 X86 :MUL r32 eax/eax upd L: 1.75ns= 4.23c T: 0.50ns= 1.217c 343 AMD64 :MUL r64 rax/eax upd L: 1.25ns= 3.02c T: 0.42ns= 1.010c 344 X86 :IMUL r8l ah/eax upd L: 1.25ns= 3.02c T: 0.42ns= 1.011c 345 X86 :IMUL r16 dx/eax upd L: 2.13ns= 5.15c T: 0.62ns= 1.493c 346 X86 :IMUL r32 edx/eax upd L: 1.75ns= 4.24c T: 0.51ns= 1.227c 347 AMD64 :IMUL r64 rdx/eax upd L: 1.67ns= 4.03c T: 0.42ns= 1.011c 348 X86 :MUL r8l ah/eax upd L: 1.25ns= 3.02c T: 0.42ns= 1.010c 349 X86 :MUL r16 dx/eax upd L: 2.13ns= 5.16c T: 0.62ns= 1.494c 350 X86 :MUL r32 edx/eax upd L: 1.81ns= 4.37c T: 0.50ns= 1.218c 351 AMD64 :MUL r64 rdx/eax upd L: 1.67ns= 4.03c T: 0.42ns= 1.011c 352 X86 :IDIV r8l 14/ 7b L: 6.26ns= 15.13c T: 2.51ns= 6.067c 353 X86 :IDIV r8l 12/ 6b L: 6.26ns= 15.13c T: 2.51ns= 6.064c 354 X86 :IDIV r8l 7/ 7b L: [no true dep.] T: 2.51ns= 6.066c 355 X86 :IDIV r8l 4/ 7b L: [no true dep.] T: 2.51ns= 6.066c 356 X86 :IDIV r8l 0/ 7b L: [no true dep.] T: 2.51ns= 6.065c 357 X86 :IDIV r8l 11/ 4b L: [no true dep.] T: 2.51ns= 6.065c 358 X86 :IDIV r8l 8/ 4b L: [no true dep.] T: 2.51ns= 6.063c 359 X86 :IDIV r8l 4/ 4b L: [no true dep.] T: 2.51ns= 6.065c 360 X86 :IDIV r8l 0/ 4b L: [no true dep.] T: 2.51ns= 6.066c 361 X86 :IDIV r8l 2^12 /2^6 L: [no true dep.] T: 2.51ns= 6.063c 362 X86 :IDIV r8l 1/ 1 no upd L: 6.26ns= 15.13c T: 6.27ns= 15.157c 363 X86 :IDIV r8l 1/ 1 EAX upd L: [no true dep.] T: 2.51ns= 6.063c 364 X86 :IDIV r16 30/15b L: 6.68ns= 16.15c T: 2.51ns= 6.063c 365 X86 :IDIV r16 26/13b L: 6.68ns= 16.17c T: 2.51ns= 6.064c 366 X86 :IDIV r16 15/15b L: [no true dep.] T: 2.51ns= 6.065c 367 X86 :IDIV r16 8/15b L: [no true dep.] T: 2.51ns= 6.063c 368 X86 :IDIV r16 0/15b L: [no true dep.] T: 2.51ns= 6.063c 369 X86 :IDIV r16 23/ 8b L: [no true dep.] T: 2.51ns= 6.062c 370 X86 :IDIV r16 16/ 8b L: [no true dep.] T: 2.51ns= 6.063c 371 X86 :IDIV r16 8/ 8b L: [no true dep.] T: 2.52ns= 6.090c 372 X86 :IDIV r16 0/ 8b L: [no true dep.] T: 2.51ns= 6.065c 373 X86 :IDIV r16 2^28 /2^14 L: [no true dep.] T: 2.51ns= 6.063c 374 X86 :IDIV r16 1/ 1 no upd L: 6.68ns= 16.15c T: 6.68ns= 16.171c 375 X86 :IDIV r16 1/ 1 rAX upd L: 6.67ns= 16.13c T: 6.68ns= 16.171c 376 X86 :IDIV r16 1/ 1 rDX upd L: 4.99ns= 12.08c T: 5.01ns= 12.126c 377 X86 :IDIV r32 62/31b L: 6.26ns= 15.13c T: 2.51ns= 6.066c 378 X86 :IDIV r32 56/28b L: 6.26ns= 15.13c T: 2.51ns= 6.066c 379 X86 :IDIV r32 48/31b L: [no true dep.] T: 2.51ns= 6.066c 380 X86 :IDIV r32 31/31b L: [no true dep.] T: 2.51ns= 6.066c 381 X86 :IDIV r32 16/31b L: [no true dep.] T: 2.51ns= 6.069c 382 X86 :IDIV r32 0/31b L: [no true dep.] T: 2.51ns= 6.071c 383 X86 :IDIV r32 47/16b L: [no true dep.] T: 2.51ns= 6.063c 384 X86 :IDIV r32 32/16b L: [no true dep.] T: 2.51ns= 6.066c 385 X86 :IDIV r32 16/16b L: [no true dep.] T: 2.51ns= 6.070c 386 X86 :IDIV r32 0/16b L: [no true dep.] T: 2.51ns= 6.065c 387 X86 :IDIV r32 2^60 /2^30 L: [no true dep.] T: 2.51ns= 6.069c 388 X86 :IDIV r32 1/ 1 no upd L: 6.26ns= 15.15c T: 6.27ns= 15.158c 389 X86 :IDIV r32 1/ 1 rAX upd L: 6.26ns= 15.13c T: 6.26ns= 15.155c 390 X86 :IDIV r32 1/ 1 rDX upd L: 4.60ns= 11.12c T: 4.60ns= 11.118c 391 AMD64 :IDIV r64 126/63b L: 7.51ns= 18.17c T: 4.18ns= 10.112c 392 AMD64 :IDIV r64 126/63b L: 7.51ns= 18.17c T: 4.18ns= 10.112c 393 AMD64 :IDIV r64 96/63b L: [no true dep.] T: 4.18ns= 10.109c 394 AMD64 :IDIV r64 63/63b L: [no true dep.] T: 4.18ns= 10.107c 395 AMD64 :IDIV r64 32/63b L: [no true dep.] T: 4.18ns= 10.108c 396 AMD64 :IDIV r64 0/63b L: [no true dep.] T: 4.18ns= 10.107c 397 AMD64 :IDIV r64 95/32b L: [no true dep.] T: 4.18ns= 10.114c 398 AMD64 :IDIV r64 64/32b L: [no true dep.] T: 4.18ns= 10.110c 399 AMD64 :IDIV r64 32/32b L: [no true dep.] T: 4.18ns= 10.110c 400 AMD64 :IDIV r64 0/32b L: [no true dep.] T: 4.18ns= 10.104c 401 AMD64 :IDIV r64 2^124/2^62 L: [no true dep.] T: 4.18ns= 10.109c 402 AMD64 :IDIV r64 1/ 1 no upd L: 7.51ns= 18.17c T: 7.52ns= 18.193c 403 AMD64 :IDIV r64 1/ 1 rAX upd L: 7.51ns= 18.17c T: 7.52ns= 18.199c 404 AMD64 :IDIV r64 1/ 1 rDX upd L: 6.26ns= 15.13c T: 6.27ns= 15.156c 405 X86 :DIV r8l 16/ 8b L: 6.26ns= 15.13c T: 2.51ns= 6.065c 406 X86 :DIV r8l 12/ 8b L: [no true dep.] T: 2.51ns= 6.066c 407 X86 :DIV r8l 8/ 8b L: [no true dep.] T: 2.51ns= 6.063c 408 X86 :DIV r8l 4/ 8b L: [no true dep.] T: 2.51ns= 6.065c 409 X86 :DIV r8l 0/ 8b L: [no true dep.] T: 2.51ns= 6.065c 410 X86 :DIV r8l 12/ 4b L: [no true dep.] T: 2.51ns= 6.063c 411 X86 :DIV r8l 8/ 4b L: [no true dep.] T: 2.51ns= 6.064c 412 X86 :DIV r8l 4/ 4b L: [no true dep.] T: 2.51ns= 6.063c 413 X86 :DIV r8l 0/ 4b L: [no true dep.] T: 2.51ns= 6.063c 414 X86 :DIV r8l 2^14 /2^7 L: [no true dep.] T: 2.51ns= 6.064c 415 X86 :DIV r8l 1/ 1 no upd L: 6.26ns= 15.13c T: 6.27ns= 15.157c 416 X86 :DIV r8l 1/ 1 EAX upd L: [no true dep.] T: 2.51ns= 6.063c 417 X86 :DIV r16 32/16b L: 6.68ns= 16.15c T: 2.51ns= 6.063c 418 X86 :DIV r16 30/15b L: 6.68ns= 16.15c T: 2.51ns= 6.063c 419 X86 :DIV r16 24/16b L: [no true dep.] T: 2.51ns= 6.063c 420 X86 :DIV r16 16/16b L: [no true dep.] T: 2.51ns= 6.066c 421 X86 :DIV r16 8/16b L: [no true dep.] T: 2.51ns= 6.062c 422 X86 :DIV r16 0/16b L: [no true dep.] T: 2.51ns= 6.064c 423 X86 :DIV r16 24/ 8b L: [no true dep.] T: 2.51ns= 6.066c 424 X86 :DIV r16 16/ 8b L: [no true dep.] T: 2.51ns= 6.065c 425 X86 :DIV r16 8/ 8b L: [no true dep.] T: 2.51ns= 6.066c 426 X86 :DIV r16 0/ 8b L: [no true dep.] T: 2.51ns= 6.064c 427 X86 :DIV r16 2^30 /2^15 L: [no true dep.] T: 2.51ns= 6.066c 428 X86 :DIV r16 1/ 1 no upd L: 6.68ns= 16.15c T: 6.68ns= 16.170c 429 X86 :DIV r16 1/ 1 rAX upd L: 6.68ns= 16.15c T: 6.68ns= 16.165c 430 X86 :DIV r32 64/32b L: 6.26ns= 15.13c T: 2.51ns= 6.062c 431 X86 :DIV r32 62/31b L: 6.26ns= 15.13c T: 2.51ns= 6.063c 432 X86 :DIV r32 48/32b L: [no true dep.] T: 2.51ns= 6.062c 433 X86 :DIV r32 32/32b L: [no true dep.] T: 2.51ns= 6.062c 434 X86 :DIV r32 16/32b L: [no true dep.] T: 2.51ns= 6.063c 435 X86 :DIV r32 0/32b L: [no true dep.] T: 2.51ns= 6.062c 436 X86 :DIV r32 48/16b L: [no true dep.] T: 2.51ns= 6.062c 437 X86 :DIV r32 32/16b L: [no true dep.] T: 2.51ns= 6.067c 438 X86 :DIV r32 16/16b L: [no true dep.] T: 2.51ns= 6.063c 439 X86 :DIV r32 0/16b L: [no true dep.] T: 2.51ns= 6.063c 440 X86 :DIV r32 2^62 /2^31 L: [no true dep.] T: 2.51ns= 6.066c 441 X86 :DIV r32 1/ 1 no upd L: 6.26ns= 15.13c T: 6.27ns= 15.159c 442 X86 :DIV r32 1/ 1 rAX upd L: 6.26ns= 15.13c T: 6.27ns= 15.158c 443 X86 :DIV r32 1/ 1 rDX upd L: 4.60ns= 11.12c T: 4.60ns= 11.129c 444 AMD64 :DIV r64 128/64b L: 7.51ns= 18.17c T: 4.18ns= 10.109c 445 AMD64 :DIV r64 126/63b L: 7.51ns= 18.17c T: 4.18ns= 10.104c 446 AMD64 :DIV r64 96/64b L: [no true dep.] T: 4.18ns= 10.109c 447 AMD64 :DIV r64 64/64b L: [no true dep.] T: 4.18ns= 10.109c 448 AMD64 :DIV r64 32/64b L: [no true dep.] T: 4.18ns= 10.108c 449 AMD64 :DIV r64 0/64b L: [no true dep.] T: 4.18ns= 10.104c 450 AMD64 :DIV r64 96/32b L: [no true dep.] T: 4.18ns= 10.103c 451 AMD64 :DIV r64 64/32b L: [no true dep.] T: 4.18ns= 10.110c 452 AMD64 :DIV r64 32/32b L: [no true dep.] T: 4.18ns= 10.105c 453 AMD64 :DIV r64 0/32b L: [no true dep.] T: 4.18ns= 10.106c 454 AMD64 :DIV r64 2^126/2^63 L: [no true dep.] T: 4.18ns= 10.104c 455 AMD64 :DIV r64 1/ 1 no upd L: 7.51ns= 18.17c T: 7.52ns= 18.188c 456 AMD64 :DIV r64 1/ 1 rAX upd L: 7.51ns= 18.17c T: 7.52ns= 18.195c 457 AMD64 :DIV r64 1/ 1 rDX upd L: 6.26ns= 15.13c T: 6.27ns= 15.159c 458 X86 :CBW L: 0.42ns= 1.01c T: 0.42ns= 1.010c 459 X86 :CWDE L: 0.42ns= 1.01c T: 0.42ns= 1.011c 460 AMD64 :CDQE L: 0.42ns= 1.01c T: 0.42ns= 1.010c 461 X86 :CWD L: 0.42ns= 1.01c T: 0.42ns= 1.010c 462 X86 :CDQ L: 0.42ns= 1.02c T: 0.42ns= 1.010c 463 AMD64 :CQO L: 0.27ns= 0.64c T: 0.24ns= 0.577c 464 X86 :CLC L: 0.17ns= 0.40c T: 0.10ns= 0.252c 465 X86 :STC L: 0.11ns= 0.25c T: 0.10ns= 0.252c 466 X86 :CMC L: 0.35ns= 0.85c T: 0.41ns= 1.002c 467 X86 :CLD L: 1.69ns= 4.10c T: 1.67ns= 4.043c 468 X86 :STD L: 1.67ns= 4.04c T: 1.67ns= 4.042c 475 LAHF :LAHF L: 1.25ns= 3.02c T: 1.25ns= 3.031c 476 LAHF :SAHF L: 0.61ns= 1.47c T: 0.82ns= 1.994c 483 X86 :PUSH r16 L: [no true dep.] T: 0.21ns= 0.505c 484 X86 :POP r16 L: [no true dep.] T: 0.21ns= 0.505c 485 X86 :PUSH r16 + POP r16 L: 3.13ns= 7.57c T: 0.42ns= 1.015c 486 AMD64 :PUSH r64 L: [no true dep.] T: 0.21ns= 0.505c 487 AMD64 :POP r64 L: [no true dep.] T: 0.21ns= 0.507c 488 AMD64 :PUSH r64 + POP r64 L: 0.22ns= 0.53c T: 0.39ns= 0.936c 489 AMD64 :PUSH imm8 L: [no true dep.] T: 0.21ns= 0.505c 490 AMD64 :PUSH imm8 + POP r64 L: 0.22ns= 0.53c T: 0.34ns= 0.815c 491 AMD64 :PUSH imm32 L: [no true dep.] T: 0.21ns= 0.505c 492 AMD64 :PUSH imm32 + POP r64 L: 0.22ns= 0.53c T: 0.21ns= 0.505c 493 X86 :PUSH [m16] L: [no true dep.] T: 0.38ns= 0.930c 494 X86 :POP [m16] L: [no true dep.] T: 0.38ns= 0.917c 495 X86 :PUSH [m16] + POP [m16] L: 4.19ns= 10.15c T: 0.84ns= 2.021c 496 AMD64 :PUSH [m64] L: [no true dep.] T: 0.38ns= 0.912c 497 AMD64 :POP [m64] L: [no true dep.] T: 0.39ns= 0.934c 498 AMD64 :PUSH [m64] + POP [m64] L: 4.18ns= 10.10c T: 0.84ns= 2.021c 499 X86 :PUSHF L: [no true dep.] T: 0.42ns= 1.010c 501 X86 :PUSHF + POPF L: 10.02ns= 24.25c T: 10.06ns= 24.334c 502 AMD64 :PUSHFQ L: [no true dep.] T: 0.42ns= 1.010c 504 AMD64 :PUSHFQ + POPFQ L: 10.02ns= 24.25c T: 10.06ns= 24.331c 505 X86 :CMPSB L: 1.66ns= 4.02c T: 1.70ns= 4.118c 506 X86 :CMPSW L: 1.68ns= 4.07c T: 1.67ns= 4.043c 507 X86 :CMPSD L: 1.67ns= 4.03c T: 1.67ns= 4.042c 508 AMD64 :CMPSQ L: 1.69ns= 4.09c T: 1.67ns= 4.042c 509 X86 :REPE CMPSB BW in L1D: 0.99 B/c 2383MiB/s 510 X86 :REPE CMPSW BW in L1D: 1.97 B/c 4776MiB/s 511 X86 :REPE CMPSD BW in L1D: 3.94 B/c 9524MiB/s 512 AMD64 :REPE CMPSQ BW in L1D: 7.83 B/c 18946MiB/s 513 X86 :LODSB L: 0.51ns= 1.23c T: 0.51ns= 1.228c 514 X86 :LODSW L: 0.51ns= 1.23c T: 0.51ns= 1.235c 515 X86 :LODSD L: 0.42ns= 1.01c T: 0.42ns= 1.010c 516 AMD64 :LODSQ L: 0.42ns= 1.01c T: 0.42ns= 1.010c 517 X86 :REP LODSB BW in L1D: 0.49 B/c 1191MiB/s 518 X86 :REP LODSW BW in L1D: 0.99 B/c 2384MiB/s 519 X86 :REP LODSD BW in L1D: 1.98 B/c 4779MiB/s 520 AMD64 :REP LODSQ BW in L1D: 3.94 B/c 9538MiB/s 521 X86 :STOSB L: 0.42ns= 1.01c T: 0.40ns= 0.958c 522 X86 :STOSW L: 0.66ns= 1.61c T: 0.42ns= 1.011c 523 X86 :STOSD L: 0.42ns= 1.01c T: 0.42ns= 1.012c 524 AMD64 :STOSQ L: 0.66ns= 1.59c T: 0.42ns= 1.011c 525 X86 :REP STOSB BW in L1D:60.31 B/c 145896MiB/s 526 X86 :REP STOSW BW in L1D:60.31 B/c 145896MiB/s 527 X86 :REP STOSD BW in L1D:60.31 B/c 145896MiB/s 528 AMD64 :REP STOSQ BW in L1D:60.31 B/c 145896MiB/s 529 X86 :MOVSB L: 1.67ns= 4.03c T: 1.67ns= 4.042c 530 X86 :MOVSW L: 1.67ns= 4.03c T: 1.67ns= 4.042c 531 X86 :MOVSD L: 1.67ns= 4.03c T: 1.67ns= 4.042c 532 AMD64 :MOVSQ L: 1.67ns= 4.03c T: 1.67ns= 4.043c 533 X86 :REP MOVSB BW in L1D:117.31 B/c 283784MiB/s 534 X86 :REP MOVSW BW in L1D:118.15 B/c 285831MiB/s 535 X86 :REP MOVSD BW in L1D:118.15 B/c 285831MiB/s 536 AMD64 :REP MOVSQ BW in L1D:118.44 B/c 286519MiB/s 537 X86 :SCASB L: 0.51ns= 1.23c T: 0.69ns= 1.658c 538 X86 :SCASW L: 0.51ns= 1.23c T: 0.52ns= 1.257c 539 X86 :SCASD L: 0.51ns= 1.23c T: 0.51ns= 1.239c 540 AMD64 :SCASQ L: 0.67ns= 1.63c T: 0.56ns= 1.364c 541 X86 :REPNE SCASB BW in L1D: 0.49 B/c 1192MiB/s 542 X86 :REPNE SCASW BW in L1D: 0.99 B/c 2383MiB/s 543 X86 :REPNE SCASD BW in L1D: 1.97 B/c 4776MiB/s 544 AMD64 :REPNE SCASQ BW in L1D: 3.94 B/c 9527MiB/s 545 X86 :XADD r8, r8 L: 0.86ns= 2.08c T: 0.42ns= 1.011c 546 X86 :XADD r16, r16 L: 0.86ns= 2.08c T: 0.42ns= 1.010c 547 X86 :XADD r32, r32 L: 0.86ns= 2.08c T: 0.42ns= 1.010c 548 AMD64 :XADD r64, r64 L: 0.86ns= 2.08c T: 0.42ns= 1.010c 549 X86 :CMPXCHG r8, r8 L: 2.42ns= 5.86c T: 2.09ns= 5.052c 550 X86 :CMPXCHG r16, r16 L: 2.08ns= 5.04c T: 2.09ns= 5.053c 551 X86 :CMPXCHG r32, r32 L: 2.08ns= 5.04c T: 2.09ns= 5.053c 552 AMD64 :CMPXCHG r64, r64 L: 2.08ns= 5.04c T: 2.09ns= 5.052c 553 CMPX8 :CMPXCHG8B L: 4.59ns= 11.11c T: 4.59ns= 11.115c 554 CMPX16 :CMPXCHG16B L: 6.80ns= 16.45c T: 6.27ns= 15.158c 555 X86 :RDTSC L: [no true dep.] T: 11.32ns= 27.373c 556 X86 :CPUID (EAX = 0) L: 44.40ns= 107.42c T: 44.56ns= 107.798c 557 X86 :CPUID (EAX = 1) L: 90.65ns= 219.29c T: 90.77ns= 219.578c 558 POPCNT :POPCNT r16, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 559 POPCNT :POPCNT r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 560 POPCNT_X64 :POPCNT r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 561 ABM :LZCNT r16, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 562 ABM :LZCNT r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 563 ABM_X64 :LZCNT r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 564 SSE4.2 :CRC32 r32, r8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 565 SSE4.2 :CRC32 r32, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 566 SSE4.2 :CRC32 r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.014c 567 SSE42_X64 :CRC32 r64, r8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 568 SSE42_X64 :CRC32 r64, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 569 X87 :FNOP L: [no true dep.] T: 0.24ns= 0.576c 570 X87 :FXCH st(i) L: 0.21ns= 0.50c T: 0.21ns= 0.505c 571 X87 :FCHS L: 0.42ns= 1.01c T: 0.42ns= 1.010c 572 X87 :FABS L: 0.42ns= 1.01c T: 0.42ns= 1.010c 573 X87 :FTST L: [no true dep.] T: 0.42ns= 1.010c 574 X87 :FXAM L: [no true dep.] T: 0.84ns= 2.028c 575 CMOV :FCMOVE st, st(i) L: 1.25ns= 3.02c T: 0.52ns= 1.263c 576 X87 :FADD st(i), st (st = 0.0) L: 1.25ns= 3.02c T: 0.42ns= 1.010c 577 X87 :FADD st(i), st L: 1.25ns= 3.02c T: 0.42ns= 1.010c 578 X87 :FADD st, st(i), FXCH st(i) L: 1.25ns= 3.02c T: 0.42ns= 1.010c 579 X87 :FMUL st(i), st (st = 0.0) L: 1.67ns= 4.04c T: 0.42ns= 1.010c 580 X87 :FMUL st(i), st L: 1.67ns= 4.04c T: 0.42ns= 1.010c 581 X87 :FMUL st, st(i), FXCH st(i) L: 1.67ns= 4.04c T: 0.42ns= 1.010c 582 X87 :FMUL + FADD st, st(i) L: 2.92ns= 7.06c T: [not enough reg] 583 X87 :FMUL st(2i) FADD st(2i+1) L: 1.67ns= 4.04c T: [not enough reg] 584 X87 :FDIV32 st(i), st L: 5.01ns= 12.13c T: 1.25ns= 3.031c 585 X87 :FDIV64 st(i), st L: 6.26ns= 15.15c T: 1.67ns= 4.041c 586 X87 :FDIV80 st(i), st L: 6.68ns= 16.16c T: 1.88ns= 4.548c 587 X87 :FDIV80 (0.0l/x) L: 5.85ns= 14.14c T: 1.88ns= 4.547c 588 X87 :FDIV80 (x/1.0l) L: 5.85ns= 14.14c T: 1.88ns= 4.546c 589 X87 :FDIV80 (x/2.0l) L: 5.85ns= 14.14c T: 1.88ns= 4.547c 590 X87 :FDIV80 (x/0.5l) L: 5.85ns= 14.14c T: 1.88ns= 4.547c 591 X87 :FSQRT32 st L: 5.43ns= 13.13c T: 1.25ns= 3.031c 592 X87 :FSQRT64 st L: 7.93ns= 19.19c T: 2.51ns= 6.062c 593 X87 :FSQRT80 st L: 8.77ns= 21.21c T: 2.92ns= 7.072c 594 X87 :FSQRT80 (0.0l) L: 5.85ns= 14.14c T: 1.88ns= 4.547c 595 X87 :FSQRT80 (1.0l) L: 5.85ns= 14.14c T: 1.88ns= 4.548c 596 X87 :FDECSTP L: [no true dep.] T: 0.24ns= 0.577c 597 X87 :FINCSTP L: [no true dep.] T: 0.24ns= 0.577c 598 X87 :FCOM st(i) L: [no true dep.] T: 0.42ns= 1.014c 599 CMOV :FCOMI st, st(i) L: [no true dep.] T: 0.42ns= 1.010c 600 X87 :FSIN80 (0.0) L: 24.62ns= 59.57c T: 25.12ns= 60.780c 601 X87 :FSIN80 (0.0) + FADD L: 24.92ns= 60.30c T: 25.09ns= 60.707c 602 X87 :FSIN80 (1.0) + FADD L: 55.13ns= 133.37c T: 55.39ns= 133.993c 603 X87 :FSIN80 (4Pi) + FADD L: 40.86ns= 98.85c T: 40.83ns= 98.772c 604 X87 :FSIN80 (2Pi) + FADD L: 40.86ns= 98.85c T: 40.84ns= 98.790c 605 X87 :FSIN80 (Pi) + FADD L: 40.86ns= 98.85c T: 40.84ns= 98.789c 606 X87 :FSIN80 (Pi/2) + FADD L: 50.23ns= 121.53c T: 48.80ns= 118.051c 607 X87 :FSIN80 (Pi/4) + FADD L: 55.13ns= 133.38c T: 55.41ns= 134.043c 608 X87 :FSIN80 (Pi/8) + FADD L: 47.19ns= 114.17c T: 47.37ns= 114.599c 609 X87 :FSIN80 (Pi/16) + FADD L: 40.86ns= 98.85c T: 40.84ns= 98.798c 610 X87 :FSIN80 (Pi/32) + FADD L: 40.86ns= 98.85c T: 40.84ns= 98.792c 611 X87 :FCOS80 (0.73908513...) L: 54.32ns= 131.41c T: 54.92ns= 132.849c 612 X87 :FCOS80 (0.73908513...)+FADD L: 54.29ns= 131.35c T: 54.57ns= 132.002c 613 X87 :FCOS80 (0.0) + FADD L: 24.05ns= 58.18c T: 24.64ns= 59.598c 614 X87 :FCOS80 (1.0) + FADD L: 46.36ns= 112.15c T: 46.53ns= 112.559c 615 X87 :FCOS80 (4Pi) + FADD L: 48.57ns= 117.49c T: 47.96ns= 116.022c 616 X87 :FCOS80 (2Pi) + FADD L: 48.57ns= 117.49c T: 47.96ns= 116.014c 617 X87 :FCOS80 (Pi) + FADD L: 48.57ns= 117.49c T: 47.96ns= 116.031c 618 X87 :FCOS80 (Pi/2) + FADD L: 41.28ns= 99.87c T: 40.75ns= 98.580c 619 X87 :FCOS80 (Pi/4) + FADD L: 46.36ns= 112.15c T: 46.54ns= 112.576c 620 X87 :FCOS80 (Pi/8) + FADD L: 54.30ns= 131.35c T: 54.56ns= 131.986c 621 X87 :FCOS80 (Pi/16) + FADD L: 48.57ns= 117.49c T: 47.96ns= 116.023c 622 X87 :FCOS80 (Pi/32) + FADD L: 48.57ns= 117.49c T: 47.96ns= 116.029c 623 MMX :EMMS L: 2.92ns= 7.07c T: 2.92ns= 7.075c 624 MMX :MOVD r32, mm L: [diff. reg. set] T: 0.42ns= 1.011c 625 MMX :MOVD mm, r32 L: [diff. reg. set] T: 0.42ns= 1.014c 626 MMX :MOVD r32, mm+MOVD mm, r32 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 627 AMD64 :MOVD r64, mm L: [diff. reg. set] T: 0.42ns= 1.010c 628 AMD64 :MOVD mm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 629 AMD64 :MOVD r64, mm+MOVD mm, r64 L: 1.67ns= 4.04c T: 0.42ns= 1.019c 630 MMX :MOVD mm, [m32] L: [memory dep.] T: 0.21ns= 0.505c 631 MMX :MOVD [m32], mm L: [memory dep.] T: 0.21ns= 0.505c 632 MMX :MOVD mm,[m32]+MOVD [m32],mm L: 2.96ns= 7.15c T: 0.50ns= 1.200c 633 MMX :MOVQ mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 634 MMX :MOVQ mm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 635 MMX :MOVQ [m64], mm L: [memory dep.] T: 0.21ns= 0.505c 636 MMX :MOVQ mm,[m64]+MOVQ [m64],mm L: 2.90ns= 7.01c T: 0.57ns= 1.371c 637 SSE :MOVNTQ [m64], mm L: [memory dep.] T: 3.15ns= 3.154c 638 SSE :PMOVMSKB r32, mm L: [diff. reg. set] T: 0.42ns= 1.010c 639 AMD64 :PMOVMSKB r64, mm L: [diff. reg. set] T: 0.42ns= 1.010c 640 SSE :MASKMOVQ mm, mm L: [memory dep.] T: 2.03ns= 2.029c 641 MMX :PADDB mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 642 MMX :PADDW mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 643 MMX :PADDD mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 644 SSE2 :PADDQ mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.511c 645 MMX :PADDSB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 646 MMX :PADDSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.014c 647 MMX :PADDUSB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 648 MMX :PADDUSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 649 MMX :PSUBB mm, mm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 650 MMX :PSUBB mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 651 MMX :PSUBW mm, mm L: 0.21ns= 0.50c T: 0.21ns= 0.510c 652 MMX :PSUBW mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 653 MMX :PSUBD mm, mm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 654 MMX :PSUBD mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 655 SSE2 :PSUBQ mm, mm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 656 SSE2 :PSUBQ mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.511c 657 MMX :PSUBSB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 658 MMX :PSUBSB mm1, mm2 L: 0.42ns= 1.02c T: 0.42ns= 1.014c 659 MMX :PSUBSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 660 MMX :PSUBSW mm1, mm2 L: 0.42ns= 1.02c T: 0.42ns= 1.014c 661 MMX :PSUBUSB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 662 MMX :PSUBUSB mm1, mm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 663 MMX :PSUBUSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 664 MMX :PSUBUSW mm1, mm2 L: 0.42ns= 1.02c T: 0.42ns= 1.014c 665 MMX :PCMPEQB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 666 MMX :PCMPEQB mm1, mm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 667 MMX :PCMPEQW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 668 MMX :PCMPEQW mm1, mm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 669 MMX :PCMPEQD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 670 MMX :PCMPEQD mm1, mm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 671 MMX :PCMPGTB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 672 MMX :PCMPGTB mm1, mm2 L: 0.42ns= 1.02c T: 0.42ns= 1.014c 673 MMX :PCMPGTW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 674 MMX :PCMPGTW mm1, mm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 675 MMX :PCMPGTD mm, mm L: 0.42ns= 1.02c T: 0.42ns= 1.014c 676 MMX :PCMPGTD mm1, mm2 L: 0.42ns= 1.02c T: 0.42ns= 1.014c 677 MMX :PAND mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 678 MMX :PAND mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 679 MMX :PANDN mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 680 MMX :PANDN mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.510c 681 MMX :POR mm, mm L: 0.42ns= 1.01c T: 0.21ns= 0.511c 682 MMX :POR mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 683 MMX :PXOR mm, mm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 684 MMX :PXOR mm1, mm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 685 MMX :PMULHW mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 686 SSE :PMULHUW mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 688 SSSE3 :PMULHRSW mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 689 MMX :PMULLW mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 690 SSE2 :PMULUDQ mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 691 SSSE3 :PMADDUBSW mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.014c 692 MMX :PMADDWD mm, mm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 693 MMX :PSLLW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 694 MMX :PSLLW mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 695 MMX :PSLLD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 696 MMX :PSLLD mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 697 MMX :PSLLQ mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 698 MMX :PSLLQ mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 699 MMX :PSRAW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 700 MMX :PSRAW mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 701 MMX :PSRAD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 702 MMX :PSRAD mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 703 MMX :PSRLW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 704 MMX :PSRLW mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 705 MMX :PSRLD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 706 MMX :PSRLD mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 707 MMX :PSRLQ mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.014c 708 MMX :PSRLQ mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 709 MMX :PUNPCKHBW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.014c 710 MMX :PUNPCKHWD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 711 MMX :PUNPCKHDQ mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 712 MMX :PUNPCKLBW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 713 MMX :PUNPCKLWD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 714 MMX :PUNPCKLDQ mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 715 MMX :PACKSSWB mm, mm L: 1.67ns= 4.04c T: 0.84ns= 2.021c 716 MMX :PACKUSWB mm, mm L: 1.67ns= 4.04c T: 0.84ns= 2.021c 717 MMX :PACKSSDW mm, mm L: 1.67ns= 4.04c T: 0.84ns= 2.021c 746 3DN_3DNPREF :PREFETCHW [mem] L: [memory dep.] T: 0.42ns= 1.011c 753 SSE :PAVGB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 754 SSE :PAVGW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.014c 755 SSE :PEXTRW r32, mm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 756 SSE :PINSRW mm, r32, im8 L: [diff. reg. set] T: 0.84ns= 2.027c 757 SSE :PEXTRW + PINSRW r32 L: 2.50ns= 6.05c T: 1.25ns= 3.032c 758 AMD64 :PEXTRW r64, mm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 759 AMD64 :PINSRW mm, r64, im8 L: [diff. reg. set] T: 0.84ns= 2.021c 760 AMD64 :PEXTRW + PINSRW r64 L: 2.50ns= 6.05c T: 1.25ns= 3.032c 761 SSE :PMAXSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 762 SSE :PMAXUB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 763 SSE :PMINSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 764 SSE :PMINUB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 765 SSE :PSADBW mm, mm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 766 SSE :PSHUFW mm, mm, im8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 767 SSE :PREFETCHNTA [mem] L: [memory dep.] T: 0.25ns= 0.597c 768 SSE :PREFETCHT0 [mem] L: [memory dep.] T: 0.25ns= 0.594c 769 SSE :PREFETCHT1 [mem] L: [memory dep.] T: 0.26ns= 0.640c 770 SSE :PREFETCHT2 [mem] L: [memory dep.] T: 0.29ns= 0.692c 771 SSE :SFENCE L: 2.50ns= 6.05c T: 2.51ns= 6.061c 772 SSE2 :LFENCE L: 2.17ns= 5.25c T: 2.17ns= 5.254c 773 SSE2 :MFENCE L: 15.12ns= 36.58c T: 15.17ns= 36.689c 774 SSSE3 :PABSB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 775 SSSE3 :PABSW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 776 SSSE3 :PABSD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 777 SSSE3 :PALIGNR mm, mm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 778 SSSE3 :PHADDW mm, mm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 779 SSSE3 :PHADDD mm, mm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 780 SSSE3 :PHADDSW mm, mm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 781 SSSE3 :PHSUBW mm, mm L: 1.25ns= 3.02c T: 0.84ns= 2.044c 782 SSSE3 :PHSUBD mm, mm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 783 SSSE3 :PHSUBSW mm, mm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 784 SSSE3 :PSHUFB mm, mm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 785 SSSE3 :PSIGNB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 786 SSSE3 :PSIGNW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 787 SSSE3 :PSIGND mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 788 SSE :MOVHLPS xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.014c 789 SSE :MOVHLPS xmm1, xmm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 790 AVX :VMOVHLPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 791 AVX :VMOVHLPS xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.42ns= 1.014c 792 SSE :MOVSS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 793 AVX :VMOVSS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 794 SSE :MOVSS xmm, [m32] L: [memory dep.] T: 0.21ns= 0.505c 795 SSE :MOVSS [m32], xmm L: [memory dep.] T: 0.21ns= 0.505c 796 SSE :MOVSS LS pair L: 2.09ns= 5.05c T: 0.35ns= 0.847c 797 AVX :VMOVSS xmm, [m32] L: [memory dep.] T: 0.21ns= 0.505c 798 AVX :VMOVSS [m32], xmm L: [memory dep.] T: 0.21ns= 0.505c 799 AVX :VMOVSS LS pair L: 2.09ns= 5.05c T: 0.28ns= 0.668c 800 SSE :MOVLPS xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 801 SSE :MOVLPS [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 802 SSE :MOVLPS LS pair L: 3.13ns= 7.58c T: 0.36ns= 0.876c 803 AVX :VMOVLPS xmm, xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 804 AVX :VMOVLPS [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 805 AVX :VMOVLPS LS pair L: 3.13ns= 7.57c T: 0.27ns= 0.660c 806 SSE :MOVHPS xmm, [m64] L: [memory dep.] T: 0.42ns= 1.010c 807 SSE :MOVHPS [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 808 SSE :MOVHPS LS pair L: 3.13ns= 7.58c T: 0.43ns= 1.046c 809 AVX :VMOVHPS xmm, xmm, [m64] L: [memory dep.] T: 0.42ns= 1.010c 810 AVX :VMOVHPS [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 811 AVX :VMOVHPS LS pair L: 3.13ns= 7.57c T: 0.42ns= 1.011c 812 SSE :MOVAPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 813 SSE :MOVAPS xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 814 SSE :MOVAPS [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 815 SSE :MOVAPS LS pair L: 2.50ns= 6.05c T: 0.40ns= 0.958c 816 AVX :VMOVAPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 817 AVX :VMOVAPS xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 818 AVX :VMOVAPS [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 819 AVX :VMOVAPS LS pair L: 2.09ns= 5.05c T: 0.34ns= 0.822c 820 SSE :MOVUPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 821 SSE :MOVUPS xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 822 SSE :MOVUPS [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 823 SSE :MOVUPS aligned LS pair L: 2.09ns= 5.05c T: 0.40ns= 0.958c 824 SSE :MOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 825 SSE :MOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.42ns= 1.011c 826 SSE :MOVUPS unaligned LS pair L: 2.09ns= 5.05c T: 0.50ns= 1.206c 827 AVX :VMOVUPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 828 AVX :VMOVUPS xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 829 AVX :VMOVUPS [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 830 AVX :VMOVUPS aligned LS pair L: 2.09ns= 5.05c T: 0.34ns= 0.822c 831 AVX :VMOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 832 AVX :VMOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.42ns= 1.010c 833 AVX :VMOVUPS unaligned LS pair L: 2.44ns= 5.90c T: 0.59ns= 1.421c 835 SSE :MOVNTPS [m128], xmm L: [memory dep.] T: 3.17ns= 3.167c 836 AVX :VMOVNTPS [m128], xmm L: [memory dep.] T: 2.98ns= 2.979c 837 SSE :MOVMSKPS r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 838 AVX :VMOVMSKPS r32, xmm L: [diff. reg. set] T: 0.42ns= 1.014c 839 AVX :VMASKMOVPS xmm,xmm,[m128+4] L: [memory dep.] T: 0.40ns= 0.971c 840 AVX :VMASKMOVPS [m128+4],xmm,xmm L: [memory dep.] T: 0.42ns= 1.010c 841 AVX :VMASKMOVPS unaligned LS pair L: 6.68ns= 16.16c T: 0.82ns= 1.990c 842 SSE :UNPCKLPS xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 843 AVX :VUNPCKLPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 844 SSE :UNPCKHPS xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 845 AVX :VUNPCKHPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 846 SSE :SHUFPS xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 847 AVX :VSHUFPS xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.514c 848 AVX :VPERMILPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 849 AVX :VPERMILPS xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 850 SSE :COMISS xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 851 AVX :VCOMISS xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 852 SSE :UCOMISS xmm, xmm L: [no true dep.] T: 0.42ns= 1.014c 853 AVX :VUCOMISS xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 854 SSE :CMPSS xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 855 SSE :CMPPS xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 856 AVX :VCMPSS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 857 AVX :VCMPPS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 858 SSE :SUBSS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 859 AVX :VSUBSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 860 SSE :SUBPS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 861 AVX :VSUBPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 862 SSE :ADDSS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 863 AVX :VADDSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 864 SSE :ADDPS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 865 AVX :VADDPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 866 SSE :MULSS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 867 AVX :VMULSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.510c 868 SSE :MULPS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 869 AVX :VMULPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.510c 870 SSE :MULSS+ADDSS xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 871 AVX :VMULSS+VADDSS xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 872 SSE :MULPS+ADDPS xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 873 AVX :VMULPS+VADDPS xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 874 SSE :MULSS xm1,xm1 ADDSS xm2,xm2 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 875 AVX :VMULSS xmm1.. VADDSS xmm2.. L: 1.67ns= 4.04c T: 0.42ns= 1.010c 876 SSE :MULPS xm1,xm1 ADDPS xm2,xm2 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 877 AVX :VMULPS xmm1.. VADDPS xmm2.. L: 1.67ns= 4.04c T: 0.42ns= 1.010c 878 SSE :MAXSS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 879 AVX :VMAXSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 880 SSE :MAXPS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 881 AVX :VMAXPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 882 SSE :MINSS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 883 AVX :VMINSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 884 SSE :MINPS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 885 AVX :VMINPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 886 SSE :ANDNPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 887 SSE :ANDNPS xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 888 AVX :VANDNPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 889 AVX :VANDNPS xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 890 SSE :ANDPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 891 SSE :ANDPS xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 892 AVX :VANDPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 893 AVX :VANDPS xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 894 SSE :ORPS xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 895 SSE :ORPS xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 896 AVX :VORPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.18ns= 0.436c 897 AVX :VORPS xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 898 SSE :XORPS xmm, xmm L: 0.09ns= 0.21c T: 0.10ns= 0.232c 899 SSE :XORPS xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 900 AVX :VXORPS xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 901 AVX :VXORPS xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 902 SSE :DIVSS xmm, xmm L: 4.59ns= 11.11c T: 1.25ns= 3.031c 903 SSE :DIVSS (0.0f/x) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 904 SSE :DIVSS (x/1.0f) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 905 SSE :DIVSS (x/2.0f) L: 4.07ns= 9.85c T: 1.25ns= 3.033c 906 SSE :DIVSS (x/0.5f) L: 4.28ns= 10.35c T: 1.25ns= 3.033c 907 AVX :VDIVSS xmm, xmm, xmm L: 4.59ns= 11.11c T: 1.25ns= 3.032c 908 AVX :VDIVSS (0.0f/x) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 909 AVX :VDIVSS (x/1.0f) L: 4.59ns= 11.11c T: 1.25ns= 3.031c 910 AVX :VDIVSS (x/2.0f) L: 4.07ns= 9.84c T: 1.25ns= 3.033c 911 AVX :VDIVSS (x/0.5f) L: 4.07ns= 9.84c T: 1.25ns= 3.034c 912 SSE :DIVPS xmm, xmm L: 4.59ns= 11.11c T: 1.25ns= 3.031c 913 SSE :DIVPS (0.0f/x) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 914 SSE :DIVPS (x/1.0f) L: 4.59ns= 11.11c T: 1.25ns= 3.031c 915 SSE :DIVPS (x/2.0f) L: 3.27ns= 7.91c T: 1.25ns= 3.031c 916 SSE :DIVPS (x/0.5f) L: 3.27ns= 7.91c T: 1.25ns= 3.031c 917 AVX :VDIVPS xmm, xmm, xmm L: 4.59ns= 11.11c T: 1.25ns= 3.032c 918 AVX :VDIVPS (0.0f/x) L: 4.59ns= 11.11c T: 1.25ns= 3.031c 919 AVX :VDIVPS (x/1.0f) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 920 AVX :VDIVPS (x/2.0f) L: 3.27ns= 7.91c T: 1.25ns= 3.031c 921 AVX :VDIVPS (x/0.5f) L: 3.56ns= 8.62c T: 1.25ns= 3.031c 922 SSE :SQRTSS xmm, xmm L: 5.01ns= 12.13c T: 1.25ns= 3.031c 923 SSE :SQRTSS (0.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.032c 924 SSE :SQRTSS (1.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.031c 925 AVX :VSQRTSS xmm, xmm, xmm L: 5.01ns= 12.13c T: 1.25ns= 3.031c 926 AVX :VSQRTSS (0.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.031c 927 AVX :VSQRTSS (1.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.031c 928 SSE :SQRTPS xmm, xmm L: 5.01ns= 12.13c T: 1.25ns= 3.031c 929 SSE :SQRTPS (0.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.032c 930 SSE :SQRTPS (1.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.031c 931 AVX :VSQRTPS xmm, xmm L: 5.01ns= 12.13c T: 1.25ns= 3.031c 932 AVX :VSQRTPS (0.