Copyright (C) 1995-2020 FinalWire Ltd. All rights reserved. aida_bench64.dll build: 4.5.837.8 Oct 21 2020 17:29:41 Arch:X64 CPUCount:4 NUMA:0 Freq: 4100.31MHz Priority:080 OS:6.3.19042 Memory: 16714884KB AllocGran:0x00010000 P:0x00001000 LP:0x0000000000200000 Memory To Test:16384KB 4K DTLB:512 2M DTLB:512 1G DTLB:512 CLFlush:64 ProcMask: 0x000000000000000f Features: X86,TSC,X87,CMOV,MMX,SSE,SSE2,SSE3,MMXP,AMD64,SSSE3,SSE4A,ABM,SSE4.1,SSE4.2,POPCNT,XOP,LAHF,CMPX8,CMPX16,AESNI,CLMUL,AVX,FMA3,FMA4,F16C,FSGSBASE,BMI,TBM,CLFLUSH,TSCINV,TOPEX,RDTSCP,3DNOWPREF,MISALIGNSSE,LNOP,PSE,4LTOP,PAGE1GB,FP128,SHARED_CU, CPU#000 Vendor: AuthenticAMD Family: 6f Model: 38 Stepping: 1 CoreType:0x10630f81 CPU#000 Type: "AMD A10-7890K Radeon R7, 12 Compute Cores 4C+8G" CPU#000 AffMask: 0x0000000000000001 CPU#000 PhysMask:0x000000000000000f CPU#000 APIC_ID:0x00000010 Phys_ID:000 Node_ID:00 CU_ID:00 Core_ID:00 CPU#000 L1I cache: 96KB, 64 byte cache line, 3 way, SMask:0000000000000003 CPU#000 L1D cache: 16KB, 64 byte cache line, 4 way, SMask:0000000000000001 CPU#000 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:0000000000000003, inclusive CPU#000 L1D 4K TLB: 64 entries, full, SMask:0000000000000001 CPU#000 L1D 2M TLB: 64 entries, full, SMask:0000000000000001 CPU#000 L1D 1G TLB: 64 entries, full, SMask:0000000000000001 CPU#000 L2D 4K TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#000 L2D 2M TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#000 L2D 1G TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#000 L1I 4K TLB: 48 entries, full, SMask:0000000000000001 CPU#000 L1I 2M TLB: 24 entries, full, SMask:0000000000000001 CPU#000 L1I 1G TLB: 24 entries, full, SMask:0000000000000001 CPU#000 L2I 4K TLB: 512 entries, 4 way, SMask:0000000000000003 CPU#000 L2I 2M TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#000 L2I 1G TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 Vendor: AuthenticAMD Family: 6f Model: 38 Stepping: 1 CoreType:0x10630f81 CPU#001 Type: "AMD A10-7890K Radeon R7, 12 Compute Cores 4C+8G" CPU#001 AffMask: 0x0000000000000002 CPU#001 PhysMask:0x000000000000000f CPU#001 APIC_ID:0x00000011 Phys_ID:000 Node_ID:00 CU_ID:00 Core_ID:01 CPU#001 L1I cache: 96KB, 64 byte cache line, 3 way, SMask:0000000000000003 CPU#001 L1D cache: 16KB, 64 byte cache line, 4 way, SMask:0000000000000002 CPU#001 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:0000000000000003, inclusive CPU#001 L1D 4K TLB: 64 entries, full, SMask:0000000000000002 CPU#001 L1D 2M TLB: 64 entries, full, SMask:0000000000000002 CPU#001 L1D 1G TLB: 64 entries, full, SMask:0000000000000002 CPU#001 L2D 4K TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 L2D 2M TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 L2D 1G TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 L1I 4K TLB: 48 entries, full, SMask:0000000000000002 CPU#001 L1I 2M TLB: 24 entries, full, SMask:0000000000000002 CPU#001 L1I 1G TLB: 24 entries, full, SMask:0000000000000002 CPU#001 L2I 4K TLB: 512 entries, 4 way, SMask:0000000000000003 CPU#001 L2I 2M TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#001 L2I 1G TLB: 1024 entries, 8 way, SMask:0000000000000003 CPU#002 Vendor: AuthenticAMD Family: 6f Model: 38 Stepping: 1 CoreType:0x10630f81 CPU#002 Type: "AMD A10-7890K Radeon R7, 12 Compute Cores 4C+8G" CPU#002 AffMask: 0x0000000000000004 CPU#002 PhysMask:0x000000000000000f CPU#002 APIC_ID:0x00000012 Phys_ID:000 Node_ID:00 CU_ID:01 Core_ID:02 CPU#002 L1I cache: 96KB, 64 byte cache line, 3 way, SMask:000000000000000c CPU#002 L1D cache: 16KB, 64 byte cache line, 4 way, SMask:0000000000000004 CPU#002 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:000000000000000c, inclusive CPU#002 L1D 4K TLB: 64 entries, full, SMask:0000000000000004 CPU#002 L1D 2M TLB: 64 entries, full, SMask:0000000000000004 CPU#002 L1D 1G TLB: 64 entries, full, SMask:0000000000000004 CPU#002 L2D 4K TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#002 L2D 2M TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#002 L2D 1G TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#002 L1I 4K TLB: 48 entries, full, SMask:0000000000000004 CPU#002 L1I 2M TLB: 24 entries, full, SMask:0000000000000004 CPU#002 L1I 1G TLB: 24 entries, full, SMask:0000000000000004 CPU#002 L2I 4K TLB: 512 entries, 4 way, SMask:000000000000000c CPU#002 L2I 2M TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#002 L2I 1G TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 Vendor: AuthenticAMD Family: 6f Model: 38 Stepping: 1 CoreType:0x10630f81 CPU#003 Type: "AMD A10-7890K Radeon R7, 12 Compute Cores 4C+8G" CPU#003 AffMask: 0x0000000000000008 CPU#003 PhysMask:0x000000000000000f CPU#003 APIC_ID:0x00000013 Phys_ID:000 Node_ID:00 CU_ID:01 Core_ID:03 CPU#003 L1I cache: 96KB, 64 byte cache line, 3 way, SMask:000000000000000c CPU#003 L1D cache: 16KB, 64 byte cache line, 4 way, SMask:0000000000000008 CPU#003 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:000000000000000c, inclusive CPU#003 L1D 4K TLB: 64 entries, full, SMask:0000000000000008 CPU#003 L1D 2M TLB: 64 entries, full, SMask:0000000000000008 CPU#003 L1D 1G TLB: 64 entries, full, SMask:0000000000000008 CPU#003 L2D 4K TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 L2D 2M TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 L2D 1G TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 L1I 4K TLB: 48 entries, full, SMask:0000000000000008 CPU#003 L1I 2M TLB: 24 entries, full, SMask:0000000000000008 CPU#003 L1I 1G TLB: 24 entries, full, SMask:0000000000000008 CPU#003 L2I 4K TLB: 512 entries, 4 way, SMask:000000000000000c CPU#003 L2I 2M TLB: 1024 entries, 8 way, SMask:000000000000000c CPU#003 L2I 1G TLB: 1024 entries, 8 way, SMask:000000000000000c Instruction Latency: Used CPUs: 1 ProcMask: 0x0000000000000008 0 X86 :NOP L: [no true dep.] T: 0.06ns= 0.24c 1 X86 :0x66 NOP L: [no true dep.] T: 0.06ns= 0.25c 2 X86 : 2x 0x66 NOP L: [no true dep.] T: 0.06ns= 0.24c 3 X86 : 3x 0x66 NOP L: [no true dep.] T: 0.06ns= 0.25c 4 X86 : 4x 0x66 NOP L: [no true dep.] T: 3.31ns= 13.58c 5 X86 : 5x 0x66 NOP L: [no true dep.] T: 3.37ns= 13.83c 6 X86 : 6x 0x66 NOP L: [no true dep.] T: 3.43ns= 14.08c 7 X86 : 7x 0x66 NOP L: [no true dep.] T: 3.50ns= 14.33c 8 X86 : 8x 0x66 NOP L: [no true dep.] T: 4.94ns= 20.25c 9 X86 : 9x 0x66 NOP L: [no true dep.] T: 5.00ns= 20.50c 10 X86 :10x 0x66 NOP L: [no true dep.] T: 5.06ns= 20.75c 11 X86 :11x 0x66 NOP L: [no true dep.] T: 5.12ns= 21.00c 12 X86 :12x 0x66 NOP L: [no true dep.] T: 6.56ns= 26.92c 13 X86 :13x 0x66 NOP L: [no true dep.] T: 6.63ns= 27.17c 14 X86 :14x 0x66 NOP L: [no true dep.] T: 6.69ns= 27.42c 15 SSE2 :PAUSE L: [no true dep.] T: 0.93ns= 3.83c 16 X86 :MOV r8, imm8 L: 0.22ns= 0.9c T: 0.12ns= 0.47c 17 X86 :MOV r16, imm16 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 18 X86 :MOV r32, imm32 L: 0.12ns= 0.5c T: 0.12ns= 0.47c 19 AMD64 :MOV r64, imm64 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 20 X86 :MOV r8, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 21 X86 :MOV r16, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 22 X86 :MOV r32, r32 L: 0.24ns= 1.0c T: 0.06ns= 0.25c 23 AMD64 :MOV r64, r64 L: 0.24ns= 1.0c T: 0.06ns= 0.24c 24 X86 :MOV r8, [m8] L: 1.16ns= 4.8c T: 0.12ns= 0.48c 25 X86 :MOV r16, [m16] L: 1.16ns= 4.8c T: 0.12ns= 0.48c 26 X86 :MOV r32, [m32] L: 0.93ns= 3.8c T: 0.12ns= 0.48c 27 AMD64 :MOV r64, [m64] L: 0.93ns= 3.8c T: 0.12ns= 0.48c 28 X86 :MOV [m8], r8 L: [memory dep.] T: 0.22ns= 0.92c 29 X86 :MOV [m16], r16 L: [memory dep.] T: 0.24ns= 1.00c 30 X86 :MOV [m32], r32 L: [memory dep.] T: 0.22ns= 0.92c 31 X86 :MOV [m32 + 8], r32 L: [memory dep.] T: 0.22ns= 0.92c 32 AMD64 :MOV [m64], r64 L: [memory dep.] T: 0.22ns= 0.92c 33 AMD64 :MOV [m64 + 16], r64 L: [memory dep.] T: 0.22ns= 0.92c 34 X86 :MOV r8,[m8]+MOV [m8],r8 L: 2.76ns= 11.3c T: 0.20ns= 0.81c 35 X86 :MOV r16,[m16]+MOV [m16],r16 L: 2.78ns= 11.4c T: 0.10ns= 0.40c 36 X86 :MOV r32,[m32]+MOV [m32],r32 L: 2.56ns= 10.5c T: 0.16ns= 0.64c 37 AMD64 :MOV r64,[m64]+MOV [m64],r64 L: 2.56ns= 10.5c T: 0.20ns= 0.80c 38 SSE2 :MOVNTI [m32], r32 L: [memory dep.] T: 1.33ns= 1.33c 39 AMD64 :MOVNTI [m64], r64 L: [memory dep.] T: 1.33ns= 1.33c 40 CMOV :CMOVNZ r16, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 41 CMOV :CMOVNZ r32, r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 42 AMD64 :CMOVNZ r64, r64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 43 X86 :MOVSX r16, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 44 X86 :MOVSX r32, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 45 AMD64 :MOVSX r64, r8 L: 0.24ns= 1.0c T: 0.11ns= 0.47c 46 X86 :MOVSX r32, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 47 AMD64 :MOVSX r64, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 48 AMD64 :MOVSXD r64, r32 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 49 X86 :MOVZX r16, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 50 X86 :MOVZX r32, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 51 AMD64 :MOVZX r64, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 52 X86 :MOVZX r32, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.50c 53 AMD64 :MOVZX r64, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 54 X86 :XCHG r8, r8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 55 X86 :XCHG r16, r16 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 56 X86 :XCHG r32, r32 L: 0.24ns= 1.0c T: 0.11ns= 0.46c 57 AMD64 :XCHG r64, r64 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 58 X86 :XCHG r1_8, r2_8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 59 X86 :XCHG r1_16, r2_16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 60 X86 :XCHG r1_32, r2_32 L: 0.24ns= 1.0c T: 0.11ns= 0.45c 61 AMD64 :XCHG r1_64, r2_64 L: 0.24ns= 1.0c T: 0.11ns= 0.45c 62 X86 :XCHG r8, [m8] L: 9.31ns= 38.2c T: 9.31ns= 38.17c 63 X86 :XCHG r16, [m16] L: 9.31ns= 38.2c T: 9.31ns= 38.17c 64 X86 :XCHG r32, [m32] L: 9.31ns= 38.2c T: 9.31ns= 38.17c 65 AMD64 :XCHG r64, [m64] L: 9.31ns= 38.2c T: 9.31ns= 38.17c 66 X86 :ADD r32, 0x04000 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 67 X86 :ADD r32, 0x08000 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 68 X86 :ADD r32, 0x10000 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 69 X86 :ADD r32, 0x20000 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 70 X86 :ADD r8, r8 L: 0.22ns= 0.9c T: 0.12ns= 0.47c 71 X86 :ADD r16, r16 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 72 X86 :ADD r32, r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 73 AMD64 :ADD r64, r64 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 74 X86 :ADD r8, [m8] L: 1.22ns= 5.0c T: 0.12ns= 0.50c 75 X86 :ADD r16, [m16] L: 1.22ns= 5.0c T: 0.12ns= 0.50c 76 X86 :ADD r32, [m32] L: 1.22ns= 5.0c T: 0.12ns= 0.50c 77 AMD64 :ADD r64, [m64] L: 1.22ns= 5.0c T: 0.12ns= 0.50c 78 X86 :ADD [m8], r8 L: 1.87ns= 7.7c T: 0.24ns= 1.00c 79 X86 :ADD [m16], r16 L: 1.87ns= 7.7c T: 0.24ns= 1.00c 80 X86 :ADD [m32], r32 L: 1.71ns= 7.0c T: 0.14ns= 0.58c 81 X86 :ADD [m32 + 8], r32 L: 1.71ns= 7.0c T: 0.26ns= 1.08c 82 AMD64 :ADD [m64], r64 L: 1.71ns= 7.0c T: 0.22ns= 0.92c 83 AMD64 :ADD [m64 + 16], r64 L: 1.71ns= 7.0c T: 0.21ns= 0.85c 84 X86 :LOCK ADD [m8], r8 L: 9.53ns= 39.1c T: 9.53ns= 39.08c 85 X86 :LOCK ADD [m16], r16 L: 9.53ns= 39.1c T: 9.53ns= 39.08c 86 X86 :LOCK ADD [m32], r32 L: 9.53ns= 39.1c T: 9.53ns= 39.08c 87 X86 :LOCK ADD [m32 + 8], r32 L: 9.53ns= 39.1c T: 9.53ns= 39.08c 88 AMD64 :LOCK ADD [m64], r64 L: 9.53ns= 39.1c T: 9.53ns= 39.08c 89 AMD64 :LOCK ADD [m64 + 16], r64 L: 9.53ns= 39.1c T: 9.53ns= 39.08c 90 X86 :ADD r8, imm8 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 91 X86 :ADD r16, imm8 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 92 X86 :ADD r32, imm8 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 93 AMD64 :ADD r64, imm8 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 94 X86 :ADD r16, imm16 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 95 X86 :ADD r32, imm32 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 96 AMD64 :ADD r64, imm32 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 97 X86 :ADD [m8], imm8 L: 1.87ns= 7.7c T: 0.22ns= 0.92c 98 X86 :ADD [m16], imm8 L: 1.87ns= 7.7c T: 0.22ns= 0.92c 99 X86 :ADD [m32], imm8 L: 1.71ns= 7.0c T: 0.15ns= 0.63c 100 AMD64 :ADD [m64], imm8 L: 1.71ns= 7.0c T: 0.22ns= 0.92c 101 X86 :ADD [m16], imm16 L: 1.87ns= 7.7c T: 0.22ns= 0.92c 102 X86 :ADD [m32], imm32 L: 1.71ns= 7.0c T: 0.07ns= 0.28c 103 AMD64 :ADD [m64], imm32 L: 1.71ns= 7.0c T: 0.22ns= 0.92c 104 X86 :ADD al, imm8 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 105 X86 :ADD ax, imm16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 106 X86 :ADD eax, imm32 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 107 AMD64 :ADD rax, imm32 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 108 X86 :SUB r8, r8 L: 0.22ns= 0.9c T: 0.12ns= 0.47c 109 X86 :SUB r16, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 110 X86 :SUB r32, r32 L: 0.12ns= 0.5c T: 0.12ns= 0.50c 111 AMD64 :SUB r64, r64 L: 0.12ns= 0.5c T: 0.12ns= 0.47c 112 X86 :SUB r1_8, r2_8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 113 X86 :SUB r1_16, r2_16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 114 X86 :SUB r1_32, r2_32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 115 AMD64 :SUB r1_64, r2_64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 116 X86 :ADC r8, r8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 117 X86 :ADC r16, r16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 118 X86 :ADC r32, r32 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 119 AMD64 :ADC r64, r64 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 120 X86 :SBB r8, r8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 121 X86 :SBB r16, r16 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 122 X86 :SBB r32, r32 L: 0.22ns= 0.9c T: 0.22ns= 0.89c 123 AMD64 :SBB r64, r64 L: 0.22ns= 0.9c T: 0.22ns= 0.89c 124 X86 :SBB r1_8, r2_8 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 125 X86 :SBB r1_16, r2_16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 126 X86 :SBB r1_32, r2_32 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 127 AMD64 :SBB r1_64, r2_64 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 128 X86 :CMP r8, r8 L: [no true dep.] T: 0.12ns= 0.48c 129 X86 :CMP r16, r16 L: [no true dep.] T: 0.12ns= 0.48c 130 X86 :CMP r32, r32 L: [no true dep.] T: 0.12ns= 0.48c 131 AMD64 :CMP r64, r64 L: [no true dep.] T: 0.12ns= 0.48c 132 X86 :CMP r1_8, r2_8 L: [no true dep.] T: 0.12ns= 0.48c 133 X86 :CMP r1_16, r2_16 L: [no true dep.] T: 0.12ns= 0.48c 134 X86 :CMP r1_32, r2_32 L: [no true dep.] T: 0.12ns= 0.48c 135 AMD64 :CMP r1_64, r2_64 L: [no true dep.] T: 0.12ns= 0.48c 136 X86 :AND r8, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 137 X86 :AND r16, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 138 X86 :AND r32, r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 139 AMD64 :AND r64, r64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 140 X86 :AND r1_8, r2_8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 141 X86 :AND r1_16, r2_16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 142 X86 :AND r1_32, r2_32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 143 AMD64 :AND r1_64, r2_64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 144 X86 :OR r8, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 145 X86 :OR r16, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 146 X86 :OR r32, r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 147 AMD64 :OR r64, r64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 148 X86 :OR r1_8, r2_8 L: 0.24ns= 1.0c T: 0.12ns= 0.50c 149 X86 :OR r1_16, r2_16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 150 X86 :OR r1_32, r2_32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 151 AMD64 :OR r1_64, r2_64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 152 X86 :XOR r8, r8 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 153 X86 :XOR r16, r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 154 X86 :XOR r32, r32 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 155 AMD64 :XOR r64, r64 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 156 X86 :XOR r1_8, r2_8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 157 X86 :XOR r1_16, r2_16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 158 X86 :XOR r1_32, r2_32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 159 AMD64 :XOR r1_64, r2_64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 160 X86 :NEG r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 161 X86 :NEG r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 162 X86 :NEG r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 163 AMD64 :NEG r64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 164 X86 :NOT