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:20 NUMA:0 Freq: 3878.37MHz Priority:080 OS:6.3.26100 Memory: 32875392KB AllocGran:0x00010000 P:0x00001000 LP:0x0000000000200000 Memory To Test:131072KB 4K DTLB:1024 2M DTLB:512 1G DTLB:1024 CLFlush:64 ProcMask: 0x00000000000fffff PCoreMask: 0x00000000000c03c3 ECoreMask: 0x000000000003fc3c 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,RDRAND,FSGSBASE,BMI,CLFLUSH,X2APIC,TSCINV,RDTSCP,3DNOWPREF,LNOP,AVX2,BMI2,ERMS,PSE,RDSEED,ADX,SMAP,PAGE1GB,PT,SHA,CLFLUSHOPT,RDT_A,CLWB,PKU,UMIP,RDPID,VAES,GFNI,VPCLMULQDQ,HYBRID,7LTOP,MOVDIRI,MOVDIR64B,WAITPKG,SERIALIZE,WBNOINVD,AVX_VNNI,AVX_NE_CONVERT,AVX_VNNI_INT8,AVX_IFMA,CMPCCXADD,FSRM,FSRS,AVX_VNNI_INT16,SHA512,SM3,SM4, CPU#000 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#000 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#000 AffMask: 0x0000000000000001 CPU#000 PhysMask:0x00000000000fffff CPU#000 APIC_ID:0x00000000 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:00 Core_ID:00 SMT_ID:00 CPU#000 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000000001 CPU#000 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000001 CPU#000 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000000001 CPU#000 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000000001, non-inclusive CPU#000 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#000 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000000001 CPU#000 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000000001 CPU#000 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000000001 CPU#000 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000001 CPU#000 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000001 CPU#000 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000001 CPU#000 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000001 CPU#000 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000001 CPU#001 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#001 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#001 AffMask: 0x0000000000000002 CPU#001 PhysMask:0x00000000000fffff CPU#001 APIC_ID:0x00000008 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:01 Core_ID:00 SMT_ID:00 CPU#001 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000000002 CPU#001 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000002 CPU#001 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000000002 CPU#001 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000000002, non-inclusive CPU#001 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#001 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000000002 CPU#001 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000000002 CPU#001 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000000002 CPU#001 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000002 CPU#001 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000002 CPU#001 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000002 CPU#001 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000002 CPU#001 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000002 CPU#002 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#002 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#002 AffMask: 0x0000000000000004 CPU#002 PhysMask:0x00000000000fffff CPU#002 APIC_ID:0x00000018 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:03 Core_ID:00 SMT_ID:00 CPU#002 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000000004 CPU#002 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000004 CPU#002 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000000003c, GLM+ L2 CPU#002 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#002 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000000004 CPU#002 L1I 4K TLB: 128 entries, full, SMask:0000000000000004 CPU#002 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000000004 CPU#002 L2I+D 1G TLB: 8 entries, full, SMask:0000000000000004 CPU#003 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#003 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#003 AffMask: 0x0000000000000008 CPU#003 PhysMask:0x00000000000fffff CPU#003 APIC_ID:0x0000001a Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:03 Core_ID:01 SMT_ID:00 CPU#003 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000000008 CPU#003 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000008 CPU#003 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000000003c, GLM+ L2 CPU#003 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#003 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000000008 CPU#003 L1I 4K TLB: 128 entries, full, SMask:0000000000000008 CPU#003 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000000008 CPU#003 L2I+D 1G TLB: 8 entries, full, SMask:0000000000000008 CPU#004 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#004 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#004 AffMask: 0x0000000000000010 CPU#004 PhysMask:0x00000000000fffff CPU#004 APIC_ID:0x0000001c Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:03 Core_ID:02 SMT_ID:00 CPU#004 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000000010 CPU#004 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000010 CPU#004 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000000003c, GLM+ L2 CPU#004 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#004 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000000010 CPU#004 L1I 4K TLB: 128 entries, full, SMask:0000000000000010 CPU#004 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000000010 CPU#004 L2I+D 1G TLB: 8 entries, full, SMask:0000000000000010 CPU#005 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#005 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#005 AffMask: 0x0000000000000020 CPU#005 PhysMask:0x00000000000fffff CPU#005 APIC_ID:0x0000001e Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:03 Core_ID:03 SMT_ID:00 CPU#005 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000000020 CPU#005 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000020 CPU#005 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000000003c, GLM+ L2 CPU#005 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#005 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000000020 CPU#005 L1I 4K TLB: 128 entries, full, SMask:0000000000000020 CPU#005 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000000020 CPU#005 L2I+D 1G TLB: 8 entries, full, SMask:0000000000000020 CPU#006 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#006 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#006 AffMask: 0x0000000000000040 CPU#006 PhysMask:0x00000000000fffff CPU#006 APIC_ID:0x00000020 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:04 Core_ID:00 SMT_ID:00 CPU#006 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000000040 CPU#006 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000040 CPU#006 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000000040 CPU#006 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000000040, non-inclusive CPU#006 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#006 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000000040 CPU#006 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000000040 CPU#006 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000000040 CPU#006 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000040 CPU#006 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000040 CPU#006 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000040 CPU#006 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000040 CPU#006 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000040 CPU#007 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#007 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#007 AffMask: 0x0000000000000080 CPU#007 PhysMask:0x00000000000fffff CPU#007 APIC_ID:0x00000028 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:05 Core_ID:00 SMT_ID:00 CPU#007 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000000080 CPU#007 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000080 CPU#007 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000000080 CPU#007 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000000080, non-inclusive CPU#007 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#007 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000000080 CPU#007 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000000080 CPU#007 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000000080 CPU#007 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000080 CPU#007 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000080 CPU#007 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000080 CPU#007 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000080 CPU#007 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000080 CPU#008 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#008 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#008 AffMask: 0x0000000000000100 CPU#008 PhysMask:0x00000000000fffff CPU#008 APIC_ID:0x00000030 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:06 Core_ID:00 SMT_ID:00 CPU#008 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000000100 CPU#008 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000100 CPU#008 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000000100 CPU#008 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000000100, non-inclusive CPU#008 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#008 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000000100 CPU#008 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000000100 CPU#008 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000000100 CPU#008 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000100 CPU#008 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000100 CPU#008 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000100 CPU#008 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000100 CPU#008 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000100 CPU#009 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#009 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#009 AffMask: 0x0000000000000200 CPU#009 PhysMask:0x00000000000fffff CPU#009 APIC_ID:0x00000038 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:07 Core_ID:00 SMT_ID:00 CPU#009 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000000200 CPU#009 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000000200 CPU#009 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000000200 CPU#009 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000000200, non-inclusive CPU#009 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#009 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000000200 CPU#009 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000000200 CPU#009 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000000200 CPU#009 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000000200 CPU#009 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000000200 CPU#009 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000000200 CPU#009 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000000200 CPU#009 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000000200 CPU#010 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#010 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#010 AffMask: 0x0000000000000400 CPU#010 PhysMask:0x00000000000fffff CPU#010 APIC_ID:0x00000040 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:08 Core_ID:00 SMT_ID:00 CPU#010 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000000400 CPU#010 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000400 CPU#010 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:0000000000003c00, GLM+ L2 CPU#010 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#010 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000000400 CPU#010 L1I 4K TLB: 128 entries, full, SMask:0000000000000400 CPU#010 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000000400 CPU#010 L2I+D 1G TLB: 8 entries, full, SMask:0000000000000400 CPU#011 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#011 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#011 AffMask: 0x0000000000000800 CPU#011 PhysMask:0x00000000000fffff CPU#011 APIC_ID:0x00000042 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:08 Core_ID:01 SMT_ID:00 CPU#011 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000000800 CPU#011 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000800 CPU#011 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:0000000000003c00, GLM+ L2 CPU#011 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#011 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000000800 CPU#011 L1I 4K TLB: 128 entries, full, SMask:0000000000000800 CPU#011 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000000800 CPU#011 L2I+D 1G TLB: 8 entries, full, SMask:0000000000000800 CPU#012 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#012 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#012 AffMask: 0x0000000000001000 CPU#012 PhysMask:0x00000000000fffff CPU#012 APIC_ID:0x00000044 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:08 Core_ID:02 SMT_ID:00 CPU#012 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000001000 CPU#012 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000001000 CPU#012 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:0000000000003c00, GLM+ L2 CPU#012 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#012 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000001000 CPU#012 L1I 4K TLB: 128 entries, full, SMask:0000000000001000 CPU#012 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000001000 CPU#012 L2I+D 1G TLB: 8 entries, full, SMask:0000000000001000 CPU#013 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#013 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#013 AffMask: 0x0000000000002000 CPU#013 PhysMask:0x00000000000fffff CPU#013 APIC_ID:0x00000046 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:08 Core_ID:03 SMT_ID:00 CPU#013 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000002000 CPU#013 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000002000 CPU#013 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:0000000000003c00, GLM+ L2 CPU#013 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#013 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000002000 CPU#013 L1I 4K TLB: 128 entries, full, SMask:0000000000002000 CPU#013 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000002000 CPU#013 L2I+D 1G TLB: 8 entries, full, SMask:0000000000002000 CPU#014 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#014 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#014 AffMask: 0x0000000000004000 CPU#014 PhysMask:0x00000000000fffff CPU#014 APIC_ID:0x00000048 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:09 Core_ID:00 SMT_ID:00 CPU#014 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000004000 CPU#014 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000004000 CPU#014 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000003c000, GLM+ L2 CPU#014 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#014 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000004000 CPU#014 L1I 4K TLB: 128 entries, full, SMask:0000000000004000 CPU#014 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000004000 CPU#014 L2I+D 1G TLB: 8 entries, full, SMask:0000000000004000 CPU#015 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#015 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#015 AffMask: 0x0000000000008000 CPU#015 PhysMask:0x00000000000fffff CPU#015 APIC_ID:0x0000004a Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:09 Core_ID:01 SMT_ID:00 CPU#015 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000008000 CPU#015 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000008000 CPU#015 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000003c000, GLM+ L2 CPU#015 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#015 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000008000 CPU#015 L1I 4K TLB: 128 entries, full, SMask:0000000000008000 CPU#015 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000008000 CPU#015 L2I+D 1G TLB: 8 entries, full, SMask:0000000000008000 CPU#016 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#016 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#016 AffMask: 0x0000000000010000 CPU#016 PhysMask:0x00000000000fffff CPU#016 APIC_ID:0x0000004c Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:09 Core_ID:02 SMT_ID:00 CPU#016 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000010000 CPU#016 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000010000 CPU#016 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000003c000, GLM+ L2 CPU#016 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#016 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000010000 CPU#016 L1I 4K TLB: 128 entries, full, SMask:0000000000010000 CPU#016 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000010000 CPU#016 L2I+D 1G TLB: 8 entries, full, SMask:0000000000010000 CPU#017 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0x200c0662 CPU#017 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#017 AffMask: 0x0000000000020000 CPU#017 PhysMask:0x00000000000fffff CPU#017 APIC_ID:0x0000004e Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:09 Core_ID:03 SMT_ID:00 CPU#017 L1I cache: 64KB, 64 byte cache line, 8 way, SMask:0000000000020000 CPU#017 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000020000 CPU#017 L2 cache: 4096KB, 64 byte cache line, 16 way, SMask:000000000003c000, GLM+ L2 CPU#017 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#017 L1D 4K+2M TLB: 48 entries, full, SMask:0000000000020000 CPU#017 L1I 4K TLB: 128 entries, full, SMask:0000000000020000 CPU#017 L2I+D 4K+2M TLB: 4096 entries, 4 way, SMask:0000000000020000 CPU#017 L2I+D 1G TLB: 8 entries, full, SMask:0000000000020000 CPU#018 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#018 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#018 AffMask: 0x0000000000040000 CPU#018 PhysMask:0x00000000000fffff CPU#018 APIC_ID:0x00000050 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:10 Core_ID:00 SMT_ID:00 CPU#018 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000040000 CPU#018 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000040000 CPU#018 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000040000 CPU#018 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000040000, non-inclusive CPU#018 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#018 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000040000 CPU#018 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000040000 CPU#018 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000040000 CPU#018 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000040000 CPU#018 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000040000 CPU#018 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000040000 CPU#018 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000040000 CPU#018 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000040000 CPU#019 Vendor: GenuineIntel Family: 6 Model: c6 Stepping: 2 CoreType:0xb00c0662 CPU#019 Type: "Intel(R) Core(TM) Ultra 7 265K" CPU#019 AffMask: 0x0000000000080000 CPU#019 PhysMask:0x00000000000fffff CPU#019 APIC_ID:0x00000058 Socket_ID:00 DieGrp_ID:00 Die_ID:00 Tile_ID:00 Module_ID:11 Core_ID:00 SMT_ID:00 CPU#019 L1I cache: 64KB, 64 byte cache line, 16 way, SMask:0000000000080000 CPU#019 L0D cache: 48KB, 64 byte cache line, 12 way, SMask:0000000000080000 CPU#019 L1D cache: 192KB, 64 byte cache line, 12 way, SMask:0000000000080000 CPU#019 L2 cache: 3072KB, 64 byte cache line, 12 way, SMask:0000000000080000, non-inclusive CPU#019 L3 cache: 30720KB, 64 byte cache line, 10 way, SMask:00000000000fffff, ADL L3 CPU#019 L1I 4K TLB: 256 entries, 8 way, SMask:0000000000080000 CPU#019 L1I 2M TLB: 32 entries, 8 way, SMask:0000000000080000 CPU#019 L1D 4K TLB(loads): 128 entries, 8 way, SMask:0000000000080000 CPU#019 L1D 2M TLB(loads): 32 entries, 4 way, SMask:0000000000080000 CPU#019 L1D 1G TLB(loads): 8 entries, full, SMask:0000000000080000 CPU#019 L1D 4K+2M+1G TLB(stores): 16 entries, full, SMask:0000000000080000 CPU#019 L2I+D 4K+2M TLB: 1024 entries, 8 way, SMask:0000000000080000 CPU#019 L2I+D 4K+1G TLB: 1024 entries, 8 way, SMask:0000000000080000 Parameters: "--tscratio=0.8571428571918367 " Instruction Latency: Used CPUs: 1 ProcMask: 0x0000000000020000 0 X86 :NOP L: [no true dep.] T: 0.03ns= 0.127c 1 X86 :0x66 NOP L: [no true dep.] T: 0.03ns= 0.126c 2 X86 : 2x 0x66 NOP L: [no true dep.] T: 0.03ns= 0.126c 3 X86 : 3x 0x66 NOP L: [no true dep.] T: 0.03ns= 0.126c 4 X86 : 4x 0x66 NOP L: [no true dep.] T: 0.03ns= 0.126c 5 X86 : 5x 0x66 NOP L: [no true dep.] T: 0.36ns= 1.407c 6 X86 : 6x 0x66 NOP L: [no true dep.] T: 0.35ns= 1.353c 7 X86 : 7x 0x66 NOP L: [no true dep.] T: 0.37ns= 1.418c 8 X86 : 8x 0x66 NOP L: [no true dep.] T: 0.36ns= 1.385c 9 X86 : 9x 0x66 NOP L: [no true dep.] T: 0.61ns= 2.352c 10 X86 :10x 0x66 NOP L: [no true dep.] T: 0.61ns= 2.350c 11 X86 :11x 0x66 NOP L: [no true dep.] T: 0.61ns= 2.350c 12 X86 :12x 0x66 NOP L: [no true dep.] T: 0.61ns= 2.350c 13 X86 :13x 0x66 NOP L: [no true dep.] T: 0.87ns= 3.357c 14 X86 :14x 0x66 NOP L: [no true dep.] T: 0.87ns= 3.357c 15 SSE2 :PAUSE L: [no true dep.] T: 19.88ns= 77.090c 16 X86 :MOV r8, imm8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 17 X86 :MOV r16, imm16 L: 0.26ns= 1.01c T: 0.03ns= 0.134c 18 X86 :MOV r32, imm32 L: 0.03ns= 0.14c T: 0.03ns= 0.133c 19 AMD64 :MOV r64, imm64 L: 0.06ns= 0.21c T: 0.05ns= 0.210c 20 X86 :MOV r8, r8 L: 0.26ns= 1.01c T: 0.03ns= 0.133c 21 X86 :MOV r16, r16 L: 0.26ns= 1.01c T: 0.03ns= 0.133c 22 X86 :MOV r32, r32 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 23 AMD64 :MOV r64, r64 L: 0.26ns= 1.01c T: 0.03ns= 0.133c 24 X86 :MOV r8, [m8] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 25 X86 :MOV r16, [m16] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 26 X86 :MOV r32, [m32] L: 1.04ns= 4.03c T: 0.09ns= 0.336c 27 AMD64 :MOV r64, [m64] L: 1.04ns= 4.03c T: 0.09ns= 0.336c 28 X86 :MOV [m8], r8 L: [memory dep.] T: 0.13ns= 0.504c 29 X86 :MOV [m16], r16 L: [memory dep.] T: 0.13ns= 0.504c 30 X86 :MOV [m32], r32 L: [memory dep.] T: 0.13ns= 0.504c 31 X86 :MOV [m32 + 2], r32 L: [memory dep.] T: 0.13ns= 0.504c 32 AMD64 :MOV [m64], r64 L: [memory dep.] T: 0.13ns= 0.504c 33 AMD64 :MOV [m64 + 4], r64 L: [memory dep.] T: 0.13ns= 0.504c 34 X86 :MOV r8,[m8]+MOV [m8],r8 L: 0.26ns= 1.01c T: 0.17ns= 0.676c 35 X86 :MOV r16,[m16]+MOV [m16],r16 L: 0.26ns= 1.01c T: 0.17ns= 0.676c 36 X86 :MOV r32,[m32]+MOV [m32],r32 L: 0.13ns= 0.50c T: 0.16ns= 0.640c 37 AMD64 :MOV r64,[m64]+MOV [m64],r64 L: 0.13ns= 0.50c T: 0.16ns= 0.619c 38 SSE2 :MOVNTI [m32], r32 L: [memory dep.] T: 0.50ns= 0.504c 39 AMD64 :MOVNTI [m64], r64 L: [memory dep.] T: 0.50ns= 0.504c 40 CMOV :CMOVNZ r16, r16 L: 0.52ns= 2.01c T: 0.08ns= 0.299c 41 CMOV :CMOVNZ r32, r32 L: 0.52ns= 2.01c T: 0.08ns= 0.300c 42 AMD64 :CMOVNZ r64, r64 L: 0.52ns= 2.01c T: 0.08ns= 0.300c 43 X86 :MOVSX r16, r8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 44 X86 :MOVSX r32, r8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 45 AMD64 :MOVSX r64, r8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 46 X86 :MOVSX r32, r16 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 47 AMD64 :MOVSX r64, r16 