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.031c 933 AVX :VSQRTPS (1.0f) L: 5.01ns= 12.13c T: 1.25ns= 3.031c 934 SSE :RCPSS xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 935 AVX :VRCPSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 936 SSE :RCPPS xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 937 AVX :VRCPPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 938 SSE :RSQRTSS xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 939 AVX :VRSQRTSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 940 SSE :RSQRTPS xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 941 AVX :VRSQRTPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 942 SSE :CVTPI2PS xmm, mm L: [diff. reg. set] T: 0.44ns= 1.071c 943 SSE :CVTPS2PI mm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 944 SSE :CVTPS2PI + CVTPI2PS L: 5.43ns= 13.13c T: 0.84ns= 2.021c 945 SSE :CVTTPS2PI mm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 946 SSE :CVTTPS2PI + CVTPI2PS L: 5.43ns= 13.13c T: 0.84ns= 2.021c 947 SSE :CVTSI2SS xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.011c 948 SSE :CVTSS2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 949 SSE :CVTSS2SI + CVTSI2SS r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 950 SSE :CVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 951 SSE :CVTTSS2SI + CVTSI2SS r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 952 AVX :VCVTSI2SS xmm, xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 953 AVX :VCVTSS2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 954 AVX :VCVTSS2SI + VCVTSI2SS r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 955 AVX :VCVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 956 AVX :VCVTTSS2SI + VCVTSI2SS r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 957 AMD64 :CVTSI2SS xmm, r64 L: [diff. reg. set] T: 0.84ns= 2.021c 958 AMD64 :CVTSS2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 959 AMD64 :CVTSS2SI + CVTSI2SS r64 L: 5.85ns= 14.14c T: 1.25ns= 3.031c 960 AMD64 :CVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 961 AMD64 :CVTTSS2SI + CVTSI2SS r64 L: 5.85ns= 14.14c T: 1.25ns= 3.031c 962 AVX_X64 :VCVTSI2SS xmm, xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 963 AVX_X64 :VCVTSS2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 964 AVX_X64 :VCVTSS2SI + VCVTSI2SS r64 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 965 AVX_X64 :VCVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 966 AVX_X64 :VCVTTSS2SI + VCVTSI2SS r64 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 967 SSE :STMXCSR [mem] L: [memory dep.] T: 0.42ns= 1.010c 968 SSE :LDMXCSR [mem] L: [memory dep.] T: 1.42ns= 3.435c 969 SSE :STMXCSR + LDMXCSR L: 4.59ns= 11.11c T: 4.61ns= 11.153c 970 SSE2 :MOVSD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 971 SSE2 :MOVSD xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 972 SSE2 :MOVSD [m64], xmm L: [memory dep.] T: 0.36ns= 0.873c 973 SSE2 :MOVSD LS pair L: 2.09ns= 5.05c T: 0.36ns= 0.866c 974 AVX :VMOVSD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.17ns= 0.408c 975 AVX :VMOVSD xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 976 AVX :VMOVSD [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 977 AVX :VMOVSD LS pair L: 2.36ns= 5.70c T: 0.28ns= 0.668c 978 SSE2 :MOVLPD xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 979 SSE2 :MOVLPD [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 980 SSE2 :MOVLPD LS pair L: 3.13ns= 7.58c T: 0.36ns= 0.876c 981 AVX :VMOVLPD xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 982 AVX :VMOVLPD [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 983 AVX :VMOVLPD LS pair L: 3.13ns= 7.57c T: 0.27ns= 0.660c 984 SSE2 :MOVHPD xmm, [m64] L: [memory dep.] T: 0.42ns= 1.010c 985 SSE2 :MOVHPD [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 986 SSE2 :MOVHPD LS pair L: 3.13ns= 7.58c T: 0.43ns= 1.051c 987 AVX :VMOVHPD xmm, [m64] L: [memory dep.] T: 0.42ns= 1.010c 988 AVX :VMOVHPD [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 989 AVX :VMOVHPD LS pair L: 3.13ns= 7.57c T: 0.42ns= 1.010c 990 SSE2 :MOVAPD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 991 SSE2 :MOVAPD xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 992 SSE2 :MOVAPD [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 993 SSE2 :MOVAPD LS pair L: 2.51ns= 6.06c T: 0.40ns= 0.958c 994 AVX :VMOVAPD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 995 AVX :VMOVAPD xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 996 AVX :VMOVAPD [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 997 AVX :VMOVAPD LS pair L: 2.09ns= 5.05c T: 0.34ns= 0.822c 998 SSE2 :MOVUPD xmm, xmm L: 0.42ns= 1.01c T: 0.18ns= 0.446c 999 SSE2 :MOVUPD xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 1000 SSE2 :MOVUPD [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 1001 SSE2 :MOVUPD aligned LS pair L: 2.09ns= 5.05c T: 0.40ns= 0.958c 1002 SSE2 :MOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 1003 SSE2 :MOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.42ns= 1.011c 1004 SSE2 :MOVUPD unaligned LS pair L: 2.09ns= 5.05c T: 0.51ns= 1.239c 1005 AVX :VMOVUPD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1006 AVX :VMOVUPD xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 1007 AVX :VMOVUPD [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 1008 AVX :VMOVUPD aligned LS pair L: 2.09ns= 5.05c T: 0.34ns= 0.822c 1009 AVX :VMOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 1010 AVX :VMOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.51ns= 1.230c 1011 AVX :VMOVUPD unaligned LS pair L: 2.09ns= 5.05c T: 0.51ns= 1.224c 1013 SSE2 :MOVNTPD [m128], xmm L: [memory dep.] T: 3.13ns= 3.125c 1014 AVX :VMOVNTPD [m128], xmm L: [memory dep.] T: 3.74ns= 3.742c 1015 SSE2 :MOVMSKPD r32, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 1016 AVX :VMOVMSKPD r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1017 AVX :VMASKMOVPD xmm,xmm,[m128+4] L: [memory dep.] T: 0.41ns= 0.980c 1018 AVX :VMASKMOVPD [m128+4],xmm,xmm L: [memory dep.] T: 0.42ns= 1.010c 1019 AVX :VMASKMOVPD unaligned LS pair L: 6.68ns= 16.16c T: 0.82ns= 1.991c 1020 SSE2 :UNPCKLPD xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1021 AVX :VUNPCKLPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1022 SSE2 :UNPCKHPD xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1023 AVX :VUNPCKHPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1024 SSE2 :SHUFPD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1025 AVX :VSHUFPD xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1026 AVX :VPERMILPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1027 AVX :VPERMILPD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1028 SSE2 :COMISD xmm, xmm L: [no true dep.] T: 0.42ns= 1.014c 1029 AVX :VCOMISD xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1030 SSE2 :UCOMISD xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1031 AVX :VUCOMISD xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1032 SSE2 :CMPSD xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1033 SSE2 :CMPPD xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1034 AVX :VCMPSD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1035 AVX :VCMPPD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1036 SSE2 :SUBSD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1037 AVX :VSUBSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1038 SSE2 :SUBPD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1039 AVX :VSUBPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1040 SSE2 :ADDSD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1041 AVX :VADDSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1042 SSE2 :ADDPD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1043 AVX :VADDPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.510c 1044 SSE2 :MULSD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1045 AVX :VMULSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1046 SSE2 :MULPD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.512c 1047 AVX :VMULPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1048 SSE2 :MULSD+ADDSD xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 1049 AVX :VMULSD+VADDSD xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1050 SSE2 :MULPD+ADDPD xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 1051 AVX :VMULPD+VADDPD xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1052 SSE2 :MULSD xm1,xm1 ADDSD xm2,xm2 L: 1.67ns= 4.04c T: 0.42ns= 1.026c 1053 AVX :VMULSD xmm1.. VADDSD xmm2.. L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1054 SSE2 :MULPD xm1,xm1 ADDPD xm2,xm2 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1055 AVX :VMULPD xmm1.. VADDPD xmm2.. L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1056 SSE2 :MAXSD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1057 AVX :VMAXSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1058 SSE2 :MAXPD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1059 AVX :VMAXPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.510c 1060 SSE2 :MINSD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.512c 1061 AVX :VMINSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1062 SSE2 :MINPD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 1063 AVX :VMINPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.510c 1064 SSE2 :ANDNPD xmm, xmm L: 0.42ns= 1.01c T: 0.18ns= 0.440c 1065 SSE2 :ANDNPD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1066 AVX :VANDNPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1067 AVX :VANDNPD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1068 SSE2 :ANDPD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1069 SSE2 :ANDPD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1070 AVX :VANDPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1071 AVX :VANDPD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.17ns= 0.400c 1072 SSE2 :ORPD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1073 SSE2 :ORPD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.18ns= 0.442c 1074 AVX :VORPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.18ns= 0.445c 1075 AVX :VORPD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1076 SSE2 :XORPD xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.248c 1077 SSE2 :XORPD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.18ns= 0.438c 1078 AVX :VXORPD xmm, xmm, xmm L: 0.08ns= 0.20c T: 0.10ns= 0.250c 1079 AVX :VXORPD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1080 SSE2 :DIVSD xmm, xmm L: 5.85ns= 14.14c T: 1.67ns= 4.042c 1081 SSE2 :DIVSD (0.0/x) L: 5.43ns= 13.13c T: 1.67ns= 4.043c 1082 SSE2 :DIVSD (x/1.0) L: 5.43ns= 13.13c T: 1.67ns= 4.042c 1083 SSE2 :DIVSD (x/2.0) L: 4.81ns= 11.64c T: 1.67ns= 4.043c 1084 SSE2 :DIVSD (x/0.5) L: 4.81ns= 11.64c T: 1.67ns= 4.043c 1085 AVX :VDIVSD xmm, xmm, xmm L: 5.85ns= 14.14c T: 1.67ns= 4.042c 1086 AVX :VDIVSD (0.0/x) L: 5.43ns= 13.13c T: 1.67ns= 4.044c 1087 AVX :VDIVSD (x/1.0) L: 5.43ns= 13.13c T: 1.67ns= 4.043c 1088 AVX :VDIVSD (x/2.0) L: 4.81ns= 11.64c T: 1.67ns= 4.043c 1089 AVX :VDIVSD (x/0.5) L: 4.81ns= 11.64c T: 1.67ns= 4.045c 1090 SSE2 :DIVPD xmm, xmm L: 5.85ns= 14.14c T: 1.67ns= 4.043c 1091 SSE2 :DIVPD (0.0/x) L: 5.43ns= 13.13c T: 1.67ns= 4.041c 1092 SSE2 :DIVPD (x/1.0) L: 5.43ns= 13.13c T: 1.67ns= 4.042c 1093 SSE2 :DIVPD (x/2.0) L: 3.86ns= 9.33c T: 1.67ns= 4.042c 1094 SSE2 :DIVPD (x/0.5) L: 3.86ns= 9.33c T: 1.67ns= 4.041c 1095 AVX :VDIVPD xmm, xmm, xmm L: 5.85ns= 14.14c T: 1.67ns= 4.044c 1096 AVX :VDIVPD (0.0/x) L: 5.43ns= 13.13c T: 1.67ns= 4.042c 1097 AVX :VDIVPD (x/1.0) L: 5.43ns= 13.13c T: 1.67ns= 4.042c 1098 AVX :VDIVPD (x/2.0) L: 3.86ns= 9.33c T: 1.67ns= 4.041c 1099 AVX :VDIVPD (x/0.5) L: 3.86ns= 9.33c T: 1.67ns= 4.043c 1100 SSE2 :SQRTSD xmm, xmm L: 7.51ns= 18.18c T: 2.22ns= 5.381c 1101 SSE2 :SQRTSD (0.0) L: 5.43ns= 13.13c T: 1.88ns= 4.549c 1102 SSE2 :SQRTSD (1.0) L: 5.43ns= 13.13c T: 1.88ns= 4.550c 1103 AVX :VSQRTSD xmm, xmm, xmm L: 7.51ns= 18.18c T: 2.51ns= 6.063c 1104 AVX :VSQRTSD (0.0) L: 5.43ns= 13.13c T: 1.88ns= 4.548c 1105 AVX :VSQRTSD (1.0) L: 5.43ns= 13.13c T: 1.88ns= 4.547c 1106 SSE2 :SQRTPD xmm, xmm L: 7.51ns= 18.18c T: 2.22ns= 5.381c 1107 SSE2 :SQRTPD (0.0) L: 5.43ns= 13.13c T: 1.88ns= 4.547c 1108 SSE2 :SQRTPD (1.0) L: 5.43ns= 13.13c T: 1.88ns= 4.548c 1109 AVX :VSQRTPD xmm, xmm L: 7.51ns= 18.18c T: 2.51ns= 6.066c 1110 AVX :VSQRTPD (0.0) L: 5.43ns= 13.13c T: 1.88ns= 4.547c 1111 AVX :VSQRTPD (1.0) L: 5.43ns= 13.13c T: 1.88ns= 4.548c 1112 SSE2 :CVTPI2PD xmm, mm L: [diff. reg. set] T: 0.42ns= 1.010c 1113 SSE2 :CVTPD2PI mm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1114 SSE2 :CVTPD2PI + CVTPI2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1115 SSE2 :CVTTPD2PI mm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1116 SSE2 :CVTTPD2PI + CVTPI2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1117 SSE2 :CVTSI2SD xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 1118 SSE2 :CVTSD2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1119 SSE2 :CVTSD2SI + CVTSI2SD r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 1120 SSE2 :CVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1121 SSE2 :CVTTSD2SI + CVTSI2SD r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 1122 AVX :VCVTSI2SD xmm, xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 1123 AVX :VCVTSD2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1124 AVX :VCVTSD2SI + VCVTSI2SD r32 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 1125 AVX :VCVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1126 AVX :VCVTTSD2SI + VCVTSI2SD r32 L: 5.01ns= 12.13c T: 0.84ns= 2.043c 1127 AMD64 :CVTSI2SD xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 1128 AMD64 :CVTSD2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1129 AMD64 :CVTSD2SI + CVTSI2SD r64 L: 5.01ns= 12.13c T: 0.85ns= 2.044c 1130 AMD64 :CVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1131 AMD64 :CVTTSD2SI + CVTSI2SD r64 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 1132 AVX_X64 :VCVTSI2SD xmm, xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 1133 AVX_X64 :VCVTSD2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1134 AVX_X64 :VCVTSD2SI + VCVTSI2SD r64 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 1135 AVX_X64 :VCVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1136 AVX_X64 :VCVTTSD2SI + VCVTSI2SD r64 L: 5.01ns= 12.13c T: 0.84ns= 2.044c 1137 SSE2 :CVTDQ2PD xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1138 SSE2 :CVTPD2DQ xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1139 SSE2 :CVTPD2DQ + CVTDQ2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1140 SSE2 :CVTTPD2DQ xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1141 SSE2 :CVTTPD2DQ + CVTDQ2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1142 AVX :VCVTDQ2PD xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1143 AVX :VCVTPD2DQ xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1144 AVX :VCVTPD2DQ + VCVTDQ2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1145 AVX :VCVTTPD2DQ xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1146 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1147 SSE2 :CVTDQ2PS xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1148 SSE2 :CVTPS2DQ xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1149 SSE2 :CVTPS2DQ + CVTDQ2PS L: 3.34ns= 8.08c T: 0.43ns= 1.030c 1150 SSE2 :CVTTPS2DQ xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1151 SSE2 :CVTTPS2DQ + CVTDQ2PS L: 3.34ns= 8.08c T: 0.43ns= 1.030c 1152 AVX :VCVTDQ2PS xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1153 AVX :VCVTPS2DQ xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1154 AVX :VCVTPS2DQ + VCVTDQ2PS L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1155 AVX :VCVTTPS2DQ xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1156 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1157 SSE2 :CVTPS2PD xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1158 SSE2 :CVTPD2PS xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1159 SSE2 :CVTPD2PS + CVTPS2PD L: 4.18ns= 10.10c T: 0.84ns= 2.021c 1160 SSE2 :CVTSS2SD xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1161 SSE2 :CVTSD2SS xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1162 SSE2 :CVTSD2SS + CVTSS2SD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1163 AVX :VCVTPS2PD xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1164 AVX :VCVTPD2PS xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1165 AVX :VCVTPD2PS + VCVTPS2PD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1166 AVX :VCVTSS2SD xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1167 AVX :VCVTSD2SS xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1168 AVX :VCVTSD2SS + VCVTSS2SD L: 4.18ns= 10.10c T: 0.84ns= 2.024c 1169 SSE2 :MOVD r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1170 SSE2 :MOVD xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 1171 SSE2 :MOVD r32, xmm+MOVD xmm, r32 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1172 AVX :VMOVD r32, xmm L: [diff. reg. set] T: 0.42ns= 1.014c 1173 AVX :VMOVD xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 1174 AVX :VMOVD r32,xmm+VMOVD xmm,r32 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1175 AMD64 :MOVQ r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1176 AMD64 :MOVQ xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 1177 AMD64 :MOVQ r64, xmm+MOVD xmm, r64 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1178 AVX_X64 :VMOVQ r64, xmm L: [diff. reg. set] T: 0.42ns= 1.014c 1179 AVX_X64 :VMOVQ xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 1180 AVX_X64 :VMOVQ r64,xmm+VMOVD xmm,r64 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1181 SSE2 :MOVD xmm, [m32] L: [memory dep.] T: 0.21ns= 0.505c 1182 SSE2 :MOVD [m32], xmm L: [memory dep.] T: 0.21ns= 0.505c 1183 SSE2 :MOVD LS pair L: 2.09ns= 5.05c T: 0.35ns= 0.847c 1184 AVX :VMOVD xmm, [m32] L: [memory dep.] T: 0.21ns= 0.505c 1185 AVX :VMOVD [m32], xmm L: [memory dep.] T: 0.21ns= 0.505c 1186 AVX :VMOVD LS pair L: 2.09ns= 5.05c T: 0.28ns= 0.668c 1187 SSE2 :MOVQ xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 1188 SSE2 :MOVQ [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 1189 SSE2 :MOVQ LS pair L: 2.09ns= 5.05c T: 0.36ns= 0.867c 1190 AVX :VMOVQ xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 1191 AVX :VMOVQ [m64], xmm L: [memory dep.] T: 0.21ns= 0.505c 1192 AVX :VMOVQ LS pair L: 2.09ns= 5.05c T: 0.31ns= 0.762c 1193 SSE2 :MOVDQ2Q mm, xmm L: [diff. reg. set] T: 0.40ns= 0.977c 1194 SSE2 :MOVQ2DQ xmm, mm L: [diff. reg. set] T: 0.42ns= 1.010c 1195 SSE2 :MOVDQ2Q + MOVQ2DQ xmm, mm L: 1.67ns= 4.04c T: 0.85ns= 2.050c 1196 SSE2 :MOVDQA xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1197 SSE2 :MOVDQA xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 1198 SSE2 :MOVDQA [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 1199 SSE2 :MOVDQA LS pair L: 2.09ns= 5.05c T: 0.40ns= 0.958c 1200 AVX :VMOVDQA xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1201 AVX :VMOVDQA xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 1202 AVX :VMOVDQA [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 1203 AVX :VMOVDQA LS pair L: 2.09ns= 5.05c T: 0.34ns= 0.822c 1204 SSE2 :MOVDQU xmm, xmm L: 0.42ns= 1.01c T: 0.19ns= 0.451c 1205 SSE2 :MOVDQU xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 1206 SSE2 :MOVDQU [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 1207 SSE2 :MOVDQU aligned LS pair L: 2.09ns= 5.05c T: 0.40ns= 0.958c 1208 SSE2 :MOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 1209 SSE2 :MOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.42ns= 1.011c 1210 SSE2 :MOVDQU unaligned LS pair L: 2.09ns= 5.05c T: 0.51ns= 1.239c 1211 AVX :VMOVDQU xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1212 AVX :VMOVDQU xmm, [m128] L: [memory dep.] T: 0.21ns= 0.505c 1213 AVX :VMOVDQU [m128], xmm L: [memory dep.] T: 0.21ns= 0.505c 1214 AVX :VMOVDQU aligned LS pair L: 2.09ns= 5.05c T: 0.34ns= 0.822c 1215 AVX :VMOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 1216 AVX :VMOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.42ns= 1.010c 1217 AVX :VMOVDQU unaligned LS pair L: 2.09ns= 5.05c T: 0.51ns= 1.224c 1218 SSE4.1 :MOVNTDQA xmm, [m128] L: [memory dep.] T: 0.52ns= 0.521c 1219 SSE2 :MOVNTDQ [m128], xmm L: [memory dep.] T: 3.33ns= 3.325c 1220 SSE4.1 :MOVNTDQA + MOVNTDQ xmm LS pair L: 176.04ns= 425.87c T: 425.87ns= 425.871c 1221 AVX :VMOVNTDQA xmm, [m128] L: [memory dep.] T: 0.52ns= 0.521c 1222 AVX :VMOVNTDQ [m128], xmm L: [memory dep.] T: 3.36ns= 3.358c 1223 AVX :VMOVNTDQA + VMOVNTDQ xmm LS pair L: 164.46ns= 397.85c T: 397.85ns= 397.850c 1224 SSE2 :PMOVMSKB r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1225 AMD64 :PMOVMSKB r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1226 AVX :VPMOVMSKB r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1227 AVX_X64 :VPMOVMSKB r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 1228 SSE2 :MASKMOVDQU xmm, xmm L: [memory dep.] T: 7.07ns= 7.067c 1229 AVX :VMASKMOVDQU xmm, xmm L: [memory dep.] T: 7.07ns= 7.067c 1230 SSE2 :PADDB xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1231 AVX :VPADDB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1232 SSE2 :PADDW xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1233 AVX :VPADDW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1234 SSE2 :PADDD xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1235 AVX :VPADDD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1236 SSE2 :PADDQ xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1237 AVX :VPADDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1238 SSE2 :PADDSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1239 AVX :VPADDSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1240 SSE2 :PADDSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1241 AVX :VPADDSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1242 SSE2 :PADDUSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1243 AVX :VPADDUSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1244 SSE2 :PADDUSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1245 AVX :VPADDUSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1246 SSE2 :PSUBB xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1247 SSE2 :PSUBB xmm1, xmm2 L: 0.42ns= 1.01c T: 0.18ns= 0.443c 1248 AVX :VPSUBB xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1249 AVX :VPSUBB xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.336c 1250 SSE2 :PSUBW xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1251 SSE2 :PSUBW xmm1, xmm2 L: 0.42ns= 1.01c T: 0.18ns= 0.440c 1252 AVX :VPSUBW xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.251c 1253 AVX :VPSUBW xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1254 SSE2 :PSUBD xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1255 SSE2 :PSUBD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1256 AVX :VPSUBD xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1257 AVX :VPSUBD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1258 SSE2 :PSUBQ xmm, xmm L: 0.15ns= 0.36c T: 0.18ns= 0.441c 1259 SSE2 :PSUBQ xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1260 AVX :VPSUBQ xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1261 AVX :VPSUBQ xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1262 SSE2 :PSUBSB xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1263 SSE2 :PSUBSB xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1264 AVX :VPSUBSB xmm, xmm, xmm L: 0.15ns= 0.36c T: 0.18ns= 0.433c 1265 AVX :VPSUBSB xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.512c 1266 SSE2 :PSUBSW xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1267 SSE2 :PSUBSW xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.511c 1268 AVX :VPSUBSW xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1269 AVX :VPSUBSW xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1270 SSE2 :PSUBUSB xmm, xmm L: 0.15ns= 0.37c T: 0.18ns= 0.429c 1271 SSE2 :PSUBUSB xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1272 AVX :VPSUBUSB xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1273 AVX :VPSUBUSB xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1274 SSE2 :PSUBUSW xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1275 SSE2 :PSUBUSW xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1276 AVX :VPSUBUSW xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1277 AVX :VPSUBUSW xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1278 SSE2 :PCMPEQB xmm, xmm L: 0.21ns= 0.50c T: 0.21ns= 0.512c 1279 SSE2 :PCMPEQB xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1280 AVX :VPCMPEQB xmm, xmm, xmm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 1281 AVX :VPCMPEQB xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1282 SSE2 :PCMPEQW xmm, xmm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 1283 SSE2 :PCMPEQW xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1284 AVX :VPCMPEQW xmm, xmm, xmm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 1285 AVX :VPCMPEQW xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.512c 1286 SSE2 :PCMPEQD xmm, xmm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 1287 SSE2 :PCMPEQD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1288 AVX :VPCMPEQD xmm, xmm, xmm L: 0.21ns= 0.50c T: 0.21ns= 0.509c 1289 AVX :VPCMPEQD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1290 SSE4.1 :PCMPEQQ xmm, xmm L: 0.21ns= 0.51c T: 0.21ns= 0.505c 1291 SSE4.1 :PCMPEQQ xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1292 AVX :VPCMPEQQ xmm, xmm, xmm L: 0.21ns= 0.51c T: 0.21ns= 0.509c 1293 AVX :VPCMPEQQ xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1294 SSE2 :PCMPGTB xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1295 SSE2 :PCMPGTB xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1296 AVX :VPCMPGTB xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1297 AVX :VPCMPGTB xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1298 SSE2 :PCMPGTW xmm, xmm L: 0.15ns= 0.37c T: 0.18ns= 0.439c 1299 SSE2 :PCMPGTW xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1300 AVX :VPCMPGTW xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1301 AVX :VPCMPGTW xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.512c 1302 SSE2 :PCMPGTD xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1303 SSE2 :PCMPGTD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.511c 1304 AVX :VPCMPGTD xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 1305 AVX :VPCMPGTD xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 1306 SSE4.2 :PCMPGTQ xmm, xmm L: 0.16ns= 0.38c T: 0.18ns= 0.443c 1307 SSE4.2 :PCMPGTQ xmm1, xmm2 L: 1.25ns= 3.02c T: 0.42ns= 1.014c 1308 AVX :VPCMPGTQ xmm, xmm, xmm L: 0.08ns= 0.20c T: 0.11ns= 0.273c 1309 AVX :VPCMPGTQ xmm1, xmm1, xmm2 L: 1.26ns= 3.05c T: 0.42ns= 1.013c 1310 SSE2 :PAND xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1311 SSE2 :PAND xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1312 AVX :VPAND xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.18ns= 0.445c 1313 AVX :VPAND xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1314 SSE2 :PANDN xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1315 SSE2 :PANDN xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1316 AVX :VPANDN xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1317 AVX :VPANDN xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.16ns= 0.389c 1318 SSE2 :POR xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1319 SSE2 :POR xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1320 AVX :VPOR xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1321 AVX :VPOR xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1322 SSE2 :PXOR xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1323 SSE2 :PXOR xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1324 AVX :VPXOR xmm, xmm, xmm L: 0.08ns= 0.19c T: 0.10ns= 0.251c 1325 AVX :VPXOR xmm1, xmm1, xmm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1326 SSE2 :PMULHW xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.512c 1327 AVX :VPMULHW xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1328 SSE2 :PMULHUW xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1329 AVX :VPMULHUW xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1330 SSSE3 :PMULHRSW xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1331 AVX :VPMULHRSW xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1332 SSE2 :PMULLW xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1333 AVX :VPMULLW xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1334 SSE4.1 :PMULLD xmm, xmm L: 4.18ns= 10.10c T: 0.43ns= 1.046c 1335 AVX :VPMULLD xmm, xmm, xmm L: 4.18ns= 10.10c T: 0.43ns= 1.046c 1336 SSE4.1 :PMULDQ xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1337 AVX :VPMULDQ xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1338 SSE2 :PMULUDQ xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1339 AVX :VPMULUDQ xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1340 SSSE3 :PMADDUBSW xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1341 AVX :VPMADDUBSW xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1342 SSE2 :PMADDWD xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1343 AVX :VPMADDWD xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 1344 SSE2 :PSLLW xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.979c 1345 AVX :VPSLLW xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.980c 1346 SSE2 :PSLLW xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1347 AVX :VPSLLW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1348 SSE2 :PSLLD xmm, xmm L: 0.84ns= 2.02c T: 0.40ns= 0.979c 1349 AVX :VPSLLD xmm, xmm, xmm L: 0.84ns= 2.02c T: 0.40ns= 0.979c 1350 SSE2 :PSLLD xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1351 AVX :VPSLLD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1352 SSE2 :PSLLQ xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.978c 1353 AVX :VPSLLQ xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.979c 1354 SSE2 :PSLLQ xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1355 AVX :VPSLLQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1356 SSE2 :PSLLDQ xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1357 AVX :VPSLLDQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1358 SSE2 :PSRAW xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.980c 1359 AVX :VPSRAW xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.978c 1360 SSE2 :PSRAW xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1361 AVX :VPSRAW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1362 SSE2 :PSRAD xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.979c 1363 AVX :VPSRAD xmm, xmm, xmm L: 0.84ns= 2.02c T: 0.41ns= 0.980c 1364 SSE2 :PSRAD xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1365 AVX :VPSRAD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1366 SSE2 :PSRLW xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.979c 1367 AVX :VPSRLW xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.978c 1368 SSE2 :PSRLW xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1369 AVX :VPSRLW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1370 SSE2 :PSRLD xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.978c 1371 AVX :VPSRLD xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.980c 1372 SSE2 :PSRLD xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1373 AVX :VPSRLD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1374 SSE2 :PSRLQ xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.978c 1375 AVX :VPSRLQ xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.980c 1376 SSE2 :PSRLQ xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1377 AVX :VPSRLQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1378 SSE2 :PSRLDQ xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1379 AVX :VPSRLDQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1380 SSE2 :PUNPCKHBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1381 AVX :VPUNPCKHBW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1382 SSE2 :PUNPCKHWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1383 AVX :VPUNPCKHWD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1384 SSE2 :PUNPCKHDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1385 AVX :VPUNPCKHDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1386 SSE2 :PUNPCKHQDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1387 AVX :VPUNPCKHQDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1388 SSE2 :PUNPCKLBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1389 AVX :VPUNPCKLBW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1390 SSE2 :PUNPCKLWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1391 AVX :VPUNPCKLWD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1392 SSE2 :PUNPCKLDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1393 AVX :VPUNPCKLDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1394 SSE2 :PUNPCKLQDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1395 AVX :VPUNPCKLQDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1396 SSE2 :PACKSSWB xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1397 AVX :VPACKSSWB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1398 SSE2 :PACKUSWB xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1399 AVX :VPACKUSWB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1400 SSE2 :PACKSSDW xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1401 AVX :VPACKSSDW xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1402 SSE4.1 :PACKUSDW xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1403 AVX :VPACKUSDW xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1404 SSE2 :PAVGB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1405 AVX :VPAVGB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1406 SSE2 :PAVGW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1407 AVX :VPAVGW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1408 SSE4.1 :PEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1409 SSE4.1 :PINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1410 SSE4.1 :PEXTRB + PINSRB r32 L: 2.50ns= 6.06c T: 0.85ns= 2.047c 1411 AVX :VPEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1412 AVX :VPINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1413 AVX :VPEXTRB + VPINSRB r32 L: 2.50ns= 6.05c T: 0.85ns= 2.046c 1414 SSE41_X64 :PEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1415 SSE41_X64 :PEXTRB r64 + PINSRB r32 L: 2.50ns= 6.05c T: 0.85ns= 2.047c 1416 AVX_X64 :VPEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1417 AVX_X64 :VPEXTRB r64 + VPINSRB r32 L: 2.50ns= 6.05c T: 0.85ns= 2.046c 1418 SSE2 :PEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1419 SSE2 :PINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1420 SSE2 :PEXTRW + PINSRW r32 L: 2.50ns= 6.05c T: 0.85ns= 2.045c 1421 AVX :VPEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1422 AVX :VPINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1423 AVX :VPEXTRW + VPINSRW r32 L: 2.50ns= 6.05c T: 0.85ns= 2.045c 1424 AMD64 :PEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1425 AMD64 :PEXTRW r64 + PINSRW r32 L: 2.50ns= 6.05c T: 0.85ns= 2.046c 1426 AVX_X64 :VPEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1427 AVX_X64 :VPEXTRW r64 + VPINSRW r32 L: 2.50ns= 6.05c T: 0.85ns= 2.045c 1428 SSE4.1 :PEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1429 SSE4.1 :PINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1430 SSE4.1 :PEXTRD + PINSRD r32 L: 2.50ns= 6.05c T: 0.85ns= 2.046c 1431 AVX :VPEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1432 AVX :VPINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1433 AVX :VPEXTRD + VPINSRD r32 L: 2.50ns= 6.06c T: 0.85ns= 2.046c 1434 SSE41_X64 :PEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1435 SSE41_X64 :PINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1436 SSE41_X64 :PEXTRD + PINSRD r64 L: 2.50ns= 6.05c T: 0.85ns= 2.047c 1437 AVX_X64 :VPEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1438 AVX_X64 :VPINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 1439 AVX_X64 :VPEXTRQ + VPINSRQ r64 L: 2.50ns= 6.06c T: 0.85ns= 2.046c 1440 SSE4.1 :EXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1441 AVX :VEXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1442 SSE41_X64 :EXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1443 AVX_X64 :VEXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 1444 SSE4.1 :INSERTPS xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1445 AVX :VINSERTPS xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1450 SSE2 :PMAXUB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1451 AVX :VPMAXUB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1452 SSE4.1 :PMAXSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1453 AVX :VPMAXSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1454 SSE4.1 :PMAXUW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1455 AVX :VPMAXUW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1456 SSE2 :PMAXSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1457 AVX :VPMAXSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1458 SSE4.1 :PMAXUD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1459 AVX :VPMAXUD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1460 SSE4.1 :PMAXSD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1461 AVX :VPMAXSD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1462 SSE2 :PMINUB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1463 AVX :VPMINUB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1464 SSE4.1 :PMINSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1465 AVX :VPMINSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1466 SSE4.1 :PMINUW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1467 AVX :VPMINUW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1468 SSE2 :PMINSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1469 AVX :VPMINSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1470 SSE4.1 :PMINUD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1471 AVX :VPMINUD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1472 SSE4.1 :PMINSD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1473 AVX :VPMINSD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1474 SSE2 :PSADBW xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1475 AVX :VPSADBW xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1476 SSSE3 :PSHUFB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1477 AVX :VPSHUFB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1478 SSE2 :PSHUFLW xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1479 AVX :VPSHUFLW xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1480 SSE2 :PSHUFHW xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1481 AVX :VPSHUFHW xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1482 SSE2 :PSHUFD xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1483 AVX :VPSHUFD xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1484 SSE3 :ADDSUBPS xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1485 AVX :VADDSUBPS xmm, xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1486 SSE3 :ADDSUBPD xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.512c 1487 AVX :VADDSUBPD xmm, xmm, xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1488 SSE3 :HADDPS xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1489 AVX :VHADDPS xmm, xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1490 SSE3 :HADDPD xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1491 AVX :VHADDPD xmm, xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1492 SSE3 :HSUBPS xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1493 AVX :VHSUBPS xmm, xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1494 SSE3 :HSUBPD xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1495 AVX :VHSUBPD xmm, xmm, xmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1496 SSE3 :MOVSLDUP xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1497 AVX :VMOVSLDUP xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1498 SSE3 :MOVSHDUP xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1499 AVX :VMOVSHDUP xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1500 SSE3 :MOVDDUP xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1501 AVX :VMOVDDUP xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1502 SSE3 :LDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 1503 AVX :VLDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 1504 SSSE3 :PABSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1505 AVX :VPABSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1506 SSSE3 :PABSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1507 AVX :VPABSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1508 SSSE3 :PABSD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1509 AVX :VPABSD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1510 SSSE3 :PALIGNR xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1511 AVX :VPALIGNR xmm, xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1512 SSSE3 :PHADDW xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1513 AVX :VPHADDW xmm, xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1514 SSSE3 :PHADDD xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1515 AVX :VPHADDD xmm, xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1516 SSSE3 :PHADDSW xmm, xmm L: 0.84ns= 2.02c T: 0.44ns= 1.071c 1517 AVX :VPHADDSW xmm, xmm, xmm L: 0.84ns= 2.02c T: 0.44ns= 1.071c 1518 SSSE3 :PHSUBW xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1519 