r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 165 X86 :NOT r16 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 166 X86 :NOT r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 167 AMD64 :NOT r64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 168 X86 :TEST r8, r8 L: [no true dep.] T: 0.12ns= 0.48c 169 X86 :TEST r16, r16 L: [no true dep.] T: 0.12ns= 0.48c 170 X86 :TEST r32, r32 L: [no true dep.] T: 0.12ns= 0.48c 171 AMD64 :TEST r64, r64 L: [no true dep.] T: 0.12ns= 0.48c 172 X86 :TEST r1_8, r2_8 L: [no true dep.] T: 0.12ns= 0.48c 173 X86 :TEST r1_16, r2_16 L: [no true dep.] T: 0.12ns= 0.48c 174 X86 :TEST r1_32, r2_32 L: [no true dep.] T: 0.12ns= 0.48c 175 AMD64 :TEST r1_64, r2_64 L: [no true dep.] T: 0.12ns= 0.48c 176 X86 :BT r16, r16 L: [no true dep.] T: 0.12ns= 0.48c 177 X86 :BT r32, r32 L: [no true dep.] T: 0.12ns= 0.48c 178 AMD64 :BT r64, r64 L: [no true dep.] T: 0.12ns= 0.49c 179 X86 :BT r16, imm8 L: [no true dep.] T: 0.12ns= 0.48c 180 X86 :BT r32, imm8 L: [no true dep.] T: 0.12ns= 0.48c 181 AMD64 :BT r64, imm8 L: [no true dep.] T: 0.12ns= 0.48c 182 X86 :BTC r16, r16 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 183 X86 :BTC r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 184 AMD64 :BTC r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 185 X86 :BTC r16, imm8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 186 X86 :BTC r32, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 187 AMD64 :BTC r64, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 188 X86 :BTR r16, r16 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 189 X86 :BTR r32, r32 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 190 AMD64 :BTR r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 191 X86 :BTR r16, imm8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 192 X86 :BTR r32, imm8 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 193 AMD64 :BTR r64, imm8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 194 X86 :BTS r16, r16 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 195 X86 :BTS r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 196 AMD64 :BTS r64, r64 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 197 X86 :BTS r16, imm8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 198 X86 :BTS r32, imm8 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 199 AMD64 :BTS r64, imm8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 200 X86 :SETC r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 201 X86 :INC r8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 202 X86 :INC r16 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 203 X86 :INC r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 204 AMD64 :INC r64 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 205 AMD64 :LEA r16, [r64 + r64] L: 0.47ns= 1.9c T: 0.22ns= 0.92c 206 AMD64 :LEA r32, [r64 + r64] L: 0.24ns= 1.0c T: 0.11ns= 0.47c 207 AMD64 :LEA r64, [r64 + r64] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 208 AMD64 :LEA r16, [r64 + r64 + disp8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 209 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.49c 210 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 211 AMD64 :LEA r16, [r64 + r64 * 8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 212 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 213 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 214 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 215 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 216 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 217 X86 :SHL r8, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 218 X86 :SHL r16, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 219 X86 :SHL r32, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.50c 220 AMD64 :SHL r64, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.50c 221 X86 :SHL r8, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.50c 222 X86 :SHL r16, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 223 X86 :SHL r32, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 224 AMD64 :SHL r64, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 225 X86 :SHL r8, cl L: 0.24ns= 1.0c T: 0.10ns= 0.42c 226 X86 :SHL r16, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 227 X86 :SHL r32, cl L: 0.24ns= 1.0c T: 0.12ns= 0.50c 228 AMD64 :SHL r64, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 229 X86 :SHR r8, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 230 X86 :SHR r16, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 231 X86 :SHR r32, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 232 AMD64 :SHR r64, 1 L: 0.24ns= 1.0c T: 0.11ns= 0.47c 233 X86 :SHR r8, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 234 X86 :SHR r16, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 235 X86 :SHR r32, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 236 AMD64 :SHR r64, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 237 X86 :SHR r8, cl L: 0.24ns= 1.0c T: 0.10ns= 0.41c 238 X86 :SHR r16, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 239 X86 :SHR r32, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 240 AMD64 :SHR r64, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 241 X86 :SAR r8, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 242 X86 :SAR r16, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 243 X86 :SAR r32, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 244 AMD64 :SAR r64, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 245 X86 :SAR r8, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 246 X86 :SAR r16, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 247 X86 :SAR r32, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 248 AMD64 :SAR r64, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 249 X86 :SAR r8, cl L: 0.24ns= 1.0c T: 0.11ns= 0.45c 250 X86 :SAR r16, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 251 X86 :SAR r32, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 252 AMD64 :SAR r64, cl L: 0.24ns= 1.0c T: 0.12ns= 0.47c 253 X86 :SHLD r1_16, r1_16, imm8 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 254 X86 :SHLD r1_32, r1_32, imm8 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 255 AMD64 :SHLD r1_64, r1_64, imm8 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 256 X86 :SHLD r1_16, r1_16, cl L: 0.98ns= 4.0c T: 0.73ns= 3.00c 257 X86 :SHLD r1_32, r1_32, cl L: 0.93ns= 3.8c T: 0.69ns= 2.83c 258 AMD64 :SHLD r1_64, r1_64, cl L: 0.93ns= 3.8c T: 0.69ns= 2.83c 259 X86 :SHRD r1_16, r1_16, imm8 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 260 X86 :SHRD r1_32, r1_32, imm8 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 261 AMD64 :SHRD r1_64, r1_64, imm8 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 262 X86 :SHRD r1_16, r1_16, cl L: 0.93ns= 3.8c T: 0.67ns= 2.75c 263 X86 :SHRD r1_32, r1_32, cl L: 0.93ns= 3.8c T: 0.69ns= 2.83c 264 AMD64 :SHRD r1_64, r1_64, cl L: 0.93ns= 3.8c T: 0.69ns= 2.83c 265 X86 :ROL r8, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 266 X86 :ROL r16, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 267 X86 :ROL r32, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 268 AMD64 :ROL r64, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 269 X86 :ROL r8, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 270 X86 :ROL r16, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 271 X86 :ROL r32, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 272 AMD64 :ROL r64, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 273 X86 :ROL r8, cl L: 0.24ns= 1.0c T: 0.11ns= 0.46c 274 X86 :ROL r16, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 275 X86 :ROL r32, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 276 AMD64 :ROL r64, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 277 X86 :ROR r8, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.47c 278 X86 :ROR r16, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 279 X86 :ROR r32, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 280 AMD64 :ROR r64, 1 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 281 X86 :ROR r8, imm8 L: 0.24ns= 1.0c T: 0.11ns= 0.47c 282 X86 :ROR r16, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 283 X86 :ROR r32, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 284 AMD64 :ROR r64, imm8 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 285 X86 :ROR r8, cl L: 0.24ns= 1.0c T: 0.11ns= 0.45c 286 X86 :ROR r16, cl L: 0.24ns= 1.0c T: 0.12ns= 0.49c 287 X86 :ROR r32, cl L: 0.24ns= 1.0c T: 0.12ns= 0.48c 288 AMD64 :ROR r64, cl L: 0.24ns= 1.0c T: 0.12ns= 0.50c 289 X86 :RCL r8, 1 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 290 X86 :RCL r16, 1 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 291 X86 :RCL r32, 1 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 292 AMD64 :RCL r64, 1 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 293 X86 :RCL r8, imm8 L: 2.91ns= 11.9c T: 2.91ns= 11.92c 294 X86 :RCL r16, imm8 L: 2.44ns= 10.0c T: 2.44ns= 10.00c 295 X86 :RCL r32, imm8 L: 1.75ns= 7.2c T: 1.75ns= 7.17c 296 AMD64 :RCL r64, imm8 L: 1.75ns= 7.2c T: 1.75ns= 7.17c 297 X86 :RCL r8, cl L: 2.82ns= 11.6c T: 2.78ns= 11.42c 298 X86 :RCL r16, cl L: 2.36ns= 9.7c T: 2.32ns= 9.50c 299 X86 :RCL r32, cl L: 1.63ns= 6.7c T: 1.63ns= 6.67c 300 AMD64 :RCL r64, cl L: 1.63ns= 6.7c T: 1.63ns= 6.67c 301 X86 :RCR r8, 1 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 302 X86 :RCR r16, 1 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 303 X86 :RCR r32, 1 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 304 AMD64 :RCR r64, 1 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 305 X86 :RCR r8, imm8 L: 2.68ns= 11.0c T: 2.68ns= 11.00c 306 X86 :RCR r16, imm8 L: 2.22ns= 9.1c T: 2.22ns= 9.08c 307 X86 :RCR r32, imm8 L: 1.63ns= 6.7c T: 1.63ns= 6.67c 308 AMD64 :RCR r64, imm8 L: 1.63ns= 6.7c T: 1.63ns= 6.67c 309 X86 :RCR r8, cl L: 2.56ns= 10.5c T: 2.56ns= 10.50c 310 X86 :RCR r16, cl L: 2.09ns= 8.6c T: 2.09ns= 8.58c 311 X86 :RCR r32, cl L: 1.61ns= 6.6c T: 1.52ns= 6.25c 312 AMD64 :RCR r64, cl L: 1.61ns= 6.6c T: 1.52ns= 6.25c 313 X86 :BSF r16, r16 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 314 X86 :BSF r32, r32 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 315 AMD64 :BSF r64, r64 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 316 X86 :BSR r16, r16 L: 0.93ns= 3.8c T: 0.93ns= 3.83c 317 X86 :BSR r32, r32 L: 0.93ns= 3.8c T: 0.93ns= 3.83c 318 AMD64 :BSR r64, r64 L: 0.93ns= 3.8c T: 0.93ns= 3.83c 319 X86 :BSWAP r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 320 AMD64 :BSWAP r64 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 327 X86 :IMUL r16, r16 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 328 X86 :IMUL r32, r32 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 329 AMD64 :IMUL r64, r64 L: 1.40ns= 5.8c T: 0.93ns= 3.83c 330 X86 :IMUL r16, r16, imm8 L: 1.16ns= 4.8c T: 0.45ns= 1.83c 331 X86 :IMUL r32, r32, imm8 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 332 AMD64 :IMUL r64, r64, imm8 L: 1.40ns= 5.8c T: 0.93ns= 3.83c 333 X86 :IMUL r16, r16, imm16 L: 1.16ns= 4.8c T: 0.45ns= 1.83c 334 X86 :IMUL r32, r32, imm32 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 335 AMD64 :IMUL r64, r64, imm32 L: 1.40ns= 5.8c T: 0.93ns= 3.83c 336 X86 :IMUL r8 (ah) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 337 X86 :IMUL r16 (dx) L: 1.40ns= 5.8c T: 0.93ns= 3.83c 338 X86 :IMUL r32 (edx) L: 1.16ns= 4.8c T: 0.93ns= 3.83c 339 AMD64 :IMUL r64 (rdx) L: 1.63ns= 6.7c T: 1.40ns= 5.75c 340 X86 :MUL r8 (ah) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 341 X86 :MUL r16 (dx) L: 1.40ns= 5.8c T: 0.93ns= 3.83c 342 X86 :MUL r32 (edx) L: 1.16ns= 4.8c T: 0.93ns= 3.83c 343 AMD64 :MUL r64 (rdx) L: 1.63ns= 6.7c T: 1.40ns= 5.75c 344 X86 :IMUL r8 (al) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 345 X86 :IMUL r16 (ax) L: 0.98ns= 4.0c T: 0.93ns= 3.83c 346 X86 :IMUL r32 (eax) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 347 AMD64 :IMUL r64 (rax) L: 1.40ns= 5.8c T: 1.38ns= 5.67c 348 X86 :MUL r8 (al) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 349 X86 :MUL r16 (ax) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 350 X86 :MUL r32 (eax) L: 0.93ns= 3.8c T: 0.93ns= 3.83c 351 AMD64 :MUL r64 (rax) L: 1.40ns= 5.8c T: 1.40ns= 5.75c 352 X86 :IDIV r8 14/ 7b (full) L: 5.12ns= 21.0c T: 4.88ns= 20.00c 353 X86 :IDIV r8 12/ 7b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 354 X86 :IDIV r8 7/ 7b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 355 X86 :IDIV r8 4/ 7b ax upd L: [no true dep.] T: 4.19ns= 17.17c 356 X86 :IDIV r8 0/ 7b L: [no true dep.] T: 3.96ns= 16.25c 357 X86 :IDIV r8 11/ 4b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 358 X86 :IDIV r8 8/ 4b ax upd L: [no true dep.] T: 4.19ns= 17.17c 359 X86 :IDIV r8 4/ 4b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 360 X86 :IDIV r8 0/ 4b L: [no true dep.] T: 3.96ns= 16.25c 361 X86 :IDIV r8 2^12/2^6 ax upd L: [no true dep.] T: 4.19ns= 17.17c 362 X86 :IDIV r8 1/1 L: 4.19ns= 17.2c T: 3.96ns= 16.25c 363 X86 :IDIV r8 1/1 ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 364 X86 :IDIV r16 30/15b (full) L: 6.28ns= 25.8c T: 6.10ns= 25.00c 365 X86 :IDIV r16 24/15b ax upd L: 5.12ns= 21.0c T: 4.96ns= 20.33c 366 X86 :IDIV r16 15/15b ax upd L: 3.72ns= 15.3c T: 3.58ns= 14.67c 367 X86 :IDIV r16 8/15b ax/dx upd L: [no true dep.] T: 3.72ns= 15.25c 368 X86 :IDIV r16 0/15b L: [no true dep.] T: 3.50ns= 14.33c 369 X86 :IDIV r16 23/ 8b ax upd L: 6.50ns= 26.7c T: 6.36ns= 26.08c 370 X86 :IDIV r16 16/ 8b ax upd L: [no true dep.] T: 4.74ns= 19.42c 371 X86 :IDIV r16 8/ 8b ax upd L: 3.72ns= 15.3c T: 3.58ns= 14.67c 372 X86 :IDIV r16 0/ 8b L: [no true dep.] T: 3.50ns= 14.33c 373 X86 :IDIV r16 2^28/2^14 ax/dx L: [no true dep.] T: 6.04ns= 24.75c 374 X86 :IDIV r16 1/1 L: 3.50ns= 14.3c T: 3.50ns= 14.33c 375 X86 :IDIV r16 1/1 ax upd L: 3.72ns= 15.3c T: 3.58ns= 14.67c 376 X86 :IDIV r16 1/1 ax/dx upd L: 3.94ns= 16.2c T: 3.72ns= 15.25c 377 X86 :IDIV r32 62/31b (full) L: 9.78ns= 40.1c T: 9.78ns= 40.08c 378 X86 :IDIV r32 62/31b 0 rem. L: 9.78ns= 40.1c T: 9.78ns= 40.08c 379 X86 :IDIV r32 48/31b eax upd L: 6.50ns= 26.7c T: 6.50ns= 26.67c 380 X86 :IDIV r32 31/31b eax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 381 X86 :IDIV r32 16/31b eax/edx L: [no true dep.] T: 3.46ns= 14.17c 382 X86 :IDIV r32 0/31b L: [no true dep.] T: 3.25ns= 13.33c 383 X86 :IDIV r32 47/16b eax upd L: 9.78ns= 40.1c T: 9.78ns= 40.08c 384 X86 :IDIV r32 32/16b eax upd L: [no true dep.] T: 6.28ns= 25.75c 385 X86 :IDIV r32 16/16b eax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 386 X86 :IDIV r32 0/16b L: [no true dep.] T: 3.25ns= 13.33c 387 X86 :IDIV r32 2^60/2^30 eax/edx L: [no true dep.] T: 9.53ns= 39.08c 388 X86 :IDIV r32 1/1 L: 3.25ns= 13.3c T: 3.25ns= 13.33c 389 X86 :IDIV r32 1/1 eax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 390 X86 :IDIV r32 1/1 eax/edx upd L: 3.43ns= 14.1c T: 3.43ns= 14.08c 391 AMD64 :IDIV r64 126/63b (full) L: 17.21ns= 70.6c T: 17.21ns= 70.58c 392 AMD64 :IDIV r64 126/63b 0 rem. L: 17.21ns= 70.6c T: 17.21ns= 70.58c 393 AMD64 :IDIV r64 96/63b rax upd L: 10.22ns= 41.9c T: 10.22ns= 41.92c 394 AMD64 :IDIV r64 63/63b rax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 395 AMD64 :IDIV r64 32/63b rax/rdx L: [no true dep.] T: 3.37ns= 13.83c 396 AMD64 :IDIV r64 0/63b L: [no true dep.] T: 3.25ns= 13.33c 397 AMD64 :IDIV r64 95/32b rax upd L: 17.21ns= 70.6c T: 17.21ns= 70.58c 398 AMD64 :IDIV r64 64/32b rax upd L: [no true dep.] T: 10.00ns= 41.00c 399 AMD64 :IDIV r64 32/32b rax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 400 AMD64 :IDIV r64 0/32b L: [no true dep.] T: 3.25ns= 13.33c 401 AMD64 :IDIV r64 2^124/2^62 rax/rdx L: [no true dep.] T: 16.97ns= 69.58c 402 AMD64 :IDIV r64 1/1 L: 3.25ns= 13.3c T: 3.25ns= 13.33c 403 AMD64 :IDIV r64 1/1 rax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 404 AMD64 :IDIV r64 1/1 rax/rdx upd L: 3.35ns= 13.8c T: 3.35ns= 13.75c 405 X86 :DIV r8 16/ 8b (full) L: 5.12ns= 21.0c T: 4.88ns= 20.00c 406 X86 :DIV r8 12/ 8b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 407 X86 :DIV r8 8/ 8b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 408 X86 :DIV r8 4/ 8b ax upd L: [no true dep.] T: 4.19ns= 17.17c 409 X86 :DIV r8 0/ 8b L: [no true dep.] T: 3.96ns= 16.25c 410 X86 :DIV r8 12/ 4b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 411 X86 :DIV r8 8/ 4b ax upd L: [no true dep.] T: 4.19ns= 17.17c 412 X86 :DIV r8 4/ 4b ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 413 X86 :DIV r8 0/ 4b L: [no true dep.] T: 3.96ns= 16.25c 414 X86 :DIV r8 2^14/2^7 ax upd L: [no true dep.] T: 4.19ns= 17.17c 415 X86 :DIV r8 1/1 L: 4.19ns= 17.2c T: 3.96ns= 16.25c 416 X86 :DIV r8 1/1 ax upd L: 4.41ns= 18.1c T: 4.19ns= 17.17c 417 X86 :DIV r16 32/16b (full) L: 6.28ns= 25.8c T: 6.10ns= 25.00c 418 