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 48 AMD64 :MOVSXD r64, r32 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 49 X86 :MOVZX r16, r8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 50 X86 :MOVZX r32, r8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 51 AMD64 :MOVZX r64, r8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 52 X86 :MOVZX r32, r16 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 53 AMD64 :MOVZX r64, r16 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 54 X86 :XCHG r8, r8 L: 0.63ns= 2.44c T: 0.66ns= 2.578c 55 X86 :XCHG r16, r16 L: 0.63ns= 2.45c T: 0.67ns= 2.581c 56 X86 :XCHG r32, r32 L: 0.63ns= 2.44c T: 0.67ns= 2.587c 57 AMD64 :XCHG r64, r64 L: 0.63ns= 2.44c T: 0.67ns= 2.581c 58 X86 :XCHG r1_8, r2_8 L: 0.62ns= 2.39c T: 0.66ns= 2.550c 59 X86 :XCHG r1_16, r2_16 L: 0.62ns= 2.41c T: 0.66ns= 2.574c 60 X86 :XCHG r1_32, r2_32 L: 0.62ns= 2.40c T: 0.66ns= 2.566c 61 AMD64 :XCHG r1_64, r2_64 L: 0.62ns= 2.42c T: 0.67ns= 2.581c 62 X86 :XCHG r8, [m8] L: 3.90ns= 15.14c T: 3.90ns= 15.139c 63 X86 :XCHG r16, [m16] L: 3.90ns= 15.14c T: 3.90ns= 15.140c 64 X86 :XCHG r32, [m32] L: 3.90ns= 15.14c T: 3.90ns= 15.141c 65 AMD64 :XCHG r64, [m64] L: 3.90ns= 15.14c T: 3.90ns= 15.141c 66 X86 :ADD r8, r8 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 67 X86 :ADD r16, r16 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 68 X86 :ADD r32, r32 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 69 AMD64 :ADD r64, r64 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 70 X86 :ADD r1_8, r2_8 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 71 X86 :ADD r1_16, r2_16 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 72 X86 :ADD r1_32, r2_32 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 73 AMD64 :ADD r1_64, r2_64 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 74 X86 :ADD r8, [m8] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 75 X86 :ADD r16, [m16] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 76 X86 :ADD r32, [m32] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 77 AMD64 :ADD r64, [m64] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 78 X86 :ADD [m8], r8 L: 0.26ns= 1.01c T: 0.14ns= 0.562c 79 X86 :ADD [m16], r16 L: 0.26ns= 1.01c T: 0.15ns= 0.563c 80 X86 :ADD [m32], r32 L: 0.26ns= 1.01c T: 0.15ns= 0.563c 81 X86 :ADD [m32 + 2], r32 L: 0.26ns= 1.01c T: 0.26ns= 1.008c 82 AMD64 :ADD [m64], r64 L: 0.26ns= 1.01c T: 0.15ns= 0.567c 83 AMD64 :ADD [m64 + 4], r64 L: 0.26ns= 1.01c T: 0.26ns= 1.008c 84 X86 :LOCK ADD [m8], r8 L: 3.90ns= 15.11c T: 3.90ns= 15.117c 85 X86 :LOCK ADD [m16], r16 L: 3.90ns= 15.11c T: 3.90ns= 15.118c 86 X86 :LOCK ADD [m32], r32 L: 3.90ns= 15.11c T: 3.90ns= 15.117c 87 X86 :LOCK ADD [m32 + 2], r32 L: 3.90ns= 15.11c T: 3.90ns= 15.116c 88 AMD64 :LOCK ADD [m64], r64 L: 3.90ns= 15.11c T: 3.90ns= 15.116c 89 AMD64 :LOCK ADD [m64 + 4], r64 L: 3.90ns= 15.11c T: 3.90ns= 15.116c 90 X86 :ADD r8, imm8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 91 X86 :ADD r16, imm8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 92 X86 :ADD r32, imm8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 93 AMD64 :ADD r64, imm8 L: 0.05ns= 0.18c T: 0.05ns= 0.194c 94 X86 :ADD r16, imm16 L: 0.26ns= 1.01c T: 0.04ns= 0.136c 95 X86 :ADD r32, imm32 L: 0.26ns= 1.01c T: 0.04ns= 0.165c 96 AMD64 :ADD r64, imm32 L: 0.06ns= 0.23c T: 0.06ns= 0.228c 97 X86 :ADD [m8], imm8 L: 0.26ns= 1.01c T: 0.14ns= 0.555c 98 X86 :ADD [m16], imm8 L: 0.26ns= 1.01c T: 0.14ns= 0.553c 99 X86 :ADD [m32], imm8 L: 0.26ns= 1.01c T: 0.14ns= 0.556c 100 AMD64 :ADD [m64], imm8 L: 0.26ns= 1.01c T: 0.14ns= 0.552c 101 X86 :ADD [m16], imm16 L: 0.26ns= 1.01c T: 0.14ns= 0.559c 102 X86 :ADD [m32], imm32 L: 0.26ns= 1.01c T: 0.14ns= 0.558c 103 AMD64 :ADD [m64], imm32 L: 0.26ns= 1.01c T: 0.14ns= 0.558c 104 X86 :ADD al, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 105 X86 :ADD ax, imm16 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 106 X86 :ADD eax, imm32 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 107 AMD64 :ADD rax, imm32 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 108 X86 :SUB r8, r8 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 109 X86 :SUB r16, r16 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 110 X86 :SUB r32, r32 L: 0.26ns= 1.00c T: 0.03ns= 0.133c 111 AMD64 :SUB r64, r64 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 112 X86 :SUB r1_8, r2_8 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 113 X86 :SUB r1_16, r2_16 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 114 X86 :SUB r1_32, r2_32 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 115 AMD64 :SUB r1_64, r2_64 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 116 X86 :ADC r8, r8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 117 X86 :ADC r16, r16 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 118 X86 :ADC r32, r32 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 119 AMD64 :ADC r64, r64 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 120 X86 :SBB r8, r8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 121 X86 :SBB r16, r16 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 122 X86 :SBB r32, r32 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 123 AMD64 :SBB r64, r64 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 124 X86 :SBB r1_8, r2_8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 125 X86 :SBB r1_16, r2_16 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 126 X86 :SBB r1_32, r2_32 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 127 AMD64 :SBB r1_64, r2_64 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 128 X86 :CMP r8, r8 L: [no true dep.] T: 0.03ns= 0.132c 129 X86 :CMP r16, r16 L: [no true dep.] T: 0.03ns= 0.132c 130 X86 :CMP r32, r32 L: [no true dep.] T: 0.03ns= 0.133c 131 AMD64 :CMP r64, r64 L: [no true dep.] T: 0.03ns= 0.133c 132 X86 :CMP r1_8, r2_8 L: [no true dep.] T: 0.03ns= 0.134c 133 X86 :CMP r1_16, r2_16 L: [no true dep.] T: 0.03ns= 0.133c 134 X86 :CMP r1_32, r2_32 L: [no true dep.] T: 0.03ns= 0.132c 135 AMD64 :CMP r1_64, r2_64 L: [no true dep.] T: 0.03ns= 0.132c 136 X86 :AND r8, r8 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 137 X86 :AND r16, r16 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 138 X86 :AND r32, r32 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 139 AMD64 :AND r64, r64 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 140 X86 :AND r1_8, r2_8 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 141 X86 :AND r1_16, r2_16 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 142 X86 :AND r1_32, r2_32 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 143 AMD64 :AND r1_64, r2_64 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 144 X86 :OR r8, r8 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 145 X86 :OR r16, r16 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 146 X86 :OR r32, r32 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 147 AMD64 :OR r64, r64 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 148 X86 :OR r1_8, r2_8 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 149 X86 :OR r1_16, r2_16 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 150 X86 :OR r1_32, r2_32 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 151 AMD64 :OR r1_64, r2_64 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 152 X86 :XOR r8, r8 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 153 X86 :XOR r16, r16 L: 0.26ns= 1.00c T: 0.03ns= 0.135c 154 X86 :XOR r32, r32 L: 0.03ns= 0.13c T: 0.03ns= 0.134c 155 AMD64 :XOR r64, r64 L: 0.03ns= 0.13c T: 0.03ns= 0.133c 156 X86 :XOR r1_8, r2_8 L: 0.26ns= 1.00c T: 0.04ns= 0.137c 157 X86 :XOR r1_16, r2_16 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 158 X86 :XOR r1_32, r2_32 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 159 AMD64 :XOR r1_64, r2_64 L: 0.26ns= 1.00c T: 0.04ns= 0.138c 160 X86 :NEG r8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 161 X86 :NEG r16 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 162 X86 :NEG r32 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 163 AMD64 :NEG r64 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 164 X86 :NOT r8 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 165 X86 :NOT r16 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 166 X86 :NOT r32 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 167 AMD64 :NOT r64 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 168 X86 :TEST r8, r8 L: [no true dep.] T: 0.03ns= 0.133c 169 X86 :TEST r16, r16 L: [no true dep.] T: 0.03ns= 0.132c 170 X86 :TEST r32, r32 L: [no true dep.] T: 0.03ns= 0.132c 171 AMD64 :TEST r64, r64 L: [no true dep.] T: 0.03ns= 0.133c 172 X86 :TEST r1_8, r2_8 L: [no true dep.] T: 0.03ns= 0.132c 173 X86 :TEST r1_16, r2_16 L: [no true dep.] T: 0.03ns= 0.132c 174 X86 :TEST r1_32, r2_32 L: [no true dep.] T: 0.03ns= 0.133c 175 AMD64 :TEST r1_64, r2_64 L: [no true dep.] T: 0.03ns= 0.132c 176 X86 :BT r16, r16 L: [no true dep.] T: 0.26ns= 1.008c 177 X86 :BT r32, r32 L: [no true dep.] T: 0.26ns= 1.008c 178 AMD64 :BT r64, r64 L: [no true dep.] T: 0.26ns= 1.008c 179 X86 :BT r16, imm8 L: [no true dep.] T: 0.26ns= 1.008c 180 X86 :BT r32, imm8 L: [no true dep.] T: 0.26ns= 1.008c 181 AMD64 :BT r64, imm8 L: [no true dep.] T: 0.26ns= 1.008c 182 X86 :BTC r16, r16 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 183 X86 :BTC r32, r32 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 184 AMD64 :BTC r64, r64 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 185 X86 :BTC r16, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 186 X86 :BTC r32, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 187 AMD64 :BTC r64, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 188 X86 :BTR r16, r16 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 189 X86 :BTR r32, r32 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 190 AMD64 :BTR r64, r64 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 191 X86 :BTR r16, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 192 X86 :BTR r32, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 193 AMD64 :BTR r64, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 194 X86 :BTS r16, r16 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 195 X86 :BTS r32, r32 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 196 AMD64 :BTS r64, r64 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 197 X86 :BTS r16, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 198 X86 :BTS r32, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 199 AMD64 :BTS r64, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 200 X86 :SETC r8 L: 0.26ns= 1.01c T: 0.03ns= 0.134c 201 X86 :INC r8 L: 0.26ns= 1.01c T: 0.26ns= 1.001c 202 X86 :INC r16 L: 0.26ns= 1.01c T: 0.26ns= 1.001c 203 X86 :INC r32 L: 0.26ns= 1.01c T: 0.26ns= 1.000c 204 AMD64 :INC r64 L: 0.15ns= 0.59c T: 0.26ns= 1.003c 205 AMD64 :LEA r16, [r64 + r64] L: 0.63ns= 2.43c T: 0.67ns= 2.614c 206 AMD64 :LEA r32, [r64 + r64] L: 0.26ns= 1.01c T: 0.04ns= 0.138c 207 AMD64 :LEA r64, [r64 + r64] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 208 AMD64 :LEA r16, [r64 + r64 + disp8] L: 0.78ns= 3.03c T: 0.66ns= 2.566c 209 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 210 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 211 AMD64 :LEA r16, [r64 + r64 * 8] L: 0.64ns= 2.47c T: 0.67ns= 2.599c 212 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.26ns= 1.01c T: 0.26ns= 1.007c 213 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.26ns= 1.01c T: 0.26ns= 1.007c 214 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 0.78ns= 3.03c T: 0.66ns= 2.557c 215 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 216 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 217 X86 :SHL r8, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 218 X86 :SHL r16, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 219 X86 :SHL r32, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 220 AMD64 :SHL r64, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 221 X86 :SHL r8, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 222 X86 :SHL r16, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 223 X86 :SHL r32, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 224 AMD64 :SHL r64, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 225 X86 :SHL r8, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 226 X86 :SHL r16, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 227 X86 :SHL r32, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 228 AMD64 :SHL r64, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 229 X86 :SHR r8, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 230 X86 :SHR r16, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 231 X86 :SHR r32, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 232 AMD64 :SHR r64, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 233 X86 :SHR r8, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 234 X86 :SHR r16, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 235 X86 :SHR r32, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 236 AMD64 :SHR r64, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 237 X86 :SHR r8, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 238 X86 :SHR r16, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 239 X86 :SHR r32, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 240 AMD64 :SHR r64, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 241 X86 :SAR r8, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 242 X86 :SAR r16, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 243 X86 :SAR r32, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 244 AMD64 :SAR r64, 1 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 245 X86 :SAR r8, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 246 X86 :SAR r16, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 247 X86 :SAR r32, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 248 AMD64 :SAR r64, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 249 X86 :SAR r8, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 250 X86 :SAR r16, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 251 X86 :SAR r32, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 252 AMD64 :SAR r64, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 253 X86 :SHLD r1_16, r1_16, imm8 L: 3.64ns= 14.11c T: 3.87ns= 14.990c 254 X86 :SHLD r1_32, r1_32, imm8 L: 0.52ns= 2.01c T: 0.13ns= 0.504c 255 AMD64 :SHLD r1_64, r1_64, imm8 L: 3.38ns= 13.11c T: 3.57ns= 13.834c 256 X86 :SHLD r1_16, r1_16, cl L: 3.64ns= 14.10c T: 3.80ns= 14.757c 257 X86 :SHLD r1_32, r1_32, cl L: 0.57ns= 2.19c T: 0.67ns= 2.599c 258 AMD64 :SHLD r1_64, r1_64, cl L: 3.38ns= 13.12c T: 3.65ns= 14.158c 259 X86 :SHRD r1_16, r1_16, imm8 L: 3.05ns= 11.83c T: 3.27ns= 12.669c 260 X86 :SHRD r1_32, r1_32, imm8 L: 0.52ns= 2.01c T: 0.13ns= 0.504c 261 AMD64 :SHRD r1_64, r1_64, imm8 L: 3.90ns= 15.11c T: 4.08ns= 15.814c 262 X86 :SHRD r1_16, r1_16, cl L: 3.12ns= 12.09c T: 3.24ns= 12.572c 263 X86 :SHRD r1_32, r1_32, cl L: 0.57ns= 2.21c T: 0.67ns= 2.590c 264 AMD64 :SHRD r1_64, r1_64, cl L: 3.90ns= 15.14c T: 4.17ns= 16.171c 265 X86 :ROL r8, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 266 X86 :ROL r16, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 267 X86 :ROL r32, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 268 AMD64 :ROL r64, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 269 X86 :ROL r8, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 270 X86 :ROL r16, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 271 X86 :ROL r32, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 272 AMD64 :ROL r64, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 273 X86 :ROL r8, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 274 X86 :ROL r16, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 275 X86 :ROL r32, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 276 AMD64 :ROL r64, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 277 X86 :ROR r8, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 278 X86 :ROR r16, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 279 X86 :ROR r32, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 280 AMD64 :ROR r64, 1 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 281 X86 :ROR r8, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 282 X86 :ROR r16, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 283 X86 :ROR r32, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 284 AMD64 :ROR r64, imm8 L: 0.26ns= 1.01c T: 0.26ns= 1.007c 285 X86 :ROR r8, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 286 X86 :ROR r16, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 287 X86 :ROR r32, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 288 AMD64 :ROR r64, cl L: 0.26ns= 1.01c T: 0.26ns= 1.007c 289 X86 :RCL r8, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 290 X86 :RCL r16, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 291 X86 :RCL r32, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 292 AMD64 :RCL r64, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 293 X86 :RCL r8, imm8 L: 2.93ns= 11.36c T: 3.11ns= 12.059c 294 X86 :RCL r16, imm8 L: 2.86ns= 11.08c T: 3.09ns= 11.986c 295 X86 :RCL r32, imm8 L: 2.93ns= 11.36c T: 3.09ns= 11.975c 296 AMD64 :RCL r64, imm8 L: 2.86ns= 11.09c T: 3.13ns= 12.150c 297 X86 :RCL r8, cl L: 3.00ns= 11.64c T: 3.08ns= 11.954c 298 X86 :RCL r16, cl L: 2.93ns= 11.35c T: 3.11ns= 12.061c 299 X86 :RCL r32, cl L: 3.00ns= 11.63c T: 3.04ns= 11.779c 300 AMD64 :RCL r64, cl L: 2.93ns= 11.36c T: 3.09ns= 11.988c 301 X86 :RCR r8, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 302 X86 :RCR r16, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 303 X86 :RCR r32, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 304 AMD64 :RCR r64, 1 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 305 X86 :RCR r8, imm8 L: 2.93ns= 11.35c T: 3.11ns= 12.051c 306 X86 :RCR r16, imm8 L: 2.86ns= 11.08c T: 3.09ns= 11.975c 307 X86 :RCR r32, imm8 L: 2.94ns= 11.39c T: 3.10ns= 12.042c 308 AMD64 :RCR r64, imm8 L: 2.86ns= 11.08c T: 3.13ns= 12.143c 309 X86 :RCR r8, cl L: 3.00ns= 11.64c T: 3.09ns= 12.001c 310 X86 :RCR r16, cl L: 2.94ns= 11.39c T: 3.10ns= 12.041c 311 X86 :RCR r32, cl L: 3.00ns= 11.63c T: 3.03ns= 11.766c 312 AMD64 :RCR r64, cl L: 2.94ns= 11.39c T: 3.11ns= 12.046c 313 X86 :BSF r16, r16 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 314 X86 :BSF r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 315 AMD64 :BSF r64, r64 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 316 X86 :BSR r16, r16 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 317 X86 :BSR r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 318 AMD64 :BSR r64, r64 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 319 X86 :BSWAP r32 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 320 AMD64 :BSWAP r64 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 321 MOVBE :MOVBE r16, [m16] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 322 MOVBE :MOVBE r32, [m32] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 323 MOVBE_X64 :MOVBE r64, [m64] L: 1.30ns= 5.04c T: 0.09ns= 0.336c 324 MOVBE :MOVBE [m16], r16 L: [memory dep.] T: 0.13ns= 0.504c 325 MOVBE :MOVBE [m32], r32 L: [memory dep.] T: 0.13ns= 0.504c 326 MOVBE_X64 :MOVBE [m64], r64 L: [memory dep.] T: 0.13ns= 0.504c 327 X86 :IMUL r16, r16 L: 1.30ns= 5.04c T: 0.66ns= 2.547c 328 X86 :IMUL r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 329 AMD64 :IMUL r64, r64 L: 1.04ns= 4.03c T: 0.16ns= 0.630c 330 X86 :IMUL r16, r16, imm8 L: 1.04ns= 4.03c T: 0.67ns= 2.584c 331 X86 :IMUL r32, r32, imm8 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 332 AMD64 :IMUL r64, r64, imm8 L: 1.04ns= 4.03c T: 0.16ns= 0.630c 333 X86 :IMUL r16, r16, imm16 L: 1.04ns= 4.03c T: 0.66ns= 2.567c 334 X86 :IMUL r32, r32, imm32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 335 AMD64 :IMUL r64, r64, imm32 L: 1.04ns= 4.03c T: 0.16ns= 0.630c 336 X86 :IMUL r8l al/eax upd L: 0.78ns= 3.02c T: 0.13ns= 0.504c 337 X86 :IMUL r16 ax/eax upd L: 1.34ns= 5.21c T: 0.39ns= 1.513c 338 X86 :IMUL r32 eax/eax upd L: 0.80ns= 3.09c T: 0.21ns= 0.817c 339 AMD64 :IMUL r64 rax/eax upd L: 1.06ns= 4.10c T: 0.21ns= 0.824c 340 X86 :MUL r8l al/eax upd L: 0.78ns= 3.02c T: 0.13ns= 0.504c 341 X86 :MUL r16 ax/eax upd L: 1.34ns= 5.21c T: 0.39ns= 1.515c 342 X86 :MUL r32 eax/eax upd L: 0.80ns= 3.09c T: 0.21ns= 0.821c 343 AMD64 :MUL r64 rax/eax upd L: 1.06ns= 4.09c T: 0.21ns= 0.824c 344 X86 :IMUL r8l ah/eax upd L: 0.78ns= 3.02c T: 0.13ns= 0.504c 345 X86 :IMUL r16 dx/eax upd L: 1.56ns= 6.04c T: 0.41ns= 1.601c 346 X86 :IMUL r32 edx/eax upd L: 1.04ns= 4.03c T: 0.21ns= 0.817c 347 AMD64 :IMUL r64 rdx/eax upd L: 1.30ns= 5.04c T: 0.21ns= 0.825c 348 X86 :MUL r8l ah/eax upd L: 0.78ns= 3.02c T: 0.13ns= 0.504c 349 X86 :MUL r16 dx/eax upd L: 1.56ns= 6.04c T: 0.45ns= 1.764c 350 X86 :MUL r32 edx/eax upd L: 1.04ns= 4.03c T: 0.21ns= 0.821c 351 AMD64 :MUL r64 rdx/eax upd L: 1.30ns= 5.04c T: 0.21ns= 0.824c 352 X86 :IDIV r8l 14/ 7b L: 2.59ns= 10.06c T: 1.04ns= 4.028c 353 X86 :IDIV r8l 12/ 6b L: 2.60ns= 10.07c T: 1.04ns= 4.028c 354 X86 :IDIV r8l 7/ 7b L: [no true dep.] T: 1.04ns= 4.029c 355 X86 :IDIV r8l 4/ 7b L: [no true dep.] T: 1.04ns= 4.030c 356 X86 :IDIV r8l 0/ 7b L: [no true dep.] T: 1.04ns= 4.028c 357 X86 :IDIV r8l 11/ 4b L: [no true dep.] T: 1.04ns= 4.028c 358 X86 :IDIV r8l 8/ 4b L: [no true dep.] T: 1.04ns= 4.029c 359 X86 :IDIV r8l 4/ 4b L: [no true dep.] T: 1.04ns= 4.030c 360 X86 :IDIV r8l 0/ 4b L: [no true dep.] T: 1.04ns= 4.030c 361 X86 :IDIV r8l 2^12 /2^6 L: [no true dep.] T: 1.04ns= 4.028c 362 X86 :IDIV r8l 1/ 1 no upd L: 2.34ns= 9.06c T: 2.34ns= 9.065c 363 X86 :IDIV r8l 1/ 1 EAX upd L: [no true dep.] T: 1.04ns= 4.029c 364 X86 :IDIV r16 30/15b L: 4.24ns= 16.43c T: 1.17ns= 4.533c 365 X86 :IDIV r16 26/13b L: 3.97ns= 15.41c T: 1.17ns= 4.533c 366 X86 :IDIV r16 15/15b L: [no true dep.] T: 1.43ns= 5.540c 367 X86 :IDIV r16 8/15b L: [no true dep.] T: 1.43ns= 5.540c 368 X86 :IDIV r16 0/15b L: [no true dep.] T: 1.43ns= 5.540c 369 X86 :IDIV r16 23/ 8b L: [no true dep.] T: 1.17ns= 4.533c 370 X86 :IDIV r16 16/ 8b L: [no true dep.] T: 1.17ns= 4.533c 371 X86 :IDIV r16 8/ 8b L: [no true dep.] T: 1.43ns= 5.540c 372 X86 :IDIV r16 0/ 8b L: [no true dep.] T: 1.43ns= 5.540c 373 X86 :IDIV r16 2^28 /2^14 L: [no true dep.] T: 1.17ns= 4.533c 374 X86 :IDIV r16 1/ 1 no upd L: 3.19ns= 12.39c T: 2.94ns= 11.416c 375 X86 :IDIV r16 1/ 1 rAX upd L: 2.85ns= 11.07c T: 2.86ns= 11.079c 376 X86 :IDIV r16 1/ 1 rDX upd L: 3.19ns= 12.36c T: 2.96ns= 11.498c 377 X86 :IDIV r32 62/31b L: 5.54ns= 21.47c T: 1.82ns= 7.051c 378 X86 :IDIV r32 56/28b L: 5.27ns= 20.46c T: 1.69ns= 6.547c 379 X86 :IDIV r32 48/31b L: [no true dep.] T: 1.30ns= 5.037c 380 X86 :IDIV r32 31/31b L: [no true dep.] T: 1.43ns= 5.540c 381 X86 :IDIV r32 16/31b L: [no true dep.] T: 1.43ns= 5.541c 382 X86 :IDIV r32 0/31b L: [no true dep.] T: 1.43ns= 5.540c 383 X86 :IDIV r32 47/16b L: [no true dep.] T: 1.82ns= 7.051c 384 X86 :IDIV r32 32/16b L: [no true dep.] T: 1.17ns= 4.533c 385 X86 :IDIV r32 16/16b L: [no true dep.] T: 1.43ns= 5.540c 386 X86 :IDIV r32 0/16b L: [no true dep.] T: 1.43ns= 5.540c 387 X86 :IDIV r32 2^60 /2^30 L: [no true dep.] T: 1.82ns= 7.051c 388 X86 :IDIV r32 1/ 1 no upd L: 3.20ns= 12.40c T: 2.94ns= 11.416c 389 X86 :IDIV r32 1/ 1 rAX upd L: 2.86ns= 11.09c T: 2.86ns= 11.079c 390 X86 :IDIV r32 1/ 1 rDX upd L: 3.18ns= 12.34c T: 2.96ns= 11.492c 391 AMD64 :IDIV r64 126/63b L: 8.39ns= 32.54c T: 3.25ns= 12.591c 392 AMD64 :IDIV r64 126/63b L: 8.39ns= 32.54c T: 3.25ns= 12.590c 393 AMD64 :IDIV r64 96/63b L: [no