AVX :VPHSUBW xmm, xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1520 SSSE3 :PHSUBD xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1521 AVX :VPHSUBD xmm, xmm, xmm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 1522 SSSE3 :PHSUBSW xmm, xmm L: 0.84ns= 2.02c T: 0.44ns= 1.071c 1523 AVX :VPHSUBSW xmm, xmm, xmm L: 0.84ns= 2.02c T: 0.44ns= 1.071c 1524 SSSE3 :PSIGNB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1525 AVX :VPSIGNB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1526 SSSE3 :PSIGNW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1527 AVX :VPSIGNW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 1528 SSSE3 :PSIGND xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1529 AVX :VPSIGND xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1530 SSE4.1 :BLENDPS xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.20ns= 0.486c 1531 AVX :VBLENDPS xmm, xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.15ns= 0.360c 1532 SSE4.1 :BLENDVPS xmm, xmm, L: 0.42ns= 1.01c T: 0.15ns= 0.353c 1533 AVX :VBLENDVPS xmm, xmm, xmm, xm L: 0.83ns= 2.02c T: 0.42ns= 1.011c 1534 SSE4.1 :BLENDPD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.16ns= 0.384c 1535 AVX :VBLENDPD xmm, xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.15ns= 0.359c 1536 SSE4.1 :BLENDVPD xmm, xmm, L: 0.42ns= 1.01c T: 0.15ns= 0.353c 1537 AVX :VBLENDVPD xmm, xmm, xmm, xm L: 0.83ns= 2.02c T: 0.42ns= 1.011c 1538 SSE4.1 :PBLENDW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1539 AVX :VPBLENDW xmm, xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1540 SSE4.1 :PBLENDVB xmm, xmm, L: 0.42ns= 1.01c T: 0.15ns= 0.353c 1541 AVX :VPBLENDVB xmm, xmm, xmm, xm L: 0.83ns= 2.02c T: 0.42ns= 1.011c 1542 SSE4.1 :DPPS xmm, xmm, imm8 L: 5.85ns= 14.14c T: 1.67ns= 4.043c 1543 AVX :VDPPS xmm, xmm, xmm, imm8 L: 5.85ns= 14.14c T: 1.67ns= 4.042c 1544 SSE4.1 :DPPD xmm, xmm, imm8 L: 3.76ns= 9.09c T: 0.44ns= 1.070c 1545 AVX :VDPPD xmm, xmm, xmm, imm8 L: 3.76ns= 9.09c T: 0.44ns= 1.070c 1546 SSE4.1 :MPSADBW xmm, xmm, imm8 L: 2.05ns= 4.96c T: 0.42ns= 1.010c 1547 AVX :VMPSADBW xmm, xmm, imm8 L: 2.05ns= 4.95c T: 0.42ns= 1.010c 1548 SSE4.1 :PHMINPOSUW xmm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1549 AVX :VPHMINPOSUW xmm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1550 SSE4.1 :PMOVSXBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1551 AVX :VPMOVSXBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1552 SSE4.1 :PMOVSXBD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1553 AVX :VPMOVSXBD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1554 SSE4.1 :PMOVSXBQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1555 AVX :VPMOVSXBQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1556 SSE4.1 :PMOVSXWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1557 AVX :VPMOVSXWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1558 SSE4.1 :PMOVSXWQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1559 AVX :VPMOVSXWQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1560 SSE4.1 :PMOVSXDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1561 AVX :VPMOVSXDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1562 SSE4.1 :PMOVZXBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1563 AVX :VPMOVZXBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1564 SSE4.1 :PMOVZXBD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1565 AVX :VPMOVZXBD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1566 SSE4.1 :PMOVZXBQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1567 AVX :VPMOVZXBQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1568 SSE4.1 :PMOVZXWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1569 AVX :VPMOVZXWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1570 SSE4.1 :PMOVZXWQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1571 AVX :VPMOVZXWQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1572 SSE4.1 :PMOVZXDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1573 AVX :VPMOVZXDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 1574 SSE4.1 :PTEST xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1575 AVX :VPTEST xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1576 AVX :VPTESTPS xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1577 AVX :VPTESTPD xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 1578 SSE4.1 :ROUNDSS xmm, xmm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1579 AVX :VROUNDSS xmm, xmm, xmm, im8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1580 SSE4.1 :ROUNDPS xmm, xmm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1581 AVX :VROUNDPS xmm, xmm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1582 SSE4.1 :ROUNDSD xmm, xmm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1583 AVX :VROUNDSD xmm, xmm, xmm, im8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1584 SSE4.1 :ROUNDPD xmm, xmm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1585 AVX :VROUNDPD xmm, xmm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1586 AVX :VBROADCASTSS xmm, m32 L: [memory dep.] T: 0.43ns= 1.029c 1587 SSE4.2 :PCMPESTRI xmm, xmm, imm8 L: 1.68ns= 4.07c T: 1.67ns= 4.042c 1588 AVX :VPCMPESTRI xmm, xmm, imm8 L: 1.67ns= 4.04c T: 1.67ns= 4.042c 1589 SSE4.2 :PCMPESTRM xmm, xmm, imm8 L: 2.09ns= 5.05c T: 2.09ns= 5.052c 1590 AVX :VPCMPESTRM xmm, xmm, imm8 L: 2.09ns= 5.05c T: 2.09ns= 5.052c 1591 SSE4.2 :PCMPISTRI xmm, xmm, imm8 L: 1.25ns= 3.02c T: 1.25ns= 3.031c 1592 AVX :VPCMPISTRI xmm, xmm, imm8 L: 1.25ns= 3.02c T: 1.25ns= 3.031c 1593 SSE4.2 :PCMPISTRM xmm, xmm, imm8 L: 1.25ns= 3.02c T: 1.25ns= 3.031c 1594 AVX :VPCMPISTRM xmm, xmm, imm8 L: 1.25ns= 3.02c T: 1.25ns= 3.031c 1595 CLMUL :PCLMULQDQ xmm, xmm, imm8 L: 2.50ns= 6.06c T: 0.42ns= 1.014c 1596 AVX_CLMUL :VPCLMULQDQ xmm,xmm,xmm,im8 L: 2.50ns= 6.05c T: 0.42ns= 1.010c 1597 AESNI :AESENC xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1598 AVX_AESNI :VAESENC xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1599 AESNI :AESENCLAST xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1600 AVX_AESNI :VAESENCLAST xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1601 AESNI :AESDEC xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1602 AVX_AESNI :VAESDEC xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1603 AESNI :AESDECLAST xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.512c 1604 AVX_AESNI :VAESDECLAST xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 1605 AESNI :AESIMC xmm, xmm L: 2.50ns= 6.05c T: 0.42ns= 1.020c 1606 AVX_AESNI :VAESIMC xmm, xmm L: 2.50ns= 6.05c T: 0.42ns= 1.020c 1607 AESNI :AESKEYGEN xmm, xmm, imm8 L: 5.01ns= 12.13c T: 5.03ns= 12.172c 1608 AVX_AESNI :VAESKEYGEN xmm, xmm, imm8 L: 5.01ns= 12.13c T: 5.03ns= 12.177c 1610 FMA3 :VFMADD132SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1611 FMA3 :VFMADD213SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1612 FMA3 :VFMADD231SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1614 FMA3 :VFMADD132PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1615 FMA3 :VFMADD213PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1616 FMA3 :VFMADD231PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1618 FMA3 :VFMSUB132SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1619 FMA3 :VFMSUB213SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1620 FMA3 :VFMSUB231SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1622 FMA3 :VFMSUB132PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1623 FMA3 :VFMSUB213PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1624 FMA3 :VFMSUB231PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1626 FMA3 :VFNMADD132SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1627 FMA3 :VFNMADD213SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1628 FMA3 :VFNMADD231SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1630 FMA3 :VFNMADD132PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1631 FMA3 :VFNMADD213PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1632 FMA3 :VFNMADD231PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1634 FMA3 :VFNMSUB132SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1635 FMA3 :VFNMSUB213SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1636 FMA3 :VFNMSUB231SS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1638 FMA3 :VFNMSUB132PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1639 FMA3 :VFNMSUB213PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1640 FMA3 :VFNMSUB231PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1642 FMA3 :VFMADDSUB132PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1643 FMA3 :VFMADDSUB213PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1644 FMA3 :VFMADDSUB231PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1646 FMA3 :VFMSUBADD132PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1647 FMA3 :VFMSUBADD213PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1648 FMA3 :VFMSUBADD231PS xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1650 FMA3 :VFMADD132SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1651 FMA3 :VFMADD213SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1652 FMA3 :VFMADD231SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1654 FMA3 :VFMADD132PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1655 FMA3 :VFMADD213PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1656 FMA3 :VFMADD231PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1658 FMA3 :VFMSUB132SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1659 FMA3 :VFMSUB213SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1660 FMA3 :VFMSUB231SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1662 FMA3 :VFMSUB132PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1663 FMA3 :VFMSUB213PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1664 FMA3 :VFMSUB231PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1666 FMA3 :VFNMADD132SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1667 FMA3 :VFNMADD213SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1668 FMA3 :VFNMADD231SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1670 FMA3 :VFNMADD132PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1671 FMA3 :VFNMADD213PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1672 FMA3 :VFNMADD231PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1674 FMA3 :VFNMSUB132SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1675 FMA3 :VFNMSUB213SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1676 FMA3 :VFNMSUB231SD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1678 FMA3 :VFNMSUB132PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1679 FMA3 :VFNMSUB213PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1680 FMA3 :VFNMSUB231PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1682 FMA3 :VFMADDSUB132PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1683 FMA3 :VFMADDSUB213PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1684 FMA3 :VFMADDSUB231PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1686 FMA3 :VFMSUBADD132PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1687 FMA3 :VFMSUBADD213PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1688 FMA3 :VFMSUBADD231PD xmm,xmm,xmm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1768 F16C :VCVTPS2PH xmm, xmm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1769 F16C :VCVTPH2PS xmm, xmm L: 2.09ns= 5.05c T: 0.42ns= 1.010c 1770 AVX :VMOVAPS ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1771 AVX :VMOVAPS ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 1772 AVX :VMOVAPS [m256], ymm L: [memory dep.] T: 0.37ns= 0.885c 1773 AVX :VMOVAPS LS pair L: 2.83ns= 6.84c T: 0.38ns= 0.915c 1774 AVX :VMOVUPS ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1775 AVX :VMOVUPS ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 1776 AVX :VMOVUPS [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 1777 AVX :VMOVUPS aligned LS pair L: 3.13ns= 7.58c T: 0.38ns= 0.915c 1778 AVX :VMOVUPS ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 1779 AVX :VMOVUPS [m256 + 4], ymm L: [memory dep.] T: 0.63ns= 1.516c 1780 AVX :VMOVUPS unaligned LS pair L: 3.11ns= 7.51c T: 0.73ns= 1.755c 1781 AVX :VMOVSLDUP ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1782 AVX :VMOVSHDUP ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1783 AVX :VMOVNTPS [m256], ymm L: [memory dep.] T: 3.71ns= 3.712c 1784 AVX :VMOVMSKPS r32, ymm L: [diff. reg. set] T: 0.42ns= 1.011c 1785 AVX :VMASKMOVPS ymm,ymm,[m256+4] L: [memory dep.] T: 0.42ns= 1.014c 1786 AVX :VMASKMOVPS [m256+4],ymm,ymm L: [memory dep.] T: 0.68ns= 1.646c 1787 AVX :VMASKMOVPS unaligned LS pair L: 7.70ns= 18.62c T: 0.86ns= 2.078c 1788 AVX :VUNPCKLPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1789 AVX :VUNPCKHPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1790 AVX :VSHUFPS ymm, ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.514c 1791 AVX :VPERMILPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1792 AVX :VPERMILPS ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1793 AVX :VCMPPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1794 AVX :VADDSUBPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1795 AVX :VHSUBPS ymm, ymm, ymm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1796 AVX :VHADDPS ymm, ymm, ymm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1797 AVX :VSUBPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1798 AVX :VADDPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1799 AVX :VMULPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1800 AVX :VMULPS+VADDPS ymm, ymm, ymm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1801 AVX :VMULPS ymm1.. VADDPS ymm2.. L: 1.67ns= 4.04c T: 0.42ns= 1.025c 1802 AVX :VMAXPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1803 AVX :VMINPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1804 AVX :VANDNPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1805 AVX :VANDNPS ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.16ns= 0.385c 1806 AVX :VANDPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1807 AVX :VANDPS ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.16ns= 0.388c 1808 AVX :VORPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1809 AVX :VORPS ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.16ns= 0.388c 1810 AVX :VXORPS ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 1811 AVX :VXORPS ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1812 AVX :VDIVPS ymm, ymm, ymm L: 4.59ns= 11.11c T: 2.09ns= 5.053c 1813 AVX :VDIVPS (0.0f/x) L: 4.59ns= 11.11c T: 2.09ns= 5.052c 1814 AVX :VDIVPS (x/1.0f) L: 4.59ns= 11.11c T: 2.09ns= 5.052c 1815 AVX :VDIVPS (x/2.0f) L: 3.24ns= 7.83c T: 2.09ns= 5.053c 1816 AVX :VDIVPS (x/0.5f) L: 3.24ns= 7.83c T: 2.09ns= 5.057c 1817 AVX :VSQRTPS ymm, ymm L: 5.01ns= 12.13c T: 2.51ns= 6.063c 1818 AVX :VSQRTPS (0.0f) L: 5.01ns= 12.13c T: 2.51ns= 6.064c 1819 AVX :VSQRTPS (1.0f) L: 5.01ns= 12.13c T: 2.51ns= 6.062c 1820 AVX :VRCPPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.42ns= 1.011c 1821 AVX :VRSQRTPS ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 1822 AVX :VBLENDPS ymm, ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.15ns= 0.360c 1823 AVX :VBLENDVPS ymm, ymm, ymm, ym L: 0.83ns= 2.02c T: 0.42ns= 1.011c 1824 AVX :VDPPS ymm, ymm, ymm, imm8 L: 5.85ns= 14.14c T: 1.67ns= 4.042c 1825 AVX :VPTESTPS ymm, ymm L: [no true dep.] T: 0.42ns= 1.010c 1826 AVX :VROUNDPS ymm, ymm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1827 AVX :VMOVAPD ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1828 AVX :VMOVAPD ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 1829 AVX :VMOVAPD [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 1830 AVX :VMOVAPD LS pair L: 3.11ns= 7.51c T: 0.38ns= 0.915c 1831 AVX :VMOVUPD ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1832 AVX :VMOVUPD ymm, [m256] L: [memory dep.] T: 0.21ns= 0.505c 1833 AVX :VMOVUPD [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 1834 AVX :VMOVUPD aligned LS pair L: 2.82ns= 6.83c T: 0.38ns= 0.915c 1835 AVX :VMOVUPD ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 1836 AVX :VMOVUPD [m256 + 4], ymm L: [memory dep.] T: 0.63ns= 1.516c 1837 AVX :VMOVUPD unaligned LS pair L: 3.09ns= 7.47c T: 0.72ns= 1.747c 1838 AVX :VMOVDDUP ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1839 AVX :VMOVNTPD [m256], ymm L: [memory dep.] T: 3.04ns= 3.038c 1840 AVX :VMOVMSKPD r32, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 1841 AVX :VMASKMOVPD ymm,ymm,[m256+4] L: [memory dep.] T: 0.42ns= 1.014c 1842 AVX :VMASKMOVPD [m256+4],ymm,ymm L: [memory dep.] T: 0.42ns= 1.014c 1843 AVX :VMASKMOVPD unaligned LS pair L: 7.10ns= 17.17c T: 0.86ns= 2.079c 1844 AVX :VUNPCKLPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1845 AVX :VUNPCKHPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1846 AVX :VSHUFPD ymm, ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 1847 AVX :VPERMILPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1848 AVX :VPERMILPD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1849 AVX :VCMPPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1850 AVX :VADDSUBPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1851 AVX :VHSUBPD ymm, ymm, ymm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1852 AVX :VHADDPD ymm, ymm, ymm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 1853 AVX :VSUBPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1854 AVX :VADDPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1855 AVX :VMULPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1856 AVX :VMULPD+VADDPD ymm, ymm, ymm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1857 AVX :VMULPD ymm1.. VADDPD ymm2.. L: 1.67ns= 4.04c T: 0.42ns= 1.025c 1858 AVX :VMAXPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1859 AVX :VMINPD ymm, ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1860 AVX :VANDNPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1861 AVX :VANDNPD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1862 AVX :VANDPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1863 AVX :VANDPD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1864 AVX :VORPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1865 AVX :VORPD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1866 AVX :VXORPD ymm, ymm, ymm L: 0.08ns= 0.20c T: 0.10ns= 0.250c 1867 AVX :VXORPD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 1868 AVX :VDIVPD ymm, ymm, ymm L: 5.85ns= 14.14c T: 3.34ns= 8.086c 1869 AVX :VDIVPD (0.0/x) L: 5.43ns= 13.13c T: 3.34ns= 8.088c 1870 AVX :VDIVPD (x/1.0) L: 5.43ns= 13.13c T: 3.34ns= 8.087c 1871 AVX :VDIVPD (x/2.0) L: 4.19ns= 10.14c T: 3.34ns= 8.086c 1872 AVX :VDIVPD (x/0.5) L: 4.19ns= 10.14c T: 3.34ns= 8.091c 1873 AVX :VSQRTPD ymm, ymm L: 7.51ns= 18.18c T: 5.03ns= 12.179c 1874 AVX :VSQRTPD (0.0) L: 5.43ns= 13.13c T: 3.76ns= 9.099c 1875 AVX :VSQRTPD (1.0) L: 5.43ns= 13.13c T: 3.76ns= 9.095c 1876 AVX :VBLENDPD ymm, ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.15ns= 0.360c 1877 AVX :VBLENDVPD ymm, ymm, ymm, ym L: 0.83ns= 2.02c T: 0.42ns= 1.011c 1878 AVX :VCVTDQ2PD ymm, xmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1879 AVX :VCVTPD2DQ xmm, ymm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1880 AVX :VCVTPD2DQ + VCVTDQ2PD L: 5.85ns= 14.14c T: 0.84ns= 2.024c 1881 AVX :VCVTTPD2DQ xmm, ymm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1882 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 5.85ns= 14.14c T: 0.84ns= 2.025c 1883 AVX :VCVTDQ2PS ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1884 AVX :VCVTPS2DQ ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1885 AVX :VCVTPS2DQ + VCVTDQ2PS L: 3.34ns= 8.08c T: 0.43ns= 1.030c 1886 AVX :VCVTTPS2DQ ymm, ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1887 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 3.34ns= 8.08c T: 0.43ns= 1.031c 1888 AVX :VCVTPS2PD ymm, xmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1889 AVX :VCVTPD2PS xmm, ymm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1890 AVX :VCVTPD2PS + VCVTPS2PD L: 5.85ns= 14.14c T: 0.84ns= 2.025c 1891 AVX :VPTESTPD ymm, ymm L: [no true dep.] T: 0.42ns= 1.014c 1892 AVX :VROUNDPD ymm, ymm, imm8 L: 3.34ns= 8.08c T: 0.43ns= 1.029c 1893 AVX :VBROADCASTSS ymm, m32 L: [memory dep.] T: 0.21ns= 0.505c 1894 AVX :VBROADCASTSD ymm, m64 L: [memory dep.] T: 0.21ns= 0.505c 1895 AVX :VBROADCASTF128 ymm, m128 L: [memory dep.] T: 0.21ns= 0.506c 1896 AVX :VEXTRACTF128 xmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1897 AVX :VINSERTF128 ym, ym, xm, im8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1898 AVX :VPERM2F128 ym, ym, ym, im8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 1899 AVX :VMOVDQA ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1900 AVX :VMOVDQA ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 1901 AVX :VMOVDQA [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 1902 AVX :VMOVDQA LS pair L: 3.12ns= 7.55c T: 0.38ns= 0.915c 1903 AVX :VMOVDQU ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 1904 AVX :VMOVDQU ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 1905 AVX :VMOVDQU [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 1906 AVX :VMOVDQU aligned LS pair L: 2.82ns= 6.83c T: 0.38ns= 0.915c 1907 AVX :VMOVDQU ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.011c 1908 AVX :VMOVDQU [m256 + 4], ymm L: [memory dep.] T: 0.63ns= 1.516c 1909 AVX :VMOVDQU unaligned LS pair L: 3.12ns= 7.55c T: 0.73ns= 1.755c 1910 AVX :VMOVNTDQ [m256], ymm L: [memory dep.] T: 3.09ns= 3.087c 1911 AVX :VLDDQU ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 1912 AVX :VZEROUPPER L: [no true dep.] T: 0.42ns= 1.010c 1913 AVX :VZEROALL L: [no true dep.] T: 4.61ns= 11.151c 1915 FMA3 :VFMADD132PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1916 FMA3 :VFMADD213PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1917 FMA3 :VFMADD231PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1919 FMA3 :VFMSUB132PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1920 FMA3 :VFMSUB213PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1921 FMA3 :VFMSUB231PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1923 FMA3 :VFNMADD132PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1924 FMA3 :VFNMADD213PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1925 FMA3 :VFNMADD231PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1927 FMA3 :VFNMSUB132PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1928 FMA3 :VFNMSUB213PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1929 FMA3 :VFNMSUB231PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1931 FMA3 :VFMADDSUB132PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1932 FMA3 :VFMADDSUB213PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1933 FMA3 :VFMADDSUB231PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1935 FMA3 :VFMSUBADD132PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1936 FMA3 :VFMSUBADD213PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1937 FMA3 :VFMSUBADD231PS ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1939 FMA3 :VFMADD132PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1940 FMA3 :VFMADD213PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1941 FMA3 :VFMADD231PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1943 FMA3 :VFMSUB132PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1944 FMA3 :VFMSUB213PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1945 FMA3 :VFMSUB231PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1947 FMA3 :VFNMADD132PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.513c 1948 FMA3 :VFNMADD213PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1949 FMA3 :VFNMADD231PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1951 FMA3 :VFNMSUB132PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1952 FMA3 :VFNMSUB213PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1953 FMA3 :VFNMSUB231PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1955 FMA3 :VFMADDSUB132PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1956 FMA3 :VFMADDSUB213PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1957 FMA3 :VFMADDSUB231PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1959 FMA3 :VFMSUBADD132PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1960 FMA3 :VFMSUBADD213PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1961 FMA3 :VFMSUBADD231PD ymm,ymm,ymm L: 1.67ns= 4.04c T: 0.21ns= 0.505c 1967 F16C :VCVTPS2PH + VCVTPH2PS L: 4.18ns= 10.10c T: 0.84ns= 2.025c 1968 F16C :VCVTPS2PH xmm, ymm, imm8 L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1969 F16C :VCVTPH2PS ymm, xmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 1970 F16C :VCVTPS2PH + VCVTPH2PS L: 2.92ns= 7.07c T: 0.84ns= 2.025c 1971 RDRAND :RDRAND r16 L: [no true dep.] T: 578.87ns=1400.372c 1972 RDRAND :RDRAND r32 L: [no true dep.] T: 570.91ns=1381.101c 1973 RDRAND_X64 :RDRAND r64 L: [no true dep.] T: 562.29ns=1360.261c 1974 X86 :MOV+ADD r8, r8 L: 0.83ns= 2.02c T: 0.25ns= 0.598c 1975 X86 :MOV+ADD r16, r16 L: 0.83ns= 2.02c T: 0.22ns= 0.528c 1976 X86 :MOV+ADD r32, r32 L: 0.21ns= 0.50c T: 0.25ns= 0.603c 1977 AMD64 :MOV+ADD r64, r64 L: 0.21ns= 0.50c T: 0.25ns= 0.611c 1978 MMX :MOVQ+PADDB mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1979 MMX :MOVQ+PADDW mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1980 MMX :MOVQ+PADDD mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1981 SSE2 :MOVQ+PADDQ mm, mm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 1983 SSE :MOVSS+ADDSS xmm, xmm L: 2.41ns= 5.82c T: 0.28ns= 0.674c 1984 AVX :VMOVSS+VADDSS xm, xm, xm L: 2.44ns= 5.90c T: 0.28ns= 0.674c 1985 SSE :MOVAPS+ADDPS xmm, xmm L: 2.66ns= 6.44c T: 0.28ns= 0.674c 1986 AVX :VMOVAPS+VADDPS xm, xm, xm L: 2.66ns= 6.44c T: 0.28ns= 0.675c 1987 SSE2 :MOVSD+ADDSD xmm, xmm L: 2.44ns= 5.90c T: 0.28ns= 0.674c 1988 AVX :VMOVSD+VADDSD xm, xm, xm L: 2.41ns= 5.82c T: 0.28ns= 0.674c 1989 SSE2 :MOVAPD+ADDPD xmm, xmm L: 2.66ns= 6.45c T: 0.28ns= 0.674c 1990 AVX :VMOVAPD+VADDPD xm, xm, xm L: 2.66ns= 6.44c T: 0.28ns= 0.675c 1991 SSE2 :MOVDQA+PADDB xmm, xmm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1992 SSE2 :MOVDQA+PADDW xmm, xmm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1993 SSE2 :MOVDQA+PADDD xmm, xmm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1994 SSE2 :MOVDQA+PADDQ xmm, xmm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1995 AVX :VMOVDQA+VPADDB xm, xm, xm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1996 AVX :VMOVDQA+VPADDW xm, xm, xm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1997 AVX :VMOVDQA+VPADDD xm, xm, xm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1998 AVX :VMOVDQA+VPADDQ xm, xm, xm L: 0.83ns= 2.02c T: 0.28ns= 0.674c 1999 AVX :VMOVAPS+VADDPS ym, ym, ym L: 2.66ns= 6.44c T: 0.28ns= 0.675c 2000 AVX :VMOVAPD+VADDPD ym, ym, ym L: 2.66ns= 6.44c T: 0.28ns= 0.675c 2001 RDSEED :RDSEED r16 L: [no true dep.] T: 566.39ns=1370.188c 2002 RDSEED :RDSEED r32 L: [no true dep.] T: 568.99ns=1376.471c 2003 RDSEED_X64 :RDSEED r64 L: [no true dep.] T: 568.31ns=1374.828c 2004 BMI :ANDN r32, r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2005 BMI_X64 :ANDN r64, r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2006 BMI :BEXTR r32, r32, r32 L: 0.84ns= 2.03c T: 0.40ns= 0.970c 2007 BMI_X64 :BEXTR r64, r64, r64 L: 0.83ns= 2.02c T: 0.40ns= 0.957c 2008 BMI :BLSI r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2009 BMI_X64 :BLSI r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2010 BMI :BLSMSK r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2011 BMI_X64 :BLSMSK r64, r64 L: 0.42ns= 1.01c T: 0.29ns= 0.690c 2012 BMI :BLSR r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2013 BMI_X64 :BLSR r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2014 BMI :TZCNT r16, r16 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2015 BMI :TZCNT r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2016 BMI_X64 :TZCNT r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2017 BMI2 :BZHI r32, r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2018 BMI2_X64 :BZHI r64, r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2019 BMI2 :MULX r32, r32, r32 L: 1.73ns= 4.17c T: 0.43ns= 1.047c 2020 BMI2_X64 :MULX r64, r64, r64 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2021 BMI2 :PDEP r32, r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.015c 2022 BMI2_X64 :PDEP r64, r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2023 BMI2 :PEXT r32, r32, r32 L: 1.25ns= 3.02c T: 0.42ns= 1.015c 2024 BMI2_X64 :PEXT r64, r64, r64 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2025 BMI2 :RORX r32, r32, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.506c 2026 BMI2_X64 :RORX r64, r64, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2027 BMI2 :SARX r32, r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2028 BMI2_X64 :SARX r64, r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2029 BMI2 :SHLX r32, r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2030 BMI2_X64 :SHLX r64, r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2031 BMI2 :SHRX r32, r32, r32 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2032 BMI2_X64 :SHRX r64, r64, r64 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2053 AVX2 :VMOVNTDQA ymm, [m256] L: [memory dep.] T: 0.52ns= 0.521c 2054 AVX2 :VMOVNTDQA + VMOVNTDQ ymm L: 174.79ns= 422.83c T: 422.83ns= 422.833c 2055 AVX2 :VPMOVMSKB r32, ymm L: [diff. reg. set] T: 0.42ns= 1.011c 2056 AVX2_X64 :VPMOVMSKB r64, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 2057 AVX2 :VPADDB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.17ns= 0.400c 2058 AVX2 :VPADDW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2059 AVX2 :VPADDD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2060 AVX2 :VPADDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2061 AVX2 :VPADDSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2062 AVX2 :VPADDSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2063 AVX2 :VPADDUSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2064 AVX2 :VPADDUSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2065 AVX2 :VPSUBB ymm, ymm, ymm L: 0.14ns= 0.34c T: 0.18ns= 0.430c 2066 AVX2 :VPSUBB ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2067 AVX2 :VPSUBW ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2068 AVX2 :VPSUBW ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2069 AVX2 :VPSUBD ymm, ymm, ymm L: 0.14ns= 0.34c T: 0.18ns= 0.428c 2070 AVX2 :VPSUBD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2071 AVX2 :VPSUBQ ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2072 AVX2 :VPSUBQ ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2073 AVX2 :VPSUBSB ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2074 AVX2 :VPSUBSB ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.508c 2075 AVX2 :VPSUBSW ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 2076 AVX2 :VPSUBSW ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 2077 AVX2 :VPSUBUSB ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2078 AVX2 :VPSUBUSB ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 2079 AVX2 :VPSUBUSW ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2080 AVX2 :VPSUBUSW ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 2081 AVX2 :VPCMPEQB ymm, ymm, ymm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 2082 AVX2 :VPCMPEQB ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.512c 2083 AVX2 :VPCMPEQW ymm, ymm, ymm L: 0.21ns= 0.50c T: 0.21ns= 0.510c 2084 AVX2 :VPCMPEQW ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 2085 AVX2 :VPCMPEQD ymm, ymm, ymm L: 0.21ns= 0.50c T: 0.21ns= 0.505c 2086 AVX2 :VPCMPEQD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.513c 2087 AVX2 :VPCMPEQQ ymm, ymm, ymm L: 0.21ns= 0.51c T: 0.21ns= 0.505c 2088 AVX2 :VPCMPEQQ ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.512c 2089 AVX2 :VPCMPGTB ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.249c 2090 AVX2 :VPCMPGTB ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.513c 2091 AVX2 :VPCMPGTW ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2092 AVX2 :VPCMPGTW ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 2093 AVX2 :VPCMPGTD ymm, ymm, ymm L: 0.14ns= 0.35c T: 0.18ns= 0.424c 2094 AVX2 :VPCMPGTD ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.21ns= 0.505c 2095 AVX2 :VPCMPGTQ ymm, ymm, ymm L: 0.09ns= 0.21c T: 0.11ns= 0.273c 2096 AVX2 :VPCMPGTQ ymm1, ymm1, ymm2 L: 1.26ns= 3.05c T: 0.42ns= 1.010c 2097 AVX2 :VPAND ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2098 AVX2 :VPAND ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2099 AVX2 :VPANDN ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2100 AVX2 :VPANDN ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2101 AVX2 :VPOR ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2102 AVX2 :VPOR ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2103 AVX2 :VPXOR ymm, ymm, ymm L: 0.08ns= 0.19c T: 0.10ns= 0.250c 2104 AVX2 :VPXOR ymm1, ymm1, ymm2 L: 0.41ns= 1.00c T: 0.14ns= 0.337c 2105 AVX2 :VPMULHW ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2106 AVX2 :VPMULHUW ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2107 AVX2 :VPMULHRSW ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2108 AVX2 :VPMULLW ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2109 AVX2 :VPMULLD ymm, ymm, ymm L: 4.18ns= 10.10c T: 0.43ns= 1.046c 2110 AVX2 :VPMULDQ ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2111 AVX2 :VPMULUDQ ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2112 AVX2 :VPMADDUBSW ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2113 AVX2 :VPMADDWD ymm, ymm, ymm L: 2.09ns= 5.05c T: 0.21ns= 0.505c 2114 AVX2 :VPSLLW ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2115 AVX2 :VPSLLW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2116 AVX2 :VPSLLD ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2117 AVX2 :VPSLLD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2118 AVX2 :VPSLLQ ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2119 AVX2 :VPSLLQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2120 AVX2 :VPSLLDQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2121 AVX2 :VPSRAW ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.011c 2122 AVX2 :VPSRAW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2123 AVX2 :VPSRAD ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2124 AVX2 :VPSRAD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2125 AVX2 :VPSRLW ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2126 AVX2 :VPSRLW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2127 AVX2 :VPSRLD ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2128 AVX2 :VPSRLD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2129 AVX2 :VPSRLQ ymm, ymm, xmm L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2130 AVX2 :VPSRLQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2131 AVX2 :VPSRLDQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.22ns= 0.525c 2132 AVX2 :VPUNPCKHBW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2133 AVX2 :VPUNPCKHWD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2134 AVX2 :VPUNPCKHDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2135 AVX2 :VPUNPCKHQDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2136 AVX2 :VPUNPCKLBW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2137 AVX2 :VPUNPCKLWD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.514c 2138 AVX2 :VPUNPCKLDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2139 AVX2 :VPUNPCKLQDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2140 AVX2 :VPACKSSWB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2141 AVX2 :VPACKUSWB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2142 AVX2 :VPACKSSDW ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2143 AVX2 :VPACKUSDW ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2144 AVX2 :VPAVGB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2145 AVX2 :VPAVGW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2146 AVX2 :VPMAXUB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2147 AVX2 :VPMAXSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2148 AVX2 :VPMAXUW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2149 AVX2 :VPMAXSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2150 AVX2 :VPMAXUD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2151 AVX2 :VPMAXSD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2152 AVX2 :VPMINUB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2153 AVX2 :VPMINSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2154 AVX2 :VPMINUW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2155 AVX2 :VPMINSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2156 AVX2 :VPMINUD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2157 AVX2 :VPMINSD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2158 AVX2 :VPSADBW ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2159 AVX2 :VPSHUFB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2160 AVX2 :VPSHUFLW ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2161 AVX2 :VPSHUFHW ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2162 AVX2 :VPSHUFD ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.514c 2163 AVX2 :VPABSB ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2164 AVX2 :VPABSW ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2165 AVX2 :VPABSD ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2166 AVX2 :VPALIGNR ymm, ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 2167 AVX2 :VPHADDW ymm, ymm, ymm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 2168 AVX2 :VPHADDD ymm, ymm, ymm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 2169 AVX2 :VPHADDSW ymm, ymm, ymm L: 0.84ns= 2.02c T: 0.44ns= 1.071c 2170 AVX2 :VPHSUBW ymm, ymm, ymm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 2171 AVX2 :VPHSUBD ymm, ymm, ymm L: 0.86ns= 2.08c T: 0.45ns= 1.082c 2172 AVX2 :VPHSUBSW ymm, ymm, ymm L: 0.86ns= 2.08c T: 0.44ns= 1.071c 2173 AVX2 :VPSIGNB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2174 AVX2 :VPSIGNW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2175 AVX2 :VPSIGND ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2176 AVX2 :VPBLENDW ymm, ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2177 AVX2 :VPBLENDVB ymm, ymm, ymm, ym