X86 :DIV r16 30/15b 0 rem. L: 6.28ns= 25.8c T: 6.10ns= 25.00c 419 X86 :DIV r16 24/16b ax upd L: 4.88ns= 20.0c T: 4.74ns= 19.42c 420 X86 :DIV r16 16/16b ax upd L: 3.72ns= 15.3c T: 3.58ns= 14.67c 421 X86 :DIV r16 8/16b ax/dx upd L: [no true dep.] T: 3.72ns= 15.25c 422 X86 :DIV r16 0/16b L: [no true dep.] T: 3.50ns= 14.33c 423 X86 :DIV r16 24/ 8b ax upd L: 6.50ns= 26.7c T: 6.36ns= 26.08c 424 X86 :DIV r16 16/ 8b ax upd L: [no true dep.] T: 4.74ns= 19.42c 425 X86 :DIV r16 8/ 8b ax upd L: 3.72ns= 15.3c T: 3.58ns= 14.67c 426 X86 :DIV r16 0/ 8b L: [no true dep.] T: 3.50ns= 14.33c 427 X86 :DIV r16 1/1 L: 3.50ns= 14.3c T: 3.50ns= 14.33c 428 X86 :DIV r16 1/1 ax upd L: 3.72ns= 15.3c T: 3.58ns= 14.67c 429 X86 :DIV r16 1/1 ax/dx upd L: 3.94ns= 16.2c T: 3.72ns= 15.25c 430 X86 :DIV r32 64/32b (full) L: 9.78ns= 40.1c T: 9.78ns= 40.08c 431 X86 :DIV r32 62/31b 0 rem. L: 9.76ns= 40.0c T: 9.76ns= 40.00c 432 X86 :DIV r32 48/32b eax upd L: 6.28ns= 25.8c T: 6.28ns= 25.75c 433 X86 :DIV r32 32/32b eax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 434 X86 :DIV r32 16/32b eax/edx L: [no true dep.] T: 3.43ns= 14.08c 435 X86 :DIV r32 0/32b L: [no true dep.] T: 3.25ns= 13.33c 436 X86 :DIV r32 48/16b eax upd L: 9.78ns= 40.1c T: 9.78ns= 40.08c 437 X86 :DIV r32 32/16b eax upd L: [no true dep.] T: 6.28ns= 25.75c 438 X86 :DIV r32 16/16b eax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 439 X86 :DIV r32 0/16b L: [no true dep.] T: 3.25ns= 13.33c 440 X86 :DIV r32 2^62/2^31 eax/edx L: [no true dep.] T: 9.78ns= 40.08c 441 X86 :DIV r32 1/1 L: 3.25ns= 13.3c T: 3.25ns= 13.33c 442 X86 :DIV r32 1/1 eax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 443 X86 :DIV r32 1/1 eax/edx upd L: 3.43ns= 14.1c T: 3.43ns= 14.08c 444 AMD64 :DIV r64 128/64b (full) L: 17.21ns= 70.6c T: 17.21ns= 70.58c 445 AMD64 :DIV r64 126/63b 0 rem. L: 17.21ns= 70.6c T: 17.21ns= 70.58c 446 AMD64 :DIV r64 96/64b rax upd L: 10.00ns= 41.0c T: 10.00ns= 41.00c 447 AMD64 :DIV r64 64/64b rax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 448 AMD64 :DIV r64 32/64b rax/rdx L: [no true dep.] T: 3.37ns= 13.83c 449 AMD64 :DIV r64 0/64b L: [no true dep.] T: 3.25ns= 13.33c 450 AMD64 :DIV r64 96/32b rax upd L: 17.21ns= 70.6c T: 17.21ns= 70.58c 451 AMD64 :DIV r64 64/32b rax upd L: [no true dep.] T: 10.00ns= 41.00c 452 AMD64 :DIV r64 32/32b rax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 453 AMD64 :DIV r64 0/32b L: [no true dep.] T: 3.25ns= 13.33c 454 AMD64 :DIV r64 2^126/2^63 rax/rdx L: [no true dep.] T: 17.21ns= 70.58c 455 AMD64 :DIV r64 1/1 L: 3.25ns= 13.3c T: 3.25ns= 13.33c 456 AMD64 :DIV r64 1/1 rax upd L: 3.25ns= 13.3c T: 3.25ns= 13.33c 457 AMD64 :DIV r64 1/1 rax/rdx upd L: 3.35ns= 13.8c T: 3.35ns= 13.75c 458 X86 :CBW L: 0.24ns= 1.0c T: 0.22ns= 0.92c 459 X86 :CWDE L: 0.24ns= 1.0c T: 0.22ns= 0.92c 460 AMD64 :CDQE L: 0.24ns= 1.0c T: 0.22ns= 0.92c 461 X86 :CWD L: 0.28ns= 1.2c T: 0.28ns= 1.17c 462 X86 :CDQ L: 0.12ns= 0.5c T: 0.12ns= 0.48c 463 AMD64 :CQO L: 0.12ns= 0.5c T: 0.12ns= 0.48c 464 X86 :CLC L: 0.12ns= 0.5c T: 0.12ns= 0.48c 465 X86 :STC L: 0.12ns= 0.5c T: 0.12ns= 0.48c 466 X86 :CMC L: 0.22ns= 0.9c T: 0.22ns= 0.89c 467 X86 :CLD L: 0.69ns= 2.8c T: 0.69ns= 2.83c 468 X86 :STD L: 0.93ns= 3.8c T: 0.93ns= 3.83c 475 LAHF :LAHF L: 0.47ns= 1.9c T: 0.47ns= 1.92c 476 LAHF :SAHF L: 0.24ns= 1.0c T: 0.24ns= 1.00c 483 X86 :PUSH r16 L: [no true dep.] T: 0.22ns= 0.92c 484 X86 :POP r16 L: [no true dep.] T: 0.24ns= 1.00c 485 X86 :PUSH r16 + POP r16 L: 2.60ns= 10.7c T: 0.33ns= 1.33c 486 AMD64 :PUSH r64 L: [no true dep.] T: 0.26ns= 1.08c 487 AMD64 :POP r64 L: [no true dep.] T: 0.22ns= 0.92c 488 AMD64 :PUSH r64 + POP r64 L: 1.69ns= 6.9c T: 0.49ns= 2.00c 489 AMD64 :PUSH imm8 L: [no true dep.] T: 0.26ns= 1.08c 490 AMD64 :PUSH imm8 + POP r64 L: 0.57ns= 2.3c T: 0.53ns= 2.17c 491 AMD64 :PUSH imm32 L: [no true dep.] T: 0.28ns= 1.17c 492 AMD64 :PUSH imm32 + POP r64 L: 0.55ns= 2.3c T: 0.57ns= 2.33c 493 X86 :PUSH [m16] L: [no true dep.] T: 0.35ns= 1.42c 494 X86 :POP [m16] L: [no true dep.] T: 0.28ns= 1.17c 495 X86 :PUSH [m16] + POP [m16] L: 3.72ns= 15.3c T: 0.73ns= 3.00c 496 AMD64 :PUSH [m64] L: [no true dep.] T: 0.39ns= 1.58c 497 AMD64 :POP [m64] L: [no true dep.] T: 0.28ns= 1.17c 498 AMD64 :PUSH [m64] + POP [m64] L: 3.41ns= 14.0c T: 0.73ns= 3.00c 499 X86 :PUSHF L: [no true dep.] T: 0.93ns= 3.83c 501 X86 :PUSHF + POPF L: 7.26ns= 29.8c T: 7.26ns= 29.75c 502 AMD64 :PUSHFQ L: [no true dep.] T: 0.93ns= 3.83c 504 AMD64 :PUSHFQ + POPFQ L: 7.26ns= 29.8c T: 7.26ns= 29.75c 505 X86 :CMPSB L: 0.69ns= 2.8c T: 0.69ns= 2.83c 506 X86 :CMPSW L: 0.69ns= 2.8c T: 0.69ns= 2.83c 507 X86 :CMPSD L: 0.69ns= 2.8c T: 0.69ns= 2.83c 508 AMD64 :CMPSQ L: 0.69ns= 2.8c T: 0.69ns= 2.83c 509 X86 :REPE CMPSB BW in L1D: 0.51 B/c 2089MiB/s 510 X86 :REPE CMPSW BW in L1D: 1.02 B/c 4171MiB/s 511 X86 :REPE CMPSD BW in L1D: 2.02 B/c 8271MiB/s 512 AMD64 :REPE CMPSQ BW in L1D: 3.99 B/c 16349MiB/s 513 X86 :LODSB L: 0.73ns= 3.0c T: 0.69ns= 2.83c 514 X86 :LODSW L: 0.69ns= 2.8c T: 0.71ns= 2.92c 515 X86 :LODSD L: 0.69ns= 2.8c T: 0.69ns= 2.83c 516 AMD64 :LODSQ L: 0.69ns= 2.8c T: 0.69ns= 2.83c 517 X86 :REP LODSB BW in L1D: 0.34 B/c 1400MiB/s 518 X86 :REP LODSW BW in L1D: 0.68 B/c 2798MiB/s 519 X86 :REP LODSD BW in L1D: 1.62 B/c 6661MiB/s 520 AMD64 :REP LODSQ BW in L1D: 3.22 B/c 13193MiB/s 521 X86 :STOSB L: 0.69ns= 2.8c T: 0.69ns= 2.83c 522 X86 :STOSW L: 0.69ns= 2.8c T: 0.69ns= 2.83c 523 X86 :STOSD L: 0.69ns= 2.8c T: 0.69ns= 2.83c 524 AMD64 :STOSQ L: 0.69ns= 2.8c T: 0.69ns= 2.83c 525 X86 :REP STOSB BW in L1D: 8.32 B/c 34119MiB/s 526 X86 :REP STOSW BW in L1D: 8.33 B/c 34153MiB/s 527 X86 :REP STOSD BW in L1D: 8.34 B/c 34205MiB/s 528 AMD64 :REP STOSQ BW in L1D: 8.35 B/c 34223MiB/s 529 X86 :MOVSB L: 0.69ns= 2.8c T: 0.69ns= 2.83c 530 X86 :MOVSW L: 0.69ns= 2.8c T: 0.69ns= 2.83c 531 X86 :MOVSD L: 0.69ns= 2.8c T: 0.69ns= 2.83c 532 AMD64 :MOVSQ L: 0.69ns= 2.8c T: 0.69ns= 2.83c 533 X86 :REP MOVSB BW in L1D:15.88 B/c 65096MiB/s 534 X86 :REP MOVSW BW in L1D:15.86 B/c 65033MiB/s 535 X86 :REP MOVSD BW in L1D:15.92 B/c 65286MiB/s 536 AMD64 :REP MOVSQ BW in L1D:15.89 B/c 65160MiB/s 537 X86 :SCASB L: 0.69ns= 2.8c T: 0.69ns= 2.83c 538 X86 :SCASW L: 0.69ns= 2.8c T: 0.69ns= 2.83c 539 X86 :SCASD L: 0.69ns= 2.8c T: 0.71ns= 2.92c 540 AMD64 :SCASQ L: 0.69ns= 2.8c T: 0.69ns= 2.83c 541 X86 :REPNE SCASB BW in L1D: 0.29 B/c 1186MiB/s 542 X86 :REPNE SCASW BW in L1D: 0.58 B/c 2370MiB/s 543 X86 :REPNE SCASD BW in L1D: 1.15 B/c 4731MiB/s 544 AMD64 :REPNE SCASQ BW in L1D: 2.30 B/c 9435MiB/s 545 X86 :XADD r8, r8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 546 X86 :XADD r16, r16 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 547 X86 :XADD r32, r32 L: 0.47ns= 1.9c T: 0.15ns= 0.63c 548 AMD64 :XADD r64, r64 L: 0.47ns= 1.9c T: 0.16ns= 0.66c 549 X86 :CMPXCHG r8, r8 L: 0.73ns= 3.0c T: 0.69ns= 2.83c 550 X86 :CMPXCHG r16, r16 L: 0.93ns= 3.8c T: 0.69ns= 2.83c 551 X86 :CMPXCHG r32, r32 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 552 AMD64 :CMPXCHG r64, r64 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 553 CMPX8 :CMPXCHG8B L: 3.50ns= 14.3c T: 1.73ns= 7.08c 554 CMPX16 :CMPXCHG16B L: 11.40ns= 46.8c T: 11.40ns= 46.75c 555 X86 :RDTSC L: [no true dep.] T: 19.77ns= 81.08c 556 X86 :CPUID (EAX = 0) L: 25.59ns=104.9c T: 25.59ns=104.92c 557 X86 :CPUID (EAX = 1) L: 80.01ns=328.1c T: 80.01ns=328.08c 558 POPCNT :POPCNT r16, r16 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 559 POPCNT :POPCNT r32, r32 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 560 POPCNT :POPCNT r64, r64 L: 0.93ns= 3.8c T: 0.93ns= 3.83c 561 ABM :LZCNT r16, r16 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 562 ABM :LZCNT r32, r32 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 563 ABM :LZCNT r64, r64 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 564 SSE4.2 :CRC32 r32, r8 L: 0.69ns= 2.8c T: 0.45ns= 1.83c 565 SSE4.2 :CRC32 r32, r16 L: 1.16ns= 4.8c T: 1.16ns= 4.75c 566 SSE4.2 :CRC32 r32, r32 L: 1.40ns= 5.8c T: 1.40ns= 5.75c 567 SSE4.2 :CRC32 r64, r8 L: 0.69ns= 2.8c T: 0.47ns= 1.92c 568 SSE4.2 :CRC32 r64, r16 L: 2.32ns= 9.5c T: 1.95ns= 8.00c 569 X87 :FNOP L: [no true dep.] T: 0.06ns= 0.24c 570 X87 :FXCH st(i) L: 0.12ns= 0.5c T: 0.12ns= 0.47c 571 X87 :FCHS L: 0.47ns= 1.9c T: 0.47ns= 1.92c 572 X87 :FABS L: 0.47ns= 1.9c T: 0.47ns= 1.92c 573 X87 :FTST L: [no true dep.] T: 0.12ns= 0.48c 574 X87 :FXAM L: [no true dep.] T: 0.12ns= 0.48c 575 CMOV :FCMOVE st, st(i) L: 0.69ns= 2.8c T: 0.69ns= 2.83c 576 X87 :FADD st(i), st (st = 0.0) L: 1.16ns= 4.8c T: 0.12ns= 0.48c 577 X87 :FADD st(i), st L: 1.16ns= 4.8c T: 0.16ns= 0.67c 578 X87 :FADD st, st(i), FXCH st(i) L: 1.16ns= 4.8c T: 0.49ns= 2.00c 579 X87 :FMUL st(i), st (st = 0.0) L: 1.16ns= 4.8c T: 0.06ns= 0.23c 580 X87 :FMUL st(i), st L: 1.16ns= 4.8c T: 0.06ns= 0.23c 581 X87 :FMUL st, st(i), FXCH st(i) L: 1.16ns= 4.8c T: 0.47ns= 1.92c 582 X87 :FMUL + FADD st, st(i) L: 2.32ns= 9.5c T: [not enough reg] 583 X87 :FMUL st(2i) FADD st(2i+1) L: 1.22ns= 5.0c T: [not enough reg] 584 X87 :FDIV32 st(i), st L: 4.19ns= 17.2c T: 1.50ns= 6.17c 585 X87 :FDIV64 st(i), st L: 7.68ns= 31.5c T: 3.25ns= 13.33c 586 X87 :FDIV80 st(i), st L: 8.84ns= 36.3c T: 3.84ns= 15.75c 587 X87 :FDIV80 (0.0l/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 588 X87 :FDIV80 (x/1.0l) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 589 X87 :FDIV80 (x/2.0l) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 590 X87 :FDIV80 (x/0.5l) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 591 X87 :FSQRT32 st L: 5.59ns= 22.9c T: 2.22ns= 9.08c 592 X87 :FSQRT64 st L: 10.22ns= 41.9c T: 4.53ns= 18.58c 593 X87 :FSQRT80 st L: 11.63ns= 47.7c T: 5.22ns= 21.42c 594 X87 :FSQRT80 (0.0l) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 595 X87 :FSQRT80 (1.0l) L: 2.09ns= 8.6c T: 1.12ns= 4.58c 596 X87 :FDECSTP L: [no true dep.] T: 0.06ns= 0.24c 597 X87 :FINCSTP L: [no true dep.] T: 0.06ns= 0.24c 598 X87 :FCOM st(i) L: [no true dep.] T: 0.12ns= 0.48c 599 CMOV :FCOMI st, st(i) L: [no true dep.] T: 0.24ns= 1.00c 600 X87 :FSIN80 (0.0) L: 15.12ns= 62.0c T: 15.12ns= 62.00c 601 X87 :FSIN80 (0.0) + FADD L: 16.71ns= 68.5c T: 15.12ns= 62.00c 602 X87 :FSIN80 (1.0) + FADD L: 40.87ns=167.6c T: 30.12ns=123.50c 603 X87 :FSIN80 (4Pi) + FADD L: 47.44ns=194.5c T: 34.88ns=143.00c 604 X87 :FSIN80 (2Pi) + FADD L: 47.44ns=194.5c T: 34.88ns=143.00c 605 X87 :FSIN80 (Pi) + FADD L: 47.76ns=195.8c T: 35.81ns=146.83c 606 X87 :FSIN80 (Pi/2) + FADD L: 47.70ns=195.6c T: 35.81ns=146.83c 607 X87 :FSIN80 (Pi/4) + FADD L: 40.00ns=164.0c T: 29.88ns=122.50c 608 X87 :FSIN80 (Pi/8) + FADD L: 39.94ns=163.8c T: 28.37ns=116.33c 609 X87 :FSIN80 (Pi/16) + FADD L: 39.94ns=163.8c T: 28.37ns=116.33c 610 X87 :FSIN80 (Pi/32) + FADD L: 39.81ns=163.3c T: 28.37ns=116.33c 611 X87 :FCOS80 (0.73908513...) L: 38.37ns=157.3c T: 28.98ns=118.83c 612 X87 :FCOS80 (0.73908513...)+FADD L: 39.49ns=161.9c T: 28.78ns=118.00c 613 X87 :FCOS80 (0.0) + FADD L: 16.71ns= 68.5c T: 15.10ns= 61.92c 614 X87 :FCOS80 (1.0) + FADD L: 40.87ns=167.6c T: 29.53ns=121.08c 615 X87 :FCOS80 (4Pi) + FADD L: 47.39ns=194.3c T: 35.81ns=146.83c 616 X87 :FCOS80 (2Pi) + FADD L: 47.42ns=194.4c T: 35.81ns=146.83c 617 X87 :FCOS80 (Pi) + FADD L: 48.33ns=198.2c T: 36.28ns=148.75c 618 X87 :FCOS80 (Pi/2) + FADD L: 47.84ns=196.2c T: 35.34ns=144.92c 619 X87 :FCOS80 (Pi/4) + FADD L: 39.98ns=163.9c T: 28.25ns=115.83c 620 X87 :FCOS80 (Pi/8) + FADD L: 39.92ns=163.7c T: 27.44ns=112.50c 621 X87 :FCOS80 (Pi/16) + FADD L: 39.98ns=163.9c T: 27.44ns=112.50c 622 X87 :FCOS80 (Pi/32) + FADD L: 39.94ns=163.8c T: 27.44ns=112.50c 623 MMX :EMMS L: 0.06ns= 0.2c T: 0.06ns= 0.24c 624 MMX :MOVD r32, mm L: [diff. reg. set] T: 0.22ns= 0.92c 625 MMX :MOVD mm, r32 L: [diff. reg. set] T: 0.22ns= 0.92c 626 MMX :MOVD r32, mm+MOVD mm, r32 L: 4.19ns= 17.2c T: 0.24ns= 1.00c 627 AMD64 :MOVD r64, mm L: [diff. reg. set] T: 0.24ns= 1.00c 628 AMD64 :MOVD mm, r64 L: [diff. reg. set] T: 0.22ns= 0.92c 629 AMD64 :MOVD r64, mm+MOVD mm, r64 L: 4.19ns= 17.2c T: 0.24ns= 1.00c 630 MMX :MOVD mm, [m32] L: [memory dep.] T: 0.12ns= 0.47c 631 MMX :MOVD [m32], mm L: [memory dep.] T: 0.24ns= 1.00c 632 MMX :MOVD mm,[m32]+MOVD [m32],mm L: 2.56ns= 10.5c T: 0.18ns= 0.74c 633 MMX :MOVQ mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 634 MMX :MOVQ mm, [m64] L: [memory dep.] T: 0.12ns= 0.48c 635 MMX :MOVQ [m64], mm L: [memory dep.] T: 0.22ns= 0.92c 636 MMX :MOVQ mm,[m64]+MOVQ [m64],mm L: 2.56ns= 10.5c T: 0.28ns= 1.17c 637 SSE :MOVNTQ [m64], mm L: [memory dep.] T: 1.33ns= 1.33c 638 SSE :PMOVMSKB r32, mm L: [diff. reg. set] T: 0.22ns= 0.92c 639 AMD64 :PMOVMSKB r64, mm L: [diff. reg. set] T: 0.22ns= 0.92c 640 SSE :MASKMOVQ mm, mm L: [memory dep.] T: 16.17ns= 16.17c 641 MMX :PADDB mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 642 MMX :PADDW mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 643 MMX :PADDD mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 644 SSE2 :PADDQ mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 645 MMX :PADDSB mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 646 MMX :PADDSW mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 647 MMX :PADDUSB mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 648 MMX :PADDUSW mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 649 MMX :PSUBB mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 650 MMX :PSUBB mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 651 MMX :PSUBW mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 652 MMX :PSUBW mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 653 MMX :PSUBD mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 654 MMX :PSUBD mm1, mm2 L: 0.49ns= 2.0c T: 0.10ns= 0.43c 655 SSE2 :PSUBQ mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 656 SSE2 :PSUBQ mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 657 MMX :PSUBSB mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 658 MMX :PSUBSB mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 659 MMX :PSUBSW mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 660 MMX :PSUBSW mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 661 MMX :PSUBUSB mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 662 MMX :PSUBUSB mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.47c 663 MMX :PSUBUSW mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 664 MMX :PSUBUSW mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 665 MMX :PCMPEQB mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 666 MMX :PCMPEQB mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 667 MMX :PCMPEQW mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.49c 668 MMX :PCMPEQW mm1, mm2 L: 0.47ns= 1.9c T: 0.11ns= 0.46c 669 MMX :PCMPEQD mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 670 MMX :PCMPEQD mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 671 MMX :PCMPGTB mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 672 MMX :PCMPGTB mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.47c 673 MMX :PCMPGTW mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 674 MMX :PCMPGTW mm1, mm2 L: 0.49ns= 2.0c T: 0.12ns= 0.47c 675 MMX :PCMPGTD mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 676 MMX :PCMPGTD mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.43c 677 MMX :PAND mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 678 MMX :PAND mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 679 MMX :PANDN mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 680 MMX :PANDN mm1, mm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 681 MMX :POR mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 682 MMX :POR mm1, mm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 683 MMX :PXOR mm, mm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 684 MMX :PXOR mm1, mm2 L: 0.49ns= 2.0c T: 0.10ns= 0.40c 685 MMX :PMULHW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 686 SSE :PMULHUW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 688 SSSE3 :PMULHRSW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 689 MMX :PMULLW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 690 SSE2 :PMULUDQ mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 691 SSSE3 :PMADDUBSW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 692 MMX :PMADDWD mm, mm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 693 MMX :PSLLW mm, mm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 694 MMX :PSLLW mm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 695 MMX :PSLLD mm, mm L: 0.69ns= 2.8c T: 0.24ns= 1.00c 696 MMX :PSLLD mm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 697 MMX :PSLLQ mm, mm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 698 MMX :PSLLQ mm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 699 MMX :PSRAW mm, mm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 700 MMX :PSRAW mm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 701 MMX :PSRAD