true dep.] T: 1.95ns= 7.554c 394 AMD64 :IDIV r64 63/63b L: [no true dep.] T: 1.43ns= 5.540c 395 AMD64 :IDIV r64 32/63b L: [no true dep.] T: 1.43ns= 5.540c 396 AMD64 :IDIV r64 0/63b L: [no true dep.] T: 1.43ns= 5.540c 397 AMD64 :IDIV r64 95/32b L: [no true dep.] T: 3.25ns= 12.591c 398 AMD64 :IDIV r64 64/32b L: [no true dep.] T: 1.95ns= 7.554c 399 AMD64 :IDIV r64 32/32b L: [no true dep.] T: 1.43ns= 5.540c 400 AMD64 :IDIV r64 0/32b L: [no true dep.] T: 1.43ns= 5.540c 401 AMD64 :IDIV r64 2^124/2^62 L: [no true dep.] T: 3.25ns= 12.590c 402 AMD64 :IDIV r64 1/ 1 no upd L: 3.19ns= 12.39c T: 2.94ns= 11.416c 403 AMD64 :IDIV r64 1/ 1 rAX upd L: 2.85ns= 11.07c T: 2.86ns= 11.080c 404 AMD64 :IDIV r64 1/ 1 rDX upd L: 3.19ns= 12.36c T: 2.96ns= 11.484c 405 X86 :DIV r8l 16/ 8b L: 2.85ns= 11.07c T: 1.04ns= 4.029c 406 X86 :DIV r8l 12/ 8b L: [no true dep.] T: 1.04ns= 4.029c 407 X86 :DIV r8l 8/ 8b L: [no true dep.] T: 1.04ns= 4.029c 408 X86 :DIV r8l 4/ 8b L: [no true dep.] T: 1.04ns= 4.029c 409 X86 :DIV r8l 0/ 8b L: [no true dep.] T: 1.04ns= 4.029c 410 X86 :DIV r8l 12/ 4b L: [no true dep.] T: 1.04ns= 4.030c 411 X86 :DIV r8l 8/ 4b L: [no true dep.] T: 1.04ns= 4.027c 412 X86 :DIV r8l 4/ 4b L: [no true dep.] T: 1.04ns= 4.029c 413 X86 :DIV r8l 0/ 4b L: [no true dep.] T: 1.04ns= 4.029c 414 X86 :DIV r8l 2^14 /2^7 L: [no true dep.] T: 1.04ns= 4.030c 415 X86 :DIV r8l 1/ 1 no upd L: 2.34ns= 9.06c T: 2.34ns= 9.065c 416 X86 :DIV r8l 1/ 1 EAX upd L: [no true dep.] T: 1.04ns= 4.029c 417 X86 :DIV r16 32/16b L: 4.24ns= 16.43c T: 1.17ns= 4.533c 418 X86 :DIV r16 30/15b L: 4.24ns= 16.43c T: 1.17ns= 4.533c 419 X86 :DIV r16 24/16b L: [no true dep.] T: 1.17ns= 4.533c 420 X86 :DIV r16 16/16b L: [no true dep.] T: 1.43ns= 5.540c 421 X86 :DIV r16 8/16b L: [no true dep.] T: 1.43ns= 5.540c 422 X86 :DIV r16 0/16b L: [no true dep.] T: 1.43ns= 5.540c 423 X86 :DIV r16 24/ 8b L: [no true dep.] T: 1.17ns= 4.533c 424 X86 :DIV r16 16/ 8b L: [no true dep.] T: 1.17ns= 4.533c 425 X86 :DIV r16 8/ 8b L: [no true dep.] T: 1.43ns= 5.540c 426 X86 :DIV r16 0/ 8b L: [no true dep.] T: 1.43ns= 5.540c 427 X86 :DIV r16 2^30 /2^15 L: [no true dep.] T: 1.17ns= 4.533c 428 X86 :DIV r16 1/ 1 no upd L: 3.19ns= 12.39c T: 2.94ns= 11.416c 429 X86 :DIV r16 1/ 1 rAX upd L: 2.85ns= 11.07c T: 2.86ns= 11.079c 430 X86 :DIV r32 64/32b L: 5.79ns= 22.47c T: 1.95ns= 7.554c 431 X86 :DIV r32 62/31b L: 5.53ns= 21.46c T: 1.82ns= 7.051c 432 X86 :DIV r32 48/32b L: [no true dep.] T: 1.17ns= 4.533c 433 X86 :DIV r32 32/32b L: [no true dep.] T: 1.43ns= 5.540c 434 X86 :DIV r32 16/32b L: [no true dep.] T: 1.43ns= 5.540c 435 X86 :DIV r32 0/32b L: [no true dep.] T: 1.43ns= 5.540c 436 X86 :DIV r32 48/16b L: [no true dep.] T: 1.95ns= 7.554c 437 X86 :DIV r32 32/16b L: [no true dep.] T: 1.17ns= 4.533c 438 X86 :DIV r32 16/16b L: [no true dep.] T: 1.43ns= 5.540c 439 X86 :DIV r32 0/16b L: [no true dep.] T: 1.43ns= 5.540c 440 X86 :DIV r32 2^62 /2^31 L: [no true dep.] T: 1.82ns= 7.052c 441 X86 :DIV r32 1/ 1 no upd L: 3.20ns= 12.40c T: 2.94ns= 11.416c 442 X86 :DIV r32 1/ 1 rAX upd L: 2.86ns= 11.09c T: 2.86ns= 11.079c 443 X86 :DIV r32 1/ 1 rDX upd L: 3.19ns= 12.36c T: 2.96ns= 11.493c 444 AMD64 :DIV r64 128/64b L: 8.39ns= 32.54c T: 3.25ns= 12.591c 445 AMD64 :DIV r64 126/63b L: 8.39ns= 32.54c T: 3.25ns= 12.591c 446 AMD64 :DIV r64 96/64b L: [no true dep.] T: 1.95ns= 7.554c 447 AMD64 :DIV r64 64/64b L: [no true dep.] T: 1.43ns= 5.540c 448 AMD64 :DIV r64 32/64b L: [no true dep.] T: 1.43ns= 5.540c 449 AMD64 :DIV r64 0/64b L: [no true dep.] T: 1.43ns= 5.540c 450 AMD64 :DIV r64 96/32b L: [no true dep.] T: 3.25ns= 12.591c 451 AMD64 :DIV r64 64/32b L: [no true dep.] T: 1.95ns= 7.554c 452 AMD64 :DIV r64 32/32b L: [no true dep.] T: 1.43ns= 5.540c 453 AMD64 :DIV r64 0/32b L: [no true dep.] T: 1.43ns= 5.540c 454 AMD64 :DIV r64 2^126/2^63 L: [no true dep.] T: 3.25ns= 12.590c 455 AMD64 :DIV r64 1/ 1 no upd L: 3.19ns= 12.39c T: 2.94ns= 11.416c 456 AMD64 :DIV r64 1/ 1 rAX upd L: 2.86ns= 11.09c T: 2.86ns= 11.079c 457 AMD64 :DIV r64 1/ 1 rDX upd L: 3.19ns= 12.36c T: 2.96ns= 11.491c 458 X86 :CBW L: 0.26ns= 1.01c T: 0.26ns= 1.007c 459 X86 :CWDE L: 0.26ns= 1.01c T: 0.26ns= 1.007c 460 AMD64 :CDQE L: 0.26ns= 1.01c T: 0.26ns= 1.007c 461 X86 :CWD L: 0.64ns= 2.50c T: 0.67ns= 2.588c 462 X86 :CDQ L: 0.07ns= 0.25c T: 0.06ns= 0.252c 463 AMD64 :CQO L: 0.07ns= 0.25c T: 0.06ns= 0.252c 464 X86 :CLC L: 0.20ns= 0.76c T: 0.26ns= 0.995c 465 X86 :STC L: 0.20ns= 0.77c T: 0.26ns= 0.995c 466 X86 :CMC L: 0.20ns= 0.76c T: 0.26ns= 0.994c 467 X86 :CLD L: 0.03ns= 0.13c T: 0.03ns= 0.130c 468 X86 :STD L: 0.03ns= 0.13c T: 0.03ns= 0.132c 475 LAHF :LAHF L: 0.26ns= 1.01c T: 0.26ns= 1.007c 476 LAHF :SAHF L: 0.20ns= 0.76c T: 0.26ns= 0.994c 483 X86 :PUSH r16 L: [no true dep.] T: 0.13ns= 0.504c 484 X86 :POP r16 L: [no true dep.] T: 0.66ns= 2.578c 485 X86 :PUSH r16 + POP r16 L: 1.56ns= 6.05c T: 0.56ns= 2.173c 486 AMD64 :PUSH r64 L: [no true dep.] T: 0.13ns= 0.504c 487 AMD64 :POP r64 L: [no true dep.] T: 0.09ns= 0.336c 488 AMD64 :PUSH r64 + POP r64 L: 0.13ns= 0.49c T: 0.23ns= 0.891c 489 AMD64 :PUSH imm8 L: [no true dep.] T: 0.13ns= 0.504c 490 AMD64 :PUSH imm8 + POP r64 L: 0.13ns= 0.49c T: 0.13ns= 0.504c 491 AMD64 :PUSH imm32 L: [no true dep.] T: 0.13ns= 0.504c 492 AMD64 :PUSH imm32 + POP r64 L: 0.13ns= 0.49c T: 0.13ns= 0.504c 493 X86 :PUSH [m16] L: [no true dep.] T: 0.13ns= 0.504c 494 X86 :POP [m16] L: [no true dep.] T: 0.67ns= 2.598c 495 X86 :PUSH [m16] + POP [m16] L: 3.12ns= 12.09c T: 0.61ns= 2.353c 496 AMD64 :PUSH [m64] L: [no true dep.] T: 0.13ns= 0.506c 497 AMD64 :POP [m64] L: [no true dep.] T: 0.67ns= 2.598c 498 AMD64 :PUSH [m64] + POP [m64] L: 3.12ns= 12.09c T: 0.61ns= 2.358c 499 X86 :PUSHF L: [no true dep.] T: 0.70ns= 2.707c 501 X86 :PUSHF + POPF L: 9.43ns= 36.57c T: 9.44ns= 36.624c 502 AMD64 :PUSHFQ L: [no true dep.] T: 0.73ns= 2.837c 504 AMD64 :PUSHFQ + POPFQ L: 9.47ns= 36.74c T: 9.48ns= 36.765c 505 X86 :CMPSB L: 0.78ns= 3.01c T: 0.76ns= 2.957c 506 X86 :CMPSW L: 0.68ns= 2.62c T: 0.67ns= 2.603c 507 X86 :CMPSD L: 0.78ns= 3.01c T: 0.76ns= 2.956c 508 AMD64 :CMPSQ L: 0.68ns= 2.62c T: 0.67ns= 2.614c 509 X86 :REPE CMPSB BW in L1D: 0.66 B/c 2566MiB/s 510 X86 :REPE CMPSW BW in L1D: 1.32 B/c 5129MiB/s 511 X86 :REPE CMPSD BW in L1D: 2.64 B/c 10247MiB/s 512 AMD64 :REPE CMPSQ BW in L1D: 5.27 B/c 20448MiB/s 513 X86 :LODSB L: 0.63ns= 2.44c T: 0.67ns= 2.616c 514 X86 :LODSW L: 0.62ns= 2.39c T: 0.67ns= 2.600c 515 X86 :LODSD L: 0.63ns= 2.44c T: 0.67ns= 2.611c 516 AMD64 :LODSQ L: 0.62ns= 2.40c T: 0.67ns= 2.597c 517 X86 :REP LODSB BW in L1D: 0.50 B/c 1925MiB/s 518 X86 :REP LODSW BW in L1D: 0.99 B/c 3848MiB/s 519 X86 :REP LODSD BW in L1D: 1.98 B/c 7689MiB/s 520 AMD64 :REP LODSQ BW in L1D: 3.96 B/c 15353MiB/s 521 X86 :STOSB L: 0.52ns= 2.02c T: 0.67ns= 2.579c 522 X86 :STOSW L: 0.53ns= 2.05c T: 0.68ns= 2.623c 523 X86 :STOSD L: 0.52ns= 2.01c T: 0.67ns= 2.579c 524 AMD64 :STOSQ L: 0.53ns= 2.05c T: 0.68ns= 2.624c 525 X86 :REP STOSB BW in L1D:15.53 B/c 60247MiB/s 526 X86 :REP STOSW BW in L1D:15.53 B/c 60247MiB/s 527 X86 :REP STOSD BW in L1D:15.53 B/c 60247MiB/s 528 AMD64 :REP STOSQ BW in L1D:15.53 B/c 60247MiB/s 529 X86 :MOVSB L: 0.73ns= 2.83c T: 0.73ns= 2.829c 530 X86 :MOVSW L: 0.67ns= 2.61c T: 0.70ns= 2.699c 531 X86 :MOVSD L: 0.73ns= 2.84c T: 0.73ns= 2.827c 532 AMD64 :MOVSQ L: 0.68ns= 2.62c T: 0.70ns= 2.698c 533 X86 :REP MOVSB BW in L1D:30.41 B/c 117953MiB/s 534 X86 :REP MOVSW BW in L1D:30.39 B/c 117860MiB/s 535 X86 :REP MOVSD BW in L1D:30.39 B/c 117860MiB/s 536 AMD64 :REP MOVSQ BW in L1D:30.39 B/c 117860MiB/s 537 X86 :SCASB L: 0.63ns= 2.44c T: 0.67ns= 2.612c 538 X86 :SCASW L: 0.62ns= 2.39c T: 0.67ns= 2.601c 539 X86 :SCASD L: 0.63ns= 2.45c T: 0.67ns= 2.618c 540 AMD64 :SCASQ L: 0.62ns= 2.40c T: 0.67ns= 2.607c 541 X86 :REPNE SCASB BW in L1D: 0.50 B/c 1924MiB/s 542 X86 :REPNE SCASW BW in L1D: 0.99 B/c 3846MiB/s 543 X86 :REPNE SCASD BW in L1D: 1.98 B/c 7683MiB/s 544 AMD64 :REPNE SCASQ BW in L1D: 3.95 B/c 15331MiB/s 545 X86 :XADD r8, r8 L: 0.63ns= 2.44c T: 0.67ns= 2.581c 546 X86 :XADD r16, r16 L: 0.63ns= 2.44c T: 0.67ns= 2.580c 547 X86 :XADD r32, r32 L: 0.63ns= 2.44c T: 0.66ns= 2.572c 548 AMD64 :XADD r64, r64 L: 0.63ns= 2.45c T: 0.66ns= 2.554c 549 X86 :CMPXCHG r8, r8 L: 1.56ns= 6.04c T: 1.57ns= 6.070c 550 X86 :CMPXCHG r16, r16 L: 1.56ns= 6.04c T: 1.57ns= 6.074c 551 X86 :CMPXCHG r32, r32 L: 1.56ns= 6.04c T: 1.57ns= 6.072c 552 AMD64 :CMPXCHG r64, r64 L: 1.56ns= 6.04c T: 1.57ns= 6.074c 553 CMPX8 :CMPXCHG8B L: 2.36ns= 9.16c T: 1.53ns= 5.948c 554 CMPX16 :CMPXCHG16B L: 5.95ns= 23.08c T: 2.58ns= 10.001c 555 X86 :RDTSC L: [no true dep.] T: 7.13ns= 27.650c 556 X86 :CPUID (EAX = 0) L: 187.38ns= 726.73c T: 187.68ns= 727.884c 557 X86 :CPUID (EAX = 1) L: 428.72ns=1662.75c T: 429.42ns=1665.436c 558 POPCNT :POPCNT r16, r16 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 559 POPCNT :POPCNT r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 560 POPCNT_X64 :POPCNT r64, r64 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 561 ABM :LZCNT r16, r16 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 562 ABM :LZCNT r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 563 ABM_X64 :LZCNT r64, r64 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 564 SSE4.2 :CRC32 r32, r8 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 565 SSE4.2 :CRC32 r32, r16 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 566 SSE4.2 :CRC32 r32, r32 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 567 SSE42_X64 :CRC32 r64, r8 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 568 SSE42_X64 :CRC32 r64, r16 L: 0.78ns= 3.02c T: 0.26ns= 1.008c 569 X87 :FNOP L: [no true dep.] T: 0.06ns= 0.252c 570 X87 :FXCH st(i) L: 0.26ns= 1.01c T: 0.26ns= 1.007c 571 X87 :FCHS L: 0.26ns= 1.01c T: 0.26ns= 1.007c 572 X87 :FABS L: 0.26ns= 1.01c T: 0.26ns= 1.007c 573 X87 :FTST L: [no true dep.] T: 0.26ns= 1.007c 574 X87 :FXAM L: [no true dep.] T: 0.26ns= 1.007c 575 CMOV :FCMOVE st, st(i) L: 0.65ns= 2.53c T: 0.66ns= 2.548c 576 X87 :FADD st(i), st (st = 0.0) L: 1.04ns= 4.03c T: 0.26ns= 1.007c 577 X87 :FADD st(i), st L: 1.04ns= 4.03c T: 0.26ns= 1.007c 578 X87 :FADD st, st(i), FXCH st(i) L: 1.82ns= 7.05c T: [not enough reg] 579 X87 :FMUL st(i), st (st = 0.0) L: 1.30ns= 5.04c T: 0.52ns= 2.014c 580 X87 :FMUL st(i), st L: 1.30ns= 5.04c T: 0.52ns= 2.014c 581 X87 :FMUL st, st(i), FXCH st(i) L: 2.08ns= 8.06c T: 0.78ns= 3.022c 582 X87 :FMUL + FADD st, st(i) L: 2.34ns= 9.06c T: [not enough reg] 583 X87 :FMUL st(2i) FADD st(2i+1) L: 1.30ns= 5.04c T: [not enough reg] 584 X87 :FDIV32 st(i), st L: 2.86ns= 11.08c T: 0.78ns= 3.022c 585 X87 :FDIV64 st(i), st L: 3.38ns= 13.09c T: 1.04ns= 4.029c 586 X87 :FDIV80 st(i), st L: 3.64ns= 14.10c T: 1.17ns= 4.533c 587 X87 :FDIV80 (0.0l/x) L: 3.64ns= 14.10c T: 1.17ns= 4.533c 588 X87 :FDIV80 (x/1.0l) L: 3.64ns= 14.10c T: 1.17ns= 4.533c 589 X87 :FDIV80 (x/2.0l) L: 3.64ns= 14.10c T: 1.17ns= 4.533c 590 X87 :FDIV80 (x/0.5l) L: 3.64ns= 14.10c T: 1.17ns= 4.533c 591 X87 :FSQRT32 st L: 2.86ns= 11.08c T: 0.93ns= 3.626c 592 X87 :FSQRT64 st L: 4.41ns= 17.12c T: 1.87ns= 7.251c 593 X87 :FSQRT80 st L: 4.93ns= 19.14c T: 2.18ns= 8.461c 594 X87 :FSQRT80 (0.0l) L: 4.93ns= 19.14c T: 2.18ns= 8.462c 595 X87 :FSQRT80 (1.0l) L: 4.93ns= 19.14c T: 2.18ns= 8.461c 596 X87 :FDECSTP L: [no true dep.] T: 0.06ns= 0.252c 597 X87 :FINCSTP L: [no true dep.] T: 0.06ns= 0.252c 598 X87 :FCOM st(i) L: [no true dep.] T: 0.26ns= 1.007c 599 CMOV :FCOMI st, st(i) L: [no true dep.] T: 0.26ns= 1.007c 600 X87 :FSIN80 (0.0) L: 16.77ns= 65.04c T: 16.79ns= 65.122c 601 X87 :FSIN80 (0.0) + FADD L: 16.85ns= 65.34c T: 16.86ns= 65.398c 602 X87 :FSIN80 (1.0) + FADD L: 43.27ns= 167.83c T: 43.32ns= 167.994c 603 X87 :FSIN80 (4Pi) + FADD L: 42.33ns= 164.18c T: 41.78ns= 162.043c 604 X87 :FSIN80 (2Pi) + FADD L: 42.33ns= 164.18c T: 41.78ns= 162.037c 605 X87 :FSIN80 (Pi) + FADD L: 42.33ns= 164.18c T: 41.78ns= 162.030c 606 X87 :FSIN80 (Pi/2) + FADD L: 46.87ns= 181.78c T: 46.44ns= 180.096c 607 X87 :FSIN80 (Pi/4) + FADD L: 44.83ns= 173.87c T: 44.87ns= 174.039c 608 X87 :FSIN80 (Pi/8) + FADD L: 35.90ns= 139.25c T: 35.34ns= 137.075c 609 X87 :FSIN80 (Pi/16) + FADD L: 43.89ns= 170.22c T: 43.34ns= 168.104c 610 X87 :FSIN80 (Pi/32) + FADD L: 43.89ns= 170.22c T: 43.34ns= 168.100c 611 X87 :FCOS80 (0.73908513...) L: 41.36ns= 160.40c T: 42.59ns= 165.165c 612 X87 :FCOS80 (0.73908513...)+FADD L: 43.02ns= 166.85c T: 43.68ns= 169.390c 613 X87 :FCOS80 (0.0) + FADD L: 16.65ns= 64.56c T: 16.90ns= 65.556c 614 X87 :FCOS80 (1.0) + FADD L: 33.11ns= 128.40c T: 33.65ns= 130.525c 615 X87 :FCOS80 (4Pi) + FADD L: 45.77ns= 177.52c T: 46.33ns= 179.669c 616 X87 :FCOS80 (2Pi) + FADD L: 45.77ns= 177.52c T: 46.33ns= 179.679c 617 X87 :FCOS80 (Pi) + FADD L: 45.77ns= 177.52c T: 46.33ns= 179.679c 618 X87 :FCOS80 (Pi/2) + FADD L: 41.03ns= 159.13c T: 41.61ns= 161.375c 619 X87 :FCOS80 (Pi/4) + FADD L: 34.67ns= 134.45c T: 35.22ns= 136.597c 620 X87 :FCOS80 (Pi/8) + FADD L: 43.02ns= 166.85c T: 43.68ns= 169.410c 621 X87 :FCOS80 (Pi/16) + FADD L: 47.33ns= 183.57c T: 47.89ns= 185.723c 622 X87 :FCOS80 (Pi/32) + FADD L: 47.33ns= 183.56c T: 47.89ns= 185.725c 623 MMX :EMMS L: 0.26ns= 1.01c T: 0.26ns= 1.007c 624 MMX :MOVD r32, mm L: [diff. reg. set] T: 0.22ns= 0.839c 625 MMX :MOVD mm, r32 L: [diff. reg. set] T: 0.14ns= 0.546c 626 MMX :MOVD r32, mm+MOVD mm, r32 L: 2.86ns= 11.08c T: 0.63ns= 2.437c 627 AMD64 :MOVD r64, mm L: [diff. reg. set] T: 0.22ns= 0.839c 628 AMD64 :MOVD mm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 629 AMD64 :MOVD r64, mm+MOVD mm, r64 L: 2.86ns= 11.08c T: 0.63ns= 2.437c 630 MMX :MOVD mm, [m32] L: [memory dep.] T: 0.09ns= 0.336c 631 MMX :MOVD [m32], mm L: [memory dep.] T: 0.13ns= 0.504c 632 MMX :MOVD mm,[m32]+MOVD [m32],mm L: 1.82ns= 7.05c T: 0.23ns= 0.881c 633 MMX :MOVQ mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 634 MMX :MOVQ mm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 635 MMX :MOVQ [m64], mm L: [memory dep.] T: 0.13ns= 0.504c 636 MMX :MOVQ mm,[m64]+MOVQ [m64],mm L: 1.82ns= 7.05c T: 0.23ns= 0.881c 637 SSE :MOVNTQ [m64], mm L: [memory dep.] T: 0.50ns= 0.504c 638 SSE :PMOVMSKB r32, mm L: [diff. reg. set] T: 0.22ns= 0.839c 639 AMD64 :PMOVMSKB r64, mm L: [diff. reg. set] T: 0.22ns= 0.839c 640 SSE :MASKMOVQ mm, mm L: [memory dep.] T: 8.06ns= 8.057c 641 MMX :PADDB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 642 MMX :PADDW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 643 MMX :PADDD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 644 SSE2 :PADDQ mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 645 MMX :PADDSB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 646 MMX :PADDSW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 647 MMX :PADDUSB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 648 MMX :PADDUSW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 649 MMX :PSUBB mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 650 MMX :PSUBB mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 651 MMX :PSUBW mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 652 MMX :PSUBW mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 653 MMX :PSUBD mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 654 MMX :PSUBD mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 655 SSE2 :PSUBQ mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 656 SSE2 :PSUBQ mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 657 MMX :PSUBSB mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 658 MMX :PSUBSB mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 659 MMX :PSUBSW mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 660 MMX :PSUBSW mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 661 MMX :PSUBUSB mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 662 MMX :PSUBUSB mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.249c 663 MMX :PSUBUSW mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 664 MMX :PSUBUSW mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 665 MMX :PCMPEQB mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 666 MMX :PCMPEQB mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.249c 667 MMX :PCMPEQW mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 668 MMX :PCMPEQW mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 669 MMX :PCMPEQD mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 670 MMX :PCMPEQD mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 671 MMX :PCMPGTB mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 672 MMX :PCMPGTB mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.249c 673 MMX :PCMPGTW mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 674 MMX :PCMPGTW mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 675 MMX :PCMPGTD mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 676 MMX :PCMPGTD mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 677 MMX :PAND mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 678 MMX :PAND mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 679 MMX :PANDN mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 680 MMX :PANDN mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 681 MMX :POR mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 682 MMX :POR mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 683 MMX :PXOR mm, mm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 684 MMX :PXOR mm1, mm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 685 MMX :PMULHW mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.380c 686 SSE :PMULHUW mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.378c 688 SSSE3 :PMULHRSW mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.380c 689 MMX :PMULLW mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.379c 690 SSE2 :PMULUDQ mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.378c 691 SSSE3 :PMADDUBSW mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.379c 692 MMX :PMADDWD mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.380c 693 MMX :PSLLW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 694 MMX :PSLLW mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 695 MMX :PSLLD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 696 MMX :PSLLD mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 697 MMX :PSLLQ mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 698 MMX :PSLLQ mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 699 MMX :PSRAW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 700 MMX :PSRAW mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 701 MMX :PSRAD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 702 MMX :PSRAD mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 703 MMX :PSRLW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 704 MMX :PSRLW mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 705 MMX :PSRLD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 706 MMX :PSRLD mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 707 MMX :PSRLQ mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 708 MMX :PSRLQ mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 709 MMX :PUNPCKHBW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 710 MMX :PUNPCKHWD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 711 MMX :PUNPCKHDQ mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 712 MMX :PUNPCKLBW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 713 MMX :PUNPCKLWD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 714 MMX :PUNPCKLDQ mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 715 MMX :PACKSSWB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 716 MMX :PACKUSWB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 717 MMX :PACKSSDW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 746 3DN_3DNPREF :PREFETCHW [mem] L: [memory dep.] T: 0.09ns= 0.336c 753 SSE :PAVGB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 754 SSE :PAVGW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 755 SSE :PEXTRW r32, mm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 756 SSE :PINSRW mm, r32, im8 L: [diff. reg. set] T: 0.18ns= 0.685c 757 SSE :PEXTRW + PINSRW r32 L: 2.86ns= 11.08c T: 0.63ns= 2.436c 758 AMD64 :PEXTRW r64, mm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 759 AMD64 :PINSRW mm, r64, im8 L: [diff. reg. set] T: 0.18ns= 0.685c 760 AMD64 :PEXTRW + PINSRW r64 L: 2.86ns= 11.08c T: 0.62ns= 2.413c 761 SSE :PMAXSW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 762 SSE :PMAXUB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 763 SSE :PMINSW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 764 SSE :PMINUB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 765 SSE :PSADBW mm, mm L: 0.78ns= 3.02c T: 0.10ns= 0.379c 766 SSE :PSHUFW mm, mm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 767 SSE :PREFETCHNTA [mem] L: [memory dep.] T: 0.09ns= 0.336c 768 SSE :PREFETCHT0 [mem] L: [memory dep.] T: 0.09ns= 0.336c 769 SSE :PREFETCHT1 [mem] L: [memory dep.] T: 0.17ns= 0.672c 770 SSE :PREFETCHT2 [mem] L: [memory dep.] T: 0.17ns= 0.672c 771 SSE :SFENCE L: 0.52ns= 2.01c T: 0.52ns= 2.014c 772 SSE2 :LFENCE L: 2.69ns= 10.45c T: 2.69ns= 10.451c 773 SSE2 :MFENCE L: 4.02ns= 15.59c T: 4.02ns= 15.595c 774 SSSE3 :PABSB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 775 SSSE3 :PABSW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 776 SSSE3 :PABSD mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 777 SSSE3 :PALIGNR mm, mm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 778 SSSE3 :PHADDW mm, mm L: 1.05ns= 4.06c T: 0.67ns= 2.588c 779 SSSE3 :PHADDD mm, mm L: 0.78ns= 3.03c T: 0.68ns= 2.632c 780 SSSE3 :PHADDSW mm, mm L: 1.05ns= 4.06c T: 0.67ns= 2.582c 781 SSSE3 :PHSUBW mm, mm L: 1.05ns= 4.06c T: 0.67ns= 2.582c 782 SSSE3 :PHSUBD mm, mm L: 0.78ns= 3.03c T: 0.68ns= 2.630c 783 SSSE3 :PHSUBSW mm, mm L: 1.05ns= 4.06c T: 0.67ns= 2.589c 784 SSSE3 :PSHUFB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 785 SSSE3 :PSIGNB mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 786 SSSE3 :PSIGNW mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 787 SSSE3 :PSIGND mm, mm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 788 SSE :MOVHLPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 789 SSE :MOVHLPS xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 790 AVX :VMOVHLPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 791 AVX :VMOVHLPS xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 792 SSE :MOVSS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 793 AVX :VMOVSS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 794 SSE :MOVSS xmm, [m32] L: [memory dep.] T: 0.09ns= 0.336c 795 SSE :MOVSS [m32], xmm L: [memory dep.] T: 0.13ns= 0.504c 796 SSE :MOVSS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.663c 797 AVX :VMOVSS xmm, [m32] L: [memory dep.] T: 0.09ns= 0.336c 798 AVX :VMOVSS [m32], xmm L: [memory dep.] T: 0.13ns= 0.504c 799 AVX :VMOVSS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 800 SSE :MOVLPS xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 801 SSE :MOVLPS [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 802 SSE :MOVLPS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 803 AVX :VMOVLPS xmm, xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 804 AVX :VMOVLPS [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 805 AVX :VMOVLPS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 806 SSE :MOVHPS xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 807 SSE :MOVHPS [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 808 SSE :MOVHPS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 809 AVX :VMOVHPS xmm, xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 810 AVX :VMOVHPS [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 811 AVX :VMOVHPS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 812 SSE :MOVAPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 813 SSE :MOVAPS xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 814 SSE :MOVAPS [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 815 SSE :MOVAPS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 816 AVX :VMOVAPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 817 AVX :VMOVAPS xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 818 AVX :VMOVAPS [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 819 AVX :VMOVAPS LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 820 SSE :MOVUPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 821 SSE :MOVUPS xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 822 SSE :MOVUPS [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 823 SSE :MOVUPS aligned LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 824 SSE :MOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 825 SSE :MOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.26ns= 1.007c 826 SSE :MOVUPS unaligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 827 AVX :VMOVUPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 828 AVX :VMOVUPS xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 829 AVX :VMOVUPS [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 830 AVX :VMOVUPS aligned LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 831 AVX :VMOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 832 AVX :VMOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.26ns= 1.007c 833 AVX :VMOVUPS unaligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 835 SSE :MOVNTPS [m128], xmm L: [memory dep.] T: 0.50ns= 0.504c 836 AVX :VMOVNTPS [m128], xmm L: [memory dep.] T: 0.50ns= 0.504c 837 SSE :MOVMSKPS r32, xmm L: [diff. reg. set] T: 0.22ns= 0.840c 838 AVX :VMOVMSKPS r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 839 AVX :VMASKMOVPS xmm,xmm,[m128+4] L: [memory dep.] T: 0.11ns= 0.420c 840 AVX :VMASKMOVPS [m128+4],xmm,xmm L: [memory dep.] T: 0.32ns= 1.259c 841 AVX :VMASKMOVPS unaligned LS pair L: 4.67ns= 18.13c T: 0.32ns= 1.259c 842 SSE :UNPCKLPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 843 AVX :VUNPCKLPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 844 SSE :UNPCKHPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 845 AVX :VUNPCKHPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 846 SSE :SHUFPS xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 847 AVX :VSHUFPS xmm, xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 848 AVX :VPERMILPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 849 AVX :VPERMILPS xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 850 SSE :COMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.840c 851 AVX :VCOMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 852 SSE :UCOMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.840c 853 AVX :VUCOMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 854 SSE :CMPSS xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 855 SSE :CMPPS xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 856 AVX :VCMPSS xmm, xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 857 AVX :VCMPPS xmm, xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 858 SSE :SUBSS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 859 AVX :VSUBSS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 860 SSE :SUBPS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 861 AVX :VSUBPS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 862 SSE :ADDSS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 863 AVX :VADDSS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 864 SSE :ADDPS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 865 AVX :VADDPS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 866 SSE :MULSS xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 867 AVX :VMULSS xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 868 SSE :MULPS xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 869 AVX :VMULPS xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 870 SSE :MULSS+ADDSS xmm, xmm L: 1.30ns= 5.04c T: 0.14ns= 0.546c 871 AVX :VMULSS+VADDSS xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.15ns= 0.577c 872 SSE :MULPS+ADDPS xmm, xmm L: 1.30ns= 5.04c T: 0.15ns= 0.576c 873 AVX :VMULPS+VADDPS xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.14ns= 0.542c 874 SSE :MULSS xm1,xm1 ADDSS xm2,xm2 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 875 AVX :VMULSS xmm1.. VADDSS xmm2.. L: 0.78ns= 3.02c T: 0.13ns= 0.504c 876 SSE :MULPS xm1,xm1 ADDPS xm2,xm2 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 877 AVX :VMULPS xmm1.. VADDPS xmm2.. L: 0.78ns= 3.02c T: 0.13ns= 0.504c 878 SSE :MAXSS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 879 AVX :VMAXSS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 880 SSE :MAXPS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 881 AVX :VMAXPS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 882 SSE :MINSS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 883 AVX :VMINSS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 884 SSE :MINPS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 885 AVX :VMINPS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 886 SSE :ANDNPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 887 SSE :ANDNPS xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 888 AVX :VANDNPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 889 AVX :VANDNPS xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 890 SSE :ANDPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 891 SSE :ANDPS xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 892 AVX :VANDPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 893 AVX :VANDPS xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 894 SSE :ORPS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 895 SSE :ORPS xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 896 AVX :VORPS xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 897 AVX :VORPS xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 898 SSE :XORPS xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.124c 899 SSE :XORPS xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 900 AVX :VXORPS xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 901 AVX :VXORPS xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 902 SSE :DIVSS xmm, xmm L: 2.60ns= 10.07c T: 0.65ns= 2.518c 903 SSE :DIVSS (0.0f/x) L: 2.60ns= 10.07c T: 0.65ns= 2.518c 904 SSE :DIVSS (x/1.0f) L: 2.60ns= 10.07c T: 0.65ns= 2.518c 905 SSE :DIVSS (x/2.0f) L: 2.50ns= 9.70c T: 0.65ns= 2.518c 906 SSE :DIVSS (x/0.5f) L: 2.50ns= 9.70c T: 0.65ns= 2.518c 907 AVX :VDIVSS xmm, xmm, xmm L: 2.60ns= 10.07c T: 0.65ns= 2.518c 908 AVX :VDIVSS (0.0f/x) L: 2.60ns= 10.07c T: 0.65ns= 2.518c 909 AVX :VDIVSS (x/1.0f) L: 2.60ns= 10.07c T: 0.65ns= 2.518c 910 AVX :VDIVSS (x/2.0f) L: 2.50ns= 9.69c T: 0.65ns= 2.518c 911 AVX :VDIVSS (x/0.5f) L: 2.50ns= 9.69c T: 0.65ns= 2.518c 912 SSE :DIVPS xmm, xmm L: 3.90ns= 15.11c T: 1.30ns= 5.037c 913 SSE :DIVPS (0.0f/x) L: 3.90ns= 15.11c T: 1.30ns= 5.036c 914 SSE :DIVPS (x/1.0f) L: 3.90ns= 15.11c T: 1.30ns= 5.037c 915 SSE :DIVPS (x/2.0f) L: 3.02ns= 11.72c T: 1.30ns= 5.036c 916 SSE :DIVPS (x/0.5f) L: 3.02ns= 11.72c T: 1.30ns= 5.037c 917 AVX :VDIVPS xmm, xmm, xmm L: 3.90ns= 15.11c T: 1.30ns= 5.037c 918 AVX :VDIVPS (0.0f/x) L: 3.90ns= 15.11c T: 1.30ns= 5.037c 919 AVX :VDIVPS (x/1.0f) L: 3.90ns= 15.11c T: 1.30ns= 5.037c 920 AVX :VDIVPS (x/2.0f) L: 3.01ns= 11.69c T: 1.30ns= 5.037c 921 AVX :VDIVPS (x/0.5f) L: 3.01ns= 11.69c T: 1.30ns= 5.037c 922 SSE :SQRTSS xmm, xmm L: 2.86ns= 11.08c T: 0.78ns= 3.022c 923 SSE :SQRTSS (0.0f) L: 2.86ns= 11.08c T: 0.78ns= 3.022c 924 SSE :SQRTSS (1.0f) L: 2.86ns= 11.08c T: 0.78ns= 3.022c 925 AVX :VSQRTSS xmm, xmm, xmm L: 2.86ns= 11.08c T: 0.78ns= 3.022c 926 AVX :VSQRTSS (0.0f) L: 2.86ns= 11.08c T: 0.78ns= 3.022c 927 AVX :VSQRTSS (1.0f) L: 2.86ns= 11.08c T: 0.78ns= 3.022c 928 SSE :SQRTPS xmm, xmm L: 4.41ns= 17.12c T: 1.56ns= 6.045c 929 SSE :SQRTPS (0.0f) L: 4.41ns= 17.12c T: 1.56ns= 6.044c 930 SSE :SQRTPS (1.0f) L: 4.41ns= 17.12c T: 1.56ns= 6.045c 931 AVX :VSQRTPS xmm, xmm L: 4.41ns= 17.12c T: 1.56ns= 6.045c 932 AVX :VSQRTPS (0.0f) L: 4.41ns= 17.12c T: 1.56ns= 6.044c 933 AVX :VSQRTPS (1.0f) L: 4.41ns= 17.12c T: 1.56ns= 6.044c 934 SSE :RCPSS xmm, xmm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 935 AVX :VRCPSS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 936 SSE :RCPPS xmm, xmm L: 1.30ns= 5.04c T: 0.26ns= 1.007c 937 AVX :VRCPPS xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.26ns= 1.007c 938 SSE :RSQRTSS xmm, xmm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 939 AVX :VRSQRTSS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 940 SSE :RSQRTPS xmm, xmm L: 1.30ns= 5.04c T: 0.26ns= 1.007c 941 AVX :VRSQRTPS xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.26ns= 1.007c 942 SSE :CVTPI2PS xmm, mm L: [diff. reg. set] T: 0.13ns= 0.504c 943 SSE :CVTPS2PI mm, xmm L: [diff. reg. set] T: 0.13ns= 0.504c 944 SSE :CVTPS2PI + CVTPI2PS L: 1.56ns= 6.04c T: 0.27ns= 1.033c 945 SSE :CVTTPS2PI mm, xmm L: [diff. reg. set] T: 0.13ns= 0.504c 946 SSE :CVTTPS2PI + CVTPI2PS L: 1.56ns= 6.04c T: 0.26ns= 1.026c 947 SSE :CVTSI2SS xmm, r32 L: [diff. reg. set] T: 0.14ns= 0.545c 948 SSE :CVTSS2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 949 SSE :CVTSS2SI + CVTSI2SS r32 L: 3.12ns= 12.08c T: 0.43ns= 1.679c 950 SSE :CVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 951 SSE :CVTTSS2SI + CVTSI2SS r32 L: 3.12ns= 12.08c T: 0.43ns= 1.679c 952 AVX :VCVTSI2SS xmm, xmm, r32 L: [diff. reg. set] T: 0.14ns= 0.546c 953 AVX :VCVTSS2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 954 AVX :VCVTSS2SI + VCVTSI2SS r32 L: 3.12ns= 12.09c T: 0.44ns= 1.695c 955 AVX :VCVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 956 AVX :VCVTTSS2SI + VCVTSI2SS r32 L: 3.12ns= 12.09c T: 0.44ns= 1.696c 957 AMD64 :CVTSI2SS xmm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 958 AMD64 :CVTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 959 AMD64 :CVTSS2SI + CVTSI2SS r64 L: 3.12ns= 12.08c T: 0.44ns= 1.697c 960 AMD64 :CVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 961 AMD64 :CVTTSS2SI + CVTSI2SS r64 L: 3.12ns= 12.08c T: 0.43ns= 1.679c 962 AVX_X64 :VCVTSI2SS xmm, xmm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 963 AVX_X64 :VCVTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 964 AVX_X64 :VCVTSS2SI + VCVTSI2SS r64 L: 3.12ns= 12.09c T: 0.43ns= 1.679c 965 AVX_X64 :VCVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 966 AVX_X64 :VCVTTSS2SI + VCVTSI2SS r64 L: 3.12ns= 12.09c T: 0.44ns= 1.697c 967 SSE :STMXCSR [mem] L: [memory dep.] T: 0.66ns= 2.558c 968 SSE :LDMXCSR [mem] L: [memory dep.] T: 2.08ns= 8.061c 969 SSE :STMXCSR + LDMXCSR L: 5.25ns= 20.35c T: 5.25ns= 20.359c 970 SSE2 :MOVSD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 971 SSE2 :MOVSD xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 972 SSE2 :MOVSD [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 973 SSE2 :MOVSD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 974 AVX :VMOVSD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 975 AVX :VMOVSD xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 976 AVX :VMOVSD [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 977 AVX :VMOVSD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 978 SSE2 :MOVLPD xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 979 SSE2 :MOVLPD [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 980 SSE2 :MOVLPD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 981 AVX :VMOVLPD xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 982 AVX :VMOVLPD [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 983 AVX :VMOVLPD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 984 SSE2 :MOVHPD xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 985 SSE2 :MOVHPD [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 986 SSE2 :MOVHPD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 987 AVX :VMOVHPD xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 988 AVX :VMOVHPD [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 989 AVX :VMOVHPD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 990 SSE2 :MOVAPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 991 SSE2 :MOVAPD xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 992 SSE2 :MOVAPD [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 993 SSE2 :MOVAPD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 994 AVX :VMOVAPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 995 AVX :VMOVAPD xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 996 AVX :VMOVAPD [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 997 AVX :VMOVAPD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 998 SSE2 :MOVUPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 999 SSE2 :MOVUPD xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 1000 SSE2 :MOVUPD [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 1001 SSE2 :MOVUPD aligned LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1002 SSE2 :MOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 1003 SSE2 :MOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.26ns= 1.007c 1004 SSE2 :MOVUPD unaligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1005 AVX :VMOVUPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1006 AVX :VMOVUPD xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 1007 AVX :VMOVUPD [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 1008 AVX :VMOVUPD aligned LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.671c 1009 AVX :VMOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 1010 AVX :VMOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.26ns= 1.007c 1011 AVX :VMOVUPD unaligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1013 SSE2 :MOVNTPD [m128], xmm L: [memory dep.] T: 0.50ns= 0.504c 1014 AVX :VMOVNTPD [m128], xmm L: [memory dep.] T: 0.50ns= 0.504c 1015 SSE2 :MOVMSKPD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.843c 1016 AVX :VMOVMSKPD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1017 AVX :VMASKMOVPD xmm,xmm,[m128+4] L: [memory dep.] T: 0.11ns= 0.420c 1018 AVX :VMASKMOVPD [m128+4],xmm,xmm L: [memory dep.] T: 0.32ns= 1.259c 1019 AVX :VMASKMOVPD unaligned LS pair L: 4.67ns= 18.13c T: 0.32ns= 1.259c 1020 SSE2 :UNPCKLPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1021 AVX :VUNPCKLPD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1022 SSE2 :UNPCKHPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1023 AVX :VUNPCKHPD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1024 SSE2 :SHUFPD xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1025 AVX :VSHUFPD xmm, xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1026 AVX :VPERMILPD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1027 AVX :VPERMILPD xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1028 SSE2 :COMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1029 AVX :VCOMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1030 SSE2 :UCOMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1031 AVX :VUCOMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1032 SSE2 :CMPSD xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1033 SSE2 :CMPPD xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1034 AVX :VCMPSD xmm, xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1035 AVX :VCMPPD xmm, xmm, xmm, imm8 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1036 SSE2 :SUBSD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1037 AVX :VSUBSD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1038 SSE2 :SUBPD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1039 AVX :VSUBPD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1040 SSE2 :ADDSD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1041 AVX :VADDSD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1042 SSE2 :ADDPD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1043 AVX :VADDPD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1044 SSE2 :MULSD xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1045 AVX :VMULSD xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1046 SSE2 :MULPD xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1047 AVX :VMULPD xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1048 SSE2 :MULSD+ADDSD xmm, xmm L: 1.30ns= 5.04c T: 0.15ns= 0.576c 1049 AVX :VMULSD+VADDSD xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.15ns= 0.575c 1050 SSE2 :MULPD+ADDPD xmm, xmm L: 1.30ns= 5.04c T: 0.14ns= 0.548c 1051 AVX :VMULPD+VADDPD xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.14ns= 0.542c 1052 SSE2 :MULSD xm1,xm1 ADDSD xm2,xm2 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1053 AVX :VMULSD xmm1.. VADDSD xmm2.. L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1054 SSE2 :MULPD xm1,xm1 ADDPD xm2,xm2 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1055 AVX :VMULPD xmm1.. VADDPD xmm2.. L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1056 SSE2 :MAXSD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1057 AVX :VMAXSD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1058 SSE2 :MAXPD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1059 AVX :VMAXPD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1060 SSE2 :MINSD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1061 AVX :VMINSD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1062 SSE2 :MINPD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1063 AVX :VMINPD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1064 SSE2 :ANDNPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1065 SSE2 :ANDNPD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1066 AVX :VANDNPD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1067 AVX :VANDNPD xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1068 SSE2 :ANDPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1069 SSE2 :ANDPD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1070 AVX :VANDPD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1071 AVX :VANDPD xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1072 SSE2 :ORPD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1073 SSE2 :ORPD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1074 AVX :VORPD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1075 AVX :VORPD xmm1, xmm1, xmm2 L: 0.27ns= 1.03c T: 0.06ns= 0.252c 1076 SSE2 :XORPD xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1077 SSE2 :XORPD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1078 AVX :VXORPD xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1079 AVX :VXORPD xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1080 SSE2 :DIVSD xmm, xmm L: 3.38ns= 13.09c T: 1.04ns= 4.029c 1081 SSE2 :DIVSD (0.0/x) L: 3.38ns= 13.09c T: 1.04ns= 4.029c 1082 SSE2 :DIVSD (x/1.0) L: 3.38ns= 13.09c T: 1.04ns= 4.029c 1083 SSE2 :DIVSD (x/2.0) L: 3.24ns= 12.58c T: 1.04ns= 4.029c 1084 SSE2 :DIVSD (x/0.5) L: 3.24ns= 12.58c T: 1.04ns= 4.029c 1085 AVX :VDIVSD xmm, xmm, xmm L: 3.38ns= 13.09c T: 1.04ns= 4.029c 1086 AVX :VDIVSD (0.0/x) L: 3.38ns= 13.09c T: 1.04ns= 4.029c 1087 AVX :VDIVSD (x/1.0) L: 3.38ns= 13.09c T: 1.04ns= 4.029c 1088 AVX :VDIVSD (x/2.0) L: 3.25ns= 12.59c T: 1.04ns= 4.029c 1089 AVX :VDIVSD (x/0.5) L: 3.25ns= 12.59c T: 1.04ns= 4.029c 1090 SSE2 :DIVPD xmm, xmm L: 5.45ns= 21.15c T: 2.08ns= 8.059c 1091 SSE2 :DIVPD (0.0/x) L: 5.45ns= 21.15c T: 2.08ns= 8.059c 1092 SSE2 :DIVPD (x/1.0) L: 5.45ns= 21.15c T: 2.08ns= 8.060c 1093 SSE2 :DIVPD (x/2.0) L: 4.22ns= 16.37c T: 2.08ns= 8.060c 1094 SSE2 :DIVPD (x/0.5) L: 4.22ns= 16.38c T: 2.08ns= 8.059c 1095 AVX :VDIVPD xmm, xmm, xmm L: 5.45ns= 21.15c T: 2.08ns= 8.059c 1096 AVX :VDIVPD (0.0/x) L: 5.45ns= 21.15c T: 2.08ns= 8.060c 1097 AVX :VDIVPD (x/1.0) L: 5.45ns= 21.15c T: 2.08ns= 8.058c 1098 AVX :VDIVPD (x/2.0) L: 4.21ns= 16.33c T: 2.08ns= 8.060c 1099 AVX :VDIVPD (x/0.5) L: 4.21ns= 16.33c T: 2.08ns= 8.060c 1100 SSE2 :SQRTSD xmm, xmm L: 4.41ns= 17.12c T: 1.56ns= 6.045c 1101 SSE2 :SQRTSD (0.0) L: 4.41ns= 17.12c T: 1.56ns= 6.045c 1102 SSE2 :SQRTSD (1.0) L: 4.41ns= 17.12c T: 1.56ns= 6.044c 1103 AVX :VSQRTSD xmm, xmm, xmm L: 4.41ns= 17.12c T: 1.56ns= 6.044c 1104 AVX :VSQRTSD (0.0) L: 4.41ns= 17.12c T: 1.56ns= 6.044c 1105 AVX :VSQRTSD (1.0) L: 4.41ns= 17.12c T: 1.56ns= 6.045c 1106 SSE2 :SQRTPD xmm, xmm L: 7.53ns= 29.21c T: 3.12ns= 12.092c 1107 SSE2 :SQRTPD (0.0) L: 7.53ns= 29.21c T: 3.12ns= 12.092c 1108 SSE2 :SQRTPD (1.0) L: 7.53ns= 29.21c T: 3.12ns= 12.089c 1109 AVX :VSQRTPD xmm, xmm L: 7.53ns= 29.21c T: 3.12ns= 12.090c 1110 AVX :VSQRTPD (0.0) L: 7.53ns= 29.21c T: 3.12ns= 12.088c 1111 AVX :VSQRTPD (1.0) L: 7.53ns= 29.21c T: 3.12ns= 12.089c 1112 SSE2 :CVTPI2PD xmm, mm L: [diff. reg. set] T: 0.13ns= 0.504c 1113 SSE2 :CVTPD2PI mm, xmm L: [diff. reg. set] T: 0.13ns= 0.504c 1114 SSE2 :CVTPD2PI + CVTPI2PD L: 1.56ns= 6.04c T: 0.26ns= 1.026c 1115 SSE2 :CVTTPD2PI mm, xmm L: [diff. reg. set] T: 0.13ns= 0.504c 1116 SSE2 :CVTTPD2PI + CVTPI2PD L: 1.56ns= 6.04c T: 0.26ns= 1.022c 1117 SSE2 :CVTSI2SD xmm, r32 L: [diff. reg. set] T: 0.14ns= 0.546c 1118 SSE2 :CVTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.840c 1119 SSE2 :CVTSD2SI + CVTSI2SD r32 L: 3.12ns= 12.08c T: 0.43ns= 1.679c 1120 SSE2 :CVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1121 SSE2 :CVTTSD2SI + CVTSI2SD r32 L: 3.12ns= 12.08c T: 0.43ns= 1.679c 1122 AVX :VCVTSI2SD xmm, xmm, r32 L: [diff. reg. set] T: 0.14ns= 0.546c 1123 AVX :VCVTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1124 AVX :VCVTSD2SI + VCVTSI2SD r32 L: 3.12ns= 12.09c T: 0.44ns= 1.695c 1125 AVX :VCVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1126 AVX :VCVTTSD2SI + VCVTSI2SD r32 L: 3.12ns= 12.09c T: 0.44ns= 1.697c 1127 AMD64 :CVTSI2SD xmm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 1128 AMD64 :CVTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1129 AMD64 :CVTSD2SI + CVTSI2SD r64 L: 3.12ns= 12.08c T: 0.43ns= 1.680c 1130 AMD64 :CVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1131 AMD64 :CVTTSD2SI + CVTSI2SD r64 L: 3.12ns= 12.08c T: 0.44ns= 1.697c 1132 AVX_X64 :VCVTSI2SD xmm, xmm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 1133 AVX_X64 :VCVTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1134 AVX_X64 :VCVTSD2SI + VCVTSI2SD r64 L: 3.12ns= 12.09c T: 0.44ns= 1.696c 1135 AVX_X64 :VCVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1136 AVX_X64 :VCVTTSD2SI + VCVTSI2SD r64 L: 3.12ns= 12.09c T: 0.44ns= 1.696c 1137 SSE2 :CVTDQ2PD xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1138 SSE2 :CVTPD2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1139 SSE2 :CVTPD2DQ + CVTDQ2PD L: 1.56ns= 6.04c T: 0.26ns= 1.008c 1140 SSE2 :CVTTPD2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1141 SSE2 :CVTTPD2DQ + CVTDQ2PD L: 1.56ns= 6.04c T: 0.26ns= 1.008c 1142 AVX :VCVTDQ2PD xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1143 AVX :VCVTPD2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1144 AVX :VCVTPD2DQ + VCVTDQ2PD L: 1.56ns= 6.04c T: 0.26ns= 1.026c 1145 AVX :VCVTTPD2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1146 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1147 SSE2 :CVTDQ2PS xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1148 SSE2 :CVTPS2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1149 SSE2 :CVTPS2DQ + CVTDQ2PS L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1150 SSE2 :CVTTPS2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1151 SSE2 :CVTTPS2DQ + CVTDQ2PS L: 1.56ns= 6.04c T: 0.27ns= 1.034c 1152 AVX :VCVTDQ2PS xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1153 AVX :VCVTPS2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1154 AVX :VCVTPS2DQ + VCVTDQ2PS L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1155 AVX :VCVTTPS2DQ xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1156 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1157 SSE2 :CVTPS2PD xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1158 SSE2 :CVTPD2PS xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1159 SSE2 :CVTPD2PS + CVTPS2PD L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1160 SSE2 :CVTSS2SD xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1161 SSE2 :CVTSD2SS xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1162 SSE2 :CVTSD2SS + CVTSS2SD L: 1.56ns= 6.04c T: 0.26ns= 1.026c 1163 AVX :VCVTPS2PD xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1164 AVX :VCVTPD2PS xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1165 AVX :VCVTPD2PS + VCVTPS2PD L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1166 AVX :VCVTSS2SD xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1167 AVX :VCVTSD2SS xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1168 AVX :VCVTSD2SS + VCVTSS2SD L: 1.56ns= 6.04c T: 0.26ns= 1.011c 1169 SSE2 :MOVD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1170 SSE2 :MOVD xmm, r32 L: [diff. reg. set] T: 0.14ns= 0.546c 1171 SSE2 :MOVD r32, xmm+MOVD xmm, r32 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1172 AVX :VMOVD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1173 AVX :VMOVD xmm, r32 L: [diff. reg. set] T: 0.14ns= 0.546c 1174 AVX :VMOVD r32,xmm+VMOVD xmm,r32 L: 2.86ns= 11.08c T: 0.44ns= 1.695c 1175 AMD64 :MOVQ r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1176 AMD64 :MOVQ xmm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 1177 AMD64 :MOVQ r64, xmm+MOVD xmm, r64 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1178 AVX_X64 :VMOVQ r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1179 AVX_X64 :VMOVQ xmm, r64 L: [diff. reg. set] T: 0.14ns= 0.546c 1180 AVX_X64 :VMOVQ r64,xmm+VMOVD xmm,r64 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1181 SSE2 :MOVD xmm, [m32] L: [memory dep.] T: 0.09ns= 0.336c 1182 SSE2 :MOVD [m32], xmm L: [memory dep.] T: 0.13ns= 0.504c 1183 SSE2 :MOVD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.669c 1184 AVX :VMOVD xmm, [m32] L: [memory dep.] T: 0.09ns= 0.336c 1185 AVX :VMOVD [m32], xmm L: [memory dep.] T: 0.13ns= 0.504c 1186 AVX :VMOVD LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1187 SSE2 :MOVQ xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 1188 SSE2 :MOVQ [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 1189 SSE2 :MOVQ LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.663c 1190 AVX :VMOVQ xmm, [m64] L: [memory dep.] T: 0.09ns= 0.336c 1191 AVX :VMOVQ [m64], xmm L: [memory dep.] T: 0.13ns= 0.504c 1192 AVX :VMOVQ LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1193 SSE2 :MOVDQ2Q mm, xmm L: [diff. reg. set] T: 0.06ns= 0.252c 1194 SSE2 :MOVQ2DQ xmm, mm L: [diff. reg. set] T: 0.06ns= 0.252c 1195 SSE2 :MOVDQ2Q + MOVQ2DQ xmm, mm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1196 SSE2 :MOVDQA xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1197 SSE2 :MOVDQA xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 1198 SSE2 :MOVDQA [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 1199 SSE2 :MOVDQA LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1200 AVX :VMOVDQA xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1201 AVX :VMOVDQA xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 1202 AVX :VMOVDQA [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 1203 AVX :VMOVDQA LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1204 SSE2 :MOVDQU xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1205 SSE2 :MOVDQU xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 1206 SSE2 :MOVDQU [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 1207 SSE2 :MOVDQU aligned LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1208 SSE2 :MOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 1209 SSE2 :MOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.26ns= 1.007c 1210 SSE2 :MOVDQU unaligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1211 AVX :VMOVDQU xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1212 AVX :VMOVDQU xmm, [m128] L: [memory dep.] T: 0.09ns= 0.336c 1213 AVX :VMOVDQU [m128], xmm L: [memory dep.] T: 0.13ns= 0.504c 1214 AVX :VMOVDQU aligned LS pair L: 1.82ns= 7.05c T: 0.17ns= 0.672c 1215 AVX :VMOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 1216 AVX :VMOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.26ns= 1.007c 1217 AVX :VMOVDQU unaligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1218 SSE4.1 :MOVNTDQA xmm, [m128] L: [memory dep.] T: 0.34ns= 0.336c 1219 SSE2 :MOVNTDQ [m128], xmm L: [memory dep.] T: 0.50ns= 0.504c 1220 SSE4.1 :MOVNTDQA + MOVNTDQ xmm LS pair L: 178.48ns= 692.19c T: 692.19ns= 692.193c 1221 AVX :VMOVNTDQA xmm, [m128] L: [memory dep.] T: 0.34ns= 0.336c 1222 AVX :VMOVNTDQ [m128], xmm L: [memory dep.] T: 0.50ns= 0.504c 1223 AVX :VMOVNTDQA + VMOVNTDQ xmm LS pair L: 188.24ns= 730.07c T: 730.07ns= 730.072c 1224 SSE2 :PMOVMSKB r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1225 AMD64 :PMOVMSKB r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1226 AVX :VPMOVMSKB r32, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1227 AVX_X64 :VPMOVMSKB r64, xmm L: [diff. reg. set] T: 0.22ns= 0.839c 1228 SSE2 :MASKMOVDQU xmm, xmm L: [memory dep.] T: 16.11ns= 16.114c 1229 AVX :VMASKMOVDQU xmm, xmm L: [memory dep.] T: 16.11ns= 16.114c 1230 SSE2 :PADDB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1231 AVX :VPADDB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1232 SSE2 :PADDW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1233 AVX :VPADDW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1234 SSE2 :PADDD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1235 AVX :VPADDD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1236 SSE2 :PADDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1237 AVX :VPADDQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1238 SSE2 :PADDSB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1239 AVX :VPADDSB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1240 SSE2 :PADDSW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1241 AVX :VPADDSW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1242 SSE2 :PADDUSB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1243 AVX :VPADDUSB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1244 SSE2 :PADDUSW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1245 AVX :VPADDUSW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1246 SSE2 :PSUBB xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1247 SSE2 :PSUBB xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1248 AVX :VPSUBB xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1249 AVX :VPSUBB xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1250 SSE2 :PSUBW xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1251 SSE2 :PSUBW xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1252 AVX :VPSUBW xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1253 AVX :VPSUBW xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1254 SSE2 :PSUBD xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1255 SSE2 :PSUBD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1256 AVX :VPSUBD xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1257 AVX :VPSUBD xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1258 SSE2 :PSUBQ xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1259 SSE2 :PSUBQ xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1260 AVX :VPSUBQ xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1261 AVX :VPSUBQ xmm1, xmm1, xmm2 L: 0.27ns= 1.03c T: 0.06ns= 0.252c 1262 SSE2 :PSUBSB xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1263 SSE2 :PSUBSB xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1264 AVX :VPSUBSB xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1265 AVX :VPSUBSB xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1266 SSE2 :PSUBSW xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1267 SSE2 :PSUBSW xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1268 AVX :VPSUBSW xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.125c 1269 AVX :VPSUBSW xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1270 SSE2 :PSUBUSB xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1271 SSE2 :PSUBUSB xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1272 AVX :VPSUBUSB xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1273 AVX :VPSUBUSB xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1274 SSE2 :PSUBUSW xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1275 SSE2 :PSUBUSW xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1276 AVX :VPSUBUSW xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1277 AVX :VPSUBUSW xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1278 SSE2 :PCMPEQB xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1279 SSE2 :PCMPEQB xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1280 AVX :VPCMPEQB xmm, xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1281 AVX :VPCMPEQB xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1282 SSE2 :PCMPEQW xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1283 SSE2 :PCMPEQW xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1284 AVX :VPCMPEQW xmm, xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1285 AVX :VPCMPEQW xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1286 SSE2 :PCMPEQD xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1287 SSE2 :PCMPEQD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1288 AVX :VPCMPEQD xmm, xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1289 AVX :VPCMPEQD xmm1, xmm1, xmm2 L: 0.27ns= 1.03c T: 0.06ns= 0.252c 1290 SSE4.1 :PCMPEQQ xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1291 SSE4.1 :PCMPEQQ xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1292 AVX :VPCMPEQQ xmm, xmm, xmm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1293 AVX :VPCMPEQQ xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1294 SSE2 :PCMPGTB xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1295 SSE2 :PCMPGTB xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1296 AVX :VPCMPGTB xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1297 AVX :VPCMPGTB xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1298 SSE2 :PCMPGTW xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1299 SSE2 :PCMPGTW xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1300 AVX :VPCMPGTW xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1301 AVX :VPCMPGTW xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1302 SSE2 :PCMPGTD xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1303 SSE2 :PCMPGTD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1304 AVX :VPCMPGTD xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1305 AVX :VPCMPGTD xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1306 SSE4.2 :PCMPGTQ xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.128c 1307 SSE4.2 :PCMPGTQ xmm1, xmm2 L: 1.04ns= 4.03c T: 0.26ns= 1.007c 1308 AVX :VPCMPGTQ xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1309 AVX :VPCMPGTQ xmm1, xmm1, xmm2 L: 1.04ns= 4.03c T: 0.26ns= 1.007c 1310 SSE2 :PAND xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1311 SSE2 :PAND xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1312 AVX :VPAND xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1313 AVX :VPAND xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1314 SSE2 :PANDN xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1315 SSE2 :PANDN xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1316 AVX :VPANDN xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1317 AVX :VPANDN xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1318 SSE2 :POR xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1319 SSE2 :POR xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1320 AVX :VPOR xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1321 AVX :VPOR xmm1, xmm1, xmm2 L: 0.25ns= 0.99c T: 0.06ns= 0.252c 1322 SSE2 :PXOR xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1323 SSE2 :PXOR xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1324 AVX :VPXOR xmm, xmm, xmm L: 0.03ns= 0.13c T: 0.03ns= 0.126c 1325 AVX :VPXOR xmm1, xmm1, xmm2 L: 0.27ns= 1.03c T: 0.06ns= 0.252c 1326 SSE2 :PMULHW xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1327 AVX :VPMULHW xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1328 SSE2 :PMULHUW xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1329 AVX :VPMULHUW xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1330 SSSE3 :PMULHRSW xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1331 AVX :VPMULHRSW xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1332 SSE2 :PMULLW xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1333 AVX :VPMULLW xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1334 SSE4.1 :PMULLD xmm, xmm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1335 AVX :VPMULLD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1336 SSE4.1 :PMULDQ xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1337 AVX :VPMULDQ xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1338 SSE2 :PMULUDQ xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1339 AVX :VPMULUDQ xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1340 SSSE3 :PMADDUBSW xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1341 AVX :VPMADDUBSW xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1342 SSE2 :PMADDWD xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1343 AVX :VPMADDWD xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1344 SSE2 :PSLLW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1345 AVX :VPSLLW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1346 SSE2 :PSLLW xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1347 AVX :VPSLLW xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1348 SSE2 :PSLLD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1349 AVX :VPSLLD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1350 SSE2 :PSLLD xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1351 AVX :VPSLLD xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1352 SSE2 :PSLLQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1353 AVX :VPSLLQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1354 SSE2 :PSLLQ xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1355 AVX :VPSLLQ xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1356 SSE2 :PSLLDQ xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1357 AVX :VPSLLDQ xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1358 SSE2 :PSRAW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1359 AVX :VPSRAW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1360 SSE2 :PSRAW xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1361 AVX :VPSRAW xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1362 SSE2 :PSRAD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1363 AVX :VPSRAD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1364 SSE2 :PSRAD xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1365 AVX :VPSRAD xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1366 SSE2 :PSRLW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1367 AVX :VPSRLW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1368 SSE2 :PSRLW xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1369 AVX :VPSRLW xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1370 SSE2 :PSRLD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1371 AVX :VPSRLD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1372 SSE2 :PSRLD xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1373 AVX :VPSRLD xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1374 SSE2 :PSRLQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1375 AVX :VPSRLQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1376 SSE2 :PSRLQ xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1377 AVX :VPSRLQ xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1378 SSE2 :PSRLDQ xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1379 AVX :VPSRLDQ xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1380 SSE2 :PUNPCKHBW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1381 AVX :VPUNPCKHBW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1382 SSE2 :PUNPCKHWD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1383 AVX :VPUNPCKHWD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1384 SSE2 :PUNPCKHDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1385 AVX :VPUNPCKHDQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1386 SSE2 :PUNPCKHQDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1387 AVX :VPUNPCKHQDQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1388 SSE2 :PUNPCKLBW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1389 AVX :VPUNPCKLBW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1390 SSE2 :PUNPCKLWD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1391 AVX :VPUNPCKLWD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1392 SSE2 :PUNPCKLDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1393 AVX :VPUNPCKLDQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1394 SSE2 :PUNPCKLQDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1395 AVX :VPUNPCKLQDQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1396 SSE2 :PACKSSWB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1397 AVX :VPACKSSWB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1398 SSE2 :PACKUSWB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1399 AVX :VPACKUSWB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1400 SSE2 :PACKSSDW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1401 AVX :VPACKSSDW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1402 SSE4.1 :PACKUSDW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1403 AVX :VPACKUSDW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1404 SSE2 :PAVGB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1405 AVX :VPAVGB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1406 SSE2 :PAVGW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1407 AVX :VPAVGW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1408 SSE4.1 :PEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1409 SSE4.1 :PINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1410 SSE4.1 :PEXTRB + PINSRB r32 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1411 AVX :VPEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1412 AVX :VPINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1413 AVX :VPEXTRB + VPINSRB r32 L: 2.86ns= 11.08c T: 0.43ns= 1.685c 1414 SSE41_X64 :PEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1415 SSE41_X64 :PEXTRB r64 + PINSRB r32 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1416 AVX_X64 :VPEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1417 AVX_X64 :VPEXTRB r64 + VPINSRB r32 L: 2.86ns= 11.08c T: 0.44ns= 1.696c 1418 SSE2 :PEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1419 SSE2 :PINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1420 SSE2 :PEXTRW + PINSRW r32 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1421 AVX :VPEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1422 AVX :VPINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1423 AVX :VPEXTRW + VPINSRW r32 L: 2.86ns= 11.08c T: 0.43ns= 1.678c 1424 AMD64 :PEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1425 AMD64 :PEXTRW r64 + PINSRW r32 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1426 AVX_X64 :VPEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1427 AVX_X64 :VPEXTRW r64 + VPINSRW r32 L: 2.86ns= 11.08c T: 0.43ns= 1.686c 1428 SSE4.1 :PEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.840c 1429 SSE4.1 :PINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1430 SSE4.1 :PEXTRD + PINSRD r32 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1431 AVX :VPEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.840c 1432 AVX :VPINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1433 AVX :VPEXTRD + VPINSRD r32 L: 2.86ns= 11.08c T: 0.43ns= 1.683c 1434 SSE41_X64 :PEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1435 SSE41_X64 :PINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1436 SSE41_X64 :PEXTRD + PINSRD r64 L: 2.86ns= 11.08c T: 0.43ns= 1.679c 1437 AVX_X64 :VPEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1438 AVX_X64 :VPINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.14ns= 0.546c 1439 AVX_X64 :VPEXTRQ + VPINSRQ r64 L: 2.86ns= 11.08c T: 0.44ns= 1.695c 1440 SSE4.1 :EXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1441 AVX :VEXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1442 SSE41_X64 :EXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1443 AVX_X64 :VEXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.839c 1444 SSE4.1 :INSERTPS xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1445 AVX :VINSERTPS xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1450 SSE2 :PMAXUB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1451 AVX :VPMAXUB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1452 SSE4.1 :PMAXSB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1453 AVX :VPMAXSB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1454 SSE4.1 :PMAXUW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1455 AVX :VPMAXUW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1456 SSE2 :PMAXSW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1457 AVX :VPMAXSW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1458 SSE4.1 :PMAXUD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1459 AVX :VPMAXUD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1460 SSE4.1 :PMAXSD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1461 AVX :VPMAXSD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1462 SSE2 :PMINUB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1463 AVX :VPMINUB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1464 SSE4.1 :PMINSB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1465 AVX :VPMINSB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1466 SSE4.1 :PMINUW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1467 AVX :VPMINUW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1468 SSE2 :PMINSW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1469 AVX :VPMINSW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1470 SSE4.1 :PMINUD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1471 AVX :VPMINUD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1472 SSE4.1 :PMINSD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1473 AVX :VPMINSD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1474 SSE2 :PSADBW xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1475 AVX :VPSADBW xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.06ns= 0.252c 1476 SSSE3 :PSHUFB xmm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1477 AVX :VPSHUFB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1478 SSE2 :PSHUFLW xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1479 AVX :VPSHUFLW xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1480 SSE2 :PSHUFHW xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1481 AVX :VPSHUFHW xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1482 SSE2 :PSHUFD xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1483 AVX :VPSHUFD xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1484 