L: 0.83ns= 2.02c T: 0.42ns= 1.011c 2178 AVX2 :VPBLENDD xmm, xmm, xmm, im8 L: 0.42ns= 1.01c T: 0.15ns= 0.359c 2179 AVX2 :VPBLENDD ymm, ymm, ymm, im8 L: 0.42ns= 1.01c T: 0.15ns= 0.360c 2180 AVX2 :VMPSADBW ymm, ymm, imm8 L: 2.05ns= 4.95c T: 0.42ns= 1.010c 2181 AVX2 :VPMOVSXBW ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2182 AVX2 :VPMOVSXBD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2183 AVX2 :VPMOVSXBQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2184 AVX2 :VPMOVSXWD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2185 AVX2 :VPMOVSXWQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2186 AVX2 :VPMOVSXDQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2187 AVX2 :VPMOVZXBW ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2188 AVX2 :VPMOVZXBD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2189 AVX2 :VPMOVZXBQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2190 AVX2 :VPMOVZXWD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2191 AVX2 :VPMOVZXWQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2192 AVX2 :VPMOVZXDQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2193 AVX2 :VPMASKMOVD xmm,xmm,[m128+4] L: [memory dep.] T: 0.41ns= 0.982c 2194 AVX2 :VPMASKMOVD [m128+4],xmm,xmm L: [memory dep.] T: 0.42ns= 1.010c 2195 AVX2 :VPMASKMOVD unaligned LS pair L: 6.68ns= 16.16c T: 0.85ns= 2.052c 2196 AVX2 :VPMASKMOVQ xmm,xmm,[m128+4] L: [memory dep.] T: 0.41ns= 0.980c 2197 AVX2 :VPMASKMOVQ [m128+4],xmm,xmm L: [memory dep.] T: 0.42ns= 1.011c 2198 AVX2 :VPMASKMOVQ unaligned LS pair L: 6.68ns= 16.16c T: 0.85ns= 2.052c 2199 AVX2 :VPMASKMOVD ymm,ymm,[m256+4] L: [memory dep.] T: 0.41ns= 0.983c 2200 AVX2 :VPMASKMOVD [m256+4],ymm,ymm L: [memory dep.] T: 0.42ns= 1.013c 2201 AVX2 :VPMASKMOVD unaligned LS pair L: 7.08ns= 17.12c T: 1.43ns= 3.470c 2202 AVX2 :VPMASKMOVQ ymm,ymm,[m256+4] L: [memory dep.] T: 0.40ns= 0.970c 2203 AVX2 :VPMASKMOVQ [m256+4],ymm,ymm L: [memory dep.] T: 0.42ns= 1.014c 2204 AVX2 :VPMASKMOVQ unaligned LS pair L: 7.70ns= 18.63c T: 1.43ns= 3.469c 2205 AVX2 :VBROADCASTSS xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.013c 2206 AVX2 :VBROADCASTSS ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2207 AVX2 :VBROADCASTSD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2208 AVX2 :VPBROADCASTB xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2209 AVX2 :VPBROADCASTB ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 2210 AVX2 :VPBROADCASTW xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2211 AVX2 :VPBROADCASTW ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2212 AVX2 :VPBROADCASTD xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2213 AVX2 :VPBROADCASTD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2214 AVX2 :VPBROADCASTQ xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2215 AVX2 :VPBROADCASTQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.011c 2216 AVX2 :VBROADCASTI128 ymm, m128 L: [memory dep.] T: 0.21ns= 0.506c 2217 AVX2 :VEXTRACTI128 xmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2218 AVX2 :VINSERTI128 ym, ym, xm, im8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2219 AVX2 :VPERM2I128 ym, ym, ym, im8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2220 AVX2 :VPERMD ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2221 AVX2 :VPERMQ ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.013c 2222 AVX2 :VPERMPS ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2223 AVX2 :VPERMPD ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 2224 AVX2 :VPSLLVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2225 AVX2 :VPSLLVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2226 AVX2 :VPSLLVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2227 AVX2 :VPSLLVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2228 AVX2 :VPSRLVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2229 AVX2 :VPSRLVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2230 AVX2 :VPSRLVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2231 AVX2 :VPSRLVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 2232 AVX2 :VPSRAVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2233 AVX2 :VPSRAVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2234 ADX :ADCX r32, r32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2235 ADX_X64 :ADCX r64, r64 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2236 ADX :ADOX r32, r32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2237 ADX_X64 :ADOX r64, r64 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2238 CLFLUSH :CLFLUSH [mem] L: [memory dep.] T: 28.50ns= 68.956c 2239 CLFLUSHOPT :CLFLUSHOPT [mem] L: [memory dep.] T: 1.64ns= 3.976c 2241 SHA :SHA1RNDS4 xmm, xmm, imm8 L: 2.50ns= 6.05c T: 1.25ns= 3.032c 2242 SHA :SHA1NEXTE xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.011c 2243 SHA :SHA1MSG1 xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 2244 SHA :SHA1MSG2 xmm, xmm L: 2.57ns= 6.21c T: 1.67ns= 4.042c 2245 SHA :SHA256RNDS2 xm, xm, L: 1.67ns= 4.04c T: 1.25ns= 3.032c 2246 SHA :SHA256MSG1 xmm, xmm L: 2.22ns= 5.38c T: 1.67ns= 4.042c 2247 SHA :SHA256MSG2 xmm, xmm L: 4.59ns= 11.11c T: 2.09ns= 5.052c 2248 X86 :MOV r1_8, r2_8 L: 0.42ns= 1.01c T: 0.11ns= 0.258c 2249 X86 :MOV r1_16, r2_16 L: 0.42ns= 1.01c T: 0.10ns= 0.253c 2250 X86 :MOV r1_32, r2_32 L: 0.10ns= 0.25c T: 0.11ns= 0.263c 2251 AMD64 :MOV r1_64, r2_64 L: 0.10ns= 0.24c T: 0.11ns= 0.262c 2252 X86 :MOVSX r1_16, r2_8 L: 0.42ns= 1.01c T: 0.12ns= 0.283c 2253 X86 :MOVSX r1_32, r2_8 L: 0.10ns= 0.25c T: 0.10ns= 0.253c 2254 AMD64 :MOVSX r1_64, r2_8 L: 0.10ns= 0.25c T: 0.10ns= 0.253c 2255 X86 :MOVSX r1_32, r2_16 L: 0.10ns= 0.25c T: 0.11ns= 0.258c 2256 AMD64 :MOVSX r1_64, r2_16 L: 0.10ns= 0.25c T: 0.10ns= 0.252c 2257 AMD64 :MOVSXD r1_64, r2_32 L: 0.10ns= 0.25c T: 0.12ns= 0.290c 2258 X86 :MOVZX r1_16, r2_8 L: 0.42ns= 1.01c T: 0.12ns= 0.283c 2259 X86 :MOVZX r1_32, r2_8 L: 0.10ns= 0.25c T: 0.10ns= 0.252c 2260 AMD64 :MOVZX r1_64, r2_8 L: 0.10ns= 0.25c T: 0.10ns= 0.252c 2261 X86 :MOVZX r1_32, r2_16 L: 0.10ns= 0.25c T: 0.11ns= 0.258c 2262 AMD64 :MOVZX r1_64, r2_16 L: 0.15ns= 0.37c T: 0.18ns= 0.433c 2263 MMX :MOVQ mm1, mm2 L: 0.21ns= 0.50c T: 0.21ns= 0.505c 2264 SSE :MOVSS xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2265 AVX :VMOVSS xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2266 SSE :MOVAPS xmm1, xmm2 L: 0.08ns= 0.20c T: 0.10ns= 0.245c 2267 AVX :VMOVAPS xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.264c 2268 SSE :MOVUPS xmm1, xmm2 L: 0.08ns= 0.20c T: 0.10ns= 0.245c 2269 AVX :VMOVUPS xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2270 SSE2 :MOVSD xmm1, xmm2 L: 0.42ns= 1.01c T: 0.18ns= 0.446c 2271 AVX :VMOVSD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.14ns= 0.337c 2272 SSE2 :MOVAPD xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.269c 2273 AVX :VMOVAPD xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2274 SSE2 :MOVUPD xmm1, xmm2 L: 0.14ns= 0.33c T: 0.18ns= 0.441c 2275 AVX :VMOVUPD xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2276 SSE2 :MOVDQA xmm1, xmm2 L: 0.15ns= 0.36c T: 0.18ns= 0.442c 2277 AVX :VMOVDQA xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2278 SSE2 :MOVDQU xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.268c 2279 AVX :VMOVDQU xmm1, xmm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2280 AVX :VMOVAPS ymm1, ymm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2281 AVX :VMOVUPS ymm1, ymm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2282 AVX :VMOVAPD ymm1, ymm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2283 AVX :VMOVUPD ymm1, ymm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2284 AVX :VMOVDQA ymm1, ymm2 L: 0.08ns= 0.20c T: 0.11ns= 0.264c 2285 AVX :VMOVDQU ymm1, ymm2 L: 0.08ns= 0.20c T: 0.11ns= 0.265c 2286 AVX2 :VPADDD+VADDPS ym, ym, ym L: 2.66ns= 6.44c T: 0.28ns= 0.675c 2287 AVX2 :VPADDQ+VADDPD ym, ym, ym L: 2.66ns= 6.44c T: 0.28ns= 0.675c 2288 AVX2 :VCMPPS+VPADDD ym, ym, ym L: 2.66ns= 6.44c T: 0.30ns= 0.717c 2289 AVX2 :VCMPPD+VPADDQ ym, ym, ym L: 2.68ns= 6.49c T: 0.30ns= 0.717c 2290 SSE :4xADDPS xm1,xm1 4x xm2,xm2 L: 6.68ns= 16.16c T: 6.68ns= 16.169c 2291 SSE :4xMULPS xm1,xm1 4x xm2,xm2 L: 6.68ns= 16.16c T: 6.68ns= 16.168c 2292 SSE2 :4xADDPD xm1,xm1 4x xm2,xm2 L: 6.68ns= 16.16c T: 6.68ns= 16.168c 2293 SSE2 :4xMULPD xm1,xm1 4x xm2,xm2 L: 6.68ns= 16.16c T: 6.68ns= 16.169c 2294 LNOP :LNOP3 [eax], eax L: [no true dep.] T: 0.12ns= 0.291c 2295 LNOP :LNOP4 [eax+disp8], eax L: [no true dep.] T: 0.10ns= 0.239c 2296 LNOP :LNOP5 [SIB+disp8], eax L: [no true dep.] T: 0.12ns= 0.293c 2297 LNOP :LNOP6 [SIB+disp8], ax L: [no true dep.] T: 0.14ns= 0.328c 2298 LNOP :LNOP7 [eax+disp32], eax L: [no true dep.] T: 0.16ns= 0.389c 2299 LNOP :LNOP8 [SIB+disp32], eax L: [no true dep.] T: 0.18ns= 0.439c 2300 LNOP :LNOP9 [SIB+disp32], ax L: [no true dep.] T: 0.24ns= 0.581c 2301 LNOP :2x66 LNOPA [SIB+disp32], ax L: [no true dep.] T: 0.27ns= 0.655c 2302 LNOP :3x66 LNOPB [SIB+disp32], ax L: [no true dep.] T: 0.30ns= 0.715c 2303 LNOP :4x66 LNOPC [SIB+disp32], ax L: [no true dep.] T: 0.32ns= 0.780c 2304 LNOP :5x66 LNOPD [SIB+disp32], ax L: [no true dep.] T: 0.35ns= 0.846c 2305 LNOP :6x66 LNOPE [SIB+disp32], ax L: [no true dep.] T: 0.38ns= 0.911c 2306 LNOP :7x66 LNOPF [SIB+disp32], ax L: [no true dep.] T: 0.40ns= 0.976c 2309 AVX2 :VGATHERDPS xmm, [xm32], xmm L: 8.37ns= 20.25c T: 1.25ns= 3.031c 2310 AVX2 :VGATHERDPS ymm, [ym32], ymm L: 9.21ns= 22.28c T: 2.09ns= 5.053c 2311 AVX2 :VGATHERQPS xmm, [xm64], xmm L: 7.54ns= 18.23c T: 0.59ns= 1.416c 2312 AVX2 :VGATHERQPS xmm, [ym64], xmm L: 8.37ns= 20.25c T: 1.25ns= 3.031c 2313 AVX2 :VGATHERDPD xmm, [xm32], xmm L: 7.54ns= 18.23c T: 0.58ns= 1.403c 2314 AVX2 :VGATHERDPD ymm, [xm32], ymm L: 8.37ns= 20.25c T: 1.25ns= 3.031c 2315 AVX2 :VGATHERQPD xmm, [xm64], xmm L: 7.54ns= 18.23c T: 0.59ns= 1.416c 2316 AVX2 :VGATHERQPD ymm, [ym64], ymm L: 8.37ns= 20.25c T: 1.25ns= 3.031c 2317 AVX2 :VPGATHERDD xmm, [xm32], xmm L: 8.37ns= 20.25c T: 1.25ns= 3.032c 2318 AVX2 :VPGATHERDD ymm, [ym32], ymm L: 9.21ns= 22.27c T: 2.09ns= 5.054c 2319 AVX2 :VPGATHERQD xmm, [xm64], xmm L: 7.54ns= 18.23c T: 0.57ns= 1.382c 2320 AVX2 :VPGATHERQD xmm, [ym64], xmm L: 8.37ns= 20.25c T: 1.25ns= 3.031c 2321 AVX2 :VPGATHERDQ xmm, [xm32], xmm L: 7.54ns= 18.23c T: 0.58ns= 1.394c 2322 AVX2 :VPGATHERDQ ymm, [xm32], ymm L: 8.37ns= 20.25c T: 1.25ns= 3.032c 2323 AVX2 :VPGATHERQQ xmm, [xm64], xmm L: 7.54ns= 18.23c T: 0.57ns= 1.389c 2324 AVX2 :VPGATHERQQ ymm, [ym64], ymm L: 8.37ns= 20.25c T: 1.25ns= 3.032c 2326 CLWB :CLWB [mem] L: [memory dep.] T: 2.65ns= 6.413c 2330 RDPID :RDPID r32/r64 L: [no true dep.] T: 2.09ns= 5.053c 2331 AVX512DQ :KADDB k, k, k L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2332 AVX512DQ :KADDW k, k, k L: 1.67ns= 4.04c T: 0.42ns= 1.014c 2333 AVX512BW :KADDD k, k, k L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2334 AVX512BW :KADDQ k, k, k L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2335 AVX512DQ :KANDB k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2336 AVX512F :KANDW k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2337 AVX512BW :KANDD k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.014c 2338 AVX512BW :KANDQ k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2339 AVX512DQ :KANDNB k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.014c 2340 AVX512F :KANDNW k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.012c 2341 AVX512BW :KANDND k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2342 AVX512BW :KANDNQ k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2343 AVX512DQ :KMOVB k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2344 AVX512DQ :KMOVB k, [mem8] L: [memory dep.] T: 0.51ns= 1.239c 2345 AVX512DQ :KMOVB [mem8], k L: [memory dep.] T: 0.21ns= 0.505c 2346 AVX512DQ :KMOVB k, [mem8] + KMOVB [mem8], k L: 3.25ns= 7.85c T: 0.42ns= 1.011c 2347 AVX512DQ :KMOVB k, r32 L: [diff. reg. set] T: 0.42ns= 1.011c 2348 AVX512DQ :KMOVB r32, k L: [diff. reg. set] T: 0.42ns= 1.011c 2349 AVX512DQ :KMOVB k, r32 + KMOVB r32, k L: 1.67ns= 4.04c T: 0.42ns= 1.014c 2350 AVX512F :KMOVW k, k L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2351 AVX512F :KMOVW k, [mem16] L: [memory dep.] T: 0.42ns= 1.010c 2352 AVX512F :KMOVW [mem16], k L: [memory dep.] T: 0.21ns= 0.505c 2353 AVX512F :KMOVW k, [mem16] + KMOVW [mem16], k L: 3.36ns= 8.12c T: 0.42ns= 1.011c 2354 AVX512F :KMOVW k, r32 L: [diff. reg. set] T: 0.42ns= 1.014c 2355 AVX512F :KMOVW r32, k L: [diff. reg. set] T: 0.42ns= 1.010c 2356 AVX512F :KMOVW k, r32 + KMOVW r32, k L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2357 AVX512BW :KMOVD k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2358 AVX512BW :KMOVD k, [mem32] L: [memory dep.] T: 0.42ns= 1.011c 2359 AVX512BW :KMOVD [mem32], k L: [memory dep.] T: 0.21ns= 0.506c 2360 AVX512BW :KMOVD k, [mem32] + KMOVD [mem32], k L: 3.24ns= 7.85c T: 0.42ns= 1.012c 2361 AVX512BW :KMOVD k, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 2362 AVX512BW :KMOVD r32, k L: [diff. reg. set] T: 0.42ns= 1.010c 2363 AVX512BW :KMOVD k, r32 + KMOVD r32, k L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2364 AVX512BW :KMOVQ k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2365 AVX512BW :KMOVQ k, [mem64] L: [memory dep.] T: 0.42ns= 1.010c 2366 AVX512BW :KMOVQ [mem64], k L: [memory dep.] T: 0.21ns= 0.505c 2367 AVX512BW :KMOVQ k, [mem64] + KMOVQ [mem64], k L: 3.26ns= 7.88c T: 0.48ns= 1.164c 2368 AVX512BW_X64 :KMOVQ k, r64 L: [diff. reg. set] T: 0.42ns= 1.011c 2369 AVX512BW_X64 :KMOVQ r64, k L: [diff. reg. set] T: 0.42ns= 1.011c 2370 AVX512BW_X64 :KMOVQ k, r64 + KMOVQ r64, k L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2371 AVX512DQ :KNOTB k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2372 AVX512F :KNOTW k, k L: 0.42ns= 1.01c T: 0.42ns= 1.011c 2373 AVX512BW :KNOTD k, k L: 0.42ns= 1.01c T: 0.42ns= 1.014c 2374 AVX512BW :KNOTQ k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2375 AVX512DQ :KORB k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2376 AVX512F :KORW k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2377 AVX512BW :KORD k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2378 AVX512BW :KORQ k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2379 AVX512DQ :KORTESTB k, k L: [no true dep.] T: 0.42ns= 1.011c 2380 AVX512F :KORTESTW k, k L: [no true dep.] T: 0.42ns= 1.014c 2381 AVX512BW :KORTESTD k, k L: [no true dep.] T: 0.42ns= 1.010c 2382 AVX512BW :KORTESTQ k, k L: [no true dep.] T: 0.42ns= 1.010c 2383 AVX512DQ :KSHIFTLB k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2384 AVX512F :KSHIFTLW k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2385 AVX512BW :KSHIFTLD k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2386 AVX512BW :KSHIFTLQ k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2387 AVX512DQ :KSHIFTRB k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2388 AVX512F :KSHIFTRW k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.014c 2389 AVX512BW :KSHIFTRD k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2390 AVX512BW :KSHIFTRQ k, k, imm8 L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2391 AVX512DQ :KTESTB k, k L: [no true dep.] T: 0.42ns= 1.010c 2392 AVX512DQ :KTESTW k, k L: [no true dep.] T: 0.42ns= 1.010c 2393 AVX512BW :KTESTD k, k L: [no true dep.] T: 0.42ns= 1.010c 2394 AVX512BW :KTESTQ k, k L: [no true dep.] T: 0.42ns= 1.010c 2395 AVX512F :KUNPCKBW k, k, k L: 1.67ns= 4.04c T: 0.42ns= 1.010c 2396 AVX512BW :KUNPCKWD k, k, k L: 1.67ns= 4.04c T: 0.42ns= 1.011c 2397 AVX512BW :KUNPCKDQ k, k, k L: 1.67ns= 4.03c T: 0.42ns= 1.013c 2398 AVX512DQ :KXNORB k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2399 AVX512F :KXNORW k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.014c 2400 AVX512BW :KXNORD k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2401 AVX512BW :KXNORQ k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.014c 2402 AVX512DQ :KXORB k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2403 AVX512F :KXORW k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2404 AVX512BW :KXORD k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2405 AVX512BW :KXORQ k, k, k L: 0.42ns= 1.01c T: 0.42ns= 1.010c 2406 AVX512F :{EVEX} VADDSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2407 AVX512VL :{EVEX} VADDPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2408 AVX512VL :{EVEX} VADDPS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2409 AVX512F :VADDPS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2410 AVX512F :{EVEX} VADDSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2411 AVX512VL :{EVEX} VADDPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2412 AVX512VL :{EVEX} VADDPD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2413 AVX512F :VADDPD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2414 AVX512F :{EVEX} VSUBSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2415 AVX512VL :{EVEX} VSUBPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2416 AVX512VL :{EVEX} VSUBPS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2417 AVX512F :VSUBPS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2418 AVX512F :{EVEX} VSUBSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2419 AVX512VL :{EVEX} VSUBPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2420 AVX512VL :{EVEX} VSUBPD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2421 AVX512F :VSUBPD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.012c 2422 AVX512F :{EVEX} VMULSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.508c 2423 AVX512VL :{EVEX} VMULPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2424 AVX512VL :{EVEX} VMULPS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2425 AVX512F :VMULPS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2426 AVX512F :{EVEX} VMULSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2427 AVX512VL :{EVEX} VMULPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2428 AVX512VL :{EVEX} VMULPD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2429 AVX512F :VMULPD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2430 AVX512F :{EVEX} VFMADD132SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2431 AVX512VL :{EVEX} VFMADD132PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2432 AVX512VL :{EVEX} VFMADD132PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2433 AVX512F :VFMADD132PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2434 AVX512F :{EVEX} VFMADD132SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2435 AVX512VL :{EVEX} VFMADD132PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2436 AVX512VL :{EVEX} VFMADD132PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2437 AVX512F :VFMADD132PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2438 AVX512F :{EVEX} VFMADD213SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2439 AVX512VL :{EVEX} VFMADD213PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2440 AVX512VL :{EVEX} VFMADD213PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2441 AVX512F :VFMADD213PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2442 AVX512F :{EVEX} VFMADD213SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2443 AVX512VL :{EVEX} VFMADD213PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2444 AVX512VL :{EVEX} VFMADD213PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2445 AVX512F :VFMADD213PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.013c 2446 AVX512F :{EVEX} VFMADD231SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2447 AVX512VL :{EVEX} VFMADD231PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2448 AVX512VL :{EVEX} VFMADD231PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2449 AVX512F :VFMADD231PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2450 AVX512F :{EVEX} VFMADD231SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2451 AVX512VL :{EVEX} VFMADD231PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2452 AVX512VL :{EVEX} VFMADD231PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2453 AVX512F :VFMADD231PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2454 AVX512F :{EVEX} VFMSUB132SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2455 AVX512VL :{EVEX} VFMSUB132PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2456 AVX512VL :{EVEX} VFMSUB132PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2457 AVX512F :VFMSUB132PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2458 AVX512F :{EVEX} VFMSUB132SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2459 AVX512VL :{EVEX} VFMSUB132PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2460 AVX512VL :{EVEX} VFMSUB132PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2461 AVX512F :VFMSUB132PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2462 AVX512F :{EVEX} VFMSUB213SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.519c 2463 AVX512VL :{EVEX} VFMSUB213PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2464 AVX512VL :{EVEX} VFMSUB213PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2465 AVX512F :VFMSUB213PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2466 AVX512F :{EVEX} VFMSUB213SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2467 AVX512VL :{EVEX} VFMSUB213PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2468 AVX512VL :{EVEX} VFMSUB213PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2469 AVX512F :VFMSUB213PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2470 AVX512F :{EVEX} VFMSUB231SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2471 AVX512VL :{EVEX} VFMSUB231PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2472 AVX512VL :{EVEX} VFMSUB231PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2473 AVX512F :VFMSUB231PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2474 AVX512F :{EVEX} VFMSUB231SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2475 AVX512VL :{EVEX} VFMSUB231PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2476 AVX512VL :{EVEX} VFMSUB231PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2477 AVX512F :VFMSUB231PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2478 AVX512F :{EVEX} VFNMADD132SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2479 AVX512VL :{EVEX} VFNMADD132PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2480 AVX512VL :{EVEX} VFNMADD132PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2481 AVX512F :VFNMADD132PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2482 AVX512F :{EVEX} VFNMADD132SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2483 AVX512VL :{EVEX} VFNMADD132PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2484 AVX512VL :{EVEX} VFNMADD132PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2485 AVX512F :VFNMADD132PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2486 AVX512F :{EVEX} VFNMADD213SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2487 AVX512VL :{EVEX} VFNMADD213PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2488 AVX512VL :{EVEX} VFNMADD213PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2489 AVX512F :VFNMADD213PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2490 AVX512F :{EVEX} VFNMADD213SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2491 AVX512VL :{EVEX} VFNMADD213PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2492 AVX512VL :{EVEX} VFNMADD213PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2493 AVX512F :VFNMADD213PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2494 AVX512F :{EVEX} VFNMADD231SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2495 AVX512VL :{EVEX} VFNMADD231PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2496 AVX512VL :{EVEX} VFNMADD231PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2497 AVX512F :VFNMADD231PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2498 AVX512F :{EVEX} VFNMADD231SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2499 AVX512VL :{EVEX} VFNMADD231PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2500 AVX512VL :{EVEX} VFNMADD231PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2501 AVX512F :VFNMADD231PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2502 AVX512F :{EVEX} VFNMSUB132SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2503 AVX512VL :{EVEX} VFNMSUB132PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2504 AVX512VL :{EVEX} VFNMSUB132PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2505 AVX512F :VFNMSUB132PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2506 AVX512F :{EVEX} VFNMSUB132SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2507 AVX512VL :{EVEX} VFNMSUB132PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2508 AVX512VL :{EVEX} VFNMSUB132PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2509 AVX512F :VFNMSUB132PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2510 AVX512F :{EVEX} VFNMSUB213SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2511 AVX512VL :{EVEX} VFNMSUB213PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2512 AVX512VL :{EVEX} VFNMSUB213PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2513 AVX512F :VFNMSUB213PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2514 AVX512F :{EVEX} VFNMSUB213SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2515 AVX512VL :{EVEX} VFNMSUB213PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2516 AVX512VL :{EVEX} VFNMSUB213PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2517 AVX512F :VFNMSUB213PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2518 AVX512F :{EVEX} VFNMSUB231SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2519 AVX512VL :{EVEX} VFNMSUB231PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2520 AVX512VL :{EVEX} VFNMSUB231PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2521 AVX512F :VFNMSUB231PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2522 AVX512F :{EVEX} VFNMSUB231SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2523 AVX512VL :{EVEX} VFNMSUB231PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2524 AVX512VL :{EVEX} VFNMSUB231PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2525 AVX512F :VFNMSUB231PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2526 AVX512VL :{EVEX} VFMADDSUB132PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2527 AVX512VL :{EVEX} VFMADDSUB132PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2528 AVX512F :VFMADDSUB132PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2529 AVX512VL :{EVEX} VFMADDSUB132PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2530 AVX512VL :{EVEX} VFMADDSUB132PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2531 AVX512F :VFMADDSUB132PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.018c 2532 AVX512VL :{EVEX} VFMADDSUB213PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2533 AVX512VL :{EVEX} VFMADDSUB213PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2534 AVX512F :VFMADDSUB213PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2535 AVX512VL :{EVEX} VFMADDSUB213PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2536 AVX512VL :{EVEX} VFMADDSUB213PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2537 AVX512F :VFMADDSUB213PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2538 AVX512VL :{EVEX} VFMADDSUB231PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2539 AVX512VL :{EVEX} VFMADDSUB231PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2540 AVX512F :VFMADDSUB231PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2541 AVX512VL :{EVEX} VFMADDSUB231PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2542 AVX512VL :{EVEX} VFMADDSUB231PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2543 AVX512F :VFMADDSUB231PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2544 AVX512VL :{EVEX} VFMSUBADD132PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2545 AVX512VL :{EVEX} VFMSUBADD132PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2546 AVX512F :VFMSUBADD132PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2547 AVX512VL :{EVEX} VFMSUBADD132PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2548 AVX512VL :{EVEX} VFMSUBADD132PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2549 AVX512F :VFMSUBADD132PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2550 AVX512VL :{EVEX} VFMSUBADD213PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2551 AVX512VL :{EVEX} VFMSUBADD213PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2552 AVX512F :VFMSUBADD213PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2553 AVX512VL :{EVEX} VFMSUBADD213PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2554 AVX512VL :{EVEX} VFMSUBADD213PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2555 AVX512F :VFMSUBADD213PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2556 AVX512VL :{EVEX} VFMSUBADD231PS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2557 AVX512VL :{EVEX} VFMSUBADD231PS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2558 AVX512F :VFMSUBADD231PS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2559 AVX512VL :{EVEX} VFMSUBADD231PD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2560 AVX512VL :{EVEX} VFMSUBADD231PD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2561 AVX512F :VFMSUBADD231PD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2562 AVX512F :{EVEX} VDIVSS xmm, xmm, xmm L: 4.59ns= 11.11c T: 1.25ns= 3.031c 2563 AVX512F :{EVEX} VDIVSS xmm (0.0f/x) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 2564 AVX512F :{EVEX} VDIVSS xmm (x/1.0f) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 2565 AVX512F :{EVEX} VDIVSS xmm (x/2.0f) L: 4.60ns= 11.12c T: 1.26ns= 3.048c 2566 AVX512F :{EVEX} VDIVSS xmm (x/0.5f) L: 4.60ns= 11.12c T: 1.26ns= 3.045c 2567 AVX512VL :{EVEX} VDIVPS xmm, xmm, xmm L: 4.59ns= 11.11c T: 1.25ns= 3.032c 2568 AVX512VL :{EVEX} VDIVPS xmm (0.0f/x) L: 4.59ns= 11.11c T: 1.25ns= 3.032c 2569 AVX512VL :{EVEX} VDIVPS xmm (x/1.0f) L: 4.59ns= 11.11c T: 1.25ns= 3.031c 2570 AVX512VL :{EVEX} VDIVPS xmm (x/2.0f) L: 4.59ns= 11.11c T: 1.26ns= 3.042c 2571 AVX512VL :{EVEX} VDIVPS xmm (x/0.5f) L: 4.60ns= 11.12c T: 1.26ns= 3.044c 2572 AVX512VL :{EVEX} VDIVPS ymm, ymm, ymm L: 4.59ns= 11.11c T: 2.09ns= 5.053c 2573 AVX512VL :{EVEX} VDIVPS ymm (0.0f/x) L: 4.59ns= 11.11c T: 2.09ns= 5.053c 2574 AVX512VL :{EVEX} VDIVPS ymm (x/1.0f) L: 4.59ns= 11.11c T: 2.09ns= 5.053c 2575 AVX512VL :{EVEX} VDIVPS ymm (x/2.0f) L: 4.60ns= 11.12c T: 2.09ns= 5.059c 2576 AVX512VL :{EVEX} VDIVPS ymm (x/0.5f) L: 4.60ns= 11.12c T: 2.09ns= 5.061c 2577 AVX512F :VDIVPS zmm, zmm, zmm L: 7.10ns= 17.17c T: 4.19ns= 10.138c 2578 AVX512F :VDIVPS zmm (0.0f/x) L: 7.09ns= 17.16c T: 4.19ns= 10.134c 2579 AVX512F :VDIVPS zmm (x/1.0f) L: 7.09ns= 17.16c T: 4.19ns= 10.138c 2580 AVX512F :VDIVPS zmm (x/2.0f) L: 7.10ns= 17.17c T: 4.20ns= 10.167c 2581 AVX512F :VDIVPS zmm (x/0.5f) L: 7.10ns= 17.17c T: 4.20ns= 10.165c 2582 AVX512F :{EVEX} VDIVSD xmm, xmm, xmm L: 5.43ns= 13.13c T: 1.67ns= 4.042c 2583 AVX512F :{EVEX} VDIVSD xmm (0.0/x) L: 5.43ns= 13.13c T: 1.67ns= 4.043c 2584 AVX512F :{EVEX} VDIVSD xmm (x/1.0) L: 5.43ns= 13.13c T: 1.67ns= 4.042c 2585 AVX512F :{EVEX} VDIVSD xmm (x/2.0) L: 5.43ns= 13.14c T: 1.67ns= 4.050c 2586 AVX512F :{EVEX} VDIVSD xmm (x/0.5) L: 5.43ns= 13.14c T: 1.68ns= 4.055c 2587 AVX512VL :{EVEX} VDIVPD xmm, xmm, xmm L: 5.43ns= 13.13c T: 1.67ns= 4.043c 2588 AVX512VL :{EVEX} VDIVPD xmm (0.0/x) L: 5.43ns= 13.13c T: 1.67ns= 4.043c 2589 AVX512VL :{EVEX} VDIVPD xmm (x/1.0) L: 5.43ns= 13.13c T: 1.67ns= 4.042c 2590 AVX512VL :{EVEX} VDIVPD xmm (x/2.0) L: 5.44ns= 13.15c T: 1.68ns= 4.054c 2591 AVX512VL :{EVEX} VDIVPD xmm (x/0.5) L: 5.43ns= 13.14c T: 1.67ns= 4.050c 2592 AVX512VL :{EVEX} VDIVPD ymm, ymm, ymm L: 5.43ns= 13.13c T: 3.35ns= 8.108c 2593 AVX512VL :{EVEX} VDIVPD ymm (0.0/x) L: 5.43ns= 13.13c T: 3.35ns= 8.114c 2594 AVX512VL :{EVEX} VDIVPD ymm (x/1.0) L: 5.43ns= 13.13c T: 3.35ns= 8.109c 2595 AVX512VL :{EVEX} VDIVPD ymm (x/2.0) L: 5.43ns= 13.14c T: 3.37ns= 8.153c 2596 AVX512VL :{EVEX} VDIVPD ymm (x/0.5) L: 5.43ns= 13.14c T: 3.36ns= 8.131c 2597 AVX512F :VDIVPD zmm, zmm, zmm L: 9.19ns= 22.22c T: 6.71ns= 16.226c 2598 AVX512F :VDIVPD zmm (0.0/x) L: 9.19ns= 22.23c T: 6.71ns= 16.224c 2599 AVX512F :VDIVPD zmm (x/1.0) L: 9.19ns= 22.23c T: 6.71ns= 16.226c 2600 AVX512F :VDIVPD zmm (x/2.0) L: 9.19ns= 22.23c T: 6.71ns= 16.235c 2601 AVX512F :VDIVPD zmm (x/0.5) L: 9.19ns= 22.23c T: 6.71ns= 16.228c 2602 AVX512F :{EVEX} VSQRTSS xmm, xmm, xmm L: 5.01ns= 12.11c T: 1.25ns= 3.032c 2603 AVX512F :{EVEX} VSQRTSS xmm, (0.0f) L: 5.01ns= 12.12c T: 1.25ns= 3.031c 2604 AVX512F :{EVEX} VSQRTSS xmm, (1.0f) L: 5.01ns= 12.11c T: 1.25ns= 3.031c 2605 AVX512VL :{EVEX} VSQRTPS xmm, xmm L: 5.01ns= 12.11c T: 1.25ns= 3.032c 2606 AVX512VL :{EVEX} VSQRTPS xmm (0.0f) L: 5.01ns= 12.11c T: 1.25ns= 3.032c 2607 AVX512VL :{EVEX} VSQRTPS xmm (1.0f) L: 5.01ns= 12.11c T: 1.25ns= 3.032c 2608 AVX512VL :{EVEX} VSQRTPS ymm, ymm L: 5.01ns= 12.11c T: 2.51ns= 6.063c 2609 AVX512VL :{EVEX} VSQRTPS ymm (0.0f) L: 5.01ns= 12.11c T: 2.51ns= 6.063c 2610 AVX512VL :{EVEX} VSQRTPS ymm (1.0f) L: 5.01ns= 12.11c T: 2.51ns= 6.063c 2611 AVX512F :VSQRTPS zmm, zmm L: 7.93ns= 19.19c T: 5.03ns= 12.169c 2612 AVX512F :VSQRTPS zmm (0.0f) L: 7.98ns= 19.32c T: 5.03ns= 12.174c 2613 AVX512F :VSQRTPS zmm (1.0f) L: 7.93ns= 19.19c T: 5.03ns= 12.170c 2614 AVX512F :{EVEX} VSQRTSD xmm, xmm, xmm L: 7.52ns= 18.18c T: 2.51ns= 6.063c 2615 AVX512F :{EVEX} VSQRTSD xmm, (0.0) L: 5.42ns= 13.12c T: 1.88ns= 4.547c 2616 AVX512F :{EVEX} VSQRTSD xmm, (1.0) L: 5.43ns= 13.13c T: 1.88ns= 4.547c 2617 AVX512VL :{EVEX} VSQRTPD xmm, xmm L: 7.52ns= 18.18c T: 2.51ns= 6.062c 2618 AVX512VL :{EVEX} VSQRTPD xmm (0.0) L: 5.43ns= 13.13c T: 1.88ns= 4.548c 2619 AVX512VL :{EVEX} VSQRTPD xmm (1.0) L: 5.43ns= 13.13c T: 1.88ns= 4.548c 2620 AVX512VL :{EVEX} VSQRTPD ymm, ymm L: 7.52ns= 18.18c T: 5.03ns= 12.179c 2621 AVX512VL :{EVEX} VSQRTPD ymm (0.0) L: 5.43ns= 13.13c T: 3.76ns= 9.096c 2622 AVX512VL :{EVEX} VSQRTPD ymm (1.0) L: 5.43ns= 13.13c T: 3.76ns= 9.095c 2623 AVX512F :VSQRTPD zmm, zmm L: 12.95ns= 31.32c T: 10.06ns= 24.342c 2624 AVX512F :VSQRTPD zmm (0.0) L: 9.61ns= 23.24c T: 7.55ns= 18.259c 2625 AVX512F :VSQRTPD zmm (1.0) L: 9.60ns= 23.23c T: 7.54ns= 18.242c 2626 AVX512F :VRCP14SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2627 AVX512VL :VRCP14PS xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2628 AVX512VL :VRCP14PS ymm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2629 AVX512F :VRCP14PS zmm, zmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 2630 AVX512F :VRCP14SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.014c 2631 AVX512VL :VRCP14PD xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2632 AVX512VL :VRCP14PD ymm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2633 AVX512F :VRCP14PD zmm, zmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 2638 AVX512F :VRSQRT14SS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2639 AVX512VL :VRSQRT14PS xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2640 AVX512VL :VRSQRT14PS ymm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2641 AVX512F :VRSQRT14PS zmm, zmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 2642 AVX512F :VRSQRT14SD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2643 AVX512VL :VRSQRT14PD xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2644 AVX512VL :VRSQRT14PD ymm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2645 AVX512F :VRSQRT14PD zmm, zmm L: 2.50ns= 6.05c T: 0.84ns= 2.021c 2652 AVX512F :{EVEX} VMINSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2653 AVX512VL :{EVEX} VMINPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2654 AVX512VL :{EVEX} VMINPS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2655 AVX512F :VMINPS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2656 AVX512F :{EVEX} VMINSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2657 AVX512VL :{EVEX} VMINPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2658 AVX512VL :{EVEX} VMINPD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2659 AVX512F :VMINPD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2660 AVX512F :{EVEX} VMAXSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2661 AVX512VL :{EVEX} VMAXPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2662 AVX512VL :{EVEX} VMAXPS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2663 AVX512F :VMAXPS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2664 AVX512F :{EVEX} VMAXSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2665 AVX512VL :{EVEX} VMAXPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2666 AVX512VL :{EVEX} VMAXPD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2667 AVX512F :VMAXPD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2668 AVX512F :VCMPSS k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2669 AVX512VL :VCMPPS k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2670 AVX512VL :VCMPPS k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2671 AVX512F :VCMPPS k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.011c 2672 AVX512F :VCMPSD k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2673 AVX512VL :VCMPPD k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2674 AVX512VL :VCMPPD k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2675 AVX512F :VCMPPD k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2676 AVX512F :{EVEX} VCOMISS xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 2677 AVX512F :{EVEX} VUCOMISS xmm, xmm L: [no true dep.] T: 0.42ns= 1.014c 2678 AVX512F :{EVEX} VCOMISD xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 2679 AVX512F :{EVEX} VUCOMISD xmm, xmm L: [no true dep.] T: 0.42ns= 1.010c 2680 AVX512VLDQ :{EVEX} VANDPS xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2681 AVX512VLDQ :{EVEX} VANDPS xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.20ns= 0.476c 2682 AVX512VLDQ :{EVEX} VANDPS ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.20ns= 0.476c 2683 AVX512VLDQ :{EVEX} VANDPS ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2684 AVX512DQ :VANDPS zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2685 AVX512DQ :VANDPS zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.510c 2686 AVX512VLDQ :{EVEX} VANDPD xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.20ns= 0.476c 2687 AVX512VLDQ :{EVEX} VANDPD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2688 AVX512VLDQ :{EVEX} VANDPD ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2689 AVX512VLDQ :{EVEX} VANDPD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2690 