mm, mm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 702 MMX :PSRAD mm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 703 MMX :PSRLW mm, mm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 704 MMX :PSRLW mm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 705 MMX :PSRLD mm, mm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 706 MMX :PSRLD mm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 707 MMX :PSRLQ mm, mm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 708 MMX :PSRLQ mm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 709 MMX :PUNPCKHBW mm, mm L: 0.47ns= 1.9c T: 0.24ns= 1.00c 710 MMX :PUNPCKHWD mm, mm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 711 MMX :PUNPCKHDQ mm, mm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 712 MMX :PUNPCKLBW mm, mm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 713 MMX :PUNPCKLWD mm, mm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 714 MMX :PUNPCKLDQ mm, mm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 715 MMX :PACKSSWB mm, mm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 716 MMX :PACKUSWB mm, mm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 717 MMX :PACKSSDW mm, mm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 746 3DNOWPREF :PREFETCHW [mem] L: [memory dep.] T: 0.12ns= 0.48c 753 SSE :PAVGB mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 754 SSE :PAVGW mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 755 SSE :PEXTRW r32, mm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 756 SSE :PINSRW mm, r32, im8 L: [diff. reg. set] T: 0.26ns= 1.08c 757 SSE :PEXTRW + PINSRW r32 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 758 AMD64 :PEXTRW r64, mm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 759 AMD64 :PINSRW mm, r64, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 760 AMD64 :PEXTRW + PINSRW r64 L: 0.49ns= 2.0c T: 0.47ns= 1.92c 761 SSE :PMAXSW mm, mm L: 0.49ns= 2.0c T: 0.11ns= 0.43c 762 SSE :PMAXUB mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 763 SSE :PMINSW mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 764 SSE :PMINUB mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 765 SSE :PSADBW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 766 SSE :PSHUFW mm, mm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 767 SSE :PREFETCHNTA [mem] L: [memory dep.] T: 0.12ns= 0.49c 768 SSE :PREFETCHT0 [mem] L: [memory dep.] T: 0.12ns= 0.47c 769 SSE :PREFETCHT1 [mem] L: [memory dep.] T: 0.12ns= 0.49c 770 SSE :PREFETCHT2 [mem] L: [memory dep.] T: 0.12ns= 0.49c 771 SSE :SFENCE L: 19.77ns= 81.1c T: 19.77ns= 81.08c 772 SSE2 :LFENCE L: 3.94ns= 16.2c T: 3.94ns= 16.17c 773 SSE2 :MFENCE L: 19.77ns= 81.1c T: 19.77ns= 81.08c 774 SSSE3 :PABSB mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 775 SSSE3 :PABSW mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 776 SSSE3 :PABSD mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 777 SSSE3 :PALIGNR mm, mm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 778 SSSE3 :PHADDW mm, mm L: 1.16ns= 4.8c T: 0.45ns= 1.83c 779 SSSE3 :PHADDD mm, mm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 780 SSSE3 :PHADDSW mm, mm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 781 SSSE3 :PHSUBW mm, mm L: 1.22ns= 5.0c T: 0.47ns= 1.92c 782 SSSE3 :PHSUBD mm, mm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 783 SSSE3 :PHSUBSW mm, mm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 784 SSSE3 :PSHUFB mm, mm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 785 SSSE3 :PSIGNB mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 786 SSSE3 :PSIGNW mm, mm L: 0.49ns= 2.0c T: 0.12ns= 0.47c 787 SSSE3 :PSIGND mm, mm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 788 SSE :MOVHLPS xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 789 SSE :MOVHLPS xmm1, xmm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 790 AVX :VMOVHLPS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 791 AVX :VMOVHLPS xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 792 SSE :MOVSS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 793 AVX :VMOVSS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 794 SSE :MOVSS xmm, [m32] L: [memory dep.] T: 0.12ns= 0.48c 795 SSE :MOVSS [m32], xmm L: [memory dep.] T: 0.24ns= 1.00c 796 SSE :MOVSS LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 797 AVX :VMOVSS xmm, [m32] L: [memory dep.] T: 0.12ns= 0.48c 798 AVX :VMOVSS [m32], xmm L: [memory dep.] T: 0.22ns= 0.92c 799 AVX :VMOVSS LS pair L: 2.56ns= 10.5c T: 0.22ns= 0.92c 800 SSE :MOVLPS xmm, [m32] L: [memory dep.] T: 0.12ns= 0.48c 801 SSE :MOVLPS [m32], xmm L: [memory dep.] T: 0.24ns= 1.00c 802 SSE :MOVLPS LS pair L: 3.03ns= 12.4c T: 0.24ns= 1.00c 803 AVX :VMOVLPS xmm, xmm, [m32] L: [memory dep.] T: 0.12ns= 0.48c 804 AVX :VMOVLPS [m32], xmm L: [memory dep.] T: 0.22ns= 0.92c 805 AVX :VMOVLPS LS pair L: 3.03ns= 12.4c T: 0.08ns= 0.34c 806 SSE :MOVHPS xmm, [m32] L: [memory dep.] T: 0.24ns= 1.00c 807 SSE :MOVHPS [m32], xmm L: [memory dep.] T: 0.22ns= 0.92c 808 SSE :MOVHPS LS pair L: 3.50ns= 14.3c T: 0.22ns= 0.92c 809 AVX :VMOVHPS xmm, xmm, [m32] L: [memory dep.] T: 0.22ns= 0.92c 810 AVX :VMOVHPS [m32], xmm L: [memory dep.] T: 0.22ns= 0.92c 811 AVX :VMOVHPS LS pair L: 3.50ns= 14.3c T: 0.22ns= 0.92c 812 SSE :MOVAPS xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 813 SSE :MOVAPS xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 814 SSE :MOVAPS [m128], xmm L: [memory dep.] T: 0.24ns= 1.00c 815 SSE :MOVAPS LS pair L: 2.56ns= 10.5c T: 0.13ns= 0.51c 816 AVX :VMOVAPS xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.25c 817 AVX :VMOVAPS xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 818 AVX :VMOVAPS [m128], xmm L: [memory dep.] T: 0.24ns= 1.00c 819 AVX :VMOVAPS LS pair L: 2.56ns= 10.5c T: 0.17ns= 0.71c 820 SSE :MOVUPS xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 821 SSE :MOVUPS xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 822 SSE :MOVUPS [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 823 SSE :MOVUPS aligned LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 824 SSE :MOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.30ns= 1.25c 825 SSE :MOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.47ns= 1.92c 826 SSE :MOVUPS unaligned LS pair L: 2.78ns= 11.4c T: 0.24ns= 1.00c 827 AVX :VMOVUPS xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 828 AVX :VMOVUPS xmm, [m128] L: [memory dep.] T: 0.12ns= 0.51c 829 AVX :VMOVUPS [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 830 AVX :VMOVUPS aligned LS pair L: 2.56ns= 10.5c T: 0.13ns= 0.54c 831 AVX :VMOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.35ns= 1.42c 832 AVX :VMOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.49ns= 2.00c 833 AVX :VMOVUPS unaligned LS pair L: 2.78ns= 11.4c T: 0.35ns= 1.42c 834 SSE4A :MOVNTSS [m32], xmm L: [memory dep.] T: 1.33ns= 1.33c 835 SSE :MOVNTPS [m128], xmm L: [memory dep.] T: 1.33ns= 1.33c 836 AVX :VMOVNTPS [m128], xmm L: [memory dep.] T: 1.33ns= 1.33c 837 SSE :MOVMSKPS r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 838 AVX :VMOVMSKPS r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 839 AVX :VMASKMOVPS xmm,xmm,[m128+4] L: [memory dep.] T: 0.26ns= 1.08c 840 AVX :VMASKMOVPS [m128+4],xmm,xmm L: [memory dep.] T: 1.87ns= 7.67c 841 AVX :VMASKMOVPS unaligned LSpair L: 7.21ns= 29.6c T: 1.87ns= 7.67c 842 SSE :UNPCKLPS xmm, xmm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 843 AVX :VUNPCKLPS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 844 SSE :UNPCKHPS xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 845 AVX :VUNPCKHPS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 846 SSE :SHUFPS xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 847 AVX :VSHUFPS xmm, xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 848 AVX :VPERMILPS xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 849 AVX :VPERMILPS xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 850 SSE :COMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 851 AVX :VCOMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 852 SSE :UCOMISS xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 853 AVX :VUCOMISS xmm, xmm L: [no true dep.] T: 0.24ns= 1.00c 854 SSE :CMPSS xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 855 SSE :CMPPS xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 856 AVX :VCMPSS xmm, xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 857 AVX :VCMPPS xmm, xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 858 SSE :SUBSS xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 859 AVX :VSUBSS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 860 SSE :SUBPS xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 861 AVX :VSUBPS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.21ns= 0.84c 862 SSE :ADDSS xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 863 AVX :VADDSS xmm, xmm, xmm L: 1.22ns= 5.0c T: 0.22ns= 0.92c 864 SSE :ADDPS xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 865 AVX :VADDPS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 866 SSE :MULSS xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 867 AVX :VMULSS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 868 SSE :MULPS xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 869 AVX :VMULPS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 870 SSE :MULSS+ADDSS xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 871 AVX :VMULSS+VADDSS xmm, xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 872 SSE :MULPS+ADDPS xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 873 AVX :VMULPS+VADDPS xmm, xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 874 SSE :MULSS xm1,xm1 ADDSS xm2,xm2 L: 1.16ns= 4.8c T: 0.22ns= 0.92c 875 AVX :VMULSS xmm1.. VADDSS xmm2.. L: 1.16ns= 4.8c T: 0.22ns= 0.92c 876 SSE :MULPS xm1,xm1 ADDPS xm2,xm2 L: 1.16ns= 4.8c T: 0.22ns= 0.92c 877 AVX :VMULPS xmm1.. VADDPS xmm2.. L: 1.16ns= 4.8c T: 0.22ns= 0.92c 878 SSE :MAXSS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 879 AVX :VMAXSS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 880 SSE :MAXPS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 881 AVX :VMAXPS xmm, xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 882 SSE :MINSS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 883 AVX :VMINSS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 884 SSE :MINPS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 885 AVX :VMINPS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 886 SSE :ANDNPS xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 887 SSE :ANDNPS xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 888 AVX :VANDNPS xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 889 AVX :VANDNPS xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 890 SSE :ANDPS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 891 SSE :ANDPS xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.44c 892 AVX :VANDPS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 893 AVX :VANDPS xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 894 SSE :ORPS xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 895 SSE :ORPS xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.47c 896 AVX :VORPS xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 897 AVX :VORPS xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 898 SSE :XORPS xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 899 SSE :XORPS xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.45c 900 AVX :VXORPS xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 901 AVX :VXORPS xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.45c 902 SSE :DIVSS xmm, xmm L: 4.19ns= 17.2c T: 1.50ns= 6.17c 903 SSE :DIVSS (0.0f/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 904 SSE :DIVSS (x/1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 905 SSE :DIVSS (x/2.0f) L: 2.07ns= 8.5c T: 1.04ns= 4.25c 906 SSE :DIVSS (x/0.5f) L: 2.07ns= 8.5c T: 1.04ns= 4.25c 907 AVX :VDIVSS xmm, xmm, xmm L: 4.19ns= 17.2c T: 1.50ns= 6.17c 908 AVX :VDIVSS (0.0f/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 909 AVX :VDIVSS (x/1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 910 AVX :VDIVSS (x/2.0f) L: 2.05ns= 8.4c T: 1.06ns= 4.33c 911 AVX :VDIVSS (x/0.5f) L: 2.05ns= 8.4c T: 1.04ns= 4.25c 912 SSE :DIVPS xmm, xmm L: 4.19ns= 17.2c T: 1.50ns= 6.17c 913 SSE :DIVPS (0.0f/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 914 SSE :DIVPS (x/1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 915 SSE :DIVPS (x/2.0f) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 916 SSE :DIVPS (x/0.5f) L: 1.79ns= 7.3c T: 1.02ns= 4.17c 917 AVX :VDIVPS xmm, xmm, xmm L: 4.19ns= 17.2c T: 1.50ns= 6.17c 918 AVX :VDIVPS (0.0f/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 919 AVX :VDIVPS (x/1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 920 AVX :VDIVPS (x/2.0f) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 921 AVX :VDIVPS (x/0.5f) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 922 SSE :SQRTSS xmm, xmm L: 5.59ns= 22.9c T: 2.22ns= 9.08c 923 SSE :SQRTSS (0.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 924 SSE :SQRTSS (1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 925 AVX :VSQRTSS xmm, xmm, xmm L: 5.59ns= 22.9c T: 2.22ns= 9.08c 926 AVX :VSQRTSS (0.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 927 AVX :VSQRTSS (1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 928 SSE :SQRTPS xmm, xmm L: 5.59ns= 22.9c T: 2.22ns= 9.08c 929 SSE :SQRTPS (0.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 930 SSE :SQRTPS (1.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 931 AVX :VSQRTPS xmm, xmm L: 5.59ns= 22.9c T: 2.22ns= 9.08c 932 AVX :VSQRTPS (0.0f) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 933 AVX :VSQRTPS (1.0f) L: 2.09ns= 8.6c T: 1.10ns= 4.50c 934 SSE :RCPSS xmm, xmm L: 1.22ns= 5.0c T: 0.22ns= 0.92c 935 AVX :VRCPSS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.21ns= 0.88c 936 SSE :RCPPS xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 937 AVX :VRCPPS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 938 SSE :RSQRTSS xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 939 AVX :VRSQRTSS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.21ns= 0.88c 940 SSE :RSQRTPS xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 941 AVX :VRSQRTPS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 942 SSE :CVTPI2PS xmm, mm L: [diff. reg. set] T: 0.22ns= 0.92c 943 SSE :CVTPS2PI mm, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 944 SSE :CVTPS2PI + CVTPI2PS L: 2.78ns= 11.4c T: 0.22ns= 0.92c 945 SSE :CVTTPS2PI mm, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 946 SSE :CVTTPS2PI + CVTPI2PS L: 2.78ns= 11.4c T: 0.22ns= 0.92c 947 SSE :CVTSI2SS xmm, r32 L: [diff. reg. set] T: 0.26ns= 1.08c 948 SSE :CVTSS2SI r32, xmm L: [diff. reg. set] T: 0.24ns= 1.00c 949 SSE :CVTSS2SI + CVTSI2SS r32 L: 6.04ns= 24.8c T: 0.65ns= 2.67c 950 SSE :CVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.24ns= 1.00c 951 SSE :CVTTSS2SI + CVTSI2SS r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 952 AVX :VCVTSI2SS xmm, xmm, r32 L: [diff. reg. set] T: 0.26ns= 1.08c 953 AVX :VCVTSS2SI r32, xmm L: [diff. reg. set] T: 0.24ns= 1.00c 954 AVX :VCVTSS2SI + VCVTSI2SS r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 955 AVX :VCVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 956 AVX :VCVTTSS2SI + VCVTSI2SS r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 957 AMD64 :CVTSI2SS xmm, r64 L: [diff. reg. set] T: 0.26ns= 1.08c 958 AMD64 :CVTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 959 AMD64 :CVTSS2SI + CVTSI2SS r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 960 AMD64 :CVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.24ns= 1.00c 961 AMD64 :CVTTSS2SI + CVTSI2SS r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 962 AVX :VCVTSI2SS xmm, xmm, r64 L: [diff. reg. set] T: 0.26ns= 1.08c 963 AVX :VCVTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 964 AVX :VCVTSS2SI + VCVTSI2SS r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 965 AVX :VCVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 966 AVX :VCVTTSS2SI + VCVTSI2SS r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 967 SSE :STMXCSR [mem] L: [memory dep.] T: 4.19ns= 17.17c 968 SSE :LDMXCSR [mem] L: [memory dep.] T: 44.08ns=180.75c 969 SSE :STMXCSR + LDMXCSR L: 7.21ns= 29.6c T: 7.21ns= 29.58c 970 SSE2 :MOVSD xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 971 SSE2 :MOVSD xmm, [m64] L: [memory dep.] T: 0.12ns= 0.48c 972 SSE2 :MOVSD [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 973 SSE2 :MOVSD LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 974 AVX :VMOVSD xmm, xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 975 AVX :VMOVSD xmm, [m64] L: [memory