SSE3 :ADDSUBPS xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1485 AVX :VADDSUBPS xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1486 SSE3 :ADDSUBPD xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1487 AVX :VADDSUBPD xmm, xmm, xmm L: 0.52ns= 2.01c T: 0.06ns= 0.252c 1488 SSE3 :HADDPS xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.648c 1489 AVX :VHADDPS xmm, xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.649c 1490 SSE3 :HADDPD xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.648c 1491 AVX :VHADDPD xmm, xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.650c 1492 SSE3 :HSUBPS xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.648c 1493 AVX :VHSUBPS xmm, xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.649c 1494 SSE3 :HSUBPD xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.649c 1495 AVX :VHSUBPD xmm, xmm, xmm L: 2.08ns= 8.07c T: 0.68ns= 2.648c 1496 SSE3 :MOVSLDUP xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1497 AVX :VMOVSLDUP xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1498 SSE3 :MOVSHDUP xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1499 AVX :VMOVSHDUP xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1500 SSE3 :MOVDDUP xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1501 AVX :VMOVDDUP xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1502 SSE3 :LDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 1503 AVX :VLDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.11ns= 0.420c 1504 SSSE3 :PABSB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1505 AVX :VPABSB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1506 SSSE3 :PABSW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1507 AVX :VPABSW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1508 SSSE3 :PABSD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1509 AVX :VPABSD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1510 SSSE3 :PALIGNR xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1511 AVX :VPALIGNR xmm, xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1512 SSSE3 :PHADDW xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.606c 1513 AVX :VPHADDW xmm, xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.607c 1514 SSSE3 :PHADDD xmm, xmm L: 0.78ns= 3.03c T: 0.68ns= 2.638c 1515 AVX :VPHADDD xmm, xmm, xmm L: 0.78ns= 3.03c T: 0.67ns= 2.602c 1516 SSSE3 :PHADDSW xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.606c 1517 AVX :VPHADDSW xmm, xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.606c 1518 SSSE3 :PHSUBW xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.607c 1519 AVX :VPHSUBW xmm, xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.606c 1520 SSSE3 :PHSUBD xmm, xmm L: 0.78ns= 3.03c T: 0.68ns= 2.637c 1521 AVX :VPHSUBD xmm, xmm, xmm L: 0.78ns= 3.03c T: 0.67ns= 2.603c 1522 SSSE3 :PHSUBSW xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.608c 1523 AVX :VPHSUBSW xmm, xmm, xmm L: 1.09ns= 4.22c T: 0.67ns= 2.607c 1524 SSSE3 :PSIGNB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1525 AVX :VPSIGNB xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1526 SSSE3 :PSIGNW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1527 AVX :VPSIGNW xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1528 SSSE3 :PSIGND xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1529 AVX :VPSIGND xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1530 SSE4.1 :BLENDPS xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1531 AVX :VBLENDPS xmm, xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1532 SSE4.1 :BLENDVPS xmm, xmm, L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1533 AVX :VBLENDVPS xmm, xmm, xmm, xm L: 0.81ns= 3.15c T: 0.68ns= 2.631c 1534 SSE4.1 :BLENDPD xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1535 AVX :VBLENDPD xmm, xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1536 SSE4.1 :BLENDVPD xmm, xmm, L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1537 AVX :VBLENDVPD xmm, xmm, xmm, xm L: 0.81ns= 3.16c T: 0.68ns= 2.632c 1538 SSE4.1 :PBLENDW xmm, xmm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1539 AVX :VPBLENDW xmm, xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1540 SSE4.1 :PBLENDVB xmm, xmm, L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1541 AVX :VPBLENDVB xmm, xmm, xmm, xm L: 0.81ns= 3.15c T: 0.68ns= 2.634c 1542 SSE4.1 :DPPS xmm, xmm, imm8 L: 5.46ns= 21.16c T: 0.70ns= 2.720c 1543 AVX :VDPPS xmm, xmm, xmm, imm8 L: 5.46ns= 21.16c T: 0.70ns= 2.722c 1544 SSE4.1 :DPPD xmm, xmm, imm8 L: 3.64ns= 14.10c T: 0.68ns= 2.624c 1545 AVX :VDPPD xmm, xmm, xmm, imm8 L: 3.64ns= 14.10c T: 0.69ns= 2.666c 1546 SSE4.1 :MPSADBW xmm, xmm, imm8 L: 1.30ns= 5.04c T: 0.68ns= 2.634c 1547 AVX :VMPSADBW xmm, xmm, imm8 L: 1.30ns= 5.04c T: 0.68ns= 2.633c 1548 SSE4.1 :PHMINPOSUW xmm, xmm L: 1.04ns= 4.03c T: 0.26ns= 1.007c 1549 AVX :VPHMINPOSUW xmm, xmm L: 1.04ns= 4.03c T: 0.26ns= 1.007c 1550 SSE4.1 :PMOVSXBW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1551 AVX :VPMOVSXBW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1552 SSE4.1 :PMOVSXBD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1553 AVX :VPMOVSXBD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1554 SSE4.1 :PMOVSXBQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1555 AVX :VPMOVSXBQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1556 SSE4.1 :PMOVSXWD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1557 AVX :VPMOVSXWD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1558 SSE4.1 :PMOVSXWQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1559 AVX :VPMOVSXWQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1560 SSE4.1 :PMOVSXDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1561 AVX :VPMOVSXDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1562 SSE4.1 :PMOVZXBW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1563 AVX :VPMOVZXBW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1564 SSE4.1 :PMOVZXBD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1565 AVX :VPMOVZXBD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1566 SSE4.1 :PMOVZXBQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1567 AVX :VPMOVZXBQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1568 SSE4.1 :PMOVZXWD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1569 AVX :VPMOVZXWD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1570 SSE4.1 :PMOVZXWQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1571 AVX :VPMOVZXWQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1572 SSE4.1 :PMOVZXDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1573 AVX :VPMOVZXDQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1574 SSE4.1 :PTEST xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1575 AVX :VPTEST xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1576 AVX :VPTESTPS xmm, xmm L: [no true dep.] T: 0.22ns= 0.839c 1577 AVX :VPTESTPD xmm, xmm L: [no true dep.] T: 0.22ns= 0.840c 1578 SSE4.1 :ROUNDSS xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1579 AVX :VROUNDSS xmm, xmm, xmm, im8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1580 SSE4.1 :ROUNDPS xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1581 AVX :VROUNDPS xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1582 SSE4.1 :ROUNDSD xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1583 AVX :VROUNDSD xmm, xmm, xmm, im8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1584 SSE4.1 :ROUNDPD xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1585 AVX :VROUNDPD xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1586 AVX :VBROADCASTSS xmm, m32 L: [memory dep.] T: 0.13ns= 0.504c 1587 SSE4.2 :PCMPESTRI xmm, xmm, imm8 L: 3.30ns= 12.79c T: 3.28ns= 12.715c 1588 AVX :VPCMPESTRI xmm, xmm, imm8 L: 3.27ns= 12.69c T: 3.34ns= 12.948c 1589 SSE4.2 :PCMPESTRM xmm, xmm, imm8 L: 2.81ns= 10.90c T: 2.72ns= 10.556c 1590 AVX :VPCMPESTRM xmm, xmm, imm8 L: 2.78ns= 10.79c T: 2.86ns= 11.108c 1591 SSE4.2 :PCMPISTRI xmm, xmm, imm8 L: 2.75ns= 10.67c T: 2.99ns= 11.600c 1592 AVX :VPCMPISTRI xmm, xmm, imm8 L: 2.75ns= 10.66c T: 2.98ns= 11.555c 1593 SSE4.2 :PCMPISTRM xmm, xmm, imm8 L: 2.23ns= 8.65c T: 2.51ns= 9.719c 1594 AVX :VPCMPISTRM xmm, xmm, imm8 L: 2.23ns= 8.64c T: 2.46ns= 9.533c 1595 CLMUL :PCLMULQDQ xmm, xmm, imm8 L: 1.04ns= 4.03c T: 0.26ns= 1.007c 1596 AVX_CLMUL :VPCLMULQDQ xmm,xmm,xmm,im8 L: 1.04ns= 4.03c T: 0.26ns= 1.007c 1597 AESNI :AESENC xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1598 AVX_AESNI :VAESENC xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1599 AESNI :AESENCLAST xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1600 AVX_AESNI :VAESENCLAST xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1601 AESNI :AESDEC xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1602 AVX_AESNI :VAESDEC xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1603 AESNI :AESDECLAST xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1604 AVX_AESNI :VAESDECLAST xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1605 AESNI :AESIMC xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1606 AVX_AESNI :VAESIMC xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1607 AESNI :AESKEYGEN xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1608 AVX_AESNI :VAESKEYGEN xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1610 FMA3 :VFMADD132SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1611 FMA3 :VFMADD213SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1612 FMA3 :VFMADD231SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1614 FMA3 :VFMADD132PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1615 FMA3 :VFMADD213PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1616 FMA3 :VFMADD231PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.250c 1618 FMA3 :VFMSUB132SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.253c 1619 FMA3 :VFMSUB213SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1620 FMA3 :VFMSUB231SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1622 FMA3 :VFMSUB132PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1623 FMA3 :VFMSUB213PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1624 FMA3 :VFMSUB231PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1626 FMA3 :VFNMADD132SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1627 FMA3 :VFNMADD213SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1628 FMA3 :VFNMADD231SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1630 FMA3 :VFNMADD132PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.256c 1631 FMA3 :VFNMADD213PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1632 FMA3 :VFNMADD231PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1634 FMA3 :VFNMSUB132SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1635 FMA3 :VFNMSUB213SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1636 FMA3 :VFNMSUB231SS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.272c 1638 FMA3 :VFNMSUB132PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1639 FMA3 :VFNMSUB213PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1640 FMA3 :VFNMSUB231PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.253c 1642 FMA3 :VFMADDSUB132PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1643 FMA3 :VFMADDSUB213PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1644 FMA3 :VFMADDSUB231PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1646 FMA3 :VFMSUBADD132PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1647 FMA3 :VFMSUBADD213PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1648 FMA3 :VFMSUBADD231PS xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1650 FMA3 :VFMADD132SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1651 FMA3 :VFMADD213SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1652 FMA3 :VFMADD231SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1654 FMA3 :VFMADD132PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1655 FMA3 :VFMADD213PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.253c 1656 FMA3 :VFMADD231PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1658 FMA3 :VFMSUB132SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1659 FMA3 :VFMSUB213SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1660 FMA3 :VFMSUB231SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1662 FMA3 :VFMSUB132PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1663 FMA3 :VFMSUB213PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1664 FMA3 :VFMSUB231PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1666 FMA3 :VFNMADD132SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1667 FMA3 :VFNMADD213SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.250c 1668 FMA3 :VFNMADD231SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1670 FMA3 :VFNMADD132PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1671 FMA3 :VFNMADD213PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1672 FMA3 :VFNMADD231PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1674 FMA3 :VFNMSUB132SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1675 FMA3 :VFNMSUB213SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1676 FMA3 :VFNMSUB231SD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1678 FMA3 :VFNMSUB132PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.253c 1679 FMA3 :VFNMSUB213PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1680 FMA3 :VFNMSUB231PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1682 FMA3 :VFMADDSUB132PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1683 FMA3 :VFMADDSUB213PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.07ns= 0.270c 1684 FMA3 :VFMADDSUB231PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1686 FMA3 :VFMSUBADD132PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1687 FMA3 :VFMSUBADD213PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1688 FMA3 :VFMSUBADD231PD xmm,xmm,xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 1768 F16C :VCVTPS2PH xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1769 F16C :VCVTPH2PS xmm, xmm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1770 AVX :VMOVAPS ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1771 AVX :VMOVAPS ymm, [m256] L: [memory dep.] T: 0.17ns= 0.672c 1772 AVX :VMOVAPS [m256], ymm L: [memory dep.] T: 0.26ns= 1.007c 1773 AVX :VMOVAPS LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1774 AVX :VMOVUPS ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1775 AVX :VMOVUPS ymm, [m256] L: [memory dep.] T: 0.17ns= 0.672c 1776 AVX :VMOVUPS [m256], ymm L: [memory dep.] T: 0.26ns= 1.007c 1777 AVX :VMOVUPS aligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1778 AVX :VMOVUPS ymm, [m256 + 4] L: [memory dep.] T: 0.22ns= 0.839c 1779 AVX :VMOVUPS [m256 + 4], ymm L: [memory dep.] T: 0.52ns= 2.014c 1780 AVX :VMOVUPS unaligned LS pair L: 1.82ns= 7.05c T: 0.52ns= 2.015c 1781 AVX :VMOVSLDUP ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1782 AVX :VMOVSHDUP ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1783 AVX :VMOVNTPS [m256], ymm L: [memory dep.] T: 1.01ns= 1.007c 1784 AVX :VMOVMSKPS r32, ymm L: [diff. reg. set] T: 0.22ns= 0.839c 1785 AVX :VMASKMOVPS ymm,ymm,[m256+4] L: [memory dep.] T: 0.22ns= 0.840c 1786 AVX :VMASKMOVPS [m256+4],ymm,ymm L: [memory dep.] T: 0.65ns= 2.518c 1787 AVX :VMASKMOVPS unaligned LS pair L: 5.19ns= 20.14c T: 0.65ns= 2.518c 1788 AVX :VUNPCKLPS ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1789 AVX :VUNPCKHPS ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1790 AVX :VSHUFPS ymm, ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1791 AVX :VPERMILPS ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1792 AVX :VPERMILPS ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1793 AVX :VCMPPS ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1794 AVX :VADDSUBPS ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1795 AVX :VHSUBPS ymm, ymm, ymm L: 2.11ns= 8.18c T: 0.69ns= 2.678c 1796 AVX :VHADDPS ymm, ymm, ymm L: 2.11ns= 8.18c T: 0.69ns= 2.679c 1797 AVX :VSUBPS ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1798 AVX :VADDPS ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1799 AVX :VMULPS ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1800 AVX :VMULPS+VADDPS ymm, ymm, ymm L: 1.30ns= 5.04c T: 0.26ns= 1.021c 1801 AVX :VMULPS ymm1.. VADDPS ymm2.. L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1802 AVX :VMAXPS ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1803 AVX :VMINPS ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1804 AVX :VANDNPS ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1805 AVX :VANDNPS ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 1806 AVX :VANDPS ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1807 AVX :VANDPS ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 1808 AVX :VORPS ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1809 AVX :VORPS ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 1810 AVX :VXORPS ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1811 AVX :VXORPS ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 1812 AVX :VDIVPS ymm, ymm, ymm L: 3.90ns= 15.11c T: 2.60ns= 10.075c 1813 AVX :VDIVPS (0.0f/x) L: 3.90ns= 15.11c T: 2.60ns= 10.075c 1814 AVX :VDIVPS (x/1.0f) L: 3.90ns= 15.11c T: 2.60ns= 10.075c 1815 AVX :VDIVPS (x/2.0f) L: 3.62ns= 14.04c T: 2.60ns= 10.073c 1816 AVX :VDIVPS (x/0.5f) L: 3.62ns= 14.04c T: 2.60ns= 10.075c 1817 AVX :VSQRTPS ymm, ymm L: 4.41ns= 17.12c T: 3.12ns= 12.088c 1818 AVX :VSQRTPS (0.0f) L: 4.41ns= 17.12c T: 3.12ns= 12.089c 1819 AVX :VSQRTPS (1.0f) L: 4.41ns= 17.12c T: 3.12ns= 12.089c 1820 AVX :VRCPPS ymm, ymm, ymm L: 1.30ns= 5.04c T: 0.52ns= 2.014c 1821 AVX :VRSQRTPS ymm, ymm, ymm L: 1.30ns= 5.04c T: 0.52ns= 2.015c 1822 AVX :VBLENDPS ymm, ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1823 AVX :VBLENDVPS ymm, ymm, ymm, ym L: 0.93ns= 3.59c T: 0.66ns= 2.566c 1824 AVX :VDPPS ymm, ymm, ymm, imm8 L: 5.47ns= 21.23c T: 1.32ns= 5.114c 1825 AVX :VPTESTPS ymm, ymm L: [no true dep.] T: 0.17ns= 0.644c 1826 AVX :VROUNDPS ymm, ymm, imm8 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1827 AVX :VMOVAPD ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1828 AVX :VMOVAPD ymm, [m256] L: [memory dep.] T: 0.17ns= 0.672c 1829 AVX :VMOVAPD [m256], ymm L: [memory dep.] T: 0.26ns= 1.007c 1830 AVX :VMOVAPD LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1831 AVX :VMOVUPD ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1832 AVX :VMOVUPD ymm, [m256] L: [memory dep.] T: 0.17ns= 0.672c 1833 AVX :VMOVUPD [m256], ymm L: [memory dep.] T: 0.26ns= 1.007c 1834 AVX :VMOVUPD aligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1835 AVX :VMOVUPD ymm, [m256 + 4] L: [memory dep.] T: 0.22ns= 0.840c 1836 AVX :VMOVUPD [m256 + 4], ymm L: [memory dep.] T: 0.52ns= 2.014c 1837 AVX :VMOVUPD unaligned LS pair L: 1.82ns= 7.05c T: 0.52ns= 2.014c 1838 AVX :VMOVDDUP ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1839 AVX :VMOVNTPD [m256], ymm L: [memory dep.] T: 1.01ns= 1.007c 1840 AVX :VMOVMSKPD r32, ymm L: [diff. reg. set] T: 0.22ns= 0.839c 1841 AVX :VMASKMOVPD ymm,ymm,[m256+4] L: [memory dep.] T: 0.22ns= 0.839c 1842 AVX :VMASKMOVPD [m256+4],ymm,ymm L: [memory dep.] T: 0.65ns= 2.518c 1843 AVX :VMASKMOVPD unaligned LS pair L: 5.19ns= 20.14c T: 0.65ns= 2.518c 1844 AVX :VUNPCKLPD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1845 AVX :VUNPCKHPD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1846 AVX :VSHUFPD ymm, ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1847 AVX :VPERMILPD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1848 AVX :VPERMILPD ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1849 AVX :VCMPPD ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1850 AVX :VADDSUBPD ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1851 AVX :VHSUBPD ymm, ymm, ymm L: 2.11ns= 8.18c T: 0.69ns= 2.679c 1852 AVX :VHADDPD ymm, ymm, ymm L: 2.11ns= 8.18c T: 0.69ns= 2.678c 1853 AVX :VSUBPD ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1854 AVX :VADDPD ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1855 AVX :VMULPD ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1856 AVX :VMULPD+VADDPD ymm, ymm, ymm L: 1.30ns= 5.04c T: 0.26ns= 1.021c 1857 AVX :VMULPD ymm1.. VADDPD ymm2.. L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1858 AVX :VMAXPD ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1859 AVX :VMINPD ymm, ymm, ymm L: 0.52ns= 2.01c T: 0.13ns= 0.504c 1860 AVX :VANDNPD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1861 AVX :VANDNPD ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 1862 AVX :VANDPD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1863 AVX :VANDPD ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 1864 AVX :VORPD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1865 AVX :VORPD ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 1866 AVX :VXORPD ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1867 AVX :VXORPD ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 1868 AVX :VDIVPD ymm, ymm, ymm L: 5.45ns= 21.15c T: 4.16ns= 16.119c 1869 AVX :VDIVPD (0.0/x) L: 5.45ns= 21.15c T: 4.16ns= 16.121c 1870 AVX :VDIVPD (x/1.0) L: 5.45ns= 21.15c T: 4.16ns= 16.122c 1871 AVX :VDIVPD (x/2.0) L: 5.18ns= 20.08c T: 4.16ns= 16.123c 1872 AVX :VDIVPD (x/0.5) L: 5.18ns= 20.08c T: 4.16ns= 16.120c 1873 AVX :VSQRTPD ymm, ymm L: 7.53ns= 29.21c T: 6.24ns= 24.191c 1874 AVX :VSQRTPD (0.0) L: 7.53ns= 29.21c T: 6.24ns= 24.186c 1875 AVX :VSQRTPD (1.0) L: 7.53ns= 29.21c T: 6.24ns= 24.188c 1876 AVX :VBLENDPD ymm, ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1877 AVX :VBLENDVPD ymm, ymm, ymm, ym L: 0.93ns= 3.60c T: 0.66ns= 2.563c 1878 AVX :VCVTDQ2PD ymm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1879 AVX :VCVTPD2DQ xmm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1880 AVX :VCVTPD2DQ + VCVTDQ2PD L: 1.56ns= 6.04c T: 0.39ns= 1.511c 1881 AVX :VCVTTPD2DQ xmm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1882 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 1.56ns= 6.04c T: 0.39ns= 1.511c 1883 AVX :VCVTDQ2PS ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1884 AVX :VCVTPS2DQ ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1885 AVX :VCVTPS2DQ + VCVTDQ2PS L: 1.56ns= 6.04c T: 0.52ns= 2.015c 1886 AVX :VCVTTPS2DQ ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1887 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 1.56ns= 6.04c T: 0.52ns= 2.015c 1888 AVX :VCVTPS2PD ymm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1889 AVX :VCVTPD2PS xmm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1890 AVX :VCVTPD2PS + VCVTPS2PD L: 1.56ns= 6.04c T: 0.39ns= 1.511c 1891 AVX :VPTESTPD ymm, ymm L: [no true dep.] T: 0.17ns= 0.644c 1892 AVX :VROUNDPD ymm, ymm, imm8 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1893 AVX :VBROADCASTSS ymm, m32 L: [memory dep.] T: 0.09ns= 0.336c 1894 AVX :VBROADCASTSD ymm, m64 L: [memory dep.] T: 0.09ns= 0.336c 1895 AVX :VBROADCASTF128 ymm, m128 L: [memory dep.] T: 0.09ns= 0.336c 1896 AVX :VEXTRACTF128 xmm, ymm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 1897 AVX :VINSERTF128 ym, ym, xm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1898 AVX :VPERM2F128 ym, ym, ym, im8 L: 1.56ns= 6.04c T: 0.26ns= 1.007c 1899 AVX :VMOVDQA ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1900 AVX :VMOVDQA ymm, [m256] L: [memory dep.] T: 0.17ns= 0.672c 1901 AVX :VMOVDQA [m256], ymm L: [memory dep.] T: 0.26ns= 1.007c 1902 AVX :VMOVDQA LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1903 AVX :VMOVDQU ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1904 AVX :VMOVDQU ymm, [m256] L: [memory dep.] T: 0.17ns= 0.672c 1905 AVX :VMOVDQU [m256], ymm L: [memory dep.] T: 0.26ns= 1.007c 1906 AVX :VMOVDQU aligned LS pair L: 1.82ns= 7.05c T: 0.26ns= 1.007c 1907 AVX :VMOVDQU ymm, [m256 + 4] L: [memory dep.] T: 0.22ns= 0.839c 1908 AVX :VMOVDQU [m256 + 4], ymm L: [memory dep.] T: 0.52ns= 2.015c 1909 AVX :VMOVDQU unaligned LS pair L: 1.82ns= 7.05c T: 0.52ns= 2.014c 1910 AVX :VMOVNTDQ [m256], ymm L: [memory dep.] T: 1.01ns= 1.007c 1911 AVX :VLDDQU ymm, [m256 + 4] L: [memory dep.] T: 0.22ns= 0.839c 1912 AVX :VZEROUPPER L: [no true dep.] T: 0.26ns= 1.007c 1913 AVX :VZEROALL L: [no true dep.] T: 0.26ns= 1.007c 1915 FMA3 :VFMADD132PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1916 FMA3 :VFMADD213PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1917 FMA3 :VFMADD231PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1919 FMA3 :VFMSUB132PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1920 FMA3 :VFMSUB213PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1921 FMA3 :VFMSUB231PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1923 FMA3 :VFNMADD132PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1924 FMA3 :VFNMADD213PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1925 FMA3 :VFNMADD231PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1927 FMA3 :VFNMSUB132PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1928 FMA3 :VFNMSUB213PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1929 FMA3 :VFNMSUB231PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1931 FMA3 :VFMADDSUB132PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1932 FMA3 :VFMADDSUB213PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1933 FMA3 :VFMADDSUB231PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1935 FMA3 :VFMSUBADD132PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1936 FMA3 :VFMSUBADD213PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1937 FMA3 :VFMSUBADD231PS ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1939 FMA3 :VFMADD132PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1940 FMA3 :VFMADD213PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1941 FMA3 :VFMADD231PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1943 FMA3 :VFMSUB132PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1944 FMA3 :VFMSUB213PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1945 FMA3 :VFMSUB231PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1947 FMA3 :VFNMADD132PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1948 FMA3 :VFNMADD213PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1949 FMA3 :VFNMADD231PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1951 FMA3 :VFNMSUB132PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1952 FMA3 :VFNMSUB213PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1953 FMA3 :VFNMSUB231PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1955 FMA3 :VFMADDSUB132PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1956 FMA3 :VFMADDSUB213PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1957 FMA3 :VFMADDSUB231PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1959 FMA3 :VFMSUBADD132PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1960 FMA3 :VFMSUBADD213PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1961 FMA3 :VFMSUBADD231PD ymm,ymm,ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 1967 F16C :VCVTPS2PH + VCVTPH2PS L: 1.56ns= 6.04c T: 0.27ns= 1.033c 1968 F16C :VCVTPS2PH xmm, ymm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 1969 F16C :VCVTPH2PS ymm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 1970 F16C :VCVTPS2PH + VCVTPH2PS L: 0.78ns= 3.02c T: 0.39ns= 1.511c 1971 RDRAND :RDRAND r16 L: [no true dep.] T: 292.41ns=1134.087c 1972 RDRAND :RDRAND r32 L: [no true dep.] T: 295.70ns=1146.822c 1973 RDRAND_X64 :RDRAND r64 L: [no true dep.] T: 293.33ns=1137.651c 1974 X86 :MOV+ADD r8, r8 L: 0.52ns= 2.01c T: 0.08ns= 0.310c 1975 X86 :MOV+ADD r16, r16 L: 0.52ns= 2.01c T: 0.08ns= 0.311c 1976 X86 :MOV+ADD r32, r32 L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1977 AMD64 :MOV+ADD r64, r64 L: 0.06ns= 0.25c T: 0.06ns= 0.252c 1978 MMX :MOVQ+PADDB mm, mm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1979 MMX :MOVQ+PADDW mm, mm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1980 MMX :MOVQ+PADDD mm, mm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1981 SSE2 :MOVQ+PADDQ mm, mm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 1983 SSE :MOVSS+ADDSS xmm, xmm L: 1.82ns= 7.05c T: 0.18ns= 0.690c 1984 AVX :VMOVSS+VADDSS xm, xm, xm L: 1.82ns= 7.05c T: 0.18ns= 0.689c 1985 SSE :MOVAPS+ADDPS xmm, xmm L: 1.82ns= 7.05c T: 0.18ns= 0.713c 1986 AVX :VMOVAPS+VADDPS xm, xm, xm L: 1.82ns= 7.05c T: 0.18ns= 0.689c 1987 SSE2 :MOVSD+ADDSD xmm, xmm L: 1.82ns= 7.05c T: 0.18ns= 0.688c 1988 AVX :VMOVSD+VADDSD xm, xm, xm L: 1.82ns= 7.05c T: 0.18ns= 0.687c 1989 SSE2 :MOVAPD+ADDPD xmm, xmm L: 1.82ns= 7.05c T: 0.18ns= 0.700c 1990 AVX :VMOVAPD+VADDPD xm, xm, xm L: 1.82ns= 7.05c T: 0.18ns= 0.704c 1991 SSE2 :MOVDQA+PADDB xmm, xmm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1992 SSE2 :MOVDQA+PADDW xmm, xmm L: 0.52ns= 2.01c T: 0.13ns= 0.506c 1993 SSE2 :MOVDQA+PADDD xmm, xmm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1994 SSE2 :MOVDQA+PADDQ xmm, xmm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1995 AVX :VMOVDQA+VPADDB xm, xm, xm L: 0.52ns= 2.01c T: 0.13ns= 0.514c 1996 AVX :VMOVDQA+VPADDW xm, xm, xm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1997 AVX :VMOVDQA+VPADDD xm, xm, xm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1998 AVX :VMOVDQA+VPADDQ xm, xm, xm L: 0.52ns= 2.01c T: 0.13ns= 0.505c 1999 AVX :VMOVAPS+VADDPS ym, ym, ym L: 1.82ns= 7.05c T: 0.27ns= 1.066c 2000 AVX :VMOVAPD+VADDPD ym, ym, ym L: 1.82ns= 7.05c T: 0.27ns= 1.066c 2001 RDSEED :RDSEED r16 L: [no true dep.] T: 293.93ns=1139.965c 2002 RDSEED :RDSEED r32 L: [no true dep.] T: 290.86ns=1128.047c 2003 RDSEED_X64 :RDSEED r64 L: [no true dep.] T: 291.45ns=1130.368c 2004 BMI :ANDN r32, r32, r32 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 2005 BMI_X64 :ANDN r64, r64, r64 L: 0.26ns= 1.01c T: 0.03ns= 0.135c 2006 BMI :BEXTR r32, r32, r32 L: 1.30ns= 5.04c T: 0.19ns= 0.745c 2007 BMI_X64 :BEXTR r64, r64, r64 L: 1.30ns= 5.04c T: 0.19ns= 0.745c 2008 BMI :BLSI r32, r32 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2009 BMI_X64 :BLSI r64, r64 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2010 BMI :BLSMSK r32, r32 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2011 BMI_X64 :BLSMSK r64, r64 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2012 BMI :BLSR r32, r32 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2013 BMI_X64 :BLSR r64, r64 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2014 BMI :TZCNT r16, r16 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 2015 BMI :TZCNT r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 2016 BMI_X64 :TZCNT r64, r64 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 2017 BMI2 :BZHI r32, r32, r32 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 2018 BMI2_X64 :BZHI r64, r64, r64 L: 0.78ns= 3.02c T: 0.15ns= 0.588c 2019 BMI2 :MULX r32, r32, r32 L: 1.04ns= 4.03c T: 0.28ns= 1.099c 2020 BMI2_X64 :MULX r64, r64, r64 L: 1.30ns= 5.04c T: 0.29ns= 1.114c 2021 BMI2 :PDEP r32, r32, r32 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2022 BMI2_X64 :PDEP r64, r64, r64 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2023 BMI2 :PEXT r32, r32, r32 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2024 BMI2_X64 :PEXT r64, r64, r64 L: 0.78ns= 3.02c T: 0.26ns= 1.008c 2025 BMI2 :RORX r32, r32, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2026 BMI2_X64 :RORX r64, r64, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2027 BMI2 :SARX r32, r32, r32 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 2028 BMI2_X64 :SARX r64, r64, r64 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 2029 BMI2 :SHLX r32, r32, r32 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 2030 BMI2_X64 :SHLX r64, r64, r64 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 2031 BMI2 :SHRX r32, r32, r32 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 2032 BMI2_X64 :SHRX r64, r64, r64 L: 0.52ns= 2.01c T: 0.06ns= 0.252c 2053 AVX2 :VMOVNTDQA ymm, [m256] L: [memory dep.] T: 0.67ns= 0.671c 2054 AVX2 :VMOVNTDQA + VMOVNTDQ ymm L: 173.60ns= 673.29c T: 673.29ns= 673.293c 2055 AVX2 :VPMOVMSKB r32, ymm L: [diff. reg. set] T: 0.22ns= 0.839c 2056 AVX2_X64 :VPMOVMSKB r64, ymm L: [diff. reg. set] T: 0.22ns= 0.839c 2057 AVX2 :VPADDB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2058 AVX2 :VPADDW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2059 AVX2 :VPADDD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2060 AVX2 :VPADDQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2061 AVX2 :VPADDSB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2062 AVX2 :VPADDSW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2063 AVX2 :VPADDUSB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2064 AVX2 :VPADDUSW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2065 AVX2 :VPSUBB ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2066 AVX2 :VPSUBB ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2067 AVX2 :VPSUBW ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2068 AVX2 :VPSUBW ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2069 AVX2 :VPSUBD ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2070 AVX2 :VPSUBD ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2071 AVX2 :VPSUBQ ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2072 AVX2 :VPSUBQ ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2073 AVX2 :VPSUBSB ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2074 AVX2 :VPSUBSB ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2075 AVX2 :VPSUBSW ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2076 AVX2 :VPSUBSW ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 2077 AVX2 :VPSUBUSB ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2078 AVX2 :VPSUBUSB ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2079 AVX2 :VPSUBUSW ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2080 AVX2 :VPSUBUSW ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2081 AVX2 :VPCMPEQB ymm, ymm, ymm L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2082 AVX2 :VPCMPEQB ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2083 AVX2 :VPCMPEQW ymm, ymm, ymm L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2084 AVX2 :VPCMPEQW ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 2085 AVX2 :VPCMPEQD ymm, ymm, ymm L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2086 AVX2 :VPCMPEQD ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2087 AVX2 :VPCMPEQQ ymm, ymm, ymm L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2088 AVX2 :VPCMPEQQ ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2089 AVX2 :VPCMPGTB ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2090 AVX2 :VPCMPGTB ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2091 AVX2 :VPCMPGTW ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2092 AVX2 :VPCMPGTW ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 2093 AVX2 :VPCMPGTD ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2094 AVX2 :VPCMPGTD ymm1, ymm1, ymm2 L: 0.25ns= 0.99c T: 0.13ns= 0.504c 2095 AVX2 :VPCMPGTQ ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2096 AVX2 :VPCMPGTQ ymm1, ymm1, ymm2 L: 1.04ns= 4.03c T: 0.52ns= 2.015c 2097 AVX2 :VPAND ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2098 AVX2 :VPAND ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2099 AVX2 :VPANDN ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2100 AVX2 :VPANDN ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2101 AVX2 :VPOR ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2102 AVX2 :VPOR ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2103 AVX2 :VPXOR ymm, ymm, ymm L: 0.06ns= 0.25c T: 0.06ns= 0.252c 2104 AVX2 :VPXOR ymm1, ymm1, ymm2 L: 0.27ns= 1.03c T: 0.13ns= 0.504c 2105 AVX2 :VPMULHW ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2106 AVX2 :VPMULHUW ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2107 AVX2 :VPMULHRSW ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2108 AVX2 :VPMULLW ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2109 AVX2 :VPMULLD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.26ns= 1.007c 2110 AVX2 :VPMULDQ ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2111 AVX2 :VPMULUDQ ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2112 AVX2 :VPMADDUBSW ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2113 AVX2 :VPMADDWD ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2114 AVX2 :VPSLLW ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2115 AVX2 :VPSLLW ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2116 AVX2 :VPSLLD ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2117 AVX2 :VPSLLD ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2118 AVX2 :VPSLLQ ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2119 AVX2 :VPSLLQ ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2120 AVX2 :VPSLLDQ ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2121 AVX2 :VPSRAW ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2122 AVX2 :VPSRAW ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2123 AVX2 :VPSRAD ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2124 AVX2 :VPSRAD ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2125 AVX2 :VPSRLW ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2126 AVX2 :VPSRLW ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2127 AVX2 :VPSRLD ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2128 AVX2 :VPSRLD ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2129 AVX2 :VPSRLQ ymm, ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2130 AVX2 :VPSRLQ ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2131 AVX2 :VPSRLDQ ymm, ymm, imm8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2132 AVX2 :VPUNPCKHBW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2133 AVX2 :VPUNPCKHWD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2134 AVX2 :VPUNPCKHDQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2135 AVX2 :VPUNPCKHQDQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2136 AVX2 :VPUNPCKLBW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2137 AVX2 :VPUNPCKLWD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2138 AVX2 :VPUNPCKLDQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2139 AVX2 :VPUNPCKLQDQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2140 AVX2 :VPACKSSWB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2141 AVX2 :VPACKUSWB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2142 AVX2 :VPACKSSDW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2143 AVX2 :VPACKUSDW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2144 AVX2 :VPAVGB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2145 AVX2 :VPAVGW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2146 AVX2 :VPMAXUB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2147 AVX2 :VPMAXSB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2148 AVX2 :VPMAXUW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2149 AVX2 :VPMAXSW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2150 AVX2 :VPMAXUD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2151 AVX2 :VPMAXSD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2152 AVX2 :VPMINUB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2153 AVX2 :VPMINSB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2154 AVX2 :VPMINUW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2155 AVX2 :VPMINSW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2156 AVX2 :VPMINUD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2157 AVX2 :VPMINSD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2158 AVX2 :VPSADBW ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.13ns= 0.504c 2159 AVX2 :VPSHUFB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.26ns= 1.007c 2160 AVX2 :VPSHUFLW ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2161 AVX2 :VPSHUFHW ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2162 AVX2 :VPSHUFD ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2163 AVX2 :VPABSB ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2164 AVX2 :VPABSW ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2165 AVX2 :VPABSD ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2166 AVX2 :VPALIGNR ymm, ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2167 AVX2 :VPHADDW ymm, ymm, ymm L: 1.31ns= 5.08c T: 1.04ns= 4.029c 2168 AVX2 :VPHADDD ymm, ymm, ymm L: 0.83ns= 3.20c T: 0.66ns= 2.547c 2169 AVX2 :VPHADDSW ymm, ymm, ymm L: 1.31ns= 5.08c T: 1.04ns= 4.029c 2170 AVX2 :VPHSUBW ymm, ymm, ymm L: 1.31ns= 5.08c T: 1.04ns= 4.029c 2171 AVX2 :VPHSUBD ymm, ymm, ymm L: 0.83ns= 3.21c T: 0.66ns= 2.547c 2172 AVX2 :VPHSUBSW ymm, ymm, ymm L: 1.31ns= 5.08c T: 1.04ns= 4.029c 2173 AVX2 :VPSIGNB ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2174 AVX2 :VPSIGNW ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2175 AVX2 :VPSIGND ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2176 AVX2 :VPBLENDW ymm, ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2177 AVX2 :VPBLENDVB ymm, ymm, ymm, ym L: 0.93ns= 3.60c T: 0.66ns= 2.564c 2178 AVX2 :VPBLENDD xmm, xmm, xmm, im8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2179 AVX2 :VPBLENDD ymm, ymm, ymm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2180 AVX2 :VMPSADBW ymm, ymm, imm8 L: 1.30ns= 5.04c T: 0.68ns= 2.640c 2181 AVX2 :VPMOVSXBW ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2182 AVX2 :VPMOVSXBD ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2183 AVX2 :VPMOVSXBQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2184 AVX2 :VPMOVSXWD ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2185 AVX2 :VPMOVSXWQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2186 AVX2 :VPMOVSXDQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2187 AVX2 :VPMOVZXBW ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2188 AVX2 :VPMOVZXBD ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2189 AVX2 :VPMOVZXBQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2190 AVX2 :VPMOVZXWD ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2191 AVX2 :VPMOVZXWQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2192 AVX2 :VPMOVZXDQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2193 AVX2 :VPMASKMOVD xmm,xmm,[m128+4] L: [memory dep.] T: 0.11ns= 0.420c 2194 AVX2 :VPMASKMOVD [m128+4],xmm,xmm L: [memory dep.] T: 0.32ns= 1.259c 2195 AVX2 :VPMASKMOVD unaligned LS pair L: 4.67ns= 18.13c T: 0.32ns= 1.259c 2196 AVX2 :VPMASKMOVQ xmm,xmm,[m128+4] L: [memory dep.] T: 0.11ns= 0.420c 2197 AVX2 :VPMASKMOVQ [m128+4],xmm,xmm L: [memory dep.] T: 0.32ns= 1.259c 2198 AVX2 :VPMASKMOVQ unaligned LS pair L: 4.67ns= 18.13c T: 0.32ns= 1.259c 2199 AVX2 :VPMASKMOVD ymm,ymm,[m256+4] L: [memory dep.] T: 0.22ns= 0.839c 2200 AVX2 :VPMASKMOVD [m256+4],ymm,ymm L: [memory dep.] T: 0.65ns= 2.518c 2201 AVX2 :VPMASKMOVD unaligned LS pair L: 5.19ns= 20.14c T: 5.04ns= 19.559c 2202 AVX2 :VPMASKMOVQ ymm,ymm,[m256+4] L: [memory dep.] T: 0.22ns= 0.839c 2203 AVX2 :VPMASKMOVQ [m256+4],ymm,ymm L: [memory dep.] T: 0.65ns= 2.518c 2204 AVX2 :VPMASKMOVQ unaligned LS pair L: 5.19ns= 20.14c T: 5.04ns= 19.556c 2205 AVX2 :VBROADCASTSS xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2206 AVX2 :VBROADCASTSS ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2207 AVX2 :VBROADCASTSD ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2208 AVX2 :VPBROADCASTB xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2209 AVX2 :VPBROADCASTB ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2210 AVX2 :VPBROADCASTW xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2211 AVX2 :VPBROADCASTW ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2212 AVX2 :VPBROADCASTD xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2213 AVX2 :VPBROADCASTD ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2214 AVX2 :VPBROADCASTQ xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2215 AVX2 :VPBROADCASTQ ymm, xmm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2216 AVX2 :VBROADCASTI128 ymm, m128 L: [memory dep.] T: 0.09ns= 0.336c 2217 AVX2 :VEXTRACTI128 xmm, ymm, imm8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2218 AVX2 :VINSERTI128 ym, ym, xm, im8 L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2219 AVX2 :VPERM2I128 ym, ym, ym, im8 L: 1.56ns= 6.04c T: 0.26ns= 1.007c 2220 AVX2 :VPERMD ymm, ymm, ymm L: 1.56ns= 6.04c T: 0.26ns= 1.007c 2221 AVX2 :VPERMQ ymm, ymm, imm8 L: 1.56ns= 6.04c T: 0.26ns= 1.007c 2222 AVX2 :VPERMPS ymm, ymm, ymm L: 1.56ns= 6.04c T: 0.26ns= 1.007c 2223 AVX2 :VPERMPD ymm, ymm, imm8 L: 1.56ns= 6.04c T: 0.26ns= 1.007c 2224 AVX2 :VPSLLVD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2225 AVX2 :VPSLLVD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2226 AVX2 :VPSLLVQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2227 AVX2 :VPSLLVQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2228 AVX2 :VPSRLVD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2229 AVX2 :VPSRLVD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2230 AVX2 :VPSRLVQ xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2231 AVX2 :VPSRLVQ ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2232 AVX2 :VPSRAVD xmm, xmm, xmm L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2233 AVX2 :VPSRAVD ymm, ymm, ymm L: 0.26ns= 1.01c T: 0.13ns= 0.504c 2234 ADX :ADCX r32, r32 L: 0.52ns= 2.01c T: 0.26ns= 1.007c 2235 ADX_X64 :ADCX r64, r64 L: 0.52ns= 2.01c T: 0.26ns= 1.007c 2236 ADX :ADOX r32, r32 L: 0.52ns= 2.01c T: 0.26ns= 1.007c 2237 ADX_X64 :ADOX r64, r64 L: 0.52ns= 2.01c T: 0.26ns= 1.007c 2238 CLFLUSH :CLFLUSH [mem] L: [memory dep.] T: 47.76ns= 185.237c 2239 CLFLUSHOPT :CLFLUSHOPT [mem] L: [memory dep.] T: 2.48ns= 9.638c 2241 SHA :SHA1RNDS4 xmm, xmm, imm8 L: 1.04ns= 4.03c T: 0.26ns= 1.007c 2242 SHA :SHA1NEXTE xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2243 SHA :SHA1MSG1 xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2244 SHA :SHA1MSG2 xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2245 SHA :SHA256RNDS2 xm, xm, L: 1.04ns= 4.03c T: 0.26ns= 1.007c 2246 SHA :SHA256MSG1 xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2247 SHA :SHA256MSG2 xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 2248 X86 :MOV r1_8, r2_8 L: 0.26ns= 1.01c T: 0.04ns= 0.137c 2249 X86 :MOV r1_16, r2_16 L: 0.26ns= 1.01c T: 0.04ns= 0.137c 2250 X86 :MOV r1_32, r2_32 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2251 AMD64 :MOV r1_64, r2_64 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2252 X86 :MOVSX r1_16, r2_8 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2253 X86 :MOVSX r1_32, r2_8 L: 0.07ns= 0.25c T: 0.06ns= 0.252c 2254 AMD64 :MOVSX r1_64, r2_8 L: 0.07ns= 0.25c T: 0.06ns= 0.252c 2255 X86 :MOVSX r1_32, r2_16 L: 0.07ns= 0.25c T: 0.06ns= 0.252c 2256 AMD64 :MOVSX r1_64, r2_16 L: 0.07ns= 0.25c T: 0.06ns= 0.252c 2257 AMD64 :MOVSXD r1_64, r2_32 L: 0.07ns= 0.25c T: 0.06ns= 0.252c 2258 X86 :MOVZX r1_16, r2_8 L: 0.26ns= 1.01c T: 0.04ns= 0.138c 2259 X86 :MOVZX r1_32, r2_8 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2260 AMD64 :MOVZX r1_64, r2_8 L: 0.03ns= 0.13c T: 0.03ns= 0.127c 2261 X86 :MOVZX r1_32, r2_16 L: 0.03ns= 0.13c T: 0.03ns= 0.135c 2262 AMD64 :MOVZX r1_64, r2_16 L: 0.03ns= 0.13c T: 0.03ns= 0.134c 2263 MMX :MOVQ mm1, mm2 L: 0.07ns= 0.25c T: 0.06ns= 0.252c 2264 SSE :MOVSS xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2265 AVX :VMOVSS xmm1, xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2266 