AVX512DQ :VANDPD zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.510c 2691 AVX512DQ :VANDPD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2692 AVX512VLDQ :{EVEX} VANDNPS xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2693 AVX512VLDQ :{EVEX} VANDNPS xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2694 AVX512VLDQ :{EVEX} VANDNPS ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2695 AVX512VLDQ :{EVEX} VANDNPS ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2696 AVX512DQ :VANDNPS zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2697 AVX512DQ :VANDNPS zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2698 AVX512VLDQ :{EVEX} VANDNPD xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2699 AVX512VLDQ :{EVEX} VANDNPD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.363c 2700 AVX512VLDQ :{EVEX} VANDNPD ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2701 AVX512VLDQ :{EVEX} VANDNPD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.20ns= 0.476c 2702 AVX512DQ :VANDNPD zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2703 AVX512DQ :VANDNPD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.509c 2704 AVX512VLDQ :{EVEX} VORPS xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2705 AVX512VLDQ :{EVEX} VORPS xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2706 AVX512VLDQ :{EVEX} VORPS ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.20ns= 0.479c 2707 AVX512VLDQ :{EVEX} VORPS ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2708 AVX512DQ :VORPS zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2709 AVX512DQ :VORPS zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2710 AVX512VLDQ :{EVEX} VORPD xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2711 AVX512VLDQ :{EVEX} VORPD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.20ns= 0.478c 2712 AVX512VLDQ :{EVEX} VORPD ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.20ns= 0.478c 2713 AVX512VLDQ :{EVEX} VORPD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2714 AVX512DQ :VORPD zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2715 AVX512DQ :VORPD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2716 AVX512VLDQ :{EVEX} VXORPS xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 2717 AVX512VLDQ :{EVEX} VXORPS xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2718 AVX512VLDQ :{EVEX} VXORPS ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 2719 AVX512VLDQ :{EVEX} VXORPS ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.20ns= 0.479c 2720 AVX512DQ :VXORPS zmm1, zmm1, zmm1 L: 0.14ns= 0.34c T: 0.20ns= 0.481c 2721 AVX512DQ :VXORPS zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2722 AVX512VLDQ :{EVEX} VXORPD xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 2723 AVX512VLDQ :{EVEX} VXORPD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2724 AVX512VLDQ :{EVEX} VXORPD ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 2725 AVX512VLDQ :{EVEX} VXORPD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.363c 2726 AVX512DQ :VXORPD zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 2727 AVX512DQ :VXORPD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2728 AVX512VL :{EVEX} VCVTPS2PH xmm, xmm, imm8 L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2729 AVX512VL :{EVEX} VCVTPS2PH xmm, ymm, imm8 L: 2.92ns= 7.07c T: 0.42ns= 1.010c 2730 AVX512F :VCVTPS2PH ymm, zmm, imm8 L: 2.92ns= 7.07c T: 0.42ns= 1.011c 2731 AVX512VL :{EVEX} VCVTPH2PS xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2732 AVX512VL :{EVEX} VCVTPH2PS ymm, xmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2733 AVX512F :VCVTPH2PS zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2734 AVX512VL :{EVEX} VCVTPS2PH + VCVTPH2PS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2735 AVX512VL :{EVEX} VCVTPS2PH + VCVTPH2PS ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2736 AVX512F :VCVTPS2PH + VCVTPH2PS zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2737 AVX512F :{EVEX} VCVTSS2SD xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.011c 2738 AVX512VL :{EVEX} VCVTPS2PD xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2739 AVX512VL :{EVEX} VCVTPS2PD ymm, xmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2740 AVX512F :VCVTPS2PD zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2741 AVX512F :{EVEX} VCVTSD2SS xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2742 AVX512VL :{EVEX} VCVTPD2PS xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2743 AVX512VL :{EVEX} VCVTPD2PS xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2744 AVX512F :VCVTPD2PS ymm, zmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2745 AVX512F :{EVEX} VCVTSD2SS + VCVTSD2SS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2746 AVX512VL :{EVEX} VCVTPD2PS + VCVTPD2PS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2747 AVX512VL :{EVEX} VCVTPD2PS + VCVTPD2PS ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2748 AVX512F :VCVTPD2PS + VCVTPD2PS zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2749 AVX512F :{EVEX} VCVTSS2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2750 AVX512F_X64 :{EVEX} VCVTSS2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 2751 AVX512F :VCVTSS2USI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2752 AVX512F_X64 :VCVTSS2USI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 2753 AVX512F :{EVEX} VCVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2754 AVX512F_X64 :{EVEX} VCVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 2755 AVX512F :VCVTTSS2USI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2756 AVX512F_X64 :VCVTTSS2USI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.011c 2757 AVX512F :{EVEX} VCVTSI2SS xmm, xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 2758 AVX512F_X64 :{EVEX} VCVTSI2SS xmm, xmm, r64 L: [diff. reg. set] T: 0.84ns= 2.021c 2759 AVX512F :VCVTUSI2SS xmm, xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 2760 AVX512F_X64 :VCVTUSI2SS xmm, xmm, r64 L: [diff. reg. set] T: 0.84ns= 2.028c 2761 AVX512F :{EVEX} VCVTSS2SI + VCVTSI2SS r32 L: 5.00ns= 12.10c T: 0.84ns= 2.022c 2762 AVX512F_X64 :{EVEX} VCVTSS2SI + VCVTSI2SS r64 L: 5.84ns= 14.13c T: 1.25ns= 3.031c 2763 AVX512F :VCVTSS2USI + VCVTUSI2SS r32 L: 5.00ns= 12.10c T: 0.84ns= 2.023c 2764 AVX512F_X64 :VCVTSS2USI + VCVTUSI2SS r64 L: 5.84ns= 14.13c T: 1.25ns= 3.031c 2765 AVX512F :{EVEX} VCVTTSS2SI + VCVTSI2SS r32 L: 5.00ns= 12.10c T: 0.75ns= 1.817c 2766 AVX512F_X64 :{EVEX} VCVTTSS2SI + VCVTSI2SS r64 L: 5.84ns= 14.13c T: 1.25ns= 3.032c 2767 AVX512F :VCVTTSS2USI + VCVTUSI2SS r32 L: 5.00ns= 12.10c T: 0.84ns= 2.026c 2768 AVX512F_X64 :VCVTTSS2USI + VCVTUSI2SS r64 L: 5.84ns= 14.13c T: 1.25ns= 3.031c 2769 AVX512F :{EVEX} VCVTSD2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2770 AVX512F_X64 :{EVEX} VCVTSD2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2771 AVX512F :VCVTSD2USI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2772 AVX512F_X64 :VCVTSD2USI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2773 AVX512F :{EVEX} VCVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2774 AVX512F_X64 :{EVEX} VCVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2775 AVX512F :VCVTTSD2USI r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2776 AVX512F_X64 :VCVTTSD2USI r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 2777 AVX512F :{EVEX} VCVTSI2SD xmm, xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 2778 AVX512F_X64 :{EVEX} VCVTSI2SD xmm, xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 2779 AVX512F :VCVTUSI2SD xmm, xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 2780 AVX512F_X64 :VCVTUSI2SD xmm, xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 2781 AVX512F :{EVEX} VCVTSD2SI + VCVTSI2SD r32 L: 5.00ns= 12.10c T: 0.84ns= 2.023c 2782 AVX512F_X64 :{EVEX} VCVTSD2SI + VCVTSI2SD r64 L: 5.00ns= 12.10c T: 0.84ns= 2.021c 2783 AVX512F :VCVTSD2USI + VCVTUSI2SD r32 L: 5.00ns= 12.10c T: 0.84ns= 2.022c 2784 AVX512F_X64 :VCVTSD2USI + VCVTUSI2SD r64 L: 5.00ns= 12.10c T: 0.84ns= 2.021c 2785 AVX512F :{EVEX} VCVTTSD2SI + VCVTSI2SD r32 L: 5.00ns= 12.10c T: 0.84ns= 2.022c 2786 AVX512F_X64 :{EVEX} VCVTTSD2SI + VCVTSI2SD r64 L: 5.00ns= 12.10c T: 0.84ns= 2.023c 2787 AVX512F :VCVTTSD2USI + VCVTUSI2SD r32 L: 5.00ns= 12.10c T: 0.84ns= 2.021c 2788 AVX512F_X64 :VCVTTSD2USI + VCVTUSI2SD r64 L: 5.00ns= 12.10c T: 0.75ns= 1.818c 2789 AVX512VL :{EVEX} VCVTPS2DQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2790 AVX512VL :{EVEX} VCVTPS2DQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2791 AVX512F :VCVTPS2DQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2792 AVX512VL :{EVEX} VCVTPS2UDQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2793 AVX512VL :{EVEX} VCVTPS2UDQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2794 AVX512F :VCVTPS2UDQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2795 AVX512VLDQ :{EVEX} VCVTPS2QQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2796 AVX512VLDQ :{EVEX} VCVTPS2QQ ymm, xmm L: 2.92ns= 7.07c T: 0.42ns= 1.011c 2797 AVX512DQ :VCVTPS2QQ zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.011c 2798 AVX512VLDQ :{EVEX} VCVTPS2UQQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2799 AVX512VLDQ :{EVEX} VCVTPS2UQQ ymm, xmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2800 AVX512DQ :VCVTPS2UQQ zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2801 AVX512VL :{EVEX} VCVTTPS2DQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2802 AVX512VL :{EVEX} VCVTTPS2DQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2803 AVX512F :VCVTTPS2DQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2804 AVX512VL :{EVEX} VCVTTPS2UDQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2805 AVX512VL :{EVEX} VCVTTPS2UDQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2806 AVX512F :VCVTTPS2UDQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2807 AVX512VLDQ :{EVEX} VCVTTPS2QQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2808 AVX512VLDQ :{EVEX} VCVTTPS2QQ ymm, xmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2809 AVX512DQ :VCVTTPS2QQ zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2810 AVX512VLDQ :{EVEX} VCVTTPS2UQQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2811 AVX512VLDQ :{EVEX} VCVTTPS2UQQ ymm, xmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 2812 AVX512DQ :VCVTTPS2UQQ zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2813 AVX512VL :{EVEX} VCVTDQ2PS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2814 AVX512VL :{EVEX} VCVTDQ2PS ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2815 AVX512F :VCVTDQ2PS zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2816 AVX512VL :{EVEX} VCVTUDQ2PS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2817 AVX512VL :{EVEX} VCVTUDQ2PS ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2818 AVX512F :VCVTUDQ2PS zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2819 AVX512VLDQ :{EVEX} VCVTQQ2PS xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2820 AVX512VLDQ :{EVEX} VCVTQQ2PS xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2821 AVX512DQ :VCVTQQ2PS ymm, zmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2822 AVX512VLDQ :{EVEX} VCVTUQQ2PS xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2823 AVX512VLDQ :{EVEX} VCVTUQQ2PS xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2824 AVX512DQ :VCVTUQQ2PS ymm, zmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2825 AVX512VL :{EVEX} VCVTPS2DQ + VCVTDQ2PS xmm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2826 AVX512VL :{EVEX} VCVTPS2DQ + VCVTDQ2PS ymm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2827 AVX512F :VCVTPS2DQ + VCVTDQ2PS zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2828 AVX512VL :{EVEX} VCVTPS2UDQ + VCVTUDQ2PS xmm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2829 AVX512VL :{EVEX} VCVTPS2UDQ + VCVTUDQ2PS ymm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2830 AVX512F :VCVTPS2UDQ + VCVTUDQ2PS zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2831 AVX512VLDQ :{EVEX} VCVTPS2QQ + VCVTQQ2PS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2832 AVX512VLDQ :{EVEX} VCVTPS2QQ + VCVTQQ2PS ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2833 AVX512DQ :VCVTPS2QQ + VCVTQQ2PS zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2834 AVX512VLDQ :{EVEX} VCVTPS2UQQ + VCVTUQQ2PS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2835 AVX512VLDQ :{EVEX} VCVTPS2UQQ + VCVTUQQ2PS ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2836 AVX512DQ :VCVTPS2UQQ + VCVTUQQ2PS zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2837 AVX512VL :{EVEX} VCVTTPS2DQ + VCVTDQ2PS xmm L: 3.33ns= 8.07c T: 0.42ns= 1.028c 2838 AVX512VL :{EVEX} VCVTTPS2DQ + VCVTDQ2PS ymm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2839 AVX512F :VCVTTPS2DQ + VCVTDQ2PS zmm L: 3.33ns= 8.07c T: 0.84ns= 2.034c 2840 AVX512VL :{EVEX} VCVTTPS2UDQ + VCVTUDQ2PS xmm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2841 AVX512VL :{EVEX} VCVTTPS2UDQ + VCVTUDQ2PS ymm L: 3.33ns= 8.07c T: 0.42ns= 1.027c 2842 AVX512F :VCVTTPS2UDQ + VCVTUDQ2PS zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2843 AVX512VLDQ :{EVEX} VCVTTPS2QQ + VCVTQQ2PS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2844 AVX512VLDQ :{EVEX} VCVTTPS2QQ + VCVTQQ2PS ymm L: 5.84ns= 14.12c T: 0.84ns= 2.021c 2845 AVX512DQ :VCVTTPS2QQ + VCVTQQ2PS zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2846 AVX512VLDQ :{EVEX} VCVTTPS2UQQ + VCVTUQQ2PS xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2847 AVX512VLDQ :{EVEX} VCVTTPS2UQQ + VCVTUQQ2PS ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2848 AVX512DQ :VCVTTPS2UQQ + VCVTUQQ2PS zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2849 AVX512VL :{EVEX} VCVTPD2DQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2850 AVX512VL :{EVEX} VCVTPD2DQ xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2851 AVX512F :VCVTPD2DQ ymm, zmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2852 AVX512VL :{EVEX} VCVTPD2UDQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2853 AVX512VL :{EVEX} VCVTPD2UDQ xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2854 AVX512F :VCVTPD2UDQ ymm, zmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 2855 AVX512VLDQ :{EVEX} VCVTPD2QQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2856 AVX512VLDQ :{EVEX} VCVTPD2QQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2857 AVX512DQ :VCVTPD2QQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2858 AVX512VLDQ :{EVEX} VCVTPD2UQQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2859 AVX512VLDQ :{EVEX} VCVTPD2UQQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2860 AVX512DQ :VCVTPD2UQQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2861 AVX512VL :{EVEX} VCVTTPD2DQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2862 AVX512VL :{EVEX} VCVTTPD2DQ xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2863 AVX512F :VCVTTPD2DQ ymm, zmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2864 AVX512VL :{EVEX} VCVTTPD2UDQ xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2865 AVX512VL :{EVEX} VCVTTPD2UDQ xmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2866 AVX512F :VCVTTPD2UDQ ymm, zmm L: 2.92ns= 7.06c T: 0.42ns= 1.011c 2867 AVX512VLDQ :{EVEX} VCVTTPD2QQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2868 AVX512VLDQ :{EVEX} VCVTTPD2QQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2869 AVX512DQ :VCVTTPD2QQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2870 AVX512VLDQ :{EVEX} VCVTTPD2UQQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2871 AVX512VLDQ :{EVEX} VCVTTPD2UQQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2872 AVX512DQ :VCVTTPD2UQQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2873 AVX512VL :{EVEX} VCVTDQ2PD xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2874 AVX512VL :{EVEX} VCVTDQ2PD ymm, xmm L: 2.92ns= 7.06c T: 0.42ns= 1.011c 2875 AVX512F :VCVTDQ2PD zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2876 AVX512VL :{EVEX} VCVTUDQ2PD xmm, xmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 2877 AVX512VL :{EVEX} VCVTUDQ2PD ymm, xmm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2878 AVX512F :VCVTUDQ2PD zmm, ymm L: 2.92ns= 7.06c T: 0.42ns= 1.010c 2879 AVX512VLDQ :{EVEX} VCVTQQ2PD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2880 AVX512VLDQ :{EVEX} VCVTQQ2PD ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2881 AVX512DQ :VCVTQQ2PD zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2882 AVX512VLDQ :{EVEX} VCVTUQQ2PD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2883 AVX512VLDQ :{EVEX} VCVTUQQ2PD ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2884 AVX512DQ :VCVTUQQ2PD zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2885 AVX512VL :{EVEX} VCVTPD2DQ + VCVTDQ2PD xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2886 AVX512VL :{EVEX} VCVTPD2DQ + VCVTDQ2PD ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2887 AVX512F :VCVTPD2DQ + VCVTDQ2PD zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2888 AVX512VL :{EVEX} VCVTPD2UDQ + VCVTUDQ2PD xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2889 AVX512VL :{EVEX} VCVTPD2UDQ + VCVTUDQ2PD ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2890 AVX512F :VCVTPD2UDQ + VCVTUDQ2PD zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2891 AVX512VLDQ :{EVEX} VCVTPD2QQ + VCVTQQ2PD xmm L: 3.33ns= 8.07c T: 0.42ns= 1.028c 2892 AVX512VLDQ :{EVEX} VCVTPD2QQ + VCVTQQ2PD ymm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2893 AVX512DQ :VCVTPD2QQ + VCVTQQ2PD zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2894 AVX512VLDQ :{EVEX} VCVTPD2UQQ + VCVTUQQ2PD xmm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2895 AVX512VLDQ :{EVEX} VCVTPD2UQQ + VCVTUQQ2PD ymm L: 3.33ns= 8.07c T: 0.42ns= 1.027c 2896 AVX512DQ :VCVTPD2UQQ + VCVTUQQ2PD zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2897 AVX512VL :{EVEX} VCVTTPD2DQ + VCVTDQ2PD xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2898 AVX512VL :{EVEX} VCVTTPD2DQ + VCVTDQ2PD ymm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2899 AVX512F :VCVTTPD2DQ + VCVTDQ2PD zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2900 AVX512VL :{EVEX} VCVTTPD2UDQ + VCVTUDQ2PD xmm L: 4.17ns= 10.08c T: 0.84ns= 2.021c 2901 AVX512VL :{EVEX} VCVTTPD2UDQ + VCVTUDQ2PD ymm L: 5.84ns= 14.12c T: 0.84ns= 2.021c 2902 AVX512F :VCVTTPD2UDQ + VCVTUDQ2PD zmm L: 5.84ns= 14.13c T: 0.84ns= 2.021c 2903 AVX512VLDQ :{EVEX} VCVTTPD2QQ + VCVTQQ2PD xmm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2904 AVX512VLDQ :{EVEX} VCVTTPD2QQ + VCVTQQ2PD ymm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2905 AVX512DQ :VCVTTPD2QQ + VCVTQQ2PD zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2906 AVX512VLDQ :{EVEX} VCVTTPD2UQQ + VCVTUQQ2PD xmm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2907 AVX512VLDQ :{EVEX} VCVTTPD2UQQ + VCVTUQQ2PD ymm L: 3.33ns= 8.07c T: 0.42ns= 1.013c 2908 AVX512DQ :VCVTTPD2UQQ + VCVTUQQ2PD zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 2909 AVX512VL :VBLENDMPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2910 AVX512VL :VBLENDMPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2911 AVX512F :VBLENDMPS zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 2912 AVX512VL :VBLENDMPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2913 AVX512VL :VBLENDMPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 2914 AVX512F :VBLENDMPD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.510c 2915 AVX512DQ :VFPCLASSSS k, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.014c 2916 AVX512VLDQ :VFPCLASSPS k, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2917 AVX512VLDQ :VFPCLASSPS k, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2918 AVX512DQ :VFPCLASSPS k, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2919 AVX512DQ :VFPCLASSSD k, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2920 AVX512VLDQ :VFPCLASSPD k, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.014c 2921 AVX512VLDQ :VFPCLASSPD k, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2922 AVX512DQ :VFPCLASSPD k, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 2923 AVX512VL :VCOMPRESSPS xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2924 AVX512VL :VCOMPRESSPS ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2925 AVX512F :VCOMPRESSPS zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 2926 AVX512VL :VCOMPRESSPD xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.027c 2927 AVX512VL :VCOMPRESSPD ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2928 AVX512F :VCOMPRESSPD zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 2929 AVX512VL :VCOMPRESSPS xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2930 AVX512VL :VCOMPRESSPS ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.027c 2931 AVX512F :VCOMPRESSPS zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2932 AVX512VL :VCOMPRESSPD xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2933 AVX512VL :VCOMPRESSPD ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2934 AVX512F :VCOMPRESSPD zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2935 AVX512VL :VEXPANDPS xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.027c 2936 AVX512VL :VEXPANDPS ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2937 AVX512F :VEXPANDPS zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 2938 AVX512VL :VEXPANDPD xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2939 AVX512VL :VEXPANDPD ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2940 AVX512F :VEXPANDPD zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2941 AVX512VL :VEXPANDPS xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2942 AVX512VL :VEXPANDPS ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2943 AVX512F :VEXPANDPS zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 2944 AVX512VL :VEXPANDPD xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2945 AVX512VL :VEXPANDPD ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 2946 AVX512F :VEXPANDPD zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 2947 AVX512F :VFIXUPIMMSS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2948 AVX512VL :VFIXUPIMMPS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2949 AVX512VL :VFIXUPIMMPS ymm, ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2950 AVX512F :VFIXUPIMMPS zmm, zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2951 AVX512F :VFIXUPIMMSD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2952 AVX512VL :VFIXUPIMMPD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2953 AVX512VL :VFIXUPIMMPD ymm, ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2954 AVX512F :VFIXUPIMMPD zmm, zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2955 AVX512F :VGETEXPSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2956 AVX512VL :VGETEXPPS xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2957 AVX512VL :VGETEXPPS ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.512c 2958 AVX512F :VGETEXPPS zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2959 AVX512F :VGETEXPSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2960 AVX512VL :VGETEXPPD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2961 AVX512VL :VGETEXPPD ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2962 AVX512F :VGETEXPPD zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2963 AVX512F :VGETMANTSS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2964 AVX512VL :VGETMANTPS xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2965 AVX512VL :VGETMANTPS ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2966 AVX512F :VGETMANTPS zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2967 AVX512F :VGETMANTSD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2968 AVX512VL :VGETMANTPD xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2969 AVX512VL :VGETMANTPD ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2970 AVX512F :VGETMANTPD zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.011c 2971 AVX512DQ :VRANGESS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2972 AVX512VLDQ :VRANGEPS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2973 AVX512VLDQ :VRANGEPS ymm, ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2974 AVX512DQ :VRANGEPS zmm, zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2975 AVX512DQ :VRANGESD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2976 AVX512VLDQ :VRANGEPD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2977 AVX512VLDQ :VRANGEPD ymm, ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2978 AVX512DQ :VRANGEPD zmm, zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2979 AVX512DQ :VREDUCESS xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2980 AVX512VLDQ :VREDUCEPS xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2981 AVX512VLDQ :VREDUCEPS ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2982 AVX512DQ :VREDUCEPS zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2983 AVX512DQ :VREDUCESD xmm, xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2984 AVX512VLDQ :VREDUCEPD xmm, xmm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2985 AVX512VLDQ :VREDUCEPD ymm, ymm, imm8 L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2986 AVX512DQ :VREDUCEPD zmm, zmm, imm8 L: 1.67ns= 4.03c T: 0.42ns= 1.010c 2987 AVX512F :VRNDSCALESS xmm, xmm, xmm, imm8 L: 3.34ns= 8.07c T: 0.42ns= 1.013c 2988 AVX512VL :VRNDSCALEPS xmm, xmm, imm8 L: 3.34ns= 8.07c T: 0.42ns= 1.013c 2989 AVX512VL :VRNDSCALEPS ymm, ymm, imm8 L: 3.34ns= 8.07c T: 0.42ns= 1.013c 2990 AVX512F :VRNDSCALEPS zmm, zmm, imm8 L: 3.34ns= 8.07c T: 0.84ns= 2.034c 2991 AVX512F :VRNDSCALESD xmm, xmm, xmm, imm8 L: 3.34ns= 8.07c T: 0.42ns= 1.013c 2992 AVX512VL :VRNDSCALEPD xmm, xmm, imm8 L: 3.34ns= 8.07c T: 0.42ns= 1.013c 2993 AVX512VL :VRNDSCALEPD ymm, ymm, imm8 L: 3.34ns= 8.07c T: 0.42ns= 1.013c 2994 AVX512F :VRNDSCALEPD zmm, zmm, imm8 L: 3.34ns= 8.07c T: 0.84ns= 2.021c 2995 AVX512F :VSCALEFSS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 2996 AVX512VL :VSCALEFPS xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2997 AVX512VL :VSCALEFPS ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 2998 AVX512F :VSCALEFPS zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 2999 AVX512F :VSCALEFSD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.513c 3000 AVX512VL :VSCALEFPD xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3001 AVX512VL :VSCALEFPD ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3002 AVX512F :VSCALEFPD zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3003 AVX512F :{EVEX} VMOVSS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3004 AVX512F :{EVEX} VMOVSS xmm1, xmm2, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3005 AVX512F :{EVEX} VMOVSS xmm, [m32] L: [memory dep.] T: 0.21ns= 0.506c 3006 AVX512F :{EVEX} VMOVSS [m32], xmm L: [memory dep.] T: 0.21ns= 0.506c 3007 AVX512F :{EVEX} VMOVSS LS pair L: 2.08ns= 5.03c T: 0.35ns= 0.857c 3008 AVX512F :{EVEX} VMOVLHPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3009 AVX512F :{EVEX} VMOVLHPS xmm1, xmm2, xmm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3010 AVX512F :{EVEX} VMOVHLPS xmm, xmm, xmm L: 0.42ns= 1.02c T: 0.42ns= 1.014c 3011 AVX512F :{EVEX} VMOVHLPS xmm1, xmm2, xmm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3012 AVX512F :{EVEX} VMOVLPS xmm, xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 3013 AVX512F :{EVEX} VMOVLPS [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 3014 AVX512F :{EVEX} VMOVHPS xmm, xmm, [m64] L: [memory dep.] T: 0.42ns= 1.010c 3015 AVX512F :{EVEX} VMOVHPS [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 3016 AVX512VL :{EVEX} VMOVAPS xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3017 AVX512VL :{EVEX} VMOVAPS xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3018 AVX512VL :{EVEX} VMOVAPS ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3019 AVX512VL :{EVEX} VMOVAPS ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3020 AVX512F :VMOVAPS zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3021 AVX512F :VMOVAPS zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3022 AVX512VL :{EVEX} VMOVAPS xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3023 AVX512VL :{EVEX} VMOVAPS ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3024 AVX512F :VMOVAPS zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3025 AVX512VL :{EVEX} VMOVAPS [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3026 AVX512VL :{EVEX} VMOVAPS [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3027 AVX512F :VMOVAPS [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3028 AVX512VL :{EVEX} VMOVAPS xmm LS pair L: 2.08ns= 5.03c T: 0.37ns= 0.885c 3029 AVX512VL :{EVEX} VMOVAPS ymm LS pair L: 3.13ns= 7.57c T: 0.35ns= 0.852c 3030 AVX512F :VMOVAPS zmm LS pair L: 2.78ns= 6.72c T: 0.42ns= 1.012c 3031 AVX512VL :{EVEX} VMOVUPS xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3032 AVX512VL :{EVEX} VMOVUPS xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3033 AVX512VL :{EVEX} VMOVUPS ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3034 AVX512VL :{EVEX} VMOVUPS ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3035 AVX512F :VMOVUPS zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3036 AVX512F :VMOVUPS zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.333c 3037 AVX512VL :{EVEX} VMOVUPS xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3038 AVX512VL :{EVEX} VMOVUPS ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3039 AVX512F :VMOVUPS zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3040 AVX512VL :{EVEX} VMOVUPS [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3041 AVX512VL :{EVEX} VMOVUPS [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3042 AVX512F :VMOVUPS [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3043 AVX512VL :{EVEX} VMOVUPS xmm LS pair L: 2.08ns= 5.03c T: 0.37ns= 0.885c 3044 AVX512VL :{EVEX} VMOVUPS ymm LS pair L: 2.82ns= 6.83c T: 0.35ns= 0.853c 3045 AVX512F :VMOVUPS zmm LS pair L: 3.18ns= 7.70c T: 0.53ns= 1.277c 3046 AVX512VL :{EVEX} VMOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 3047 AVX512VL :{EVEX} VMOVUPS ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3048 AVX512F :VMOVUPS zmm, [m512 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3049 AVX512VL :{EVEX} VMOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.49ns= 1.182c 3050 AVX512VL :{EVEX} VMOVUPS [m256 + 4], ymm L: [memory dep.] T: 0.70ns= 1.687c 3051 AVX512F :VMOVUPS [m512 + 4], zmm L: [memory dep.] T: 0.91ns= 2.192c 3052 AVX512VL :{EVEX} VMOVUPS xmm + 4 LS pair L: 2.08ns= 5.03c T: 0.55ns= 1.327c 3053 AVX512VL :{EVEX} VMOVUPS ymm + 4 LS pair L: 2.87ns= 6.95c T: 0.78ns= 1.885c 3054 AVX512F :VMOVUPS zmm + 4 LS pair L: 3.75ns= 9.08c T: 0.99ns= 2.389c 3055 AVX512VL :{EVEX} VMOVNTPS [m128], xmm L: [memory dep.] T: 0.99ns= 2.384c 3056 AVX512VL :{EVEX} VMOVNTPS [m256], ymm L: [memory dep.] T: 1.20ns= 2.906c 3057 AVX512F :VMOVNTPS [m512], zmm L: [memory dep.] T: 2.19ns= 5.289c 3058 AVX512VL :{EVEX} VMOVSLDUP xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3059 AVX512VL :{EVEX} VMOVSLDUP ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3060 AVX512F :VMOVSLDUP zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3061 AVX512VL :{EVEX} VMOVSHDUP xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3062 AVX512VL :{EVEX} VMOVSHDUP ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3063 AVX512F :VMOVSHDUP zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3064 AVX512F :{EVEX} VMOVSD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3065 AVX512F :{EVEX} VMOVSD xmm1, xmm2, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3066 AVX512F :{EVEX} VMOVSD xmm, [m64] L: [memory dep.] T: 0.21ns= 0.506c 3067 AVX512F :{EVEX} VMOVSD [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 3068 AVX512F :{EVEX} VMOVSD LS pair L: 2.08ns= 5.03c T: 0.36ns= 0.862c 3069 AVX512F :{EVEX} VMOVLPD xmm, xmm, [m64] L: [memory dep.] T: 0.21ns= 0.505c 3070 AVX512F :{EVEX} VMOVLPD [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 3071 AVX512F :{EVEX} VMOVHPD xmm, xmm, [m64] L: [memory dep.] T: 0.42ns= 1.014c 3072 AVX512F :{EVEX} VMOVHPD [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 3073 AVX512VL :{EVEX} VMOVAPD xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3074 AVX512VL :{EVEX} VMOVAPD xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3075 AVX512VL :{EVEX} VMOVAPD ymm, ymm L: 0.42ns= 1.01c T: 0.20ns= 0.480c 3076 AVX512VL :{EVEX} VMOVAPD ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3077 AVX512F :VMOVAPD zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.509c 3078 AVX512F :VMOVAPD zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3079 AVX512VL :{EVEX} VMOVAPD xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3080 AVX512VL :{EVEX} VMOVAPD ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3081 AVX512F :VMOVAPD zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3082 AVX512VL :{EVEX} VMOVAPD [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3083 AVX512VL :{EVEX} VMOVAPD [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3084 AVX512F :VMOVAPD [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3085 AVX512VL :{EVEX} VMOVAPD xmm LS pair L: 2.44ns= 5.90c T: 0.38ns= 0.927c 3086 AVX512VL :{EVEX} VMOVAPD ymm LS pair L: 3.13ns= 7.58c T: 0.35ns= 0.852c 3087 AVX512F :VMOVAPD zmm LS pair L: 2.75ns= 6.65c T: 0.42ns= 1.012c 3088 AVX512VL :{EVEX} VMOVUPD xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3089 AVX512VL :{EVEX} VMOVUPD xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3090 AVX512VL :{EVEX} VMOVUPD ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3091 AVX512VL :{EVEX} VMOVUPD ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3092 AVX512F :VMOVUPD zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3093 AVX512F :VMOVUPD zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3094 AVX512VL :{EVEX} VMOVUPD xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3095 AVX512VL :{EVEX} VMOVUPD ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3096 AVX512F :VMOVUPD zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3097 AVX512VL :{EVEX} VMOVUPD [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3098 AVX512VL :{EVEX} VMOVUPD [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3099 AVX512F :VMOVUPD [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3100 AVX512VL :{EVEX} VMOVUPD xmm LS pair L: 2.45ns= 5.93c T: 0.37ns= 0.885c 3101 AVX512VL :{EVEX} VMOVUPD ymm LS pair L: 3.13ns= 7.57c T: 0.35ns= 0.852c 3102 AVX512F :VMOVUPD zmm LS pair L: 2.82ns= 6.82c T: 0.42ns= 1.012c 3103 AVX512VL :{EVEX} VMOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 3104 AVX512VL :{EVEX} VMOVUPD ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3105 AVX512F :VMOVUPD zmm, [m512 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3106 AVX512VL :{EVEX} VMOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.49ns= 1.182c 3107 AVX512VL :{EVEX} VMOVUPD [m256 + 4], ymm L: [memory dep.] T: 0.80ns= 1.947c 3108 AVX512F :VMOVUPD [m512 + 4], zmm L: [memory dep.] T: 0.91ns= 2.192c 3109 AVX512VL :{EVEX} VMOVUPD xmm + 4 LS pair L: 2.45ns= 5.92c T: 0.71ns= 1.707c 3110 AVX512VL :{EVEX} VMOVUPD ymm + 4 LS pair L: 2.89ns= 7.00c T: 0.78ns= 1.885c 3111 AVX512F :VMOVUPD zmm + 4 LS pair L: 3.76ns= 9.10c T: 0.99ns= 2.390c 3112 AVX512VL :{EVEX} VMOVNTPD [m128], xmm L: [memory dep.] T: 0.99ns= 2.388c 3113 AVX512VL :{EVEX} VMOVNTPD [m256], ymm L: [memory dep.] T: 1.20ns= 2.901c 3114 AVX512F :VMOVNTPD [m512], zmm L: [memory dep.] T: 2.18ns= 5.271c 3115 AVX512VL :{EVEX} VMOVDDUP xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3116 AVX512VL :{EVEX} VMOVDDUP ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3117 AVX512F :VMOVDDUP zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3118 AVX512VL :{EVEX} VBROADCASTSS xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3119 AVX512VL :{EVEX} VBROADCASTSS ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3120 AVX512F :VBROADCASTSS zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3121 AVX512VL :{EVEX} VBROADCASTSS xmm, [m32] L: [memory dep.] T: 0.21ns= 0.506c 3122 AVX512VL :{EVEX} VBROADCASTSS ymm, [m32] L: [memory dep.] T: 0.21ns= 0.506c 3123 AVX512F :VBROADCASTSS zmm, [m32] L: [memory dep.] T: 0.21ns= 0.506c 3124 AVX512VLDQ :VBROADCASTF32X2 ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3125 AVX512DQ :VBROADCASTF32X2 zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3126 AVX512VLDQ :VBROADCASTF32X2 ymm, [m64] L: [memory dep.] T: 0.21ns= 0.506c 3127 AVX512DQ :VBROADCASTF32X2 zmm, [m64] L: [memory dep.] T: 0.21ns= 0.506c 3128 AVX512VL :VBROADCASTF32X4 ymm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3129 AVX512F :VBROADCASTF32X4 zmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3130 AVX512DQ :VBROADCASTF32X8 zmm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3131 AVX512VL :{EVEX} VBROADCASTSD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3132 AVX512F :VBROADCASTSD zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.017c 3133 AVX512VL :{EVEX} VBROADCASTSD ymm, [m64] L: [memory dep.] T: 0.21ns= 0.506c 3134 AVX512F :VBROADCASTSD zmm, [m64] L: [memory dep.] T: 0.21ns= 0.506c 3135 AVX512VLDQ :VBROADCASTF64X2 ymm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3136 AVX512DQ :VBROADCASTF64X2 zmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3137 AVX512F :VBROADCASTF64X4 zmm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3138 AVX512F :{EVEX} VEXTRACTPS r32, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3139 AVX512F :{EVEX} VEXTRACTPS [m32], xmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 3140 AVX512VL :VEXTRACTF32X4 xmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3141 AVX512F :VEXTRACTF32X4 xmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 3142 AVX512VL :VEXTRACTF32X4 [m128], ymm, imm8 L: [memory dep.] T: 0.44ns= 1.054c 3143 AVX512F :VEXTRACTF32X4 [m128], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 3144 AVX512DQ :VEXTRACTF32X8 ymm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3145 AVX512DQ :VEXTRACTF32X8 [m256], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 3146 AVX512VLDQ :VEXTRACTF64X2 xmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3147 AVX512DQ :VEXTRACTF64X2 xmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3148 AVX512VLDQ :VEXTRACTF64X2 [m128], ymm, imm8 L: [memory dep.] T: 0.44ns= 1.054c 3149 AVX512DQ :VEXTRACTF64X2 [m128], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 3150 AVX512F :VEXTRACTF64X4 ymm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3151 AVX512F :VEXTRACTF64X4 [m256], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 3152 AVX512F :{EVEX} VINSERTPS xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3153 AVX512F :{EVEX} VINSERTPS xmm, xmm, [m32], im8 L: [memory dep.] T: 0.42ns= 1.014c 3154 AVX512VL :VINSERTF32X4 ymm, ymm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 3155 AVX512F :VINSERTF32X4 zmm, zmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.017c 3156 AVX512VL :VINSERTF32X4 ymm, ymm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 3157 AVX512F :VINSERTF32X4 zmm, zmm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 3158 AVX512DQ :VINSERTF32X8 zmm, zmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3159 AVX512DQ :VINSERTF32X8 zmm, zmm, [m256], imm8 L: [memory dep.] T: 0.22ns= 0.525c 3160 AVX512VLDQ :VINSERTF64X2 ymm, ymm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3161 AVX512DQ :VINSERTF64X2 zmm, zmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3162 AVX512VLDQ :VINSERTF64X2 ymm, ymm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 3163 AVX512DQ :VINSERTF64X2 zmm, zmm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 3164 AVX512F :VINSERTF64X4 zmm, zmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3165 AVX512F :VINSERTF64X4 zmm, zmm, [m256], imm8 L: [memory dep.] T: 0.22ns= 0.525c 3166 AVX512VL :{EVEX} VUNPCKLPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3167 AVX512VL :{EVEX} VUNPCKLPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3168 AVX512F :VUNPCKLPS zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3169 AVX512VL :{EVEX} VUNPCKHPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3170 AVX512VL :{EVEX} VUNPCKHPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3171 AVX512F :VUNPCKHPS zmm, zmm, zmm L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3172 AVX512VL :{EVEX} VUNPCKLPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3173 AVX512VL :{EVEX} VUNPCKLPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.014c 3174 AVX512F :VUNPCKLPD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3175 AVX512VL :{EVEX} VUNPCKHPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 3176 AVX512VL :{EVEX} VUNPCKHPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3177 AVX512F :VUNPCKHPD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3178 AVX512VL :{EVEX} VSHUFPS xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3179 AVX512VL :{EVEX} VSHUFPS ymm, ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3180 AVX512F :VSHUFPS zmm, zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3181 AVX512VL :{EVEX} VSHUFPD xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3182 AVX512VL :{EVEX} VSHUFPD ymm, ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3183 AVX512F :VSHUFPD zmm, zmm, zmm, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3184 AVX512VL :VSHUFF32X4 ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3185 AVX512F :VSHUFF32X4 zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3186 AVX512VL :VSHUFF64X2 ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3187 AVX512F :VSHUFF64X2 zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3188 AVX512VL :{EVEX} VPERMPS ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3189 AVX512F :VPERMPS zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3190 AVX512VL :{EVEX} VPERMPD ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3191 AVX512F :VPERMPD zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3192 AVX512VL :{EVEX} VPERMPD ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3193 AVX512F :VPERMPD zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3194 AVX512VL :{EVEX} VPERMILPS xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3195 AVX512VL :{EVEX} VPERMILPS ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3196 AVX512F :VPERMILPS zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3197 AVX512VL :{EVEX} VPERMILPS xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 3198 AVX512VL :{EVEX} VPERMILPS ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3199 AVX512F :VPERMILPS zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3200 AVX512VL :VPERMI2PS xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3201 AVX512VL :VPERMI2PS ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3202 AVX512F :VPERMI2PS zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3203 AVX512VL :VPERMT2PS xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3204 AVX512VL :VPERMT2PS ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 3205 AVX512F :VPERMT2PS zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3206 AVX512VL :{EVEX} VPERMILPD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3207 AVX512VL :{EVEX} VPERMILPD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3208 AVX512F :VPERMILPD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3209 AVX512VL :{EVEX} VPERMILPD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3210 AVX512VL :{EVEX} VPERMILPD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3211 AVX512F :VPERMILPD zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3212 AVX512VL :VPERMI2PD xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3213 AVX512VL :VPERMI2PD ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3214 AVX512F :VPERMI2PD zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3215 AVX512VL :VPERMT2PD xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.011c 3216 AVX512VL :VPERMT2PD ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3217 AVX512F :VPERMT2PD zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3234 AVX512VL :VGATHERDPS xmm {k}, [xm32] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 3235 AVX512VL :VGATHERDPS ymm {k}, [ym32] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 3236 AVX512F :VGATHERDPS zmm {k}, [zm32] + KMOVW L: 10.47ns= 25.32c T: 3.76ns= 9.095c 3237 AVX512VL :VGATHERQPS xmm {k}, [xm64] + KMOVW L: 7.13ns= 17.24c T: 0.86ns= 2.084c 3238 AVX512VL :VGATHERQPS xmm {k}, [ym64] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 3239 AVX512F :VGATHERQPS ymm {k}, [zm64] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 3240 AVX512VL :VGATHERDPD xmm {k}, [xm32] + KMOVW L: 7.13ns= 17.24c T: 0.86ns= 2.085c 3241 AVX512VL :VGATHERDPD ymm {k}, [xm32] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 3242 AVX512F :VGATHERDPD zmm {k}, [ym32] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 3243 AVX512VL :VGATHERQPD xmm {k}, [xm64] + KMOVW L: 7.13ns= 17.24c T: 0.86ns= 2.084c 3244 AVX512VL :VGATHERQPD ymm {k}, [ym64] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 3245 AVX512F :VGATHERQPD zmm {k}, [zm64] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 3246 AVX512VL :VSCATTERDPS [xm32] {k}, xmm + KMOVW L: [memory dep.] T: 2.51ns= 6.063c 3247 AVX512VL :VSCATTERDPS [ym32] {k}, ymm + KMOVW L: [memory dep.] T: 3.34ns= 8.084c 3248 AVX512F :VSCATTERDPS [zm32] {k}, zmm + KMOVW L: [memory dep.] T: 5.01ns= 12.127c 3249 AVX512VL :VSCATTERQPS [xm64] {k}, xmm + KMOVW L: [memory dep.] T: 2.09ns= 5.052c 3250 AVX512VL :VSCATTERQPS [ym64] {k}, xmm + KMOVW L: [memory dep.] T: 2.51ns= 6.064c 3251 AVX512F :VSCATTERQPS [zm64] {k}, ymm + KMOVW L: [memory dep.] T: 3.34ns= 8.085c 3252 AVX512VL :VSCATTERDPD [xm32] {k}, xmm + KMOVW L: [memory dep.] T: 2.09ns= 5.053c 3253 AVX512VL :VSCATTERDPD [xm32] {k}, ymm + KMOVW L: [memory dep.] T: 2.51ns= 6.063c 3254 AVX512F :VSCATTERDPD [ym32] {k}, zmm + KMOVW L: [memory dep.] T: 3.34ns= 8.085c 3255 AVX512VL :VSCATTERQPD [xm64] {k}, xmm + KMOVW L: [memory dep.] T: 2.09ns= 5.052c 3256 AVX512VL :VSCATTERQPD [ym64] {k}, ymm + KMOVW L: [memory dep.] T: 2.51ns= 6.063c 3257 AVX512F :VSCATTERQPD [zm64] {k}, zmm + KMOVW L: [memory dep.] T: 3.34ns= 8.085c 3258 AVX512VLBW :{EVEX} VPADDB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.20ns= 0.479c 3259 AVX512VLBW :{EVEX} VPADDB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3260 AVX512BW :VPADDB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3261 AVX512VLBW :{EVEX} VPADDSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3262 AVX512VLBW :{EVEX} VPADDSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3263 AVX512BW :VPADDSB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3264 AVX512VLBW :{EVEX} VPADDUSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3265 AVX512VLBW :{EVEX} VPADDUSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3266 AVX512BW :VPADDUSB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3267 AVX512VLBW :{EVEX} VPADDW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.20ns= 0.476c 3268 AVX512VLBW :{EVEX} VPADDW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3269 AVX512BW :VPADDW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3270 AVX512VLBW :{EVEX} VPADDSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3271 AVX512VLBW :{EVEX} VPADDSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3272 AVX512BW :VPADDSW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3273 AVX512VLBW :{EVEX} VPADDUSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3274 AVX512VLBW :{EVEX} VPADDUSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3275 AVX512BW :VPADDUSW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3276 AVX512VL :{EVEX} VPADDD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3277 AVX512VL :{EVEX} VPADDD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3278 AVX512F :VPADDD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3279 AVX512VL :{EVEX} VPADDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3280 AVX512VL :{EVEX} VPADDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3281 AVX512F :VPADDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3282 AVX512VLBW :{EVEX} VPSUBB xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3283 AVX512VLBW :{EVEX} VPSUBB xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3284 AVX512VLBW :{EVEX} VPSUBB ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3285 AVX512VLBW :{EVEX} VPSUBB ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3286 AVX512BW :VPSUBB zmm1, zmm1, zmm1 L: 0.15ns= 0.36c T: 0.20ns= 0.481c 3287 AVX512BW :VPSUBB zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3288 AVX512VLBW :{EVEX} VPSUBSB xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3289 AVX512VLBW :{EVEX} VPSUBSB xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3290 AVX512VLBW :{EVEX} VPSUBSB ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3291 AVX512VLBW :{EVEX} VPSUBSB ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3292 AVX512BW :VPSUBSB zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.333c 3293 AVX512BW :VPSUBSB zmm1, zmm1, zmm2 L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3294 AVX512VLBW :{EVEX} VPSUBUSB xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3295 AVX512VLBW :{EVEX} VPSUBUSB xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3296 AVX512VLBW :{EVEX} VPSUBUSB ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3297 AVX512VLBW :{EVEX} VPSUBUSB ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3298 AVX512BW :VPSUBUSB zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3299 AVX512BW :VPSUBUSB zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3300 AVX512VLBW :{EVEX} VPSUBW xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3301 AVX512VLBW :{EVEX} VPSUBW xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3302 AVX512VLBW :{EVEX} VPSUBW ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3303 AVX512VLBW :{EVEX} VPSUBW ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3304 AVX512BW :VPSUBW zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3305 AVX512BW :VPSUBW zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.510c 3306 AVX512VLBW :{EVEX} VPSUBSW xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3307 AVX512VLBW :{EVEX} VPSUBSW xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3308 AVX512VLBW :{EVEX} VPSUBSW ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3309 AVX512VLBW :{EVEX} VPSUBSW ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3310 AVX512BW :VPSUBSW zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3311 AVX512BW :VPSUBSW zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3312 AVX512VLBW :{EVEX} VPSUBUSW xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3313 AVX512VLBW :{EVEX} VPSUBUSW xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3314 AVX512VLBW :{EVEX} VPSUBUSW ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3315 AVX512VLBW :{EVEX} VPSUBUSW ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3316 AVX512BW :VPSUBUSW zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3317 AVX512BW :VPSUBUSW zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3318 AVX512VL :{EVEX} VPSUBD xmm1, xmm1, xmm1 L: 0.15ns= 0.37c T: 0.20ns= 0.481c 3319 AVX512VL :{EVEX} VPSUBD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3320 AVX512VL :{EVEX} VPSUBD ymm1, ymm1, ymm1 L: 0.15ns= 0.36c T: 0.20ns= 0.478c 3321 AVX512VL :{EVEX} VPSUBD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3322 AVX512F :VPSUBD zmm1, zmm1, zmm1 L: 0.14ns= 0.33c T: 0.20ns= 0.481c 3323 AVX512F :VPSUBD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3324 AVX512VL :{EVEX} VPSUBQ xmm1, xmm1, xmm1 L: 0.14ns= 0.35c T: 0.20ns= 0.480c 3325 AVX512VL :{EVEX} VPSUBQ xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3326 AVX512VL :{EVEX} VPSUBQ ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3327 AVX512VL :{EVEX} VPSUBQ ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3328 AVX512F :VPSUBQ zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3329 AVX512F :VPSUBQ zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3330 AVX512VLBW :{EVEX} VPMULLW xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3331 AVX512VLBW :{EVEX} VPMULLW ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.513c 3332 AVX512BW :VPMULLW zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 3333 AVX512VLBW :{EVEX} VPMULHW xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.513c 3334 AVX512VLBW :{EVEX} VPMULHW ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3335 AVX512BW :VPMULHW zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 3336 AVX512VLBW :{EVEX} VPMULHUW xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3337 AVX512VLBW :{EVEX} VPMULHUW ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3338 AVX512BW :VPMULHUW zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.017c 3339 AVX512VLBW :{EVEX} VPMULHRSW xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3340 AVX512VLBW :{EVEX} VPMULHRSW ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.512c 3341 AVX512BW :VPMULHRSW zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.017c 3342 AVX512VL :{EVEX} VPMULDQ xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3343 AVX512VL :{EVEX} VPMULDQ ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3344 AVX512F :VPMULDQ zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 3345 AVX512VL :{EVEX} VPMULUDQ xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.513c 3346 AVX512VL :{EVEX} VPMULUDQ ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3347 AVX512F :VPMULUDQ zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.011c 3348 AVX512VL :{EVEX} VPMULLD xmm, xmm, xmm L: 4.17ns= 10.09c T: 0.42ns= 1.013c 3349 AVX512VL :{EVEX} VPMULLD ymm, ymm, ymm L: 4.17ns= 10.09c T: 0.42ns= 1.013c 3350 AVX512F :VPMULLD zmm, zmm, zmm L: 4.17ns= 10.09c T: 0.84ns= 2.034c 3351 AVX512VLDQ :{EVEX} VPMULLQ xmm, xmm, xmm L: 6.26ns= 15.14c T: 0.63ns= 1.516c 3352 AVX512VLDQ :{EVEX} VPMULLQ ymm, ymm, ymm L: 6.26ns= 15.14c T: 0.63ns= 1.516c 3353 AVX512DQ :VPMULLQ zmm, zmm, zmm L: 6.26ns= 15.14c T: 1.25ns= 3.031c 3354 AVX512VLBW :{EVEX} VPMADDUBSW xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3355 AVX512VLBW :{EVEX} VPMADDUBSW ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3356 AVX512BW :VPMADDUBSW zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 3357 AVX512VLBW :{EVEX} VPMADDWD xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3358 AVX512VLBW :{EVEX} VPMADDWD ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 3359 AVX512BW :VPMADDWD zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 3360 AVX512VL_IFMA :{EVEX} VPMADD52LUQ xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3361 AVX512VL_IFMA :{EVEX} VPMADD52LUQ ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3362 AVX512_IFMA :VPMADD52LUQ zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3363 AVX512VL_IFMA :{EVEX} VPMADD52HUQ xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3364 AVX512VL_IFMA :{EVEX} VPMADD52HUQ ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.512c 3365 AVX512_IFMA :VPMADD52HUQ zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 3366 AVX512VLBW :{EVEX} VPMINSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3367 AVX512VLBW :{EVEX} VPMINSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3368 AVX512BW :VPMINSB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3369 AVX512VLBW :{EVEX} VPMINUB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3370 AVX512VLBW :{EVEX} VPMINUB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3371 AVX512BW :VPMINUB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3372 AVX512VLBW :{EVEX} VPMINSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3373 AVX512VLBW :{EVEX} VPMINSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3374 AVX512BW :VPMINSW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3375 AVX512VLBW :{EVEX} VPMINUW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3376 AVX512VLBW :{EVEX} VPMINUW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3377 AVX512BW :VPMINUW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3378 AVX512VL :{EVEX} VPMINSD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3379 AVX512VL :{EVEX} VPMINSD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3380 AVX512F :VPMINSD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3381 AVX512VL :{EVEX} VPMINUD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3382 AVX512VL :{EVEX} VPMINUD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3383 AVX512F :VPMINUD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3384 AVX512VL :VPMINSQ xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 3385 AVX512VL :VPMINSQ ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3386 AVX512F :VPMINSQ zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3387 AVX512VL :VPMINUQ xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3388 AVX512VL :VPMINUQ ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3389 AVX512F :VPMINUQ zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3390 AVX512VLBW :{EVEX} VPMAXSB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3391 AVX512VLBW :{EVEX} VPMAXSB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3392 AVX512BW :VPMAXSB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3393 AVX512VLBW :{EVEX} VPMAXUB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3394 AVX512VLBW :{EVEX} VPMAXUB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3395 AVX512BW :VPMAXUB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3396 AVX512VLBW :{EVEX} VPMAXSW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3397 AVX512VLBW :{EVEX} VPMAXSW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3398 AVX512BW :VPMAXSW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3399 AVX512VLBW :{EVEX} VPMAXUW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3400 AVX512VLBW :{EVEX} VPMAXUW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3401 AVX512BW :VPMAXUW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3402 AVX512VL :{EVEX} VPMAXSD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3403 AVX512VL :{EVEX} VPMAXSD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3404 AVX512F :VPMAXSD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3405 AVX512VL :{EVEX} VPMAXUD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3406 AVX512VL :{EVEX} VPMAXUD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3407 AVX512F :VPMAXUD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3408 AVX512VL :VPMAXSQ xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3409 AVX512VL :VPMAXSQ ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3410 AVX512F :VPMAXSQ zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3411 AVX512VL :VPMAXUQ xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3412 AVX512VL :VPMAXUQ ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 3413 AVX512F :VPMAXUQ zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3414 AVX512VLBW :VPCMPB k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3415 AVX512VLBW :VPCMPB k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3416 AVX512BW :VPCMPB k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3417 AVX512VLBW :VPCMPUB k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.014c 3418 AVX512VLBW :VPCMPUB k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3419 AVX512BW :VPCMPUB k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3420 AVX512VLBW :VPCMPW k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.014c 3421 AVX512VLBW :VPCMPW k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3422 AVX512BW :VPCMPW k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3423 AVX512VLBW :VPCMPUW k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3424 AVX512VLBW :VPCMPUW k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3425 AVX512BW :VPCMPUW k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3426 AVX512VL :VPCMPD k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3427 AVX512VL :VPCMPD k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.014c 3428 AVX512F :VPCMPD k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3429 AVX512VL :VPCMPUD k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.014c 3430 AVX512VL :VPCMPUD k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3431 AVX512F :VPCMPUD k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3432 AVX512VL :VPCMPQ k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3433 AVX512VL :VPCMPQ k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3434 AVX512F :VPCMPQ k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3435 AVX512VL :VPCMPUQ k1, xmm, xmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3436 AVX512VL :VPCMPUQ k1, ymm, ymm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3437 AVX512F :VPCMPUQ k1, zmm, zmm, imm8 L: [diff. reg. set] T: 0.42ns= 1.010c 3438 AVX512VLBW :{EVEX} VPCMPEQB k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3439 AVX512VLBW :{EVEX} VPCMPEQB k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3440 AVX512BW :VPCMPEQB k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3441 AVX512VLBW :{EVEX} VPCMPEQW k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.014c 3442 AVX512VLBW :{EVEX} VPCMPEQW k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3443 AVX512BW :VPCMPEQW k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3444 AVX512VL :{EVEX} VPCMPEQD k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3445 AVX512VL :{EVEX} VPCMPEQD k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3446 AVX512F :VPCMPEQD k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3447 AVX512VL :{EVEX} VPCMPEQQ k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3448 AVX512VL :{EVEX} VPCMPEQQ k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3449 AVX512F :VPCMPEQQ k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3450 AVX512VLBW :{EVEX} VPCMPGTB k1, xmm, xmm L: [diff. reg. set] T: 0.14ns= 0.335c 3451 AVX512VLBW :{EVEX} VPCMPGTB k1, ymm, ymm L: [diff. reg. set] T: 0.14ns= 0.335c 3452 AVX512BW :VPCMPGTB k1, zmm, zmm L: [diff. reg. set] T: 0.14ns= 0.335c 3453 AVX512VLBW :{EVEX} VPCMPGTW k1, xmm, xmm L: [diff. reg. set] T: 0.14ns= 0.335c 3454 AVX512VLBW :{EVEX} VPCMPGTW k1, ymm, ymm L: [diff. reg. set] T: 0.14ns= 0.335c 3455 AVX512BW :VPCMPGTW k1, zmm, zmm L: [diff. reg. set] T: 0.14ns= 0.335c 3456 AVX512VL :{EVEX} VPCMPGTD k1, xmm, xmm L: [diff. reg. set] T: 0.14ns= 0.335c 3457 AVX512VL :{EVEX} VPCMPGTD k1, ymm, ymm L: [diff. reg. set] T: 0.14ns= 0.334c 3458 AVX512F :VPCMPGTD k1, zmm, zmm L: [diff. reg. set] T: 0.14ns= 0.334c 3459 AVX512VL :{EVEX} VPCMPGTQ k1, xmm, xmm L: [diff. reg. set] T: 0.14ns= 0.335c 3460 AVX512VL :{EVEX} VPCMPGTQ k1, ymm, ymm L: [diff. reg. set] T: 0.14ns= 0.335c 3461 AVX512F :VPCMPGTQ k1, zmm, zmm L: [diff. reg. set] T: 0.14ns= 0.334c 3462 AVX512VLBW :VPTESTMB k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3463 AVX512VLBW :VPTESTMB k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3464 AVX512BW :VPTESTMB k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.017c 3465 AVX512VLBW :VPTESTMW k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3466 AVX512VLBW :VPTESTMW k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.014c 3467 AVX512BW :VPTESTMW k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3468 AVX512VL :VPTESTMD k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3469 AVX512VL :VPTESTMD k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3470 AVX512F :VPTESTMD k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3471 AVX512VL :VPTESTMQ k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3472 AVX512VL :VPTESTMQ k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3473 AVX512F :VPTESTMQ k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3474 AVX512VLBW :VPTESTNMB k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.014c 3475 AVX512VLBW :VPTESTNMB k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3476 AVX512BW :VPTESTNMB k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.017c 3477 AVX512VLBW :VPTESTNMW k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3478 AVX512VLBW :VPTESTNMW k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.014c 3479 AVX512BW :VPTESTNMW k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3480 AVX512VL :VPTESTNMD k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3481 AVX512VL :VPTESTNMD k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3482 AVX512F :VPTESTNMD k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3483 AVX512VL :VPTESTNMQ k1, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3484 AVX512VL :VPTESTNMQ k1, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3485 AVX512F :VPTESTNMQ k1, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3486 AVX512VL :{EVEX} VPANDD xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3487 AVX512VL :{EVEX} VPANDD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3488 AVX512VL :{EVEX} VPANDD ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3489 AVX512VL :{EVEX} VPANDD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.364c 3490 AVX512F :VPANDD zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3491 AVX512F :VPANDD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3492 AVX512VL :{EVEX} VPANDQ xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3493 AVX512VL :{EVEX} VPANDQ xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3494 AVX512VL :{EVEX} VPANDQ ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3495 AVX512VL :{EVEX} VPANDQ ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3496 AVX512F :VPANDQ zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3497 AVX512F :VPANDQ zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3498 AVX512VL :{EVEX} VPANDND xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3499 AVX512VL :{EVEX} VPANDND xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.20ns= 0.478c 3500 AVX512VL :{EVEX} VPANDND ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3501 AVX512VL :{EVEX} VPANDND ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3502 AVX512F :VPANDND zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3503 AVX512F :VPANDND zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3504 AVX512VL :{EVEX} VPANDNQ xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3505 AVX512VL :{EVEX} VPANDNQ xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3506 AVX512VL :{EVEX} VPANDNQ ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3507 AVX512VL :{EVEX} VPANDNQ ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3508 AVX512F :VPANDNQ zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.509c 3509 AVX512F :VPANDNQ zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3510 AVX512VL :{EVEX} VPORD xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3511 AVX512VL :{EVEX} VPORD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3512 AVX512VL :{EVEX} VPORD ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3513 AVX512VL :{EVEX} VPORD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.20ns= 0.477c 3514 AVX512F :VPORD zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3515 AVX512F :VPORD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3516 AVX512VL :{EVEX} VPORQ xmm1, xmm1, xmm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3517 AVX512VL :{EVEX} VPORQ xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.20ns= 0.478c 3518 AVX512VL :{EVEX} VPORQ ymm1, ymm1, ymm1 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3519 AVX512VL :{EVEX} VPORQ ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.20ns= 0.479c 3520 AVX512F :VPORQ zmm1, zmm1, zmm1 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3521 AVX512F :VPORQ zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.510c 3522 AVX512VL :{EVEX} VPXORD xmm1, xmm1, xmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3523 AVX512VL :{EVEX} VPXORD xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3524 AVX512VL :{EVEX} VPXORD ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3525 AVX512VL :{EVEX} VPXORD ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3526 AVX512F :VPXORD zmm1, zmm1, zmm1 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3527 AVX512F :VPXORD zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3528 AVX512VL :{EVEX} VPXORQ xmm1, xmm1, xmm1 L: 0.14ns= 0.35c T: 0.20ns= 0.480c 3529 AVX512VL :{EVEX} VPXORQ xmm1, xmm1, xmm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3530 AVX512VL :{EVEX} VPXORQ ymm1, ymm1, ymm1 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3531 AVX512VL :{EVEX} VPXORQ ymm1, ymm1, ymm2 L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3532 AVX512F :VPXORQ zmm1, zmm1, zmm1 L: 0.14ns= 0.35c T: 0.14ns= 0.344c 3533 AVX512F :VPXORQ zmm1, zmm1, zmm2 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3534 AVX512VLBW :VPMOVWB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3535 AVX512VLBW :VPMOVWB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3536 AVX512BW :VPMOVWB ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3537 AVX512VL :VPMOVDB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3538 AVX512VL :VPMOVDB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3539 AVX512F :VPMOVDB xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3540 AVX512VL :VPMOVDW xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3541 AVX512VL :VPMOVDW xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3542 AVX512F :VPMOVDW ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.034c 3543 AVX512VL :VPMOVQB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3544 AVX512VL :VPMOVQB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3545 AVX512F :VPMOVQB xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3546 AVX512VL :VPMOVQW xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3547 AVX512VL :VPMOVQW xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3548 AVX512F :VPMOVQW xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3549 AVX512VL :VPMOVQD xmm, xmm L: 0.42ns= 1.01c T: 0.36ns= 0.878c 3550 AVX512VL :VPMOVQD xmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3551 AVX512F :VPMOVQD ymm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3552 AVX512VLBW :VPMOVSWB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3553 AVX512VLBW :VPMOVSWB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3554 AVX512BW :VPMOVSWB ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3555 AVX512VL :VPMOVSDB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3556 AVX512VL :VPMOVSDB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3557 AVX512F :VPMOVSDB xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3558 AVX512VL :VPMOVSDW xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3559 AVX512VL :VPMOVSDW xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3560 AVX512F :VPMOVSDW ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.034c 3561 AVX512VL :VPMOVSQB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3562 AVX512VL :VPMOVSQB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3563 AVX512F :VPMOVSQB xmm, zmm L: 1.67ns= 4.04c T: 0.84ns= 2.021c 3564 AVX512VL :VPMOVSQW xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3565 AVX512VL :VPMOVSQW xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3566 AVX512F :VPMOVSQW xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3567 AVX512VL :VPMOVSQD xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3568 AVX512VL :VPMOVSQD xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3569 AVX512F :VPMOVSQD ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.034c 3570 AVX512VLBW :VPMOVUSWB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3571 AVX512VLBW :VPMOVUSWB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3572 AVX512BW :VPMOVUSWB ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3573 AVX512VL :VPMOVUSDB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3574 AVX512VL :VPMOVUSDB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3575 AVX512F :VPMOVUSDB xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3576 AVX512VL :VPMOVUSDW xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3577 AVX512VL :VPMOVUSDW xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3578 AVX512F :VPMOVUSDW ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3579 AVX512VL :VPMOVUSQB xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3580 AVX512VL :VPMOVUSQB xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3581 AVX512F :VPMOVUSQB xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3582 AVX512VL :VPMOVUSQW xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.010c 3583 AVX512VL :VPMOVUSQW xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3584 AVX512F :VPMOVUSQW xmm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3585 AVX512VL :VPMOVUSQD xmm, xmm L: 0.83ns= 2.02c T: 0.42ns= 1.011c 3586 AVX512VL :VPMOVUSQD xmm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3587 AVX512F :VPMOVUSQD ymm, zmm L: 1.67ns= 4.03c T: 0.84ns= 2.021c 3588 AVX512VLBW :{EVEX} VPMOVSXBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3589 AVX512VLBW :{EVEX} VPMOVSXBW ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3590 AVX512BW :VPMOVSXBW zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3591 AVX512VL :{EVEX} VPMOVSXBD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3592 AVX512VL :{EVEX} VPMOVSXBD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3593 AVX512F :VPMOVSXBD zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3594 AVX512VL :{EVEX} VPMOVSXBQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3595 AVX512VL :{EVEX} VPMOVSXBQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3596 AVX512F :VPMOVSXBQ zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3597 AVX512VL :{EVEX} VPMOVSXWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3598 AVX512VL :{EVEX} VPMOVSXWD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3599 AVX512F :VPMOVSXWD zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3600 AVX512VL :{EVEX} VPMOVSXWQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.514c 3601 AVX512VL :{EVEX} VPMOVSXWQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3602 AVX512F :VPMOVSXWQ zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3603 AVX512VL :{EVEX} VPMOVSXDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3604 AVX512VL :{EVEX} VPMOVSXDQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3605 AVX512F :VPMOVSXDQ zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3606 AVX512VLBW :{EVEX} VPMOVZXBW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3607 AVX512VLBW :{EVEX} VPMOVZXBW ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3608 AVX512BW :VPMOVZXBW zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3609 AVX512VL :{EVEX} VPMOVZXBD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.514c 3610 AVX512VL :{EVEX} VPMOVZXBD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3611 AVX512F :VPMOVZXBD zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3612 AVX512VL :{EVEX} VPMOVZXBQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3613 AVX512VL :{EVEX} VPMOVZXBQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3614 AVX512F :VPMOVZXBQ zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3615 AVX512VL :{EVEX} VPMOVZXWD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3616 AVX512VL :{EVEX} VPMOVZXWD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3617 AVX512F :VPMOVZXWD zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3618 AVX512VL :{EVEX} VPMOVZXWQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.514c 3619 AVX512VL :{EVEX} VPMOVZXWQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3620 AVX512F :VPMOVZXWQ zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3621 AVX512VL :{EVEX} VPMOVZXDQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3622 AVX512VL :{EVEX} VPMOVZXDQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3623 AVX512F :VPMOVZXDQ zmm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3624 AVX512VLBW :{EVEX} VPABSB xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3625 AVX512VLBW :{EVEX} VPABSB ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3626 AVX512BW :VPABSB zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3627 AVX512VLBW :{EVEX} VPABSW xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3628 AVX512VLBW :{EVEX} VPABSW ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3629 AVX512BW :VPABSW zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3630 AVX512VL :{EVEX} VPABSD xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3631 AVX512VL :{EVEX} VPABSD ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3632 AVX512F :VPABSD zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3633 AVX512VL :VPABSQ xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3634 AVX512VL :VPABSQ ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3635 AVX512F :VPABSQ zmm, zmm L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3636 AVX512VLBW :{EVEX} VPSADBW xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3637 AVX512VLBW :{EVEX} VPSADBW ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3638 AVX512BW :VPSADBW zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3639 AVX512VLBW :VDBPSADBW xmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3640 AVX512VLBW :VDBPSADBW ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 3641 AVX512BW :VDBPSADBW zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3642 AVX512VLBW :{EVEX} VPALIGNR xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3643 AVX512VLBW :{EVEX} VPALIGNR ymm, ymm, ymm, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.014c 3644 AVX512BW :VPALIGNR zmm, zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3645 AVX512VL :VALIGND xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3646 AVX512VL :VALIGND ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3647 AVX512F :VALIGND zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 3648 AVX512VL :VALIGNQ xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3649 AVX512VL :VALIGNQ ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3650 AVX512F :VALIGNQ zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3651 AVX512VLBW :{EVEX} VPAVGB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3652 AVX512VLBW :{EVEX} VPAVGB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3653 AVX512BW :VPAVGB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 3654 AVX512VLBW :{EVEX} VPAVGW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3655 AVX512VLBW :{EVEX} VPAVGW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3656 AVX512BW :VPAVGW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3657 AVX512VLBW :VPBLENDMB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3658 AVX512VLBW :VPBLENDMB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3659 AVX512BW :VPBLENDMB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.509c 3660 AVX512VLBW :VPBLENDMW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3661 AVX512VLBW :VPBLENDMW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3662 AVX512BW :VPBLENDMW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3663 AVX512VL :VPBLENDMD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3664 AVX512VL :VPBLENDMD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3665 AVX512F :VPBLENDMD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3666 AVX512VL :VPBLENDMQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3667 AVX512VL :VPBLENDMQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3668 AVX512F :VPBLENDMQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3669 AVX512VLCD :VPCONFLICTD xmm, xmm L: 4.88ns= 11.80c T: 2.51ns= 6.064c 3670 AVX512VLCD :VPCONFLICTD ymm, ymm L: 7.03ns= 17.00c T: 3.76ns= 9.095c 3671 AVX512CD :VPCONFLICTD zmm, zmm L: 11.04ns= 26.72c T: 8.13ns= 19.673c 3672 AVX512VLCD :VPCONFLICTQ xmm, xmm L: 1.67ns= 4.03c T: 0.84ns= 2.022c 3673 AVX512VLCD :VPCONFLICTQ ymm, ymm L: 5.30ns= 12.82c T: 2.51ns= 6.064c 3674 AVX512CD :VPCONFLICTQ zmm, zmm L: 7.19ns= 17.40c T: 4.71ns= 11.391c 3675 AVX512VL :VPCOMPRESSD xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.022c 3676 AVX512VL :VPCOMPRESSD ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3677 AVX512F :VPCOMPRESSD zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3678 AVX512VL :VPCOMPRESSQ xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3679 AVX512VL :VPCOMPRESSQ ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3680 AVX512F :VPCOMPRESSQ zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3681 AVX512VL :VPCOMPRESSD xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3682 AVX512VL :VPCOMPRESSD ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3683 AVX512F :VPCOMPRESSD zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3684 AVX512VL :VPCOMPRESSQ xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3685 AVX512VL :VPCOMPRESSQ ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3686 AVX512F :VPCOMPRESSQ zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3687 AVX512VL :VPEXPANDD xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3688 AVX512VL :VPEXPANDD ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3689 AVX512F :VPEXPANDD zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 3690 AVX512VL :VPEXPANDQ xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3691 AVX512VL :VPEXPANDQ ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3692 AVX512F :VPEXPANDQ zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3693 AVX512VL :VPEXPANDD xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3694 AVX512VL :VPEXPANDD ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3695 AVX512F :VPEXPANDD zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.034c 3696 AVX512VL :VPEXPANDQ xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3697 AVX512VL :VPEXPANDQ ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3698 AVX512F :VPEXPANDQ zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 3699 AVX512VLCD :VPLZCNTD xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3700 AVX512VLCD :VPLZCNTD ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3701 AVX512CD :VPLZCNTD zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3702 AVX512VLCD :VPLZCNTQ xmm, xmm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3703 AVX512VLCD :VPLZCNTQ ymm, ymm L: 1.67ns= 4.03c T: 0.21ns= 0.505c 3704 AVX512CD :VPLZCNTQ zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.017c 3705 AVX512VL_VBMI :VPMULTISHIFTQB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3706 AVX512VL_VBMI :VPMULTISHIFTQB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3707 AVX512_VBMI :VPMULTISHIFTQB zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 3708 AVX512VLBW :{EVEX} VPSLLW xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.977c 3709 AVX512VLBW :{EVEX} VPSLLW ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3710 AVX512BW :VPSLLW zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3711 AVX512VL :{EVEX} VPSLLD xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.988c 3712 AVX512VL :{EVEX} VPSLLD ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3713 AVX512F :VPSLLD zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 3714 AVX512VL :{EVEX} VPSLLQ xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.990c 3715 AVX512VL :{EVEX} VPSLLQ ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3716 AVX512F :VPSLLQ zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.57ns= 1.388c 3717 AVX512VLBW :{EVEX} VPSLLW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3718 AVX512VLBW :{EVEX} VPSLLW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3719 AVX512BW :VPSLLW zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3720 AVX512VL :{EVEX} VPSLLD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3721 AVX512VL :{EVEX} VPSLLD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3722 AVX512F :VPSLLD zmm, zmm, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3723 AVX512VL :{EVEX} VPSLLQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3724 AVX512VL :{EVEX} VPSLLQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3725 AVX512F :VPSLLQ zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3726 AVX512VLBW :{EVEX} VPSLLDQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3727 AVX512VLBW :{EVEX} VPSLLDQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3728 AVX512BW :VPSLLDQ zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3729 AVX512VLBW :{EVEX} VPSLLVW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3730 AVX512VLBW :{EVEX} VPSLLVW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3731 AVX512BW :VPSLLVW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3732 AVX512VL :{EVEX} VPSLLVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3733 AVX512VL :{EVEX} VPSLLVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3734 AVX512F :VPSLLVD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3735 AVX512VL :{EVEX} VPSLLVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3736 AVX512VL :{EVEX} VPSLLVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3737 AVX512F :VPSLLVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3738 AVX512VLBW :{EVEX} VPSRLW xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.988c 3739 AVX512VLBW :{EVEX} VPSRLW ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3740 AVX512BW :VPSRLW zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3741 AVX512VL :{EVEX} VPSRLD xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.988c 3742 AVX512VL :{EVEX} VPSRLD ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3743 AVX512F :VPSRLD zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 3744 AVX512VL :{EVEX} VPSRLQ xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.987c 3745 AVX512VL :{EVEX} VPSRLQ ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3746 AVX512F :VPSRLQ zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3747 AVX512VLBW :{EVEX} VPSRLW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3748 AVX512VLBW :{EVEX} VPSRLW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3749 AVX512BW :VPSRLW zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3750 AVX512VL :{EVEX} VPSRLD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3751 AVX512VL :{EVEX} VPSRLD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3752 AVX512F :VPSRLD zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3753 AVX512VL :{EVEX} VPSRLQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3754 AVX512VL :{EVEX} VPSRLQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3755 AVX512F :VPSRLQ zmm, zmm, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3756 AVX512VLBW :{EVEX} VPSRLDQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3757 AVX512VLBW :{EVEX} VPSRLDQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.514c 3758 AVX512BW :VPSRLDQ zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3759 AVX512VLBW :{EVEX} VPSRLVW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3760 AVX512VLBW :{EVEX} VPSRLVW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3761 AVX512BW :VPSRLVW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3762 AVX512VL :{EVEX} VPSRLVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3763 AVX512VL :{EVEX} VPSRLVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3764 AVX512F :VPSRLVD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3765 AVX512VL :{EVEX} VPSRLVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3766 AVX512VL :{EVEX} VPSRLVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3767 AVX512F :VPSRLVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3768 AVX512VLBW :{EVEX} VPSRAW xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.40ns= 0.975c 3769 AVX512VLBW :{EVEX} VPSRAW ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3770 AVX512BW :VPSRAW zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3771 AVX512VL :{EVEX} VPSRAD xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.41ns= 0.987c 3772 AVX512VL :{EVEX} VPSRAD ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3773 AVX512F :VPSRAD zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3774 AVX512VL :VPSRAQ xmm, xmm, xmm L: 0.83ns= 2.02c T: 0.66ns= 1.592c 3775 AVX512VL :VPSRAQ ymm, ymm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3776 AVX512F :VPSRAQ zmm, zmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 3777 AVX512VLBW :{EVEX} VPSRAW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3778 AVX512VLBW :{EVEX} VPSRAW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3779 AVX512BW :VPSRAW zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3780 AVX512VL :{EVEX} VPSRAD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3781 AVX512VL :{EVEX} VPSRAD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3782 AVX512F :VPSRAD zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.011c 3783 AVX512VL :VPSRAQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3784 AVX512VL :VPSRAQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3785 AVX512F :VPSRAQ zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3786 AVX512VLBW :{EVEX} VPSRAVW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3787 AVX512VLBW :{EVEX} VPSRAVW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3788 AVX512BW :VPSRAVW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3789 AVX512VL :{EVEX} VPSRAVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3790 AVX512VL :{EVEX} VPSRAVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3791 AVX512F :VPSRAVD zmm, zmm, zmm L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3792 AVX512VL :VPSRAVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3793 AVX512VL :VPSRAVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3794 AVX512F :VPSRAVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3795 AVX512VL :VPROLD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3796 AVX512VL :VPROLD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3797 AVX512F :VPROLD zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3798 AVX512VL :VPROLQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3799 AVX512VL :VPROLQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3800 AVX512F :VPROLQ zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3801 AVX512VL :VPROLVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3802 AVX512VL :VPROLVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3803 AVX512F :VPROLVD zmm, zmm, zmm L: 0.42ns= 1.02c T: 0.42ns= 1.017c 3804 AVX512VL :VPROLVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3805 AVX512VL :VPROLVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3806 AVX512F :VPROLVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3807 AVX512VL :VPRORD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3808 AVX512VL :VPRORD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3809 AVX512F :VPRORD zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3810 AVX512VL :VPRORQ xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3811 AVX512VL :VPRORQ ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.513c 3812 AVX512F :VPRORQ zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3813 AVX512VL :VPRORVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3814 AVX512VL :VPRORVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3815 AVX512F :VPRORVD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3816 AVX512VL :VPRORVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 3817 AVX512VL :VPRORVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3818 AVX512F :VPRORVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 3819 AVX512VL :VPTERNLOGD xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.17ns= 0.416c 3820 AVX512VL :VPTERNLOGD ymm, ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.17ns= 0.417c 3821 AVX512F :VPTERNLOGD zmm, zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3822 AVX512VL :VPTERNLOGQ xmm, xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.17ns= 0.416c 3823 AVX512VL :VPTERNLOGQ ymm, ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.17ns= 0.416c 3824 AVX512F :VPTERNLOGQ zmm, zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.510c 3825 AVX512F :{EVEX} VMOVD r32, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3826 AVX512F :{EVEX} VMOVD xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 3827 AVX512F :{EVEX} VMOVD r32, xmm + xmm, r32 L: 1.67ns= 4.03c T: 0.42ns= 1.011c 3828 AVX512F :{EVEX} VMOVD xmm, [m32] L: [memory dep.] T: 0.21ns= 0.506c 3829 AVX512F :{EVEX} VMOVD [m32], xmm L: [memory dep.] T: 0.21ns= 0.506c 3830 AVX512F :{EVEX} VMOVD xmm, [m32] + [m32], xmm L: 2.08ns= 5.03c T: 0.35ns= 0.857c 3831 AVX512F_X64 :{EVEX} VMOVQ r64, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3832 AVX512F_X64 :{EVEX} VMOVQ xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 3833 AVX512F_X64 :{EVEX} VMOVQ r64, xmm + xmm, r64 L: 1.67ns= 4.03c T: 0.42ns= 1.011c 3834 AVX512F_X64 :{EVEX} VMOVQ xmm, [m64] L: [memory dep.] T: 0.21ns= 0.506c 3835 AVX512F_X64 :{EVEX} VMOVQ [m64], xmm L: [memory dep.] T: 0.21ns= 0.506c 3836 AVX512F_X64 :{EVEX} VMOVQ xmm, [m64] + [m64], xmm L: 2.08ns= 5.03c T: 0.36ns= 0.862c 3837 AVX512VL :VMOVDQA32 xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3838 AVX512VL :VMOVDQA32 xmm1, xmm2 L: 0.08ns= 0.20c T: 0.13ns= 0.321c 3839 AVX512VL :VMOVDQA32 ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3840 AVX512VL :VMOVDQA32 ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3841 AVX512F :VMOVDQA32 zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.510c 3842 AVX512F :VMOVDQA32 zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3843 AVX512VL :VMOVDQA32 xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3844 AVX512VL :VMOVDQA32 ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3845 AVX512F :VMOVDQA32 zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3846 AVX512VL :VMOVDQA32 [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3847 AVX512VL :VMOVDQA32 [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3848 AVX512F :VMOVDQA32 [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3849 AVX512VL :VMOVDQA32 xmm LS pair L: 2.45ns= 5.92c T: 0.37ns= 0.885c 3850 AVX512VL :VMOVDQA32 ymm LS pair L: 3.13ns= 7.58c T: 0.35ns= 0.852c 3851 AVX512F :VMOVDQA32 zmm LS pair L: 2.77ns= 6.70c T: 0.42ns= 1.012c 3852 AVX512VL :VMOVDQA64 xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3853 AVX512VL :VMOVDQA64 xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3854 AVX512VL :VMOVDQA64 ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3855 AVX512VL :VMOVDQA64 ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3856 AVX512F :VMOVDQA64 zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3857 AVX512F :VMOVDQA64 zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3858 AVX512VL :VMOVDQA64 xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3859 AVX512VL :VMOVDQA64 ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3860 AVX512F :VMOVDQA64 zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3861 AVX512VL :VMOVDQA64 [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3862 AVX512VL :VMOVDQA64 [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3863 AVX512F :VMOVDQA64 [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3864 AVX512VL :VMOVDQA64 xmm LS pair L: 2.08ns= 5.03c T: 0.37ns= 0.885c 3865 AVX512VL :VMOVDQA64 ymm LS pair L: 3.09ns= 7.47c T: 0.35ns= 0.852c 3866 AVX512F :VMOVDQA64 zmm LS pair L: 2.77ns= 6.70c T: 0.42ns= 1.012c 3867 AVX512VLBW :VMOVDQU8 xmm, xmm L: 0.42ns= 1.01c T: 0.20ns= 0.476c 3868 AVX512VLBW :VMOVDQU8 xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3869 AVX512VLBW :VMOVDQU8 ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3870 AVX512VLBW :VMOVDQU8 ymm1, ymm2 L: 0.15ns= 0.36c T: 0.14ns= 0.343c 3871 AVX512BW :VMOVDQU8 zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3872 AVX512BW :VMOVDQU8 zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3873 AVX512VLBW :VMOVDQU8 xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3874 AVX512VLBW :VMOVDQU8 ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3875 AVX512BW :VMOVDQU8 zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3876 AVX512VLBW :VMOVDQU8 [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3877 AVX512VLBW :VMOVDQU8 [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3878 AVX512BW :VMOVDQU8 [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3879 AVX512VLBW :VMOVDQU8 xmm LS pair L: 2.08ns= 5.03c T: 0.37ns= 0.885c 3880 AVX512VLBW :VMOVDQU8 ymm LS pair L: 3.13ns= 7.58c T: 0.35ns= 0.852c 3881 AVX512BW :VMOVDQU8 zmm LS pair L: 2.77ns= 6.70c T: 0.42ns= 1.012c 3882 AVX512VLBW :VMOVDQU8 xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 3883 AVX512VLBW :VMOVDQU8 ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3884 AVX512BW :VMOVDQU8 zmm, [m512 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3885 AVX512VLBW :VMOVDQU8 [m128 + 4], xmm L: [memory dep.] T: 0.58ns= 1.400c 3886 AVX512VLBW :VMOVDQU8 [m256 + 4], ymm L: [memory dep.] T: 0.70ns= 1.687c 3887 AVX512BW :VMOVDQU8 [m512 + 4], zmm L: [memory dep.] T: 1.04ns= 2.509c 3888 AVX512VLBW :VMOVDQU8 xmm + 4 LS pair L: 2.08ns= 5.03c T: 0.55ns= 1.328c 3889 AVX512VLBW :VMOVDQU8 ymm + 4 LS pair L: 2.88ns= 6.97c T: 0.78ns= 1.885c 3890 AVX512BW :VMOVDQU8 zmm + 4 LS pair L: 2.89ns= 7.00c T: 0.99ns= 2.389c 3891 AVX512VLBW :VMOVDQU16 xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.362c 3892 AVX512VLBW :VMOVDQU16 xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3893 AVX512VLBW :VMOVDQU16 ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.360c 3894 AVX512VLBW :VMOVDQU16 ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3895 AVX512BW :VMOVDQU16 zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3896 AVX512BW :VMOVDQU16 zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3897 AVX512VLBW :VMOVDQU16 xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3898 AVX512VLBW :VMOVDQU16 ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3899 AVX512BW :VMOVDQU16 zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3900 AVX512VLBW :VMOVDQU16 [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3901 AVX512VLBW :VMOVDQU16 [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3902 AVX512BW :VMOVDQU16 [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3903 AVX512VLBW :VMOVDQU16 xmm LS pair L: 2.59ns= 6.27c T: 0.37ns= 0.885c 3904 AVX512VLBW :VMOVDQU16 ymm LS pair L: 2.83ns= 6.85c T: 0.40ns= 0.969c 3905 AVX512BW :VMOVDQU16 zmm LS pair L: 2.77ns= 6.70c T: 0.42ns= 1.012c 3906 AVX512VLBW :VMOVDQU16 xmm, [m128 + 4] L: [memory dep.] T: 0.45ns= 1.095c 3907 AVX512VLBW :VMOVDQU16 ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3908 AVX512BW :VMOVDQU16 zmm, [m512 + 4] L: [memory dep.] T: 0.43ns= 1.031c 3909 AVX512VLBW :VMOVDQU16 [m128 + 4], xmm L: [memory dep.] T: 0.49ns= 1.182c 3910 AVX512VLBW :VMOVDQU16 [m256 + 4], ymm L: [memory dep.] T: 0.80ns= 1.945c 3911 AVX512BW :VMOVDQU16 [m512 + 4], zmm L: [memory dep.] T: 0.91ns= 2.192c 3912 AVX512VLBW :VMOVDQU16 xmm + 4 LS pair L: 2.45ns= 5.93c T: 0.55ns= 1.328c 3913 AVX512VLBW :VMOVDQU16 ymm + 4 LS pair L: 2.89ns= 7.00c T: 0.78ns= 1.885c 3914 AVX512BW :VMOVDQU16 zmm + 4 LS pair L: 3.86ns= 9.33c T: 0.99ns= 2.389c 3915 AVX512VL :VMOVDQU32 xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3916 AVX512VL :VMOVDQU32 xmm1, xmm2 L: 0.13ns= 0.33c T: 0.20ns= 0.479c 3917 AVX512VL :VMOVDQU32 ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3918 AVX512VL :VMOVDQU32 ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3919 AVX512F :VMOVDQU32 zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3920 AVX512F :VMOVDQU32 zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3921 AVX512VL :VMOVDQU32 xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3922 AVX512VL :VMOVDQU32 ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3923 AVX512F :VMOVDQU32 zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3924 AVX512VL :VMOVDQU32 [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3925 AVX512VL :VMOVDQU32 [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3926 AVX512F :VMOVDQU32 [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3927 AVX512VL :VMOVDQU32 xmm LS pair L: 2.08ns= 5.03c T: 0.37ns= 0.885c 3928 AVX512VL :VMOVDQU32 ymm LS pair L: 3.13ns= 7.57c T: 0.35ns= 0.852c 3929 AVX512F :VMOVDQU32 zmm LS pair L: 3.18ns= 7.70c T: 0.42ns= 1.012c 3930 AVX512VL :VMOVDQU32 xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 3931 AVX512VL :VMOVDQU32 ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3932 AVX512F :VMOVDQU32 zmm, [m512 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3933 AVX512VL :VMOVDQU32 [m128 + 4], xmm L: [memory dep.] T: 0.49ns= 1.182c 3934 AVX512VL :VMOVDQU32 [m256 + 4], ymm L: [memory dep.] T: 0.70ns= 1.687c 3935 AVX512F :VMOVDQU32 [m512 + 4], zmm L: [memory dep.] T: 1.04ns= 2.513c 3936 AVX512VL :VMOVDQU32 xmm + 4 LS pair L: 2.08ns= 5.03c T: 0.55ns= 1.327c 3937 AVX512VL :VMOVDQU32 ymm + 4 LS pair L: 2.88ns= 6.97c T: 0.78ns= 1.885c 3938 AVX512F :VMOVDQU32 zmm + 4 LS pair L: 3.82ns= 9.23c T: 0.99ns= 2.390c 3939 AVX512VL :VMOVDQU64 xmm, xmm L: 0.42ns= 1.01c T: 0.15ns= 0.363c 3940 AVX512VL :VMOVDQU64 xmm1, xmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.333c 3941 AVX512VL :VMOVDQU64 ymm, ymm L: 0.42ns= 1.01c T: 0.15ns= 0.361c 3942 AVX512VL :VMOVDQU64 ymm1, ymm2 L: 0.08ns= 0.20c T: 0.14ns= 0.335c 3943 AVX512F :VMOVDQU64 zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 3944 AVX512F :VMOVDQU64 zmm1, zmm2 L: 0.08ns= 0.20c T: 0.14ns= 0.334c 3945 AVX512VL :VMOVDQU64 xmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 3946 AVX512VL :VMOVDQU64 ymm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 3947 AVX512F :VMOVDQU64 zmm, [m512] L: [memory dep.] T: 0.21ns= 0.506c 3948 AVX512VL :VMOVDQU64 [m128], xmm L: [memory dep.] T: 0.21ns= 0.506c 3949 AVX512VL :VMOVDQU64 [m256], ymm L: [memory dep.] T: 0.21ns= 0.506c 3950 AVX512F :VMOVDQU64 [m512], zmm L: [memory dep.] T: 0.42ns= 1.011c 3951 AVX512VL :VMOVDQU64 xmm LS pair L: 2.45ns= 5.92c T: 0.37ns= 0.885c 3952 AVX512VL :VMOVDQU64 ymm LS pair L: 3.13ns= 7.58c T: 0.35ns= 0.852c 3953 AVX512F :VMOVDQU64 zmm LS pair L: 2.78ns= 6.73c T: 0.42ns= 1.012c 3954 AVX512VL :VMOVDQU64 xmm, [m128 + 4] L: [memory dep.] T: 0.31ns= 0.758c 3955 AVX512VL :VMOVDQU64 ymm, [m256 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3956 AVX512F :VMOVDQU64 zmm, [m512 + 4] L: [memory dep.] T: 0.42ns= 1.010c 3957 AVX512VL :VMOVDQU64 [m128 + 4], xmm L: [memory dep.] T: 0.58ns= 1.401c 3958 AVX512VL :VMOVDQU64 [m256 + 4], ymm L: [memory dep.] T: 0.70ns= 1.687c 3959 AVX512F :VMOVDQU64 [m512 + 4], zmm L: [memory dep.] T: 0.91ns= 2.192c 3960 AVX512VL :VMOVDQU64 xmm + 4 LS pair L: 2.08ns= 5.03c T: 0.55ns= 1.327c 3961 AVX512VL :VMOVDQU64 ymm + 4 LS pair L: 2.79ns= 6.75c T: 0.78ns= 1.885c 3962 AVX512F :VMOVDQU64 zmm + 4 LS pair L: 3.86ns= 9.33c T: 0.99ns= 2.389c 3963 AVX512VL :{EVEX} VMOVNTDQA xmm, [m128] L: [memory dep.] T: 0.40ns= 0.964c 3964 AVX512VL :{EVEX} VMOVNTDQA ymm, [m256] L: [memory dep.] T: 0.40ns= 0.956c 3965 AVX512F :VMOVNTDQA zmm, [m512] L: [memory dep.] T: 0.40ns= 0.980c 3966 AVX512VL :{EVEX} VMOVNTDQ [m128], xmm L: [memory dep.] T: 0.99ns= 2.388c 3967 AVX512VL :{EVEX} VMOVNTDQ [m256], ymm L: [memory dep.] T: 1.18ns= 2.864c 3968 AVX512F :VMOVNTDQ [m512], zmm L: [memory dep.] T: 2.19ns= 5.302c 3969 AVX512VL :{EVEX} VMOVNTDQA + VMOVNTDQ xmm L: 176.65ns= 427.33c T: 6.20ns= 14.997c 3970 AVX512VL :{EVEX} VMOVNTDQA + VMOVNTDQ ymm L: 161.50ns= 390.68c T: 6.64ns= 16.063c 3971 AVX512F :VMOVNTDQA + VMOVNTDQ zmm L: 168.39ns= 407.35c T: 9.34ns= 22.594c 3972 AVX512VLBW :VPMOVB2M k, xmm L: [diff. reg. set] T: 0.42ns= 1.014c 3973 AVX512VLBW :VPMOVB2M k, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3974 AVX512BW :VPMOVB2M k, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3975 AVX512VLBW :VPMOVW2M k, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3976 AVX512VLBW :VPMOVW2M k, ymm L: [diff. reg. set] T: 0.42ns= 1.014c 3977 AVX512BW :VPMOVW2M k, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3978 AVX512VLDQ :VPMOVD2M k, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3979 AVX512VLDQ :VPMOVD2M k, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3980 AVX512DQ :VPMOVD2M k, zmm L: [diff. reg. set] T: 0.42ns= 1.021c 3981 AVX512VLDQ :VPMOVQ2M k, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 3982 AVX512VLDQ :VPMOVQ2M k, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 3983 AVX512DQ :VPMOVQ2M k, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 3984 AVX512VLBW :VPMOVM2B xmm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3985 AVX512VLBW :VPMOVM2B ymm, k L: [diff. reg. set] T: 0.15ns= 0.362c 3986 AVX512BW :VPMOVM2B zmm, k L: [diff. reg. set] T: 0.21ns= 0.505c 3987 AVX512VLBW :VPMOVM2W xmm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3988 AVX512VLBW :VPMOVM2W ymm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3989 AVX512BW :VPMOVM2W zmm, k L: [diff. reg. set] T: 0.21ns= 0.510c 3990 AVX512VLDQ :VPMOVM2D xmm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3991 AVX512VLDQ :VPMOVM2D ymm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3992 AVX512DQ :VPMOVM2D zmm, k L: [diff. reg. set] T: 0.21ns= 0.505c 3993 AVX512VLDQ :VPMOVM2Q xmm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3994 AVX512VLDQ :VPMOVM2Q ymm, k L: [diff. reg. set] T: 0.15ns= 0.361c 3995 AVX512DQ :VPMOVM2Q zmm, k L: [diff. reg. set] T: 0.21ns= 0.505c 3996 AVX512VLBW :VPMOVB2M + VPMOVM2B xmm L: 2.50ns= 6.05c T: 0.42ns= 1.011c 3997 AVX512VLBW :VPMOVB2M + VPMOVM2B ymm L: 2.50ns= 6.05c T: 0.42ns= 1.011c 3998 AVX512BW :VPMOVB2M + VPMOVM2B zmm L: 2.54ns= 6.13c T: 0.49ns= 1.190c 3999 AVX512VLBW :VPMOVW2M + VPMOVM2W xmm L: 2.50ns= 6.05c T: 0.42ns= 1.011c 4000 AVX512VLBW :VPMOVW2M + VPMOVM2W ymm L: 2.51ns= 6.08c T: 0.43ns= 1.042c 4001 AVX512BW :VPMOVW2M + VPMOVM2W zmm L: 2.54ns= 6.13c T: 0.49ns= 1.190c 4002 AVX512VLDQ :VPMOVD2M + VPMOVM2D xmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 4003 AVX512VLDQ :VPMOVD2M + VPMOVM2D ymm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 4004 AVX512DQ :VPMOVD2M + VPMOVM2D zmm L: 1.67ns= 4.03c T: 0.49ns= 1.181c 4005 AVX512VLDQ :VPMOVQ2M + VPMOVM2Q xmm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 4006 AVX512VLDQ :VPMOVQ2M + VPMOVM2Q ymm L: 1.67ns= 4.03c T: 0.42ns= 1.011c 4007 AVX512DQ :VPMOVQ2M + VPMOVM2Q zmm L: 1.67ns= 4.03c T: 0.49ns= 1.181c 4008 AVX512VLBW :VPBROADCASTB xmm, r8 L: [diff. reg. set] T: 0.42ns= 1.010c 4009 AVX512VLBW :VPBROADCASTB ymm, r8 L: [diff. reg. set] T: 0.42ns= 1.010c 4010 AVX512BW :VPBROADCASTB zmm, r8 L: [diff. reg. set] T: 0.42ns= 1.010c 4011 AVX512VLBW :VPBROADCASTW xmm, r16 L: [diff. reg. set] T: 0.42ns= 1.010c 4012 AVX512VLBW :VPBROADCASTW ymm, r16 L: [diff. reg. set] T: 0.42ns= 1.010c 4013 AVX512BW :VPBROADCASTW zmm, r16 L: [diff. reg. set] T: 0.42ns= 1.010c 4014 AVX512VL :VPBROADCASTD xmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 4015 AVX512VL :VPBROADCASTD ymm, r32 L: [diff. reg. set] T: 0.42ns= 1.014c 4016 AVX512F :VPBROADCASTD zmm, r32 L: [diff. reg. set] T: 0.42ns= 1.010c 4017 AVX512VL_X64 :VPBROADCASTQ xmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 4018 AVX512VL_X64 :VPBROADCASTQ ymm, r64 L: [diff. reg. set] T: 0.42ns= 1.011c 4019 AVX512F_X64 :VPBROADCASTQ zmm, r64 L: [diff. reg. set] T: 0.42ns= 1.010c 4020 AVX512VLBW :{EVEX} VPBROADCASTB xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4021 AVX512VLBW :{EVEX} VPBROADCASTB ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4022 AVX512BW :VPBROADCASTB zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4023 AVX512VLBW :{EVEX} VPBROADCASTW xmm, xmm L: 0.42ns= 1.02c T: 0.42ns= 1.014c 4024 AVX512VLBW :{EVEX} VPBROADCASTW ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4025 AVX512BW :VPBROADCASTW zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4026 AVX512VL :{EVEX} VPBROADCASTD xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4027 AVX512VL :{EVEX} VPBROADCASTD ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4028 AVX512F :VPBROADCASTD zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4029 AVX512VL :{EVEX} VPBROADCASTQ xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4030 AVX512VL :{EVEX} VPBROADCASTQ ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4031 AVX512F :VPBROADCASTQ zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4032 AVX512VLDQ :VBROADCASTI32X2 xmm, xmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4033 AVX512VLDQ :VBROADCASTI32X2 ymm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4034 AVX512DQ :VBROADCASTI32X2 zmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4035 AVX512VL :VBROADCASTI32X4 ymm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 4036 AVX512F :VBROADCASTI32X4 zmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 4037 AVX512DQ :VBROADCASTI32X8 zmm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 4038 AVX512VLDQ :VBROADCASTI64X2 ymm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 4039 AVX512DQ :VBROADCASTI64X2 zmm, [m128] L: [memory dep.] T: 0.21ns= 0.506c 4040 AVX512F :VBROADCASTI64X4 zmm, [m256] L: [memory dep.] T: 0.21ns= 0.506c 4041 AVX512VLCD :VPBROADCASTMB2Q xmm, k L: [diff. reg. set] T: 0.42ns= 1.010c 4042 AVX512VLCD :VPBROADCASTMB2Q ymm, k L: [diff. reg. set] T: 0.42ns= 1.010c 4043 AVX512CD :VPBROADCASTMB2Q zmm, k L: [diff. reg. set] T: 0.42ns= 1.011c 4044 AVX512VLCD :VPBROADCASTMW2D xmm, k L: [diff. reg. set] T: 0.42ns= 1.010c 4045 AVX512VLCD :VPBROADCASTMW2D ymm, k L: [diff. reg. set] T: 0.42ns= 1.010c 4046 AVX512CD :VPBROADCASTMW2D zmm, k L: [diff. reg. set] T: 0.42ns= 1.010c 4047 AVX512BW :{EVEX} VPEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 4048 AVX512BW :{EVEX} VPEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 4049 AVX512DQ :{EVEX} VPEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 4050 AVX512DQ_X64 :{EVEX} VPEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.42ns= 1.010c 4051 AVX512BW :{EVEX} VPINSRB xmm, xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 4052 AVX512BW :{EVEX} VPINSRW xmm, xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 4053 AVX512DQ :{EVEX} VPINSRD xmm, xmm, r32, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 4054 AVX512DQ_X64 :{EVEX} VPINSRQ xmm, xmm, r64, im8 L: [diff. reg. set] T: 0.45ns= 1.097c 4055 AVX512BW :{EVEX} VPEXTRB + VPINSRB xmm, im8 L: 2.50ns= 6.05c T: 0.84ns= 2.023c 4056 AVX512BW :{EVEX} VPEXTRW + VPINSRW xmm, im8 L: 2.50ns= 6.05c T: 0.75ns= 1.803c 4057 AVX512DQ :{EVEX} VPEXTRD + VPINSRD xmm, im8 L: 2.50ns= 6.05c T: 0.84ns= 2.025c 4058 AVX512DQ_X64 :{EVEX} VPEXTRQ + VPINSRQ xmm, im8 L: 2.50ns= 6.05c T: 0.84ns= 2.031c 4059 AVX512VL :VEXTRACTI32X4 xmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4060 AVX512F :VEXTRACTI32X4 xmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4061 AVX512VL :VEXTRACTI32X4 [m128], ymm, imm8 L: [memory dep.] T: 0.44ns= 1.054c 4062 AVX512F :VEXTRACTI32X4 [m128], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 4063 AVX512DQ :VEXTRACTI32X8 ymm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4064 AVX512DQ :VEXTRACTI32X8 [m256], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 4065 AVX512VLDQ :VEXTRACTI64X2 xmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4066 AVX512DQ :VEXTRACTI64X2 xmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4067 AVX512VLDQ :VEXTRACTI64X2 [m128], ymm, imm8 L: [memory dep.] T: 0.44ns= 1.054c 4068 AVX512DQ :VEXTRACTI64X2 [m128], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 4069 AVX512F :VEXTRACTI64X4 ymm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4070 AVX512F :VEXTRACTI64X4 [m256], zmm, imm8 L: [memory dep.] T: 0.42ns= 1.014c 4071 AVX512VL :VINSERTI32X4 ymm, ymm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4072 AVX512F :VINSERTI32X4 zmm, zmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4073 AVX512VL :VINSERTI32X4 ymm, ymm, [m128], imm8 L: [memory dep.] T: 0.55ns= 1.337c 4074 AVX512F :VINSERTI32X4 zmm, zmm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 4075 AVX512DQ :VINSERTI32X8 zmm, zmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4076 AVX512DQ :VINSERTI32X8 zmm, zmm, [m256], imm8 L: [memory dep.] T: 0.22ns= 0.525c 4077 AVX512VLDQ :VINSERTI64X2 ymm, ymm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4078 AVX512DQ :VINSERTI64X2 zmm, zmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4079 AVX512VLDQ :VINSERTI64X2 ymm, ymm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 4080 AVX512DQ :VINSERTI64X2 zmm, zmm, [m128], imm8 L: [memory dep.] T: 0.22ns= 0.525c 4081 AVX512F :VINSERTI64X4 zmm, zmm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4082 AVX512F :VINSERTI64X4 zmm, zmm, [m256], imm8 L: [memory dep.] T: 0.56ns= 1.352c 4083 AVX512VLBW :{EVEX} VPACKSSWB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4084 AVX512VLBW :{EVEX} VPACKSSWB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4085 AVX512BW :VPACKSSWB zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4086 AVX512VLBW :{EVEX} VPACKUSWB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4087 AVX512VLBW :{EVEX} VPACKUSWB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4088 AVX512BW :VPACKUSWB zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4089 AVX512VLBW :{EVEX} VPACKSSDW xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4090 AVX512VLBW :{EVEX} VPACKSSDW ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4091 AVX512BW :VPACKSSDW zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4092 AVX512VLBW :{EVEX} VPACKUSDW xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4093 AVX512VLBW :{EVEX} VPACKUSDW ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4094 AVX512BW :VPACKUSDW zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4095 AVX512VLBW :{EVEX} VPUNPCKLBW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4096 AVX512VLBW :{EVEX} VPUNPCKLBW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4097 AVX512BW :VPUNPCKLBW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4098 AVX512VLBW :{EVEX} VPUNPCKHBW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4099 AVX512VLBW :{EVEX} VPUNPCKHBW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.514c 4100 AVX512BW :VPUNPCKHBW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4101 AVX512VLBW :{EVEX} VPUNPCKLWD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4102 AVX512VLBW :{EVEX} VPUNPCKLWD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4103 AVX512BW :VPUNPCKLWD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4104 AVX512VLBW :{EVEX} VPUNPCKHWD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4105 AVX512VLBW :{EVEX} VPUNPCKHWD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4106 AVX512BW :VPUNPCKHWD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4107 AVX512VL :{EVEX} VPUNPCKLDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4108 AVX512VL :{EVEX} VPUNPCKLDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4109 AVX512F :VPUNPCKLDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4110 AVX512VL :{EVEX} VPUNPCKHDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4111 AVX512VL :{EVEX} VPUNPCKHDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4112 AVX512F :VPUNPCKHDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4113 AVX512VL :{EVEX} VPUNPCKLQDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4114 AVX512VL :{EVEX} VPUNPCKLQDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4115 AVX512F :VPUNPCKLQDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4116 AVX512VL :{EVEX} VPUNPCKHQDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4117 AVX512VL :{EVEX} VPUNPCKHQDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4118 AVX512F :VPUNPCKHQDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4119 AVX512VLBW :{EVEX} VPSHUFB xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.514c 4120 AVX512VLBW :{EVEX} VPSHUFB ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4121 AVX512BW :VPSHUFB zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4122 AVX512VLBW :{EVEX} VPSHUFLW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.514c 4123 AVX512VLBW :{EVEX} VPSHUFLW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4124 AVX512BW :VPSHUFLW zmm, zmm, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.017c 4125 AVX512VLBW :{EVEX} VPSHUFHW xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4126 AVX512VLBW :{EVEX} VPSHUFHW ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4127 AVX512BW :VPSHUFHW zmm, zmm, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4128 AVX512VL :{EVEX} VPSHUFD xmm, xmm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.514c 4129 AVX512VL :{EVEX} VPSHUFD ymm, ymm, imm8 L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4130 AVX512F :VPSHUFD zmm, zmm, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.017c 4131 AVX512VL :VSHUFI32X4 ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4132 AVX512F :VSHUFI32X4 zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4133 AVX512VL :VSHUFI64X2 ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4134 AVX512F :VSHUFI64X2 zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4135 AVX512VL_VBMI :VPERMB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4136 AVX512VL_VBMI :VPERMB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4137 AVX512_VBMI :VPERMB zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4138 AVX512VLBW :VPERMW xmm, xmm, xmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 4139 AVX512VLBW :VPERMW ymm, ymm, ymm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 4140 AVX512BW :VPERMW zmm, zmm, zmm L: 1.67ns= 4.03c T: 0.42ns= 1.010c 4141 AVX512VL :{EVEX} VPERMD ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4142 AVX512F :VPERMD zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4143 AVX512VL :VPERMQ ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4144 AVX512F :VPERMQ zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4145 AVX512VL :{EVEX} VPERMQ ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4146 AVX512F :VPERMQ zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4147 AVX512VL_VBMI :VPERMI2B xmm, xmm, xmm L: 2.09ns= 5.05c T: 0.84ns= 2.040c 4148 AVX512VL_VBMI :VPERMI2B ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4149 AVX512_VBMI :VPERMI2B zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4150 AVX512VLBW :VPERMI2W xmm, xmm, xmm L: 2.92ns= 7.07c T: 0.84ns= 2.039c 4151 AVX512VLBW :VPERMI2W ymm, ymm, ymm L: 2.92ns= 7.06c T: 0.84ns= 2.021c 4152 AVX512BW :VPERMI2W zmm, zmm, zmm L: 2.92ns= 7.06c T: 0.84ns= 2.021c 4153 AVX512VL :VPERMI2D xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4154 AVX512VL :VPERMI2D ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4155 AVX512F :VPERMI2D zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4156 AVX512VL :VPERMI2Q xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4157 AVX512VL :VPERMI2Q ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4158 AVX512F :VPERMI2Q zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4159 AVX512VL_VBMI :VPERMT2B xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4160 AVX512VL_VBMI :VPERMT2B ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4161 AVX512_VBMI :VPERMT2B zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4162 AVX512VLBW :VPERMT2W xmm, xmm, xmm L: 2.92ns= 7.06c T: 0.84ns= 2.021c 4163 AVX512VLBW :VPERMT2W ymm, ymm, ymm L: 2.92ns= 7.06c T: 0.84ns= 2.021c 4164 AVX512BW :VPERMT2W zmm, zmm, zmm L: 2.92ns= 7.06c T: 0.84ns= 2.021c 4165 AVX512VL :VPERMT2D xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4166 AVX512VL :VPERMT2D ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4167 AVX512F :VPERMT2D zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.017c 4168 AVX512VL :VPERMT2Q xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4169 AVX512VL :VPERMT2Q ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4170 AVX512F :VPERMT2Q zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4171 AVX512VL :VPGATHERDD xmm {k}, [xm32] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 4172 AVX512VL :VPGATHERDD ymm {k}, [ym32] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 4173 AVX512F :VPGATHERDD zmm {k}, [zm32] + KMOVW L: 10.47ns= 25.32c T: 3.76ns= 9.094c 4174 AVX512VL :VPGATHERQD xmm {k}, [xm64] + KMOVW L: 7.13ns= 17.24c T: 0.86ns= 2.085c 4175 AVX512VL :VPGATHERQD xmm {k}, [ym64] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 4176 AVX512F :VPGATHERQD ymm {k}, [zm64] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 4177 AVX512VL :VPGATHERDQ xmm {k}, [xm32] + KMOVW L: 7.13ns= 17.24c T: 0.86ns= 2.084c 4178 AVX512VL :VPGATHERDQ ymm {k}, [xm32] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.031c 4179 AVX512F :VPGATHERDQ zmm {k}, [ym32] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 4180 AVX512VL :VPGATHERQQ xmm {k}, [xm64] + KMOVW L: 7.13ns= 17.24c T: 0.86ns= 2.085c 4181 AVX512VL :VPGATHERQQ ymm {k}, [ym64] + KMOVW L: 7.96ns= 19.26c T: 1.25ns= 3.032c 4182 AVX512F :VPGATHERQQ zmm {k}, [zm64] + KMOVW L: 8.79ns= 21.27c T: 2.09ns= 5.052c 4183 AVX512VL :VPSCATTERDD [xm32] {k}, xmm + KMOVW L: [memory dep.] T: 2.51ns= 6.064c 4184 AVX512VL :VPSCATTERDD [ym32] {k}, ymm + KMOVW L: [memory dep.] T: 3.34ns= 8.085c 4185 AVX512F :VPSCATTERDD [zm32] {k}, zmm + KMOVW L: [memory dep.] T: 5.01ns= 12.127c 4186 AVX512VL :VPSCATTERQD [xm64] {k}, xmm + KMOVW L: [memory dep.] T: 2.09ns= 5.053c 4187 AVX512VL :VPSCATTERQD [ym64] {k}, xmm + KMOVW L: [memory dep.] T: 2.51ns= 6.063c 4188 AVX512F :VPSCATTERQD [zm64] {k}, ymm + KMOVW L: [memory dep.] T: 3.34ns= 8.085c 4189 AVX512VL :VPSCATTERDQ [xm32] {k}, xmm + KMOVW L: [memory dep.] T: 2.09ns= 5.054c 4190 AVX512VL :VPSCATTERDQ [xm32] {k}, ymm + KMOVW L: [memory dep.] T: 2.51ns= 6.063c 4191 AVX512F :VPSCATTERDQ [ym32] {k}, zmm + KMOVW L: [memory dep.] T: 3.34ns= 8.084c 4192 AVX512VL :VPSCATTERQQ [xm64] {k}, xmm + KMOVW L: [memory dep.] T: 2.09ns= 5.055c 4193 AVX512VL :VPSCATTERQQ [ym64] {k}, ymm + KMOVW L: [memory dep.] T: 2.51ns= 6.063c 4194 AVX512F :VPSCATTERQQ [zm64] {k}, zmm + KMOVW L: [memory dep.] T: 3.34ns= 8.085c 4195 AVX :VMOVAPS+VEXTRACTF128 [m128], ym, im8 L: [memory dep.] T: 0.84ns= 2.021c 4196 AVX2 :VMOVDQA+VEXTRACTI128 [m128], ym, im8 L: [memory dep.] T: 0.84ns= 2.021c 4197 AVX512VL :VMOVAPS+VEXTRACTF32X4 [m128], ym, im8 L: [memory dep.] T: 0.94ns= 2.284c 4198 AVX512F :VMOVAPS+VEXTRACTF32X4 [m128], zm, im8 L: [memory dep.] T: 0.94ns= 2.284c 4199 AVX512DQ :VMOVAPS+VEXTRACTF32X8 [m256], zm, im8 L: [memory dep.] T: 0.94ns= 2.284c 4200 AVX512VLDQ :VMOVAPD+VEXTRACTF64X2 [m128], ym, im8 L: [memory dep.] T: 0.94ns= 2.284c 4201 AVX512DQ :VMOVAPD+VEXTRACTF64X2 [m128], zm, im8 L: [memory dep.] T: 0.94ns= 2.284c 4202 AVX512F :VMOVAPD+VEXTRACTF64X4 [m256], zm, im8 L: [memory dep.] T: 0.94ns= 2.284c 4203 AVX512VL :VMOVDQA32+VEXTRACTI32X4 [m128],ym,im8 L: [memory dep.] T: 1.11ns= 2.695c 4204 AVX512F :VMOVDQA32+VEXTRACTI32X4 [m128],zm,im8 L: [memory dep.] T: 0.94ns= 2.284c 4205 AVX512DQ :VMOVDQA32+VEXTRACTI32X8 [m256],zm,im8 L: [memory dep.] T: 0.94ns= 2.284c 4206 AVX512VLDQ :VMOVDQA64+VEXTRACTI64X2 [m128],ym,im8 L: [memory dep.] T: 0.94ns= 2.284c 4207 AVX512DQ :VMOVDQA64+VEXTRACTI64X2 [m128],zm,im8 L: [memory dep.] T: 0.94ns= 2.284c 4208 AVX512F :VMOVDQA64+VEXTRACTI64X4 [m256],zm,im8 L: [memory dep.] T: 0.94ns= 2.284c 4209 AVX :VMOVAPS+VINSERTF128 ym, [m128], im8 L: [memory dep.] T: 0.42ns= 1.021c 4210 AVX2 :VMOVDQA+VINSERTI128 ym, [m128], im8 L: [memory dep.] T: 0.42ns= 1.021c 4211 AVX512VL :VMOVAPS+VINSERTF32X4 ym, [m128], im8 L: [memory dep.] T: 0.42ns= 1.018c 4212 AVX512F :VMOVAPS+VINSERTF32X4 zm, [m128], im8 L: [memory dep.] T: 0.42ns= 1.018c 4213 AVX512DQ :VMOVAPS+VINSERTF32X8 zm, [m256], im8 L: [memory dep.] T: 0.42ns= 1.018c 4214 AVX512VLDQ :VMOVAPD+VINSERTF64x2 ym, [m128], im8 L: [memory dep.] T: 0.42ns= 1.018c 4215 AVX512DQ :VMOVAPD+VINSERTF64X4 zm, [m128], im8 L: [memory dep.] T: 0.42ns= 1.018c 4216 AVX512F :VMOVAPD+VINSERTF64X4 zm, [m256], im8 L: [memory dep.] T: 0.42ns= 1.018c 4217 AVX512VL :VMOVDQA32+VINSERTI32X4 ym, [m128],im8 L: [memory dep.] T: 0.42ns= 1.018c 4218 AVX512F :VMOVDQA32+VINSERTI32X4 zm, [m128],im8 L: [memory dep.] T: 0.42ns= 1.018c 4219 AVX512DQ :VMOVDQA32+VINSERTI32X8 zm, [m256],im8 L: [memory dep.] T: 0.42ns= 1.018c 4220 AVX512VLDQ :VMOVDQA64+VINSERTI64x2 ym, [m128],im8 L: [memory dep.] T: 0.42ns= 1.018c 4221 AVX512DQ :VMOVDQA64+VINSERTI64X4 zm, [m128],im8 L: [memory dep.] T: 0.42ns= 1.018c 4222 AVX512F :VMOVDQA64+VINSERTI64X4 zm, [m256],im8 L: [memory dep.] T: 0.42ns= 1.018c 4229 AVX512VL_VNNI :{EVEX}VPDPBUSD xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4230 AVX512VL_VNNI :{EVEX}VPDPBUSD ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4231 AVX512_VNNI :{EVEX}VPDPBUSD zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 4232 AVX512VL_VNNI :{EVEX}VPDPBUSDS xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4233 AVX512VL_VNNI :{EVEX}VPDPBUSDS ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4234 AVX512_VNNI :{EVEX}VPDPBUSDS zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.017c 4235 AVX512VL_VNNI :{EVEX}VPDPWSSD xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4236 AVX512VL_VNNI :{EVEX}VPDPWSSD ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.513c 4237 AVX512_VNNI :{EVEX}VPDPWSSD zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 4238 AVX512VL_VNNI :{EVEX}VPDPWSSDS xmm, xmm, xmm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4239 AVX512VL_VNNI :{EVEX}VPDPWSSDS ymm, ymm, ymm L: 2.08ns= 5.04c T: 0.21ns= 0.505c 4240 AVX512_VNNI :{EVEX}VPDPWSSDS zmm, zmm, zmm L: 2.08ns= 5.04c T: 0.42ns= 1.010c 4241 AVX512VL_BITALG :VPOPCNTB xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4242 AVX512VL_BITALG :VPOPCNTB ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4243 AVX512_BITALG :VPOPCNTB zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4244 AVX512VL_BITALG :VPOPCNTW xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.014c 4245 AVX512VL_BITALG :VPOPCNTW ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4246 AVX512_BITALG :VPOPCNTW zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4247 AVX512VL_VPOPCNTDQ :VPOPCNTD xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4248 AVX512VL_VPOPCNTDQ :VPOPCNTD ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4249 AVX512_VPOPCNTDQ :VPOPCNTD zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4250 AVX512VL_VPOPCNTDQ :VPOPCNTQ xmm, xmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4251 AVX512VL_VPOPCNTDQ :VPOPCNTQ ymm, ymm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4252 AVX512_VPOPCNTDQ :VPOPCNTQ zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4253 AVX512VL_BITALG :VPSHUFBITQMB k, xmm, xmm L: [diff. reg. set] T: 0.42ns= 1.010c 4254 AVX512VL_BITALG :VPSHUFBITQMB k, ymm, ymm L: [diff. reg. set] T: 0.42ns= 1.010c 4255 AVX512_BITALG :VPSHUFBITQMB k, zmm, zmm L: [diff. reg. set] T: 0.42ns= 1.010c 4256 AVX512VL_VBMI2 :VPCOMPRESSB xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4257 AVX512VL_VBMI2 :VPCOMPRESSB ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4258 AVX512_VBMI2 :VPCOMPRESSB zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4259 AVX512VL_VBMI2 :VPCOMPRESSW xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4260 AVX512VL_VBMI2 :VPCOMPRESSW ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.027c 4261 AVX512_VBMI2 :VPCOMPRESSW zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4262 AVX512VL_VBMI2 :VPCOMPRESSB xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.027c 4263 AVX512VL_VBMI2 :VPCOMPRESSB ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4264 AVX512_VBMI2 :VPCOMPRESSB zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4265 AVX512VL_VBMI2 :VPCOMPRESSW xmm {k}, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4266 AVX512VL_VBMI2 :VPCOMPRESSW ymm {k}, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4267 AVX512_VBMI2 :VPCOMPRESSW zmm {k}, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4268 AVX512VL_VBMI2 :VPEXPANDB xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4269 AVX512VL_VBMI2 :VPEXPANDB ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4270 AVX512_VBMI2 :VPEXPANDB zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4271 AVX512VL_VBMI2 :VPEXPANDW xmm, xmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4272 AVX512VL_VBMI2 :VPEXPANDW ymm, ymm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4273 AVX512_VBMI2 :VPEXPANDW zmm, zmm L: 1.25ns= 3.02c T: 0.84ns= 2.021c 4274 AVX512VL_VBMI2 :VPEXPANDB xmm {k}, xmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4275 AVX512VL_VBMI2 :VPEXPANDB ymm {k}, ymm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4276 AVX512_VBMI2 :VPEXPANDB zmm {k}, zmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4277 AVX512VL_VBMI2 :VPEXPANDW xmm {k}, xmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4278 AVX512VL_VBMI2 :VPEXPANDW ymm {k}, ymm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4279 AVX512_VBMI2 :VPEXPANDW zmm {k}, zmm L: 2.08ns= 5.04c T: 0.84ns= 2.021c 4280 AVX512VL_VBMI2 :VPSHLDW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4281 AVX512VL_VBMI2 :VPSHLDW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4282 AVX512_VBMI2 :VPSHLDW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4283 AVX512VL_VBMI2 :VPSHLDD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 4284 AVX512VL_VBMI2 :VPSHLDD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4285 AVX512_VBMI2 :VPSHLDD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4286 AVX512VL_VBMI2 :VPSHLDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4287 AVX512VL_VBMI2 :VPSHLDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4288 AVX512_VBMI2 :VPSHLDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4289 AVX512VL_VBMI2 :VPSHRDW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4290 AVX512VL_VBMI2 :VPSHRDW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 4291 AVX512_VBMI2 :VPSHRDW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4292 AVX512VL_VBMI2 :VPSHRDD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4293 AVX512VL_VBMI2 :VPSHRDD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4294 AVX512_VBMI2 :VPSHRDD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 4295 AVX512VL_VBMI2 :VPSHRDQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4296 AVX512VL_VBMI2 :VPSHRDQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 4297 AVX512_VBMI2 :VPSHRDQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4298 AVX512VL_VBMI2 :VPSHLDVW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 4299 AVX512VL_VBMI2 :VPSHLDVW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4300 AVX512_VBMI2 :VPSHLDVW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4301 AVX512VL_VBMI2 :VPSHLDVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4302 AVX512VL_VBMI2 :VPSHLDVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4303 AVX512_VBMI2 :VPSHLDVD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4304 AVX512VL_VBMI2 :VPSHLDVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4305 AVX512VL_VBMI2 :VPSHLDVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.513c 4306 AVX512_VBMI2 :VPSHLDVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4307 AVX512VL_VBMI2 :VPSHRDVW xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 4308 AVX512VL_VBMI2 :VPSHRDVW ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4309 AVX512_VBMI2 :VPSHRDVW zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4310 AVX512VL_VBMI2 :VPSHRDVD xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.512c 4311 AVX512VL_VBMI2 :VPSHRDVD ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4312 AVX512_VBMI2 :VPSHRDVD zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4313 AVX512VL_VBMI2 :VPSHRDVQ xmm, xmm, xmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4314 AVX512VL_VBMI2 :VPSHRDVQ ymm, ymm, ymm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4315 AVX512_VBMI2 :VPSHRDVQ zmm, zmm, zmm L: 0.42ns= 1.01c T: 0.42ns= 1.011c 4316 AVX+VAES :VAESDEC ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.513c 4317 AVX512VL+VAES :{EVEX} VAESDEC xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4318 AVX512VL+VAES :{EVEX} VAESDEC ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4319 AVX512F+VAES :VAESDEC zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4320 AVX+VAES :VAESDECLAST ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4321 AVX512VL+VAES :{EVEX} VAESDECLAST xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4322 AVX512VL+VAES :{EVEX} VAESDECLAST ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4323 AVX512F+VAES :VAESDECLAST zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4324 AVX+VAES :VAESENC ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4325 AVX512VL+VAES :{EVEX} VAESENC xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.513c 4326 AVX512VL+VAES :{EVEX} VAESENC ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4327 AVX512F+VAES :VAESENC zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4328 AVX+VAES :VAESENCLAST ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.513c 4329 AVX512VL+VAES :{EVEX} VAESENCLAST xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4330 AVX512VL+VAES :{EVEX} VAESENCLAST ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4331 AVX512F+VAES :VAESENCLAST zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4332 AVX+VPCLMULQDQ :VPCLMULQDQ ymm, ymm, ymm, imm8 L: 3.34ns= 8.07c T: 0.84ns= 2.021c 4333 AVX512VL+VPCLMULQDQ :{EVEX} VPCLMULQDQ xmm, xmm, xmm, imm8 L: 2.50ns= 6.05c T: 0.42ns= 1.010c 4334 AVX512VL+VPCLMULQDQ :{EVEX} VPCLMULQDQ ymm, ymm, ymm, imm8 L: 3.34ns= 8.07c T: 0.84ns= 2.021c 4335 AVX512F+VPCLMULQDQ :VPCLMULQDQ zmm, zmm, zmm, imm8 L: 3.34ns= 8.07c T: 0.84ns= 2.021c 4336 GFNI :GF2P8AFFINEINVQB xmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4337 AVX+GFNI :VGF2P8AFFINEINVQB xmm, xmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4338 AVX+GFNI :VGF2P8AFFINEINVQB ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4339 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEINVQB x, x, x, im8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4340 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEINVQB y, y, y, im8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4341 AVX512F+GFNI :VGF2P8AFFINEINVQB zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4342 GFNI :GF2P8AFFINEQB xmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4343 AVX+GFNI :VGF2P8AFFINEQB xmm, xmm, xmm, imm8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4344 AVX+GFNI :VGF2P8AFFINEQB ymm, ymm, ymm, imm8 L: 1.25ns= 3.02c T: 0.21ns= 0.512c 4345 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB xm, xm, xm, im8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4346 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB ym, ym, ym, im8 L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4347 AVX512F+GFNI :VGF2P8AFFINEQB zmm, zmm, zmm, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4348 GFNI :GF2P8MULB xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4349 AVX+GFNI :VGF2P8MULB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4350 AVX+GFNI :VGF2P8MULB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4351 AVX512VL+GFNI :{EVEX} VGF2P8MULB xmm, xmm, xmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4352 AVX512VL+GFNI :{EVEX} VGF2P8MULB ymm, ymm, ymm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4353 AVX512F+GFNI :VGF2P8MULB zmm, zmm, zmm L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4354 X86 :SHLD r1_16, r2_16, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4355 X86 :SHLD r1_32, r2_32, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4356 AMD64 :SHLD r1_64, r2_64, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4357 X86 :SHLD r1_16, r2_16, cl L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4358 X86 :SHLD r1_32, r2_32, cl L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4359 AMD64 :SHLD r1_64, r2_64, cl L: 1.25ns= 3.02c T: 0.42ns= 1.011c 4360 X86 :SHRD r1_16, r2_16, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4361 X86 :SHRD r1_32, r2_32, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4362 AMD64 :SHRD r1_64, r2_64, imm8 L: 1.25ns= 3.02c T: 0.42ns= 1.010c 4363 X86 :SHRD r1_16, r2_16, cl L: 1.79ns= 4.33c T: 0.42ns= 1.010c 4364 X86 :SHRD r1_32, r2_32, cl L: 1.79ns= 4.33c T: 0.42ns= 1.010c 4365 AMD64 :SHRD r1_64, r2_64, cl L: 1.79ns= 4.33c T: 0.42ns= 1.010c 4366 X86 :ADC r8, imm8 L: 0.42ns= 1.01c T: 0.84ns= 2.021c 4367 X86 :ADC r16, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4368 X86 :ADC r32, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4369 AMD64 :ADC r64, imm8 L: 0.42ns= 1.02c T: 0.42ns= 1.025c 4370 X86 :ADC r16, imm16 L: 0.45ns= 1.10c T: 0.92ns= 2.218c 4371 X86 :ADC r32, imm32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4372 AMD64 :ADC r64, imm32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4373 X86 :ADC al, imm8 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4374 X86 :ADC ax, imm16 L: 0.85ns= 2.07c T: 1.20ns= 2.891c 4375 X86 :ADC eax, imm32 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4376 AMD64 :ADC rax, imm32 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4377 X86 :ADC r8, imm8_0 L: 0.42ns= 1.01c T: 0.84ns= 2.021c 4378 X86 :ADC r16, imm8_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4379 X86 :ADC r32, imm8_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4380 AMD64 :ADC r64, imm8_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4381 X86 :ADC r16, imm16_0 L: 0.45ns= 1.10c T: 0.89ns= 2.158c 4382 X86 :ADC r32, imm32_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4383 AMD64 :ADC r64, imm32_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4384 X86 :ADC al, imm8_0 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4385 X86 :ADC ax, imm16_0 L: 0.85ns= 2.07c T: 1.19ns= 2.890c 4386 X86 :ADC eax, imm32_0 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4387 AMD64 :ADC rax, imm32_0 L: 0.84ns= 2.04c T: 0.84ns= 2.043c 4388 X86 :SBB r8, imm8 L: 0.42ns= 1.01c T: 0.84ns= 2.021c 4389 X86 :SBB r16, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4390 X86 :SBB r32, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4391 AMD64 :SBB r64, imm8 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4392 X86 :SBB r16, imm16 L: 0.45ns= 1.10c T: 0.94ns= 2.271c 4393 X86 :SBB r32, imm32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4394 AMD64 :SBB r64, imm32 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4395 X86 :SBB al, imm8 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4396 X86 :SBB ax, imm16 L: 0.85ns= 2.07c T: 1.20ns= 2.898c 4397 X86 :SBB eax, imm32 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4398 AMD64 :SBB rax, imm32 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4399 X86 :SBB r8, imm8_0 L: 0.42ns= 1.02c T: 0.84ns= 2.025c 4400 X86 :SBB r16, imm8_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4401 X86 :SBB r32, imm8_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4402 AMD64 :SBB r64, imm8_0 L: 0.42ns= 1.02c T: 0.42ns= 1.025c 4403 X86 :SBB r16, imm16_0 L: 0.45ns= 1.10c T: 0.93ns= 2.254c 4404 X86 :SBB r32, imm32_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4405 AMD64 :SBB r64, imm32_0 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4406 X86 :SBB al, imm8_0 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4407 X86 :SBB ax, imm16_0 L: 0.85ns= 2.07c T: 1.20ns= 2.895c 4408 X86 :SBB eax, imm32_0 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4409 AMD64 :SBB rax, imm32_0 L: 0.83ns= 2.02c T: 0.84ns= 2.021c 4410 AMD64 :LEA r16, [disp32] L: 0.43ns= 1.05c T: 0.38ns= 0.931c 4411 AMD64 :LEA r32, [disp32] L: 0.11ns= 0.25c T: 0.16ns= 0.391c 4412 AMD64 :LEA r64, [disp32] L: 0.11ns= 0.26c T: 0.18ns= 0.429c 4413 AMD64 :LEA r16, [r64] L: 0.83ns= 2.02c T: 0.42ns= 1.010c 4414 AMD64 :LEA r32, [r64] L: 0.42ns= 1.01c T: 0.11ns= 0.277c 4415 AMD64 :LEA r64, [r64] L: 0.42ns= 1.01c T: 0.12ns= 0.288c 4416 AMD64 :LEA r16, [r64 + disp8] L: 0.83ns= 2.02c T: 0.39ns= 0.938c 4417 AMD64 :LEA r32, [r64 + disp8] L: 0.42ns= 1.01c T: 0.11ns= 0.275c 4418 AMD64 :LEA r64, [r64 + disp8] L: 0.42ns= 1.01c T: 0.10ns= 0.253c 4419 AMD64 :LEA r16, [r64 + disp32] L: 0.84ns= 2.04c T: 0.38ns= 0.911c 4420 AMD64 :LEA r32, [r64 + disp32] L: 0.42ns= 1.01c T: 0.14ns= 0.340c 4421 AMD64 :LEA r64, [r64 + disp32] L: 0.42ns= 1.01c T: 0.16ns= 0.375c 4422 AMD64 :LEA r16, [r64 + r64] L: 0.84ns= 2.04c T: 0.45ns= 1.081c 4423 AMD64 :LEA r32, [r64 + r64] L: 0.42ns= 1.01c T: 0.11ns= 0.276c 4424 AMD64 :LEA r64, [r64 + r64] L: 0.42ns= 1.01c T: 0.10ns= 0.253c 4425 AMD64 :LEA r16, [r64 + r64 + disp8] L: 0.83ns= 2.02c T: 0.38ns= 0.914c 4426 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.42ns= 1.01c T: 0.11ns= 0.261c 4427 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.42ns= 1.01c T: 0.12ns= 0.292c 4428 AMD64 :LEA r16, [r64 + r64 + disp32] L: 0.83ns= 2.02c T: 0.38ns= 0.926c 4429 AMD64 :LEA r32, [r64 + r64 + disp32] L: 0.42ns= 1.01c T: 0.16ns= 0.392c 4430 AMD64 :LEA r64, [r64 + r64 + disp32] L: 0.42ns= 1.02c T: 0.21ns= 0.508c 4431 AMD64 :LEA r16, [r64 + r64 * 8] L: 0.83ns= 2.02c T: 0.39ns= 0.946c 4432 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4433 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4434 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 0.83ns= 2.02c T: 0.38ns= 0.926c 4435 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4436 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.42ns= 1.01c T: 0.21ns= 0.513c 4437 AMD64 :LEA r16, [r64 + r64 * 8 + disp32] L: 0.83ns= 2.02c T: 0.39ns= 0.937c 4438 AMD64 :LEA r32, [r64 + r64 * 8 + disp32] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4439 AMD64 :LEA r64, [r64 + r64 * 8 + disp32] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4440 AMD64 :ASP LEA r16, [disp32] L: 0.42ns= 1.01c T: 0.39ns= 0.943c 4441 AMD64 :ASP LEA r32, [disp32] L: 0.11ns= 0.26c T: 0.19ns= 0.450c 4442 AMD64 :ASP LEA r64, [disp32] L: 0.11ns= 0.26c T: 0.20ns= 0.490c 4443 AMD64 :ASP LEA r16, [r32] L: 0.83ns= 2.02c T: 0.39ns= 0.937c 4444 AMD64 :ASP LEA r32, [r32] L: 0.42ns= 1.01c T: 0.10ns= 0.252c 4445 AMD64 :ASP LEA r64, [r32] L: 0.42ns= 1.01c T: 0.10ns= 0.253c 4446 AMD64 :ASP LEA r16, [r32 + disp8] L: 0.83ns= 2.02c T: 0.38ns= 0.913c 4447 AMD64 :ASP LEA r32, [r32 + disp8] L: 0.42ns= 1.01c T: 0.11ns= 0.261c 4448 AMD64 :ASP LEA r64, [r32 + disp8] L: 0.42ns= 1.01c T: 0.12ns= 0.292c 4449 AMD64 :ASP LEA r16, [r32 + disp32] L: 0.84ns= 2.04c T: 0.39ns= 0.932c 4450 AMD64 :ASP LEA r32, [r32 + disp32] L: 0.42ns= 1.01c T: 0.16ns= 0.392c 4451 AMD64 :ASP LEA r64, [r32 + disp32] L: 0.42ns= 1.01c T: 0.18ns= 0.427c 4452 AMD64 :ASP LEA r16, [r32 + r32] L: 0.83ns= 2.02c T: 0.38ns= 0.914c 4453 AMD64 :ASP LEA r32, [r32 + r32] L: 0.42ns= 1.01c T: 0.11ns= 0.261c 4454 AMD64 :ASP LEA r64, [r32 + r32] L: 0.42ns= 1.01c T: 0.12ns= 0.291c 4455 AMD64 :ASP LEA r16, [r32 + r32 + disp8] L: 0.83ns= 2.02c T: 0.39ns= 0.938c 4456 AMD64 :ASP LEA r32, [r32 + r32 + disp8] L: 0.42ns= 1.01c T: 0.12ns= 0.293c 4457 AMD64 :ASP LEA r64, [r32 + r32 + disp8] L: 0.42ns= 1.01c T: 0.13ns= 0.324c 4458 AMD64 :ASP LEA r16, [r32 + r32 + disp32] L: 0.83ns= 2.02c T: 0.39ns= 0.943c 4459 AMD64 :ASP LEA r32, [r32 + r32 + disp32] L: 0.42ns= 1.01c T: 0.19ns= 0.448c 4460 AMD64 :ASP LEA r64, [r32 + r32 + disp32] L: 0.42ns= 1.01c T: 0.20ns= 0.490c 4461 AMD64 :ASP LEA r16, [r32 + r32 * 8] L: 0.83ns= 2.02c T: 0.38ns= 0.927c 4462 AMD64 :ASP LEA r32, [r32 + r32 * 8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4463 AMD64 :ASP LEA r64, [r32 + r32 * 8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4464 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp8] L: 0.83ns= 2.02c T: 0.39ns= 0.945c 4465 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4466 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp8] L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4467 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp32] L: 0.83ns= 2.02c T: 0.39ns= 0.951c 4468 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp32] L: 0.42ns= 1.01c T: 0.21ns= 0.507c 4469 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp32] L: 0.42ns= 1.01c T: 0.22ns= 0.538c 4479 AVX512VL_VP2INTERSE :VP2INTERSECTD k1+1, xmm, xmm L: [diff. reg. set] T: 3.34ns= 8.084c 4480 AVX512VL_VP2INTERSE :VP2INTERSECTD k1+1, ymm, ymm L: [diff. reg. set] T: 5.00ns= 12.088c 4481 AVX512_VP2INTERSECT :VP2INTERSECTD k1+1, zmm, zmm L: [diff. reg. set] T: 10.35ns= 25.046c 4482 AVX512VL_VP2INTERSE :VP2INTERSECTQ k1+1, xmm, xmm L: [diff. reg. set] T: 1.67ns= 4.042c 4483 AVX512VL_VP2INTERSE :VP2INTERSECTQ k1+1, ymm, ymm L: [diff. reg. set] T: 3.34ns= 8.084c 4484 AVX512_VP2INTERSECT :VP2INTERSECTQ k1+1, zmm, zmm L: [diff. reg. set] T: 6.56ns= 15.858c 4485 AVX512VL_VP2INTERSE :VP2INTERSECTD + VPMOVM2D xmm low L: 5.12ns= 12.38c T: 3.34ns= 8.084c 4486 AVX512VL_VP2INTERSE :VP2INTERSECTD + VPMOVM2D xmm high L: 5.50ns= 13.32c T: 3.34ns= 8.077c 4487 AVX512VL_VP2INTERSE :VP2INTERSECTD + VPMOVM2D ymm low L: 12.01ns= 29.05c T: 5.18ns= 12.523c 4488 AVX512VL_VP2INTERSE :VP2INTERSECTD + VPMOVM2D ymm high L: 7.10ns= 17.18c T: 5.14ns= 12.430c 4489 AVX512_VP2INTERSECT :VP2INTERSECTD + VPMOVM2D zmm low L: 17.57ns= 42.50c T: 10.66ns= 25.796c 4490 AVX512_VP2INTERSECT :VP2INTERSECTD + VPMOVM2D zmm high L: 13.37ns= 32.35c T: 10.60ns= 25.636c 4491 AVX512VL_VP2INTERSE :VP2INTERSECTQ + VPMOVM2Q xmm low L: 3.20ns= 7.73c T: 2.09ns= 5.052c 4492 AVX512VL_VP2INTERSE :VP2INTERSECTQ + VPMOVM2Q xmm high L: 3.06ns= 7.40c T: 2.09ns= 5.052c 4493 AVX512VL_VP2INTERSE :VP2INTERSECTQ + VPMOVM2Q ymm low L: 5.22ns= 12.63c T: 3.34ns= 8.084c 4494 AVX512VL_VP2INTERSE :VP2INTERSECTQ + VPMOVM2Q ymm high L: 5.53ns= 13.37c T: 3.34ns= 8.083c 4495 AVX512_VP2INTERSECT :VP2INTERSECTQ + VPMOVM2Q zmm low L: 13.14ns= 31.78c T: 6.79ns= 16.423c 4496 AVX512_VP2INTERSECT :VP2INTERSECTQ + VPMOVM2Q zmm high L: 8.60ns= 20.80c T: 6.74ns= 16.311c 4500 MOVDIRI :MOVDIRI [m32], r32 L: [memory dep.] T: 32.54ns= 78.710c 4501 MOVDIRI_X64 :MOVDIRI [m64], r64 L: [memory dep.] T: 39.19ns= 94.800c 4502 MOVDIR64B :MOVDIR64B r64, m512 L: [memory dep.] T: 7.54ns= 18.237c 4509 AVX512VLBW :{EVEX} VPADDB xmm{k}, xmm, xmm L: 1.25ns= 3.02c T: 0.16ns= 0.381c 4510 AVX512VLBW :{EVEX} VPADDB ymm{k}, ymm, ymm L: 1.25ns= 3.02c T: 0.16ns= 0.381c 4511 AVX512BW :VPADDB zmm{k}, zmm, zmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4512 AVX512VLBW :{EVEX} VPADDW xmm{k}, xmm, xmm L: 1.25ns= 3.02c T: 0.16ns= 0.381c 4513 AVX512VLBW :{EVEX} VPADDW ymm{k}, ymm, ymm L: 1.25ns= 3.02c T: 0.16ns= 0.381c 4514 AVX512BW :VPADDW zmm{k}, zmm, zmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4515 AVX512VL :{EVEX} VPADDD xmm{k}, xmm, xmm L: 0.42ns= 1.01c T: 0.20ns= 0.490c 4516 AVX512VL :{EVEX} VPADDD ymm{k}, ymm, ymm L: 0.42ns= 1.01c T: 0.16ns= 0.381c 4517 AVX512F :VPADDD zmm{k}, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4518 AVX512VL :{EVEX} VPADDQ xmm{k}, xmm, xmm L: 0.42ns= 1.01c T: 0.16ns= 0.381c 4519 AVX512VL :{EVEX} VPADDQ ymm{k}, ymm, ymm L: 0.42ns= 1.01c T: 0.16ns= 0.381c 4520 AVX512F :VPADDQ zmm{k}, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4521 AVX512VLBW :VDBPSADBW xmm{k}, xmm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 4522 AVX512VLBW :VDBPSADBW ymm{k}, ymm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 4523 AVX512BW :VDBPSADBW zmm{k}, zmm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 4524 AVX512VLBW :{EVEX} VPMADDUBSW xmm{k}, xmm, xmm L: 2.92ns= 7.07c T: 0.21ns= 0.505c 4525 AVX512VLBW :{EVEX} VPMADDUBSW ymm{k}, ymm, ymm L: 2.92ns= 7.07c T: 0.21ns= 0.505c 4526 AVX512BW :VPMADDUBSW zmm{k}, zmm, zmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 4527 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB xm{k},xm,xm,im8 L: 3.34ns= 8.08c T: 0.21ns= 0.505c 4528 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB ym{k},ym,ym,im8 L: 3.34ns= 8.08c T: 0.21ns= 0.505c 4529 AVX512F+GFNI :VGF2P8AFFINEQB zmm{k}, zmm, zmm, imm8 L: 3.34ns= 8.08c T: 0.42ns= 1.010c 4530 GFNI :GF2P8AFFINEQB + PADDB xmm L: 2.50ns= 6.05c T: 0.30ns= 0.722c 4531 AVX+GFNI :VGF2P8AFFINEQB + VPADDB xmm L: 2.50ns= 6.05c T: 0.30ns= 0.722c 4532 AVX+GFNI :VGF2P8AFFINEQB + VPADDB ymm L: 2.50ns= 6.05c T: 0.30ns= 0.722c 4533 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB + VPADDB xmm L: 2.50ns= 6.05c T: 0.33ns= 0.792c 4534 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB + VPADDB ymm L: 2.50ns= 6.05c T: 0.33ns= 0.792c 4535 AVX512F+GFNI :VGF2P8AFFINEQB + VPADDB xmm L: 2.50ns= 6.05c T: 0.47ns= 1.132c 4536 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB + VPADDB xmm{k} L: 5.01ns= 12.11c T: 0.34ns= 0.828c 4537 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB + VPADDB ymm{k} L: 5.01ns= 12.12c T: 0.34ns= 0.828c 4538 AVX512F+GFNI :VGF2P8AFFINEQB + VPADDB zmm{k} L: 5.01ns= 12.11c T: 0.47ns= 1.147c 4952 AVX512VLBW :{EVEX} VPADDB xmm{k}{z}, xmm, xmm L: 1.25ns= 3.02c T: 0.16ns= 0.382c 4953 AVX512VLBW :{EVEX} VPADDB ymm{k}{z}, ymm, ymm L: 1.25ns= 3.02c T: 0.16ns= 0.382c 4954 AVX512BW :VPADDB zmm{k}{z}, zmm, zmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4955 AVX512VLBW :{EVEX} VPADDW xmm{k}{z}, xmm, xmm L: 1.25ns= 3.02c T: 0.16ns= 0.382c 4956 AVX512VLBW :{EVEX} VPADDW ymm{k}{z}, ymm, ymm L: 1.25ns= 3.02c T: 0.16ns= 0.382c 4957 AVX512BW :VPADDW zmm{k}{z}, zmm, zmm L: 1.25ns= 3.02c T: 0.21ns= 0.505c 4958 AVX512VL :{EVEX} VPADDD xmm{k}{z}, xmm, xmm L: 0.42ns= 1.01c T: 0.16ns= 0.382c 4959 AVX512VL :{EVEX} VPADDD ymm{k}{z}, ymm, ymm L: 0.42ns= 1.01c T: 0.16ns= 0.382c 4960 AVX512F :VPADDD zmm{k}{z}, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4961 AVX512VL :{EVEX} VPADDQ xmm{k}{z}, xmm, xmm L: 0.42ns= 1.01c T: 0.16ns= 0.382c 4962 AVX512VL :{EVEX} VPADDQ ymm{k}{z}, ymm, ymm L: 0.42ns= 1.01c T: 0.16ns= 0.382c 4963 AVX512F :VPADDQ zmm{k}{z}, zmm, zmm L: 0.42ns= 1.01c T: 0.21ns= 0.505c 4964 AVX512VLBW :VDBPSADBW xmm{k}{z}, xmm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 4965 AVX512VLBW :VDBPSADBW ymm{k}{z}, ymm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 4966 AVX512BW :VDBPSADBW zmm{k}{z}, zmm, imm8 L: 2.09ns= 5.05c T: 0.42ns= 1.010c 4967 AVX512VLBW :{EVEX} VPMADDUBSW xmm{k}{z}, xmm, xmm L: 2.92ns= 7.07c T: 0.21ns= 0.505c 4968 AVX512VLBW :{EVEX} VPMADDUBSW ymm{k}{z}, ymm, ymm L: 2.92ns= 7.07c T: 0.21ns= 0.505c 4969 AVX512BW :VPMADDUBSW zmm{k}{z}, zmm, zmm L: 2.92ns= 7.07c T: 0.42ns= 1.010c 4970 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB x{k}{z},x,x,i8 L: 3.34ns= 8.08c T: 0.21ns= 0.505c 4971 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB y{k}{z},y,y,i8 L: 3.34ns= 8.08c T: 0.21ns= 0.505c 4972 AVX512F+GFNI :VGF2P8AFFINEQB z{k}{z}, z, z, i8 L: 3.34ns= 8.08c T: 0.42ns= 1.010c 4973 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB+VPADDB x{k}{z} L: 5.01ns= 12.11c T: 0.34ns= 0.829c 4974 AVX512VL+GFNI :{EVEX} VGF2P8AFFINEQB+VPADDB y{k}{z} L: 5.01ns= 12.11c T: 0.34ns= 0.829c 4975 AVX512F+GFNI :VGF2P8AFFINEQB+VPADDB z{k}{z} L: 5.01ns= 12.11c T: 0.47ns= 1.147c 4976 AVX512DQ :KANDNB k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4977 AVX512F :KANDNW k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4978 AVX512BW :KANDND k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 4979 AVX512BW :KANDNQ k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 4980 AVX512DQ :KXNORB k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4981 AVX512F :KXNORW k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4982 AVX512BW :KXNORD k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4983 AVX512BW :KXNORQ k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4984 AVX512DQ :KXORB k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 4985 AVX512F :KXORW k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4986 AVX512BW :KXORD k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.010c 4987 AVX512BW :KXORQ k1, k1, k2 L: 0.42ns= 1.01c T: 0.42ns= 1.014c 5018 FMA3 :VFMADD231SS+VADDSS xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 5019 FMA3 :VFMADD231PS+VADDPS xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 5020 FMA3 :VFMADD231PS+VADDPS ymm, ymm, ymm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 5021 AVX512F :VFMADD231PS+VADDPS zmm, zmm, zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 5022 FMA3 :VFMADD231SS+VMULSS xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5023 FMA3 :VFMADD231PS+VMULPS xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5024 FMA3 :VFMADD231PS+VMULPS ymm, ymm, ymm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 5025 AVX512F :VFMADD231PS+VMULPS zmm, zmm, zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 5026 FMA3 :VFMADD231SD+VADDSD xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5027 FMA3 :VFMADD231PD+VADDPD xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.030c 5028 FMA3 :VFMADD231PD+VADDPD ymm, ymm, ymm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5029 AVX512F :VFMADD231PD+VADDPD zmm, zmm, zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c 5030 FMA3 :VFMADD231SD+VMULSD xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5031 FMA3 :VFMADD231PD+VMULPD xmm, xmm, xmm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5032 FMA3 :VFMADD231PD+VMULPD ymm, ymm, ymm L: 3.34ns= 8.08c T: 0.43ns= 1.031c 5033 AVX512F :VFMADD231PD+VMULPD zmm, zmm, zmm L: 3.33ns= 8.07c T: 0.84ns= 2.021c