dep.] T: 0.12ns= 0.48c 976 AVX :VMOVSD [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 977 AVX :VMOVSD LS pair L: 2.56ns= 10.5c T: 0.17ns= 0.70c 978 SSE2 :MOVLPD xmm, [m64] L: [memory dep.] T: 0.11ns= 0.47c 979 SSE2 :MOVLPD [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 980 SSE2 :MOVLPD LS pair L: 3.03ns= 12.4c T: 0.24ns= 1.00c 981 AVX :VMOVLPD xmm, [m64] L: [memory dep.] T: 0.12ns= 0.49c 982 AVX :VMOVLPD [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 983 AVX :VMOVLPD LS pair L: 3.03ns= 12.4c T: 0.12ns= 0.48c 984 SSE2 :MOVHPD xmm, [m64] L: [memory dep.] T: 0.22ns= 0.92c 985 SSE2 :MOVHPD [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 986 SSE2 :MOVHPD LS pair L: 3.50ns= 14.3c T: 0.22ns= 0.92c 987 AVX :VMOVHPD xmm, [m64] L: [memory dep.] T: 0.24ns= 1.00c 988 AVX :VMOVHPD [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 989 AVX :VMOVHPD LS pair L: 3.50ns= 14.3c T: 0.22ns= 0.92c 990 SSE2 :MOVAPD xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 991 SSE2 :MOVAPD xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 992 SSE2 :MOVAPD [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 993 SSE2 :MOVAPD LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 994 AVX :VMOVAPD xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 995 AVX :VMOVAPD xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 996 AVX :VMOVAPD [m128], xmm L: [memory dep.] T: 0.24ns= 1.00c 997 AVX :VMOVAPD LS pair L: 2.56ns= 10.5c T: 0.17ns= 0.71c 998 SSE2 :MOVUPD xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 999 SSE2 :MOVUPD xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 1000 SSE2 :MOVUPD [m128], xmm L: [memory dep.] T: 0.24ns= 1.00c 1001 SSE2 :MOVUPD aligned LS pair L: 2.56ns= 10.5c T: 0.13ns= 0.51c 1002 SSE2 :MOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.30ns= 1.25c 1003 SSE2 :MOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.47ns= 1.92c 1004 SSE2 :MOVUPD unaligned LS pair L: 2.78ns= 11.4c T: 0.15ns= 0.63c 1005 AVX :VMOVUPD xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 1006 AVX :VMOVUPD xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 1007 AVX :VMOVUPD [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 1008 AVX :VMOVUPD aligned LS pair L: 2.56ns= 10.5c T: 0.17ns= 0.71c 1009 AVX :VMOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.26ns= 1.08c 1010 AVX :VMOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.47ns= 1.92c 1011 AVX :VMOVUPD unaligned LS pair L: 2.78ns= 11.4c T: 0.37ns= 1.50c 1012 SSE4A :MOVNTSD [m64], xmm L: [memory dep.] T: 1.33ns= 1.33c 1013 SSE2 :MOVNTPD [m128], xmm L: [memory dep.] T: 1.33ns= 1.33c 1014 AVX :VMOVNTPD [m128], xmm L: [memory dep.] T: 1.33ns= 1.33c 1015 SSE2 :MOVMSKPD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1016 AVX :VMOVMSKPD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1017 AVX :VMASKMOVPD xmm,xmm,[m128+4] L: [memory dep.] T: 0.41ns= 1.67c 1018 AVX :VMASKMOVPD [m128+4],xmm,xmm L: [memory dep.] T: 1.87ns= 7.67c 1019 AVX :VMASKMOVPD unaligned LSpair L: 7.21ns= 29.6c T: 1.87ns= 7.67c 1020 SSE2 :UNPCKLPD xmm, xmm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1021 AVX :VUNPCKLPD xmm, xmm, xmm L: 0.47ns= 1.9c T: 0.24ns= 1.00c 1022 SSE2 :UNPCKHPD xmm, xmm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1023 AVX :VUNPCKHPD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1024 SSE2 :SHUFPD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1025 AVX :VSHUFPD xmm, xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1026 AVX :VPERMILPD xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1027 AVX :VPERMILPD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1028 SSE2 :COMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 1029 AVX :VCOMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 1030 SSE2 :UCOMISD xmm, xmm L: [no true dep.] T: 0.24ns= 1.00c 1031 AVX :VUCOMISD xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 1032 SSE2 :CMPSD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1033 SSE2 :CMPPD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1034 AVX :VCMPSD xmm, xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1035 AVX :VCMPPD xmm, xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1036 SSE2 :SUBSD xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.69c 1037 AVX :VSUBSD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 1038 SSE2 :SUBPD xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 1039 AVX :VSUBPD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 1040 SSE2 :ADDSD xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1041 AVX :VADDSD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1042 SSE2 :ADDPD xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1043 AVX :VADDPD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1044 SSE2 :MULSD xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1045 AVX :VMULSD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1046 SSE2 :MULPD xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1047 AVX :VMULPD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1048 SSE2 :MULSD+ADDSD xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 1049 AVX :VMULSD+VADDSD xmm, xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 1050 SSE2 :MULPD+ADDPD xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 1051 AVX :VMULPD+VADDPD xmm, xmm, xmm L: 2.32ns= 9.5c T: 0.24ns= 1.00c 1052 SSE2 :MULSD xm1,xm1 ADDSD xm2,xm2 L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1053 AVX :VMULSD xmm1.. VADDSD xmm2.. L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1054 SSE2 :MULPD xm1,xm1 ADDPD xm2,xm2 L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1055 AVX :VMULPD xmm1.. VADDPD xmm2.. L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1056 SSE2 :MAXSD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1057 AVX :VMAXSD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1058 SSE2 :MAXPD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1059 AVX :VMAXPD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1060 SSE2 :MINSD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1061 AVX :VMINSD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1062 SSE2 :MINPD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1063 AVX :VMINPD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1064 SSE2 :ANDNPD xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1065 SSE2 :ANDNPD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1066 AVX :VANDNPD xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1067 AVX :VANDNPD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1068 SSE2 :ANDPD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1069 SSE2 :ANDPD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.44c 1070 AVX :VANDPD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1071 AVX :VANDPD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1072 SSE2 :ORPD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1073 SSE2 :ORPD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1074 AVX :VORPD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1075 AVX :VORPD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1076 SSE2 :XORPD xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1077 SSE2 :XORPD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1078 AVX :VXORPD xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.47c 1079 AVX :VXORPD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1080 SSE2 :DIVSD xmm, xmm L: 7.68ns= 31.5c T: 3.25ns= 13.33c 1081 SSE2 :DIVSD (0.0/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1082 SSE2 :DIVSD (x/1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1083 SSE2 :DIVSD (x/2.0) L: 2.07ns= 8.5c T: 1.04ns= 4.25c 1084 SSE2 :DIVSD (x/0.5) L: 2.19ns= 9.0c T: 1.04ns= 4.25c 1085 AVX :VDIVSD xmm, xmm, xmm L: 7.68ns= 31.5c T: 3.25ns= 13.33c 1086 AVX :VDIVSD (0.0/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1087 AVX :VDIVSD (x/1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1088 AVX :VDIVSD (x/2.0) L: 2.05ns= 8.4c T: 1.04ns= 4.25c 1089 AVX :VDIVSD (x/0.5) L: 2.05ns= 8.4c T: 1.04ns= 4.25c 1090 SSE2 :DIVPD xmm, xmm L: 7.68ns= 31.5c T: 3.25ns= 13.33c 1091 SSE2 :DIVPD (0.0/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1092 SSE2 :DIVPD (x/1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1093 SSE2 :DIVPD (x/2.0) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 1094 SSE2 :DIVPD (x/0.5) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 1095 AVX :VDIVPD xmm, xmm, xmm L: 7.68ns= 31.5c T: 3.25ns= 13.33c 1096 AVX :VDIVPD (0.0/x) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1097 AVX :VDIVPD (x/1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1098 AVX :VDIVPD (x/2.0) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 1099 AVX :VDIVPD (x/0.5) L: 1.67ns= 6.8c T: 1.04ns= 4.25c 1100 SSE2 :SQRTSD xmm, xmm L: 10.22ns= 41.9c T: 4.53ns= 18.58c 1101 SSE2 :SQRTSD (0.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1102 SSE2 :SQRTSD (1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1103 AVX :VSQRTSD xmm, xmm, xmm L: 10.22ns= 41.9c T: 4.53ns= 18.58c 1104 AVX :VSQRTSD (0.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1105 AVX :VSQRTSD (1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1106 SSE2 :SQRTPD xmm, xmm L: 10.22ns= 41.9c T: 4.53ns= 18.58c 1107 SSE2 :SQRTPD (0.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1108 SSE2 :SQRTPD (1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1109 AVX :VSQRTPD xmm, xmm L: 10.22ns= 41.9c T: 4.53ns= 18.58c 1110 AVX :VSQRTPD (0.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1111 AVX :VSQRTPD (1.0) L: 2.09ns= 8.6c T: 1.04ns= 4.25c 1112 SSE2 :CVTPI2PD xmm, mm L: [diff. reg. set] T: 0.24ns= 1.00c 1113 SSE2 :CVTPD2PI mm, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1114 SSE2 :CVTPD2PI + CVTPI2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1115 SSE2 :CVTTPD2PI mm, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1116 SSE2 :CVTTPD2PI + CVTPI2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1117 SSE2 :CVTSI2SD xmm, r32 L: [diff. reg. set] T: 0.26ns= 1.08c 1118 SSE2 :CVTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1119 SSE2 :CVTSD2SI + CVTSI2SD r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1120 SSE2 :CVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1121 SSE2 :CVTTSD2SI + CVTSI2SD r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1122 AVX :VCVTSI2SD xmm, xmm, r32 L: [diff. reg. set] T: 0.26ns= 1.08c 1123 AVX :VCVTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1124 AVX :VCVTSD2SI + VCVTSI2SD r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1125 AVX :VCVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1126 AVX :VCVTTSD2SI + VCVTSI2SD r32 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1127 AMD64 :CVTSI2SD xmm, r64 L: [diff. reg. set] T: 0.26ns= 1.08c 1128 AMD64 :CVTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1129 AMD64 :CVTSD2SI + CVTSI2SD r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1130 AMD64 :CVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1131 AMD64 :CVTTSD2SI + CVTSI2SD r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1132 AVX :VCVTSI2SD xmm, xmm, r64 L: [diff. reg. set] T: 0.26ns= 1.08c 1133 AVX :VCVTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1134 AVX :VCVTSD2SI + VCVTSI2SD r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1135 AVX :VCVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1136 AVX :VCVTTSD2SI + VCVTSI2SD r64 L: 6.04ns= 24.8c T: 0.22ns= 0.92c 1137 SSE2 :CVTDQ2PD xmm, xmm L: 1.87ns= 7.7c T: 0.09ns= 0.38c 1138 SSE2 :CVTPD2DQ xmm, xmm L: 1.87ns= 7.7c T: 0.09ns= 0.39c 1139 SSE2 :CVTPD2DQ + CVTDQ2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1140 SSE2 :CVTTPD2DQ xmm, xmm L: 1.87ns= 7.7c T: 0.22ns= 0.92c 1141 SSE2 :CVTTPD2DQ + CVTDQ2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1142 AVX :VCVTDQ2PD xmm, xmm L: 1.87ns= 7.7c T: 0.09ns= 0.37c 1143 AVX :VCVTPD2DQ xmm, xmm L: 1.87ns= 7.7c T: 0.09ns= 0.39c 1144 AVX :VCVTPD2DQ + VCVTDQ2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1145 AVX :VCVTTPD2DQ xmm, xmm L: 1.87ns= 7.7c T: 0.09ns= 0.37c 1146 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1147 SSE2 :CVTDQ2PS xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1148 SSE2 :CVTPS2DQ xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1149 SSE2 :CVTPS2DQ + CVTDQ2PS L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1150 SSE2 :CVTTPS2DQ xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1151 SSE2 :CVTTPS2DQ + CVTDQ2PS L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1152 AVX :VCVTDQ2PS xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1153 AVX :VCVTPS2DQ xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1154 AVX :VCVTPS2DQ + VCVTDQ2PS L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1155 AVX :VCVTTPS2DQ xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1156 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1157 SSE2 :CVTPS2PD xmm, xmm L: 1.87ns= 7.7c T: 0.22ns= 0.92c 1158 SSE2 :CVTPD2PS xmm, xmm L: 1.95ns= 8.0c T: 0.24ns= 1.00c 1159 SSE2 :CVTPD2PS + CVTPS2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1160 SSE2 :CVTSS2SD xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1161 SSE2 :CVTSD2SS xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1162 SSE2 :CVTSD2SS + CVTSS2SD L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1163 AVX :VCVTPS2PD xmm, xmm L: 1.87ns= 7.7c T: 0.22ns= 0.92c 1164 AVX :VCVTPD2PS xmm, xmm L: 1.87ns= 7.7c T: 0.22ns= 0.92c 1165 AVX :VCVTPD2PS + VCVTPS2PD L: 3.25ns= 13.3c T: 0.22ns= 0.92c 1166 AVX :VCVTSS2SD xmm, xmm, xmm L: 0.98ns= 4.0c T: 0.24ns= 1.00c 1167 AVX :VCVTSD2SS xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1168 AVX :VCVTSD2SS + VCVTSS2SD L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1169 SSE2 :MOVD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1170 SSE2 :MOVD xmm, r32 L: [diff. reg. set] T: 0.22ns= 0.92c 1171 SSE2 :MOVD r32, xmm+MOVD xmm, r32 L: 4.19ns= 17.2c T: 0.24ns= 1.00c 1172 AVX :VMOVD r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1173 AVX :VMOVD xmm, r32 L: [diff. reg. set] T: 0.22ns= 0.92c 1174 AVX :VMOVD r32,xmm+VMOVD xmm,r32 L: 4.19ns= 17.2c T: 0.24ns= 1.00c 1175 AMD64 :MOVD r64, xmm L: [diff. reg. set] T: 0.24ns= 1.00c 1176 AMD64 :MOVD xmm, r64 L: [diff. reg. set] T: 0.22ns= 0.92c 1177 AMD64 :MOVD r64, xmm+MOVD xmm, r64 L: 4.19ns= 17.2c T: 0.24ns= 1.00c 1178 AVX :VMOVD r64, xmm L: [diff. reg. set] T: 0.24ns= 1.00c 1179 AVX :VMOVD xmm, r64 L: [diff. reg. set] T: 0.24ns= 1.00c 1180 AVX :VMOVD r64,xmm+VMOVD xmm,r64 L: 4.19ns= 17.2c T: 0.20ns= 0.84c 1181 SSE2 :MOVD xmm, [m32] L: [memory dep.] T: 0.12ns= 0.48c 1182 SSE2 :MOVD [m32], xmm L: [memory dep.] T: 0.22ns= 0.92c 1183 SSE2 :MOVD LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 1184 AVX :VMOVD xmm, [m32] L: [memory dep.] T: 0.12ns= 0.48c 1185 AVX :VMOVD [m32], xmm L: [memory dep.] T: 0.22ns= 0.92c 1186 AVX :VMOVD LS pair L: 2.56ns= 10.5c T: 0.22ns= 0.92c 1187 SSE2 :MOVQ xmm, [m64] L: [memory dep.] T: 0.12ns= 0.48c 1188 SSE2 :MOVQ [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 1189 SSE2 :MOVQ LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 1190 AVX :VMOVQ xmm, [m64] L: [memory dep.] T: 0.12ns= 0.48c 1191 AVX :VMOVQ [m64], xmm L: [memory dep.] T: 0.22ns= 0.92c 1192 AVX :VMOVQ LS pair L: 2.56ns= 10.5c T: 0.13ns= 0.53c 1193 SSE2 :MOVDQ2Q mm, xmm L: [diff. reg. set] T: 0.12ns= 0.48c 1194 SSE2 :MOVQ2DQ xmm, mm L: [diff. reg. set] T: 0.12ns= 0.48c 1195 SSE2 :MOVDQ2Q + MOVQ2DQ xmm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1196 SSE2 :MOVDQA xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 1197 SSE2 :MOVDQA xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 1198 SSE2 :MOVDQA [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 1199 SSE2 :MOVDQA LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 1200 AVX :VMOVDQA xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 1201 AVX :VMOVDQA xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 1202 AVX :VMOVDQA [m128], xmm L: [memory dep.] T: 0.24ns= 1.00c 1203 AVX :VMOVDQA LS pair L: 2.56ns= 10.5c T: 0.13ns= 0.51c 1204 SSE2 :MOVDQU xmm, xmm L: 0.06ns= 0.3c T: 0.06ns= 0.24c 1205 SSE2 :MOVDQU xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 1206 SSE2 :MOVDQU [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 1207 SSE2 :MOVDQU aligned LS pair L: 2.56ns= 10.5c T: 0.24ns= 1.00c 1208 SSE2 :MOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.22ns= 0.92c 1209 SSE2 :MOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.47ns= 1.92c 1210 SSE2 :MOVDQU unaligned LS pair L: 2.78ns= 11.4c T: 0.14ns= 0.59c 1211 AVX :VMOVDQU xmm, xmm L: 0.06ns= 0.2c T: 0.06ns= 0.24c 1212 AVX :VMOVDQU xmm, [m128] L: [memory dep.] T: 0.12ns= 0.48c 1213 AVX :VMOVDQU [m128], xmm L: [memory dep.] T: 0.22ns= 0.92c 1214 AVX :VMOVDQU aligned LS pair L: 2.56ns= 10.5c T: 0.11ns= 0.45c 1215 AVX :VMOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.24ns= 1.00c 1216 AVX :VMOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.47ns= 1.92c 1217 AVX :VMOVDQU unaligned LS pair L: 2.78ns= 11.4c T: 0.49ns= 2.00c 1218 SSE4.1 :MOVNTDQA xmm, [m128] L: [memory dep.] T: 0.50ns= 0.50c 1219 SSE2 :MOVNTDQ [m128], xmm L: [memory dep.] T: 1.42ns= 1.42c 1220 SSE4.1 :MOVNTDQA + MOVNTDQ L: 2.56ns= 10.5c T: 10.50ns= 10.50c 1221 AVX :VMOVNTDQA xmm, [m128] L: [memory dep.] T: 0.47ns= 0.47c 1222 AVX :VMOVNTDQ [m128], xmm L: [memory dep.] T: 1.33ns= 1.33c 1223 AVX :VMOVNTDQA + VMOVNTDQ L: 2.56ns= 10.5c T: 10.50ns= 10.50c 1224 SSE2 :PMOVMSKB r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1225 AMD64 :PMOVMSKB r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1226 AVX :VPMOVMSKB r32, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1227 AVX :VPMOVMSKB r64, xmm L: [diff. reg. set] T: 0.22ns= 0.92c 1228 SSE2 :MASKMOVDQU xmm, xmm L: [memory dep.] T: 31.50ns= 31.50c 1229 AVX :VMASKMOVDQU xmm, xmm L: [memory dep.] T: 31.50ns= 31.50c 1230 SSE2 :PADDB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1231 AVX :VPADDB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1232 SSE2 :PADDW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1233 AVX :VPADDW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1234 SSE2 :PADDD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1235 AVX :VPADDD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1236 SSE2 :PADDQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1237 AVX :VPADDQ xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1238 SSE2 :PADDSB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1239 AVX :VPADDSB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1240 SSE2 :PADDSW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1241 AVX :VPADDSW xmm, xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1242 SSE2 :PADDUSB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1243 AVX :VPADDUSB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1244 SSE2 :PADDUSW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1245 AVX :VPADDUSW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1246 SSE2 :PSUBB xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1247 SSE2 :PSUBB xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.51c 1248 AVX :VPSUBB xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1249 AVX :VPSUBB xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1250 SSE2 :PSUBW xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1251 SSE2 :PSUBW xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1252 AVX :VPSUBW xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.49c 1253 AVX :VPSUBW xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1254 SSE2 :PSUBD xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 1255 SSE2 :PSUBD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1256 AVX :VPSUBD xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.49c 1257 AVX :VPSUBD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1258 SSE2 :PSUBQ xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 1259 SSE2 :PSUBQ xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1260 AVX :VPSUBQ xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1261 AVX :VPSUBQ xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1262 SSE2 :PSUBSB xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1263 SSE2 :PSUBSB xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1264 AVX :VPSUBSB xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1265 AVX :VPSUBSB xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1266 SSE2 :PSUBSW xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1267 SSE2 :PSUBSW xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1268 AVX :VPSUBSW xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1269 AVX :VPSUBSW xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1270 SSE2 :PSUBUSB xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1271 SSE2 :PSUBUSB xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1272 AVX :VPSUBUSB xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1273 AVX :VPSUBUSB xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1274 SSE2 :PSUBUSW xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.49c 1275 SSE2 :PSUBUSW xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1276 AVX :VPSUBUSW xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1277 AVX :VPSUBUSW xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1278 SSE2 :PCMPEQB xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1279 SSE2 :PCMPEQB xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1280 AVX :VPCMPEQB xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1281 AVX :VPCMPEQB xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1282 SSE2 :PCMPEQW xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1283 SSE2 :PCMPEQW xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1284 AVX :VPCMPEQW xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.47c 1285 AVX :VPCMPEQW xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1286 SSE2 :PCMPEQD xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1287 SSE2 :PCMPEQD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1288 AVX :VPCMPEQD xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1289 AVX :VPCMPEQD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1290 SSE4.1 :PCMPEQQ xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1291 SSE4.1 :PCMPEQQ xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1292 AVX :VPCMPEQQ xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.49c 1293 AVX :VPCMPEQQ xmm1, xmm1, xmm2 L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1294 SSE2 :PCMPGTB xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1295 SSE2 :PCMPGTB xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.44c 1296 AVX :VPCMPGTB xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1297 AVX :VPCMPGTB xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.47c 1298 SSE2 :PCMPGTW xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 1299 SSE2 :PCMPGTW xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1300 AVX :VPCMPGTW xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1301 AVX :VPCMPGTW xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1302 SSE2 :PCMPGTD xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1303 SSE2 :PCMPGTD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1304 AVX :VPCMPGTD xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 1305 AVX :VPCMPGTD xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1306 SSE4.2 :PCMPGTQ xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.49c 1307 SSE4.2 :PCMPGTQ xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1308 AVX :VPCMPGTQ xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1309 AVX :VPCMPGTQ xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1310 SSE2 :PAND xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1311 SSE2 :PAND xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1312 AVX :VPAND xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1313 AVX :VPAND xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.11ns= 0.46c 1314 SSE2 :PANDN xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1315 SSE2 :PANDN xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1316 AVX :VPANDN xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1317 AVX :VPANDN xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.51c 1318 SSE2 :POR xmm, xmm L: 0.49ns= 2.0c T: 0.11ns= 0.43c 1319 SSE2 :POR xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1320 AVX :VPOR xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1321 AVX :VPOR xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1322 SSE2 :PXOR xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1323 SSE2 :PXOR xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1324 AVX :VPXOR xmm, xmm, xmm L: 0.12ns= 0.5c T: 0.12ns= 0.50c 1325 AVX :VPXOR xmm1, xmm1, xmm2 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1326 SSE2 :PMULHW xmm, xmm L: 0.98ns= 4.0c T: 0.24ns= 1.00c 1327 AVX :VPMULHW xmm, xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1328 SSE2 :PMULHUW xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1329 AVX :VPMULHUW xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1330 SSSE3 :PMULHRSW xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1331 AVX :VPMULHRSW xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1332 SSE2 :PMULLW xmm, xmm L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1333 AVX :VPMULLW xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1334 SSE4.1 :PMULLD xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1335 AVX :VPMULLD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.43ns= 1.75c 1336 SSE4.1 :PMULDQ xmm, xmm L: 0.98ns= 4.0c T: 0.24ns= 1.00c 1337 AVX :VPMULDQ xmm, xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1338 SSE2 :PMULUDQ xmm, xmm L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1339 AVX :VPMULUDQ xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1340 SSSE3 :PMADDUBSW xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1341 AVX :VPMADDUBSW xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1342 SSE2 :PMADDWD xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1343 AVX :VPMADDWD xmm, xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1344 SSE2 :PSLLW xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1345 AVX :VPSLLW xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1346 SSE2 :PSLLW xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1347 AVX :VPSLLW xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1348 SSE2 :PSLLD xmm, xmm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 1349 AVX :VPSLLD xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1350 SSE2 :PSLLD xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1351 AVX :VPSLLD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1352 SSE2 :PSLLQ xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1353 AVX :VPSLLQ xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1354 SSE2 :PSLLQ xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1355 AVX :VPSLLQ xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1356 SSE2 :PSLLDQ xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1357 AVX :VPSLLDQ xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1358 SSE2 :PSRAW xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1359 AVX :VPSRAW xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1360 SSE2 :PSRAW xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1361 AVX :VPSRAW xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1362 SSE2 :PSRAD xmm, xmm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 1363 AVX :VPSRAD xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1364 SSE2 :PSRAD xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1365 AVX :VPSRAD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1366 SSE2 :PSRLW xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1367 AVX :VPSRLW xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1368 SSE2 :PSRLW xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1369 AVX :VPSRLW xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1370 SSE2 :PSRLD xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1371 AVX :VPSRLD xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1372 SSE2 :PSRLD xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1373 AVX :VPSRLD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1374 SSE2 :PSRLQ xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1375 AVX :VPSRLQ xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1376 SSE2 :PSRLQ xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1377 AVX :VPSRLQ xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1378 SSE2 :PSRLDQ xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1379 AVX :VPSRLDQ xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1380 SSE2 :PUNPCKHBW xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1381 AVX :VPUNPCKHBW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1382 SSE2 :PUNPCKHWD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1383 AVX :VPUNPCKHWD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1384 SSE2 :PUNPCKHDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1385 AVX :VPUNPCKHDQ xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1386 SSE2 :PUNPCKHQDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1387 AVX :VPUNPCKHQDQ xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1388 SSE2 :PUNPCKLBW xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1389 AVX :VPUNPCKLBW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1390 SSE2 :PUNPCKLWD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1391 AVX :VPUNPCKLWD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1392 SSE2 :PUNPCKLDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1393 AVX :VPUNPCKLDQ xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1394 SSE2 :PUNPCKLQDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1395 AVX :VPUNPCKLQDQ xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1396 SSE2 :PACKSSWB xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1397 AVX :VPACKSSWB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1398 SSE2 :PACKUSWB xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1399 AVX :VPACKUSWB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1400 SSE2 :PACKSSDW xmm, xmm L: 0.47ns= 1.9c T: 0.24ns= 1.00c 1401 AVX :VPACKSSDW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1402 SSE4.1 :PACKUSDW xmm, xmm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1403 AVX :VPACKUSDW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1404 SSE2 :PAVGB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1405 AVX :VPAVGB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1406 SSE2 :PAVGW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1407 AVX :VPAVGW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1408 SSE4.1 :PEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1409 SSE4.1 :PINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.28ns= 1.17c 1410 SSE4.1 :PEXTRB + PINSRB r32 L: 5.12ns= 21.0c T: 0.26ns= 1.08c 1411 AVX :VPEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1412 AVX :VPINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.28ns= 1.17c 1413 AVX :VPEXTRB + VPINSRB r32 L: 5.12ns= 21.0c T: 0.24ns= 1.00c 1414 SSE4.1 :PEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1415 SSE4.1 :PEXTRB r64 + PINSRB r32 L: 5.12ns= 21.0c T: 0.28ns= 1.17c 1416 AVX :VPEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1417 AVX :VPEXTRB r64 + VPINSRB r32 L: 5.12ns= 21.0c T: 0.24ns= 1.00c 1418 SSE2 :PEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1419 SSE2 :PINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.28ns= 1.17c 1420 SSE2 :PEXTRW + PINSRW r32 L: 5.12ns= 21.0c T: 0.26ns= 1.08c 1421 AVX :VPEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1422 AVX :VPINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.26ns= 1.08c 1423 AVX :VPEXTRW + VPINSRW r32 L: 5.12ns= 21.0c T: 0.24ns= 1.00c 1424 AMD64 :PEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1425 AMD64 :PEXTRW r64 + PINSRW r32 L: 5.12ns= 21.0c T: 0.28ns= 1.17c 1426 AVX :VPEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1427 AVX :VPEXTRW r64 + VPINSRW r32 L: 5.12ns= 21.0c T: 0.24ns= 1.00c 1428 SSE4.1 :PEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1429 SSE4.1 :PINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.28ns= 1.17c 1430 SSE4.1 :PEXTRD + PINSRD r32 L: 5.12ns= 21.0c T: 0.28ns= 1.17c 1431 AVX :VPEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1432 AVX :VPINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.30ns= 1.25c 1433 AVX :VPEXTRD + VPINSRD r32 L: 5.12ns= 21.0c T: 0.24ns= 1.00c 1434 SSE4.1 :PEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1435 SSE4.1 :PINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.28ns= 1.17c 1436 SSE4.1 :PEXTRD + PINSRD r64 L: 5.12ns= 21.0c T: 0.28ns= 1.17c 1437 AVX :VPEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1438 AVX :VPINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.26ns= 1.08c 1439 AVX :VPEXTRQ + VPINSRQ r64 L: 5.12ns= 21.0c T: 0.24ns= 1.00c 1440 SSE4.1 :EXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1441 AVX :VEXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1442 SSE4.1 :EXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.24ns= 1.00c 1443 AVX :VEXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.22ns= 0.92c 1444 SSE4.1 :INSERTPS xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1445 AVX :VINSERTPS xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1446 SSE4A :EXTRQ xmm, im8, im8 L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1447 SSE4A :EXTRQ xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1448 SSE4A :INSERTQ xmm, xmm, im8, im8 L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1449 SSE4A :INSERTQ xmm, xmm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 1450 SSE2 :PMAXUB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1451 AVX :VPMAXUB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1452 SSE4.1 :PMAXSB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1453 AVX :VPMAXSB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1454 SSE4.1 :PMAXUW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1455 AVX :VPMAXUW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1456 SSE2 :PMAXSW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1457 AVX :VPMAXSW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1458 SSE4.1 :PMAXUD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1459 AVX :VPMAXUD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1460 SSE4.1 :PMAXSD xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1461 AVX :VPMAXSD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1462 SSE2 :PMINUB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1463 AVX :VPMINUB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1464 SSE4.1 :PMINSB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1465 AVX :VPMINSB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1466 SSE4.1 :PMINUW xmm, xmm L: 0.49ns= 2.0c T: 0.13ns= 0.53c 1467 AVX :VPMINUW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1468 SSE2 :PMINSW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1469 AVX :VPMINSW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1470 SSE4.1 :PMINUD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1471 AVX :VPMINUD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1472 SSE4.1 :PMINSD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1473 AVX :VPMINSD xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1474 SSE2 :PSADBW xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1475 AVX :VPSADBW xmm, xmm, xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1476 SSSE3 :PSHUFB xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1477 AVX :VPSHUFB xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1478 SSE2 :PSHUFLW xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1479 AVX :VPSHUFLW xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1480 SSE2 :PSHUFHW xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1481 AVX :VPSHUFHW xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1482 SSE2 :PSHUFD xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1483 AVX :VPSHUFD xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1484 SSE3 :ADDSUBPS xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.88c 1485 AVX :VADDSUBPS xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1486 SSE3 :ADDSUBPD xmm, xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1487 AVX :VADDSUBPD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.10ns= 0.40c 1488 SSE3 :HADDPS xmm, xmm L: 2.56ns= 10.5c T: 0.45ns= 1.83c 1489 AVX :VHADDPS xmm, xmm, xmm L: 2.56ns= 10.5c T: 0.47ns= 1.92c 1490 SSE3 :HADDPD xmm, xmm L: 2.56ns= 10.5c T: 0.47ns= 1.92c 1491 AVX :VHADDPD xmm, xmm, xmm L: 2.56ns= 10.5c T: 0.47ns= 1.92c 1492 SSE3 :HSUBPS xmm, xmm L: 2.56ns= 10.5c T: 0.47ns= 1.92c 1493 AVX :VHSUBPS xmm, xmm, xmm L: 2.56ns= 10.5c T: 0.47ns= 1.92c 1494 SSE3 :HSUBPD xmm, xmm L: 2.68ns= 11.0c T: 0.47ns= 1.92c 1495 AVX :VHSUBPD xmm, xmm, xmm L: 2.56ns= 10.5c T: 0.47ns= 1.92c 1496 SSE3 :MOVSLDUP xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1497 AVX :VMOVSLDUP xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1498 SSE3 :MOVSHDUP xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1499 AVX :VMOVSHDUP xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1500 SSE3 :MOVDDUP xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1501 AVX :VMOVDDUP xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1502 SSE3 :LDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.39ns= 1.58c 1503 AVX :VLDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.28ns= 1.17c 1504 SSSE3 :PABSB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1505 AVX :VPABSB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1506 SSSE3 :PABSW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1507 AVX :VPABSW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1508 SSSE3 :PABSD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1509 AVX :VPABSD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1510 SSSE3 :PALIGNR xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1511 AVX :VPALIGNR xmm, xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1512 SSSE3 :PHADDW xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1513 AVX :VPHADDW xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1514 SSSE3 :PHADDD xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1515 AVX :VPHADDD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1516 SSSE3 :PHADDSW xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1517 AVX :VPHADDSW xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.41ns= 1.67c 1518 SSSE3 :PHSUBW xmm, xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1519 AVX :VPHSUBW xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.45ns= 1.83c 1520 SSSE3 :PHSUBD xmm, xmm L: 1.16ns= 4.8c T: 0.45ns= 1.83c 1521 AVX :VPHSUBD xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.43ns= 1.75c 1522 SSSE3 :PHSUBSW xmm, xmm L: 1.16ns= 4.8c T: 0.45ns= 1.83c 1523 AVX :VPHSUBSW xmm, xmm, xmm L: 1.16ns= 4.8c T: 0.45ns= 1.83c 1524 SSSE3 :PSIGNB xmm, xmm L: 0.49ns= 2.0c T: 0.13ns= 0.52c 1525 AVX :VPSIGNB xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1526 SSSE3 :PSIGNW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1527 AVX :VPSIGNW xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1528 SSSE3 :PSIGND xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1529 AVX :VPSIGND xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1530 SSE4.1 :BLENDPS xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1531 AVX :VBLENDPS xmm, xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1532 SSE4.1 :BLENDVPS xmm, xmm, L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1533 AVX :VBLENDVPS xmm, xmm, xmm, xm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1534 SSE4.1 :BLENDPD xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1535 AVX :VBLENDPD xmm, xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1536 SSE4.1 :BLENDVPD xmm, xmm, L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1537 AVX :VBLENDVPD xmm, xmm, xmm, xm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1538 SSE4.1 :PBLENDW xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1539 AVX :VPBLENDW xmm, xmm, xmm, im8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1540 SSE4.1 :PBLENDVB xmm, xmm, L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1541 AVX :VPBLENDVB xmm, xmm, xmm, xm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1542 SSE4.1 :DPPS xmm, xmm, imm8 L: 5.81ns= 23.8c T: 0.35ns= 1.42c 1543 AVX :VDPPS xmm, xmm, xmm, imm8 L: 5.81ns= 23.8c T: 0.35ns= 1.42c 1544 SSE4.1 :DPPD xmm, xmm, imm8 L: 3.50ns= 14.3c T: 0.41ns= 1.67c 1545 AVX :VDPPD xmm, xmm, xmm, imm8 L: 3.50ns= 14.3c T: 0.41ns= 1.67c 1546 SSE4.1 :MPSADBW xmm, xmm, imm8 L: 2.32ns= 9.5c T: 0.89ns= 3.67c 1547 AVX :VMPSADBW xmm, xmm, imm8 L: 2.32ns= 9.5c T: 0.93ns= 3.83c 1548 SSE4.1 :PHMINPOSUW xmm, xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1549 AVX :VPHMINPOSUW xmm, xmm L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1550 SSE4.1 :PMOVSXBW xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1551 AVX :VPMOVSXBW xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1552 SSE4.1 :PMOVSXBD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1553 AVX :VPMOVSXBD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1554 SSE4.1 :PMOVSXBQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1555 AVX :VPMOVSXBQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1556 SSE4.1 :PMOVSXWD xmm, xmm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1557 AVX :VPMOVSXWD xmm, xmm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1558 SSE4.1 :PMOVSXWQ xmm, xmm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1559 AVX :VPMOVSXWQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1560 SSE4.1 :PMOVSXDQ xmm, xmm L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1561 AVX :VPMOVSXDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1562 SSE4.1 :PMOVZXBW xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1563 AVX :VPMOVZXBW xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1564 SSE4.1 :PMOVZXBD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1565 AVX :VPMOVZXBD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1566 SSE4.1 :PMOVZXBQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1567 AVX :VPMOVZXBQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1568 SSE4.1 :PMOVZXWD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1569 AVX :VPMOVZXWD xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1570 SSE4.1 :PMOVZXWQ xmm, xmm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1571 AVX :VPMOVZXWQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1572 SSE4.1 :PMOVZXDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1573 AVX :VPMOVZXDQ xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1574 SSE4.1 :PTEST xmm, xmm L: [no true dep.] T: 0.24ns= 1.00c 1575 AVX :VPTEST xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 1576 AVX :VPTESTPS xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 1577 AVX :VPTESTPD xmm, xmm L: [no true dep.] T: 0.22ns= 0.92c 1578 SSE4.1 :ROUNDSS xmm, xmm, imm8 L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1579 AVX :VROUNDSS xmm, xmm, xmm, im8 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1580 SSE4.1 :ROUNDPS xmm, xmm, imm8 L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1581 AVX :VROUNDPS xmm, xmm, imm8 L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1582 SSE4.1 :ROUNDSD xmm, xmm, imm8 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1583 AVX :VROUNDSD xmm, xmm, xmm, im8 L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1584 SSE4.1 :ROUNDPD xmm, xmm, imm8 L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1585 AVX :VROUNDPD xmm, xmm, imm8 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1586 AVX :VBROADCASTSS xmm, m32 L: [memory dep.] T: 0.24ns= 1.00c 1587 SSE4.2 :PCMPESTRI xmm, xmm, imm8 L: 2.56ns= 10.5c T: 2.56ns= 10.50c 1588 AVX :VPCMPESTRI xmm, xmm, imm8 L: 2.32ns= 9.5c T: 2.32ns= 9.50c 1589 SSE4.2 :PCMPESTRM xmm, xmm, imm8 L: 2.50ns= 10.3c T: 2.32ns= 9.50c 1590 AVX :VPCMPESTRM xmm, xmm, imm8 L: 2.32ns= 9.5c T: 2.32ns= 9.50c 1591 SSE4.2 :PCMPISTRI xmm, xmm, imm8 L: 1.16ns= 4.8c T: 1.16ns= 4.75c 1592 AVX :VPCMPISTRI xmm, xmm, imm8 L: 0.93ns= 3.8c T: 0.93ns= 3.83c 1593 SSE4.2 :PCMPISTRM xmm, xmm, imm8 L: 1.16ns= 4.8c T: 1.16ns= 4.75c 1594 AVX :VPCMPISTRM xmm, xmm, imm8 L: 1.16ns= 4.8c T: 1.16ns= 4.75c 1595 CLMUL :PCLMULQDQ xmm, xmm, imm8 L: 3.03ns= 12.4c T: 1.54ns= 6.33c 1596 AVX :VPCLMULQDQ xmm,xmm,xmm,im8 L: 3.03ns= 12.4c T: 1.54ns= 6.33c 1597 AESNI :AESENC xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1598 AVX :VAESENC xmm, xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1599 AESNI :AESENCLAST xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1600 AVX :VAESENCLAST xmm, xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1601 AESNI :AESDEC xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1602 AVX :VAESDEC xmm, xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1603 AESNI :AESDECLAST xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1604 AVX :VAESDECLAST xmm, xmm, xmm L: 2.09ns= 8.6c T: 0.22ns= 0.92c 1605 AESNI :AESIMC xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1606 AVX :VAESIMC xmm, xmm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1607 AESNI :AESKEYGEN xmm, xmm, imm8 L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1608 AVX :VAESKEYGEN xmm, xmm, imm8 L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1609 FMA4 :VFMADDSS xmm,xmm,xmm,xmm L: 1.22ns= 5.0c T: 0.12ns= 0.48c 1610 FMA3 :VFMADD132SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1611 FMA3 :VFMADD213SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.49c 1612 FMA3 :VFMADD231SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.11ns= 0.45c 1613 FMA4 :VFMADDPS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1614 FMA3 :VFMADD132PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1615 FMA3 :VFMADD213PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.11ns= 0.45c 1616 FMA3 :VFMADD231PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1617 FMA4 :VFMSUBSS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1618 FMA3 :VFMSUB132SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1619 FMA3 :VFMSUB213SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1620 FMA3 :VFMSUB231SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1621 FMA4 :VFMSUBPS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1622 FMA3 :VFMSUB132PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.49c 1623 FMA3 :VFMSUB213PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1624 FMA3 :VFMSUB231PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1625 FMA4 :VFNMADDSS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1626 FMA3 :VFNMADD132SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.49c 1627 FMA3 :VFNMADD213SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1628 FMA3 :VFNMADD231SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1629 FMA4 :VFNMADDPS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1630 FMA3 :VFNMADD132PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.49c 1631 FMA3 :VFNMADD213PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1632 FMA3 :VFNMADD231PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1633 FMA4 :VFNMSUBSS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.50c 1634 FMA3 :VFNMSUB132SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1635 FMA3 :VFNMSUB213SS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1636 FMA3 :VFNMSUB231SS xmm,xmm,xmm L: 1.22ns= 5.0c T: 0.12ns= 0.50c 1637 FMA4 :VFNMSUBPS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1638 FMA3 :VFNMSUB132PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1639 FMA3 :VFNMSUB213PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1640 FMA3 :VFNMSUB231PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1641 FMA4 :VFMADDSUBPS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1642 FMA3 :VFMADDSUB132PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1643 FMA3 :VFMADDSUB213PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.47c 1644 FMA3 :VFMADDSUB231PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1645 FMA4 :VFMSUBADDPS xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1646 FMA3 :VFMSUBADD132PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1647 FMA3 :VFMSUBADD213PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1648 FMA3 :VFMSUBADD231PS xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1649 FMA4 :VFMADDSD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1650 FMA3 :VFMADD132SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1651 FMA3 :VFMADD213SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1652 FMA3 :VFMADD231SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1653 FMA4 :VFMADDPD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1654 FMA3 :VFMADD132PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1655 FMA3 :VFMADD213PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1656 FMA3 :VFMADD231PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1657 FMA4 :VFMSUBSD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1658 FMA3 :VFMSUB132SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1659 FMA3 :VFMSUB213SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.11ns= 0.45c 1660 FMA3 :VFMSUB231SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1661 FMA4 :VFMSUBPD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1662 FMA3 :VFMSUB132PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1663 FMA3 :VFMSUB213PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1664 FMA3 :VFMSUB231PD xmm,xmm,xmm L: 1.22ns= 5.0c T: 0.12ns= 0.48c 1665 FMA4 :VFNMADDSD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1666 FMA3 :VFNMADD132SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1667 FMA3 :VFNMADD213SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1668 FMA3 :VFNMADD231SD xmm,xmm,xmm L: 1.22ns= 5.0c T: 0.12ns= 0.48c 1669 FMA4 :VFNMADDPD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1670 FMA3 :VFNMADD132PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1671 FMA3 :VFNMADD213PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.13ns= 