SSE :MOVAPS xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.129c 2267 AVX :VMOVAPS xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2268 SSE :MOVUPS xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.129c 2269 AVX :VMOVUPS xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2270 SSE2 :MOVSD xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2271 AVX :VMOVSD xmm1, xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 2272 SSE2 :MOVAPD xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.127c 2273 AVX :VMOVAPD xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2274 SSE2 :MOVUPD xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.127c 2275 AVX :VMOVUPD xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2276 SSE2 :MOVDQA xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.128c 2277 AVX :VMOVDQA xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.127c 2278 SSE2 :MOVDQU xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2279 AVX :VMOVDQU xmm1, xmm2 L: 0.03ns= 0.13c T: 0.03ns= 0.126c 2280 AVX :VMOVAPS ymm1, ymm2 L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2281 AVX :VMOVUPS ymm1, ymm2 L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2282 AVX :VMOVAPD ymm1, ymm2 L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2283 AVX :VMOVUPD ymm1, ymm2 L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2284 AVX :VMOVDQA ymm1, ymm2 L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2285 AVX :VMOVDQU ymm1, ymm2 L: 0.13ns= 0.50c T: 0.13ns= 0.504c 2286 AVX2 :VPADDD+VADDPS ym, ym, ym L: 1.82ns= 7.05c T: 0.27ns= 1.062c 2287 AVX2 :VPADDQ+VADDPD ym, ym, ym L: 1.82ns= 7.05c T: 0.27ns= 1.066c 2288 AVX2 :VCMPPS+VPADDD ym, ym, ym L: 1.82ns= 7.05c T: 0.29ns= 1.129c 2289 AVX2 :VCMPPD+VPADDQ ym, ym, ym L: 1.82ns= 7.05c T: 0.29ns= 1.129c 2290 SSE :4xADDPS xm1,xm1 4x xm2,xm2 L: 2.08ns= 8.06c T: 2.08ns= 8.059c 2291 SSE :4xMULPS xm1,xm1 4x xm2,xm2 L: 3.12ns= 12.09c T: 3.12ns= 12.088c 2292 SSE2 :4xADDPD xm1,xm1 4x xm2,xm2 L: 2.08ns= 8.06c T: 2.08ns= 8.058c 2293 SSE2 :4xMULPD xm1,xm1 4x xm2,xm2 L: 3.12ns= 12.09c T: 3.12ns= 12.088c 2294 LNOP :LNOP3 [eax], eax L: [no true dep.] T: 0.05ns= 0.178c 2295 LNOP :LNOP4 [eax+disp8], eax L: [no true dep.] T: 0.03ns= 0.126c 2296 LNOP :LNOP5 [SIB+disp8], eax L: [no true dep.] T: 0.03ns= 0.127c 2297 LNOP :LNOP6 [SIB+disp8], ax L: [no true dep.] T: 0.03ns= 0.135c 2298 LNOP :LNOP7 [eax+disp32], eax L: [no true dep.] T: 0.05ns= 0.178c 2299 LNOP :LNOP8 [SIB+disp32], eax L: [no true dep.] T: 0.06ns= 0.219c 2300 LNOP :LNOP9 [SIB+disp32], ax L: [no true dep.] T: 0.06ns= 0.218c 2301 LNOP :2x66 LNOPA [SIB+disp32], ax L: [no true dep.] T: 0.05ns= 0.211c 2302 LNOP :3x66 LNOPB [SIB+disp32], ax L: [no true dep.] T: 0.09ns= 0.336c 2303 LNOP :4x66 LNOPC [SIB+disp32], ax L: [no true dep.] T: 0.35ns= 1.343c 2304 LNOP :5x66 LNOPD [SIB+disp32], ax L: [no true dep.] T: 0.35ns= 1.343c 2305 LNOP :6x66 LNOPE [SIB+disp32], ax L: [no true dep.] T: 0.35ns= 1.343c 2306 LNOP :7x66 LNOPF [SIB+disp32], ax L: [no true dep.] T: 0.35ns= 1.343c 2309 AVX2 :VGATHERDPS xmm, [xm32], xmm L: 1.43ns= 5.54c T: 1.43ns= 5.541c 2310 AVX2 :VGATHERDPS ymm, [ym32], ymm L: 2.53ns= 9.82c T: 2.53ns= 9.823c 2311 AVX2 :VGATHERQPS xmm, [xm64], xmm L: 1.10ns= 4.28c T: 1.10ns= 4.281c 2312 AVX2 :VGATHERQPS xmm, [ym64], xmm L: 2.08ns= 8.06c T: 2.08ns= 8.059c 2313 AVX2 :VGATHERDPD xmm, [xm32], xmm L: 1.17ns= 4.53c T: 1.17ns= 4.533c 2314 AVX2 :VGATHERDPD ymm, [xm32], ymm L: 1.75ns= 6.80c T: 1.75ns= 6.800c 2315 AVX2 :VGATHERQPD xmm, [xm64], xmm L: 1.04ns= 4.03c T: 1.04ns= 4.029c 2316 AVX2 :VGATHERQPD ymm, [ym64], ymm L: 1.75ns= 6.80c T: 1.75ns= 6.800c 2317 AVX2 :VPGATHERDD xmm, [xm32], xmm L: 1.43ns= 5.54c T: 1.43ns= 5.540c 2318 AVX2 :VPGATHERDD ymm, [ym32], ymm L: 2.53ns= 9.82c T: 2.53ns= 9.823c 2319 AVX2 :VPGATHERQD xmm, [xm64], xmm L: 1.10ns= 4.28c T: 1.10ns= 4.281c 2320 AVX2 :VPGATHERQD xmm, [ym64], xmm L: 2.08ns= 8.06c T: 2.08ns= 8.060c 2321 AVX2 :VPGATHERDQ xmm, [xm32], xmm L: 1.17ns= 4.53c T: 1.17ns= 4.533c 2322 AVX2 :VPGATHERDQ ymm, [xm32], ymm L: 1.75ns= 6.80c T: 1.75ns= 6.800c 2323 AVX2 :VPGATHERQQ xmm, [xm64], xmm L: 1.04ns= 4.03c T: 1.04ns= 4.029c 2324 AVX2 :VPGATHERQQ ymm, [ym64], ymm L: 1.75ns= 6.80c T: 1.75ns= 6.799c 2326 CLWB :CLWB [mem] L: [memory dep.] T: 4.84ns= 18.772c 2330 RDPID :RDPID r32/r64 L: [no true dep.] T: 3.03ns= 11.765c 4195 AVX :VMOVAPS+VEXTRACTF128 [m128], ym, im8 L: [memory dep.] T: 0.26ns= 1.007c 4196 AVX2 :VMOVDQA+VEXTRACTI128 [m128], ym, im8 L: [memory dep.] T: 0.26ns= 1.007c 4209 AVX :VMOVAPS+VINSERTF128 ym, [m128], im8 L: [memory dep.] T: 0.17ns= 0.672c 4210 AVX2 :VMOVDQA+VINSERTI128 ym, [m128], im8 L: [memory dep.] T: 0.17ns= 0.671c 4316 AVX+VAES :VAESDEC ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 4320 AVX+VAES :VAESDECLAST ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 4324 AVX+VAES :VAESENC ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 4328 AVX+VAES :VAESENCLAST ymm, ymm, ymm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 4332 AVX+VPCLMULQDQ :VPCLMULQDQ ymm, ymm, ymm, imm8 L: 1.04ns= 4.03c T: 0.52ns= 2.014c 4336 GFNI :GF2P8AFFINEINVQB xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 4337 AVX+GFNI :VGF2P8AFFINEINVQB xmm, xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 4338 AVX+GFNI :VGF2P8AFFINEINVQB ymm, ymm, ymm, imm8 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 4342 GFNI :GF2P8AFFINEQB xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 4343 AVX+GFNI :VGF2P8AFFINEQB xmm, xmm, xmm, imm8 L: 0.78ns= 3.02c T: 0.13ns= 0.504c 4344 AVX+GFNI :VGF2P8AFFINEQB ymm, ymm, ymm, imm8 L: 0.78ns= 3.02c T: 0.26ns= 1.007c 4348 GFNI :GF2P8MULB xmm, xmm L: 1.04ns= 4.03c T: 0.26ns= 1.007c 4349 AVX+GFNI :VGF2P8MULB xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.26ns= 1.007c 4350 AVX+GFNI :VGF2P8MULB ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.52ns= 2.015c 4354 X86 :SHLD r1_16, r2_16, imm8 L: 3.64ns= 14.14c T: 3.85ns= 14.923c 4355 X86 :SHLD r1_32, r2_32, imm8 L: 0.52ns= 2.01c T: 0.13ns= 0.503c 4356 AMD64 :SHLD r1_64, r2_64, imm8 L: 3.38ns= 13.09c T: 3.57ns= 13.833c 4357 X86 :SHLD r1_16, r2_16, cl L: 3.65ns= 14.14c T: 3.79ns= 14.693c 4358 X86 :SHLD r1_32, r2_32, cl L: 0.57ns= 2.19c T: 0.67ns= 2.591c 4359 AMD64 :SHLD r1_64, r2_64, cl L: 3.38ns= 13.12c T: 3.65ns= 14.158c 4360 X86 :SHRD r1_16, r2_16, imm8 L: 3.05ns= 11.83c T: 3.27ns= 12.665c 4361 X86 :SHRD r1_32, r2_32, imm8 L: 0.52ns= 2.01c T: 0.13ns= 0.503c 4362 AMD64 :SHRD r1_64, r2_64, imm8 L: 3.90ns= 15.12c T: 4.09ns= 15.861c 4363 X86 :SHRD r1_16, r2_16, cl L: 3.12ns= 12.09c T: 3.18ns= 12.344c 4364 X86 :SHRD r1_32, r2_32, cl L: 0.57ns= 2.20c T: 0.67ns= 2.591c 4365 AMD64 :SHRD r1_64, r2_64, cl L: 3.90ns= 15.14c T: 4.17ns= 16.175c 4366 X86 :ADC r8, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4367 X86 :ADC r16, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4368 X86 :ADC r32, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4369 AMD64 :ADC r64, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4370 X86 :ADC r16, imm16 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4371 X86 :ADC r32, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4372 AMD64 :ADC r64, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4373 X86 :ADC al, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4374 X86 :ADC ax, imm16 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4375 X86 :ADC eax, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4376 AMD64 :ADC rax, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4377 X86 :ADC r8, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4378 X86 :ADC r16, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4379 X86 :ADC r32, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4380 AMD64 :ADC r64, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4381 X86 :ADC r16, imm16_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4382 X86 :ADC r32, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4383 AMD64 :ADC r64, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4384 X86 :ADC al, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4385 X86 :ADC ax, imm16_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4386 X86 :ADC eax, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4387 AMD64 :ADC rax, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4388 X86 :SBB r8, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4389 X86 :SBB r16, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4390 X86 :SBB r32, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4391 AMD64 :SBB r64, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4392 X86 :SBB r16, imm16 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4393 X86 :SBB r32, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4394 AMD64 :SBB r64, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4395 X86 :SBB al, imm8 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4396 X86 :SBB ax, imm16 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4397 X86 :SBB eax, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4398 AMD64 :SBB rax, imm32 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4399 X86 :SBB r8, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4400 X86 :SBB r16, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4401 X86 :SBB r32, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4402 AMD64 :SBB r64, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4403 X86 :SBB r16, imm16_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4404 X86 :SBB r32, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4405 AMD64 :SBB r64, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4406 X86 :SBB al, imm8_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4407 X86 :SBB ax, imm16_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4408 X86 :SBB eax, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.014c 4409 AMD64 :SBB rax, imm32_0 L: 0.52ns= 2.01c T: 0.52ns= 2.015c 4410 AMD64 :LEA r16, [disp32] L: 0.61ns= 2.38c T: 0.67ns= 2.595c 4411 AMD64 :LEA r32, [disp32] L: 0.04ns= 0.17c T: 0.05ns= 0.186c 4412 AMD64 :LEA r64, [disp32] L: 0.05ns= 0.20c T: 0.05ns= 0.208c 4413 AMD64 :LEA r16, [r64] L: 0.64ns= 2.48c T: 0.67ns= 2.617c 4414 AMD64 :LEA r32, [r64] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4415 AMD64 :LEA r64, [r64] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4416 AMD64 :LEA r16, [r64 + disp8] L: 0.63ns= 2.43c T: 0.67ns= 2.615c 4417 AMD64 :LEA r32, [r64 + disp8] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4418 AMD64 :LEA r64, [r64 + disp8] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4419 AMD64 :LEA r16, [r64 + disp32] L: 0.62ns= 2.42c T: 0.67ns= 2.586c 4420 AMD64 :LEA r32, [r64 + disp32] L: 0.26ns= 1.01c T: 0.04ns= 0.146c 4421 AMD64 :LEA r64, [r64 + disp32] L: 0.26ns= 1.01c T: 0.05ns= 0.178c 4422 AMD64 :LEA r16, [r64 + r64] L: 0.63ns= 2.43c T: 0.67ns= 2.612c 4423 AMD64 :LEA r32, [r64 + r64] L: 0.26ns= 1.01c T: 0.04ns= 0.172c 4424 AMD64 :LEA r64, [r64 + r64] L: 0.26ns= 1.01c T: 0.04ns= 0.136c 4425 AMD64 :LEA r16, [r64 + r64 + disp8] L: 0.78ns= 3.03c T: 0.66ns= 2.552c 4426 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4427 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4428 AMD64 :LEA r16, [r64 + r64 + disp32] L: 0.78ns= 3.03c T: 0.67ns= 2.591c 4429 AMD64 :LEA r32, [r64 + r64 + disp32] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4430 AMD64 :LEA r64, [r64 + r64 + disp32] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4431 AMD64 :LEA r16, [r64 + r64 * 8] L: 0.64ns= 2.47c T: 0.67ns= 2.600c 4432 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.26ns= 1.01c T: 0.26ns= 1.007c 4433 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.26ns= 1.01c T: 0.26ns= 1.007c 4434 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 0.78ns= 3.03c T: 0.66ns= 2.557c 4435 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4436 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4437 AMD64 :LEA r16, [r64 + r64 * 8 + disp32] L: 0.78ns= 3.03c T: 0.67ns= 2.591c 4438 AMD64 :LEA r32, [r64 + r64 * 8 + disp32] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4439 AMD64 :LEA r64, [r64 + r64 * 8 + disp32] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4440 AMD64 :ASP LEA r16, [disp32] L: 0.64ns= 2.46c T: 0.67ns= 2.597c 4441 AMD64 :ASP LEA r32, [disp32] L: 0.05ns= 0.20c T: 0.05ns= 0.184c 4442 AMD64 :ASP LEA r64, [disp32] L: 0.05ns= 0.20c T: 0.05ns= 0.213c 4443 AMD64 :ASP LEA r16, [r32] L: 0.63ns= 2.43c T: 0.67ns= 2.610c 4444 AMD64 :ASP LEA r32, [r32] L: 0.26ns= 1.01c T: 0.04ns= 0.136c 4445 AMD64 :ASP LEA r64, [r32] L: 0.26ns= 1.01c T: 0.04ns= 0.136c 4446 AMD64 :ASP LEA r16, [r32 + disp8] L: 0.58ns= 2.25c T: 0.66ns= 2.564c 4447 AMD64 :ASP LEA r32, [r32 + disp8] L: 0.26ns= 1.01c T: 0.04ns= 0.136c 4448 AMD64 :ASP LEA r64, [r32 + disp8] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4449 AMD64 :ASP LEA r16, [r32 + disp32] L: 0.61ns= 2.37c T: 0.67ns= 2.593c 4450 AMD64 :ASP LEA r32, [r32 + disp32] L: 0.26ns= 1.01c T: 0.05ns= 0.181c 4451 AMD64 :ASP LEA r64, [r32 + disp32] L: 0.26ns= 1.01c T: 0.05ns= 0.207c 4452 AMD64 :ASP LEA r16, [r32 + r32] L: 0.58ns= 2.25c T: 0.66ns= 2.558c 4453 AMD64 :ASP LEA r32, [r32 + r32] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4454 AMD64 :ASP LEA r64, [r32 + r32] L: 0.26ns= 1.01c T: 0.04ns= 0.137c 4455 AMD64 :ASP LEA r16, [r32 + r32 + disp8] L: 0.78ns= 3.03c T: 0.66ns= 2.552c 4456 AMD64 :ASP LEA r32, [r32 + r32 + disp8] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4457 AMD64 :ASP LEA r64, [r32 + r32 + disp8] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4458 AMD64 :ASP LEA r16, [r32 + r32 + disp32] L: 0.78ns= 3.04c T: 0.67ns= 2.580c 4459 AMD64 :ASP LEA r32, [r32 + r32 + disp32] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4460 AMD64 :ASP LEA r64, [r32 + r32 + disp32] L: 0.52ns= 2.01c T: 0.08ns= 0.311c 4461 AMD64 :ASP LEA r16, [r32 + r32 * 8] L: 0.59ns= 2.30c T: 0.66ns= 2.552c 4462 AMD64 :ASP LEA r32, [r32 + r32 * 8] L: 0.26ns= 1.01c T: 0.26ns= 1.007c 4463 AMD64 :ASP LEA r64, [r32 + r32 * 8] L: 0.26ns= 1.01c T: 0.26ns= 1.007c 4464 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp8] L: 0.78ns= 3.03c T: 0.66ns= 2.559c 4465 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp8] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4466 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp8] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4467 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp32] L: 0.78ns= 3.04c T: 0.66ns= 2.572c 4468 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp32] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4469 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp32] L: 0.52ns= 2.01c T: 0.26ns= 1.007c 4500 MOVDIRI :MOVDIRI [m32], r32 L: [memory dep.] T: 41.38ns= 160.505c 4501 MOVDIRI_X64 :MOVDIRI [m64], r64 L: [memory dep.] T: 41.33ns= 160.290c 4502 MOVDIR64B :MOVDIR64B r64, m512 L: [memory dep.] T: 12.43ns= 48.199c 4503 WAITPKG :TPAUSE r32, , L: [no true dep.] T: 22.12ns= 85.789c 4505 WAITPKG :UMWAIT r32, , L: [no true dep.] T: 31.22ns= 121.088c 4506 SERIALIZE :SERIALIZE L: [no true dep.] T: 11.71ns= 45.419c 4530 GFNI :GF2P8AFFINEQB + PADDB xmm L: 1.30ns= 5.03c T: 0.16ns= 0.607c 4531 AVX+GFNI :VGF2P8AFFINEQB + VPADDB xmm L: 1.30ns= 5.03c T: 0.16ns= 0.614c 4532 AVX+GFNI :VGF2P8AFFINEQB + VPADDB ymm L: 1.30ns= 5.03c T: 0.31ns= 1.201c 4539 AVX_VNNI :VPDPBUSD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4540 AVX_VNNI :VPDPBUSD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4541 AVX_VNNI :VPDPBUSDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4542 AVX_VNNI :VPDPBUSDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4543 AVX_VNNI :VPDPWSSD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4544 AVX_VNNI :VPDPWSSD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4545 AVX_VNNI :VPDPWSSDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4546 AVX_VNNI :VPDPWSSDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4880 AVX_IFMA :VPMADD52LUQ xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4881 AVX_IFMA :VPMADD52LUQ ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4882 AVX_IFMA :VPMADD52HUQ xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4883 AVX_IFMA :VPMADD52HUQ ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4884 AVX_VNNI_INT8 :VPDPBSSD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4885 AVX_VNNI_INT8 :VPDPBSSD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4886 AVX_VNNI_INT8 :VPDPBSSDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4887 AVX_VNNI_INT8 :VPDPBSSDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4888 AVX_VNNI_INT8 :VPDPBSUD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4889 AVX_VNNI_INT8 :VPDPBSUD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4890 AVX_VNNI_INT8 :VPDPBSUDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4891 AVX_VNNI_INT8 :VPDPBSUDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4892 AVX_VNNI_INT8 :VPDPBUUD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4893 AVX_VNNI_INT8 :VPDPBUUD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4894 AVX_VNNI_INT8 :VPDPBUUDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4895 AVX_VNNI_INT8 :VPDPBUUDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4896 AVX_NE_CONVERT :VBCSTNEBF162PS xmm1, [m16] L: [memory dep.] T: 0.09ns= 0.336c 4897 AVX_NE_CONVERT :VBCSTNEBF162PS ymm1, [m16] L: [memory dep.] T: 0.09ns= 0.336c 4898 AVX_NE_CONVERT :VBCSTNESH2PS xmm1, [m16] L: [memory dep.] T: 0.09ns= 0.336c 4899 AVX_NE_CONVERT :VBCSTNESH2PS ymm1, [m16] L: [memory dep.] T: 0.09ns= 0.336c 4900 AVX_NE_CONVERT :VCVTNEEBF162PS xmm1, [m128] L: [memory dep.] T: 0.09ns= 0.336c 4901 AVX_NE_CONVERT :VCVTNEEBF162PS ymm1, [m256] L: [memory dep.] T: 0.17ns= 0.672c 4902 AVX_NE_CONVERT :VCVTNEEPH2PS xmm1, [m128] L: [memory dep.] T: 0.09ns= 0.336c 4903 AVX_NE_CONVERT :VCVTNEEPH2PS ymm1, [m256] L: [memory dep.] T: 0.17ns= 0.672c 4904 AVX_NE_CONVERT :VCVTNEOBF162PS xmm1, [m128] L: [memory dep.] T: 0.09ns= 0.336c 4905 AVX_NE_CONVERT :VCVTNEOBF162PS ymm1, [m256] L: [memory dep.] T: 0.17ns= 0.672c 4906 AVX_NE_CONVERT :VCVTNEOPH2PS xmm1, [m128] L: [memory dep.] T: 0.09ns= 0.336c 4907 AVX_NE_CONVERT :VCVTNEOPH2PS ymm1, [m256] L: [memory dep.] T: 0.17ns= 0.672c 4908 AVX_NE_CONVERT :VCVTNEPS2BF16 xmm1, xmm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 4909 AVX_NE_CONVERT :VCVTNEPS2BF16 xmm1, ymm2 L: 0.26ns= 1.01c T: 0.06ns= 0.252c 4910 CMPCCXADD :CMPBEXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.255c 4911 CMPCCXADD :CMPBEXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4912 CMPCCXADD :CMPBXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4913 CMPCCXADD :CMPBXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4914 CMPCCXADD :CMPLEXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.254c 4915 CMPCCXADD :CMPLEXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.255c 4916 CMPCCXADD :CMPLXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.258c 4917 CMPCCXADD :CMPLXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4918 CMPCCXADD :CMPNBEXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.258c 4919 CMPCCXADD :CMPNBEXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.256c 4920 CMPCCXADD :CMPNBXADD [m32], r32, r32 L: 4.45ns= 17.24c T: 4.45ns= 17.258c 4921 CMPCCXADD :CMPNBXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.260c 4922 CMPCCXADD :CMPNLEXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4923 CMPCCXADD :CMPNLEXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.253c 4924 CMPCCXADD :CMPNLXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4925 CMPCCXADD :CMPNLXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.257c 4926 CMPCCXADD :CMPNOXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.256c 4927 CMPCCXADD :CMPNOXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.260c 4928 CMPCCXADD :CMPNPXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.258c 4929 CMPCCXADD :CMPNPXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4930 CMPCCXADD :CMPNSXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.261c 4931 CMPCCXADD :CMPNSXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.258c 4932 CMPCCXADD :CMPNZXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.258c 4933 CMPCCXADD :CMPNZXADD [m64], r64, r64 L: 4.45ns= 17.24c T: 4.45ns= 17.255c 4934 CMPCCXADD :CMPOXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4935 CMPCCXADD :CMPOXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4936 CMPCCXADD :CMPPXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4937 CMPCCXADD :CMPPXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4938 CMPCCXADD :CMPSXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.257c 4939 CMPCCXADD :CMPSXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.257c 4940 CMPCCXADD :CMPZXADD [m32], r32, r32 L: 4.45ns= 17.25c T: 4.45ns= 17.259c 4941 CMPCCXADD :CMPZXADD [m64], r64, r64 L: 4.45ns= 17.25c T: 4.45ns= 17.258c 4988 AVX_VNNI_INT16 :VPDPWUSD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4989 AVX_VNNI_INT16 :VPDPWUSD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4990 AVX_VNNI_INT16 :VPDPWUSDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4991 AVX_VNNI_INT16 :VPDPWUSDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4992 AVX_VNNI_INT16 :VPDPWSUD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4993 AVX_VNNI_INT16 :VPDPWSUD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4994 AVX_VNNI_INT16 :VPDPWSUDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4995 AVX_VNNI_INT16 :VPDPWSUDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4996 AVX_VNNI_INT16 :VPDPWUUD xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4997 AVX_VNNI_INT16 :VPDPWUUD ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 4998 AVX_VNNI_INT16 :VPDPWUUDS xmm, xmm, xmm L: 1.04ns= 4.03c T: 0.06ns= 0.252c 4999 AVX_VNNI_INT16 :VPDPWUUDS ymm, ymm, ymm L: 1.04ns= 4.03c T: 0.13ns= 0.504c 5000 SHA512 :VSHA512RNDS2 ymm, ymm, xmm L: 1.56ns= 6.04c T: 0.52ns= 2.015c 5001 SHA512 :VSHA512MSG1 ymm, xmm L: 1.04ns= 4.03c T: 0.52ns= 2.015c 5002 SHA512 :VSHA512MSG2 ymm, ymm L: 1.04ns= 4.03c T: 0.52ns= 2.014c 5003 SM3 :VSM3RNDS2 xmm, xmm, xmm, i8 L: 1.04ns= 4.03c T: 0.26ns= 1.007c 5004 SM3 :VSM3MSG1 xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 5005 SM3 :VSM3MSG2 xmm, xmm, xmm L: 0.78ns= 3.02c T: 0.26ns= 1.007c 5006 SM4 :VSM4RNDS4 xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.13ns= 0.504c 5007 SM4 :VSM4RNDS4 ymm, ymm, ymm L: 1.30ns= 5.04c T: 0.26ns= 1.007c 5008 SM4 :VSM4KEY4 xmm, xmm, xmm L: 1.30ns= 5.04c T: 0.13ns= 0.504c 5009 SM4 :VSM4KEY4 ymm, ymm, ymm L: 1.30ns= 5.04c T: 0.26ns= 1.007c 5018 FMA3 :VFMADD231SS+VADDSS xmm, xmm, xmm L: 1.56ns= 6.04c T: 0.15ns= 0.589c 5019 FMA3 :VFMADD231PS+VADDPS xmm, xmm, xmm L: 1.56ns= 6.04c T: 0.15ns= 0.588c 5020 FMA3 :VFMADD231PS+VADDPS ymm, ymm, ymm L: 1.56ns= 6.04c T: 0.27ns= 1.050c 5022 FMA3 :VFMADD231SS+VMULSS xmm, xmm, xmm L: 1.82ns= 7.05c T: 0.16ns= 0.610c 5023 FMA3 :VFMADD231PS+VMULPS xmm, xmm, xmm L: 1.82ns= 7.05c T: 0.16ns= 0.610c 5024 FMA3 :VFMADD231PS+VMULPS ymm, ymm, ymm L: 1.82ns= 7.05c T: 0.27ns= 1.052c 5026 FMA3 :VFMADD231SD+VADDSD xmm, xmm, xmm L: 1.56ns= 6.04c T: 0.16ns= 0.611c 5027 FMA3 :VFMADD231PD+VADDPD xmm, xmm, xmm L: 1.56ns= 6.04c T: 0.15ns= 0.588c 5028 FMA3 :VFMADD231PD+VADDPD ymm, ymm, ymm L: 1.56ns= 6.04c T: 0.27ns= 1.049c 5030 FMA3 :VFMADD231SD+VMULSD xmm, xmm, xmm L: 1.82ns= 7.05c T: 0.16ns= 0.608c 5031 FMA3 :VFMADD231PD+VMULPD xmm, xmm, xmm L: 1.82ns= 7.05c T: 0.16ns= 0.609c 5032 FMA3 :VFMADD231PD+VMULPD ymm, ymm, ymm L: 1.82ns= 7.05c T: 0.27ns= 1.049c