0.55c 1672 FMA3 :VFNMADD231PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1673 FMA4 :VFNMSUBSD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1674 FMA3 :VFNMSUB132SD xmm,xmm,xmm L: 1.22ns= 5.0c T: 0.12ns= 0.48c 1675 FMA3 :VFNMSUB213SD xmm,xmm,xmm L: 1.22ns= 5.0c T: 0.12ns= 0.48c 1676 FMA3 :VFNMSUB231SD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1677 FMA4 :VFNMSUBPD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1678 FMA3 :VFNMSUB132PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1679 FMA3 :VFNMSUB213PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1680 FMA3 :VFNMSUB231PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1681 FMA4 :VFMADDSUBPD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1682 FMA3 :VFMADDSUB132PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1683 FMA3 :VFMADDSUB213PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1684 FMA3 :VFMADDSUB231PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1685 FMA4 :VFMSUBADDPD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1686 FMA3 :VFMSUBADD132PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.09ns= 0.38c 1687 FMA3 :VFMSUBADD213PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1688 FMA3 :VFMSUBADD231PD xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.12ns= 0.48c 1689 XOP :VFRCZSS xmm, xmm L: 2.32ns= 9.5c T: 0.22ns= 0.92c 1690 XOP :VFRCZPS xmm, xmm L: 2.44ns= 10.0c T: 0.37ns= 1.50c 1691 XOP :VFRCZSD xmm, xmm L: 2.32ns= 9.5c T: 0.35ns= 1.42c 1692 XOP :VFRCZPD xmm, xmm L: 2.32ns= 9.5c T: 0.35ns= 1.42c 1693 XOP :VPCMOV xmm, xmm, xmm, xmm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1694 XOP :VPCOMB xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1695 XOP :VPCOMB xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1696 XOP :VPCOMW xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1697 XOP :VPCOMW xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1698 XOP :VPCOMD xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1699 XOP :VPCOMD xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1700 XOP :VPCOMQ xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1701 XOP :VPCOMQ xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1702 XOP :VPCOMUB xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.47c 1703 XOP :VPCOMUB xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1704 XOP :VPCOMUW xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 1705 XOP :VPCOMUW xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1706 XOP :VPCOMUD xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.50c 1707 XOP :VPCOMUD xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1708 XOP :VPCOMUQ xmm, xmm, xmm, imm8 L: 0.12ns= 0.5c T: 0.12ns= 0.49c 1709 XOP :VPCOMUQ xm1, xm1, xm2, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1710 XOP :VPERMIL2PS xm,xm,xm,xm,im L: 0.69ns= 2.8c T: 0.24ns= 1.00c 1711 XOP :VPERMIL2PD xm,xm,xm,xm,im L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1712 XOP :VPHADDBW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.47c 1713 XOP :VPHADDBD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1714 XOP :VPHADDBQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1715 XOP :VPHADDWD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1716 XOP :VPHADDWQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1717 XOP :VPHADDDQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1718 XOP :VPHADDUBW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1719 XOP :VPHADDUBD xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1720 XOP :VPHADDUBQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1721 XOP :VPHADDUWD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1722 XOP :VPHADDUWQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1723 XOP :VPHADDUDQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1724 XOP :VPHSUBBW xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1725 XOP :VPHSUBWD xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1726 XOP :VPHSUBDQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1727 XOP :VPMACSWW xmm,xmm,xmm,xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1728 XOP :VPMACSWW xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1729 XOP :VPMACSWD xmm,xmm,xmm,xmm L: 0.98ns= 4.0c T: 0.24ns= 1.00c 1730 XOP :VPMACSWD xm1,xm2,xm2,xm1 L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1731 XOP :VPMACSDD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1732 XOP :VPMACSDD xm1,xm2,xm2,xm1 L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1733 XOP :VPMACSDQL xmm,xmm,xmm,xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1734 XOP :VPMACSDQL xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1735 XOP :VPMACSDQH xmm,xmm,xmm,xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1736 XOP :VPMACSDQH xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1737 XOP :VPMACSSWW xmm,xmm,xmm,xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1738 XOP :VPMACSSWW xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1739 XOP :VPMACSSWD xmm,xmm,xmm,xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1740 XOP :VPMACSSWD xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1741 XOP :VPMACSSDD xmm,xmm,xmm,xmm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1742 XOP :VPMACSSDD xm1,xm2,xm2,xm1 L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1743 XOP :VPMACSSDQL xmm,xmm,xmm,xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1744 XOP :VPMACSSDQL xm1,xm2,xm2,xm1 L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1745 XOP :VPMACSSDQH xmm,xmm,xmm,xmm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1746 XOP :VPMACSSDQH xm1,xm2,xm2,xm1 L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1747 XOP :VPMADCSWD xmm,xmm,xmm,xmm L: 0.93ns= 3.8c T: 0.24ns= 1.00c 1748 XOP :VPMADCSWD xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1749 XOP :VPMADCSSWD xmm,xmm,xmm,xmm L: 0.98ns= 4.0c T: 0.22ns= 0.92c 1750 XOP :VPMADCSSWD xm1,xm2,xm2,xm1 L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1751 XOP :VPPERM xmm, xmm, xmm, xmm L: 0.47ns= 1.9c T: 0.24ns= 1.00c 1752 XOP :VPROTB xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1753 XOP :VPROTB xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1754 XOP :VPROTW xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1755 XOP :VPROTW xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1756 XOP :VPROTD xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1757 XOP :VPROTD xmm, xmm, imm8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1758 XOP :VPROTQ xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1759 XOP :VPROTQ xmm, xmm, imm8 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1760 XOP :VPSHAB xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1761 XOP :VPSHAW xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.24ns= 1.00c 1762 XOP :VPSHAD xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1763 XOP :VPSHAQ xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 1764 XOP :VPSHLB xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1765 XOP :VPSHLW xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.22ns= 0.92c 1766 XOP :VPSHLD xmm, xmm, xmm L: 0.73ns= 3.0c T: 0.24ns= 1.00c 1767 XOP :VPSHLQ xmm, xmm, xmm L: 0.69ns= 2.8c T: 0.22ns= 0.92c 1768 F16C :VCVTPS2PH xmm, xmm, imm8 L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1769 F16C :VCVTPH2PS xmm, xmm L: 1.87ns= 7.7c T: 0.43ns= 1.75c 1770 AVX :VMOVAPS ymm, ymm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1771 AVX :VMOVAPS ymm, [m256] L: [memory dep.] T: 0.24ns= 1.00c 1772 AVX :VMOVAPS [m256], ymm L: [memory dep.] T: 0.47ns= 1.92c 1773 AVX :VMOVAPS LS pair L: 2.56ns= 10.5c T: 0.35ns= 1.42c 1774 AVX :VMOVUPS ymm, ymm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1775 AVX :VMOVUPS ymm, [m256] L: [memory dep.] T: 0.24ns= 1.00c 1776 AVX :VMOVUPS [m256], ymm L: [memory dep.] T: 0.47ns= 1.92c 1777 AVX :VMOVUPS aligned LS pair L: 2.56ns= 10.5c T: 0.35ns= 1.42c 1778 AVX :VMOVUPS ymm, [m256 + 4] L: [memory dep.] T: 1.16ns= 4.75c 1779 AVX :VMOVUPS [m256 + 4], ymm L: [memory dep.] T: 0.93ns= 3.83c 1780 AVX :VMOVUPS unaligned LS pair L: 2.85ns= 11.7c T: 1.12ns= 4.58c 1781 AVX :VMOVSLDUP ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.47ns= 1.92c 1782 AVX :VMOVSHDUP ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.47ns= 1.92c 1783 AVX :VMOVNTPS [m256], ymm L: [memory dep.] T: 2.67ns= 2.67c 1784 AVX :VMOVMSKPS r32, ymm L: [diff. reg. set] T: 0.22ns= 0.92c 1785 AVX :VMASKMOVPS ymm,ymm,[m256+4] L: [memory dep.] T: 0.89ns= 3.67c 1786 AVX :VMASKMOVPS [m256+4],ymm,ymm L: [memory dep.] T: 3.72ns= 15.25c 1787 AVX :VMASKMOVPS unaligned LSpair L: 8.45ns= 34.7c T: 3.50ns= 14.33c 1788 AVX :VUNPCKLPS ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1789 AVX :VUNPCKHPS ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1790 AVX :VSHUFPS ymm, ymm, ymm, imm8 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1791 AVX :VPERMILPS ymm, ymm, ymm L: 0.69ns= 2.8c T: 0.47ns= 1.92c 1792 AVX :VPERMILPS ymm, ymm, imm8 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1793 AVX :VCMPPS ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1794 AVX :VADDSUBPS ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1795 AVX :VHSUBPS ymm, ymm, ymm L: 2.56ns= 10.5c T: 0.93ns= 3.83c 1796 AVX :VHADDPS ymm, ymm, ymm L: 2.56ns= 10.5c T: 0.93ns= 3.83c 1797 AVX :VSUBPS ymm, ymm, ymm L: 1.22ns= 5.0c T: 0.47ns= 1.92c 1798 AVX :VADDPS ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1799 AVX :VMULPS ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1800 AVX :VMULPS+VADDPS ymm, ymm, ymm L: 2.32ns= 9.5c T: 0.47ns= 1.92c 1801 AVX :VMULPS ymm1.. VADDPS ymm2.. L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1802 AVX :VMAXPS ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1803 AVX :VMINPS ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1804 AVX :VANDNPS ymm, ymm, ymm L: 0.24ns= 1.0c T: 0.22ns= 0.92c 1805 AVX :VANDNPS ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1806 AVX :VANDPS ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1807 AVX :VANDPS ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1808 AVX :VORPS ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1809 AVX :VORPS ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 1810 AVX :VXORPS ymm, ymm, ymm L: 0.24ns= 1.0c T: 0.22ns= 0.92c 1811 AVX :VXORPS ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1812 AVX :VDIVPS ymm, ymm, ymm L: 4.19ns= 17.2c T: 3.03ns= 12.42c 1813 AVX :VDIVPS (0.0f/x) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1814 AVX :VDIVPS (x/1.0f) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1815 AVX :VDIVPS (x/2.0f) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1816 AVX :VDIVPS (x/0.5f) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1817 AVX :VSQRTPS ymm, ymm L: 5.59ns= 22.9c T: 4.41ns= 18.08c 1818 AVX :VSQRTPS (0.0f) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1819 AVX :VSQRTPS (1.0f) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1820 AVX :VRCPPS ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.43ns= 1.75c 1821 AVX :VRSQRTPS ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.45ns= 1.83c 1822 AVX :VBLENDPS ymm, ymm, ymm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1823 AVX :VBLENDVPS ymm, ymm, ymm, ym L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1824 AVX :VDPPS ymm, ymm, ymm, imm8 L: 6.28ns= 25.8c T: 1.24ns= 5.08c 1825 AVX :VPTESTPS ymm, ymm L: [no true dep.] T: 0.49ns= 2.00c 1826 AVX :VROUNDPS ymm, ymm, imm8 L: 0.98ns= 4.0c T: 0.49ns= 2.00c 1827 AVX :VMOVAPD ymm, ymm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1828 AVX :VMOVAPD ymm, [m256] L: [memory dep.] T: 0.22ns= 0.92c 1829 AVX :VMOVAPD [m256], ymm L: [memory dep.] T: 0.47ns= 1.92c 1830 AVX :VMOVAPD LS pair L: 2.56ns= 10.5c T: 0.30ns= 1.25c 1831 AVX :VMOVUPD ymm, ymm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1832 AVX :VMOVUPD ymm, [m256] L: [memory dep.] T: 0.22ns= 0.92c 1833 AVX :VMOVUPD [m256], ymm L: [memory dep.] T: 0.47ns= 1.92c 1834 AVX :VMOVUPD aligned LS pair L: 2.56ns= 10.5c T: 0.39ns= 1.58c 1835 AVX :VMOVUPD ymm, [m256 + 4] L: [memory dep.] T: 0.71ns= 2.92c 1836 AVX :VMOVUPD [m256 + 4], ymm L: [memory dep.] T: 0.93ns= 3.83c 1837 AVX :VMOVUPD unaligned LS pair L: 2.85ns= 11.7c T: 0.77ns= 3.17c 1838 AVX :VMOVDDUP ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1839 AVX :VMOVNTPD [m256], ymm L: [memory dep.] T: 2.67ns= 2.67c 1840 AVX :VMOVMSKPD r32, ymm L: [diff. reg. set] T: 0.22ns= 0.92c 1841 AVX :VMASKMOVPD ymm,ymm,[m256+4] L: [memory dep.] T: 0.77ns= 3.17c 1842 AVX :VMASKMOVPD [m256+4],ymm,ymm L: [memory dep.] T: 3.72ns= 15.25c 1843 AVX :VMASKMOVPD unaligned LSpair L: 8.47ns= 34.8c T: 3.50ns= 14.33c 1844 AVX :VUNPCKLPD ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1845 AVX :VUNPCKHPD ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1846 AVX :VSHUFPD ymm, ymm, ymm, imm8 L: 0.49ns= 2.0c T: 0.47ns= 1.92c 1847 AVX :VPERMILPD ymm, ymm, ymm L: 0.69ns= 2.8c T: 0.47ns= 1.92c 1848 AVX :VPERMILPD ymm, ymm, imm8 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 1849 AVX :VCMPPD ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1850 AVX :VADDSUBPD ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1851 AVX :VHSUBPD ymm, ymm, ymm L: 2.56ns= 10.5c T: 0.93ns= 3.83c 1852 AVX :VHADDPD ymm, ymm, ymm L: 2.56ns= 10.5c T: 0.93ns= 3.83c 1853 AVX :VSUBPD ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1854 AVX :VADDPD ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1855 AVX :VMULPD ymm, ymm, ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1856 AVX :VMULPD+VADDPD ymm, ymm, ymm L: 2.32ns= 9.5c T: 0.47ns= 1.92c 1857 AVX :VMULPD ymm1.. VADDPD ymm2.. L: 1.16ns= 4.8c T: 0.47ns= 1.92c 1858 AVX :VMAXPD ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1859 AVX :VMINPD ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1860 AVX :VANDNPD ymm, ymm, ymm L: 0.24ns= 1.0c T: 0.22ns= 0.92c 1861 AVX :VANDNPD ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1862 AVX :VANDPD ymm, ymm, ymm L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1863 AVX :VANDPD ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1864 AVX :VORPD ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1865 AVX :VORPD ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1866 AVX :VXORPD ymm, ymm, ymm L: 0.24ns= 1.0c T: 0.22ns= 0.92c 1867 AVX :VXORPD ymm1, ymm1, ymm2 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1868 AVX :VDIVPD ymm, ymm, ymm L: 7.66ns= 31.4c T: 6.50ns= 26.67c 1869 AVX :VDIVPD (0.0/x) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1870 AVX :VDIVPD (x/1.0) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1871 AVX :VDIVPD (x/2.0) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1872 AVX :VDIVPD (x/0.5) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1873 AVX :VSQRTPD ymm, ymm L: 10.22ns= 41.9c T: 9.06ns= 37.17c 1874 AVX :VSQRTPD (0.0) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1875 AVX :VSQRTPD (1.0) L: 2.09ns= 8.6c T: 2.09ns= 8.58c 1876 AVX :VBLENDPD ymm, ymm, ymm, im8 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1877 AVX :VBLENDVPD ymm, ymm, ymm, ym L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1878 AVX :VCVTDQ2PD ymm, xmm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1879 AVX :VCVTPD2DQ xmm, ymm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1880 AVX :VCVTPD2DQ + VCVTDQ2PD L: 3.50ns= 14.3c T: 0.93ns= 3.83c 1881 AVX :VCVTTPD2DQ xmm, ymm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1882 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 3.50ns= 14.3c T: 0.87ns= 3.58c 1883 AVX :VCVTDQ2PS ymm, ymm L: 0.93ns= 3.8c T: 0.47ns= 1.92c 1884 AVX :VCVTPS2DQ ymm, ymm L: 0.93ns= 3.8c T: 0.47ns= 1.92c 1885 AVX :VCVTPS2DQ + VCVTDQ2PS L: 1.87ns= 7.7c T: 0.93ns= 3.83c 1886 AVX :VCVTTPS2DQ ymm, ymm L: 0.93ns= 3.8c T: 0.47ns= 1.92c 1887 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 1.87ns= 7.7c T: 0.93ns= 3.83c 1888 AVX :VCVTPS2PD ymm, xmm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1889 AVX :VCVTPD2PS xmm, ymm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1890 AVX :VCVTPD2PS + VCVTPS2PD L: 3.50ns= 14.3c T: 0.87ns= 3.58c 1891 AVX :VPTESTPD ymm, ymm L: [no true dep.] T: 0.47ns= 1.92c 1892 AVX :VROUNDPD ymm, ymm, imm8 L: 0.93ns= 3.8c T: 0.47ns= 1.92c 1893 AVX :VBROADCASTSS ymm, m32 L: [memory dep.] T: 0.13ns= 0.54c 1894 AVX :VBROADCASTSD ymm, m64 L: [memory dep.] T: 0.12ns= 0.51c 1895 AVX :VBROADCASTF128 ymm, m128 L: [memory dep.] T: 0.13ns= 0.52c 1896 AVX :VEXTRACTF128 xmm, ymm, imm8 L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1897 AVX :VINSERTF128 ym, ym, xm, im8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1898 AVX :VPERM2F128 ym, ym, ym, im8 L: 1.22ns= 5.0c T: 0.81ns= 3.33c 1899 AVX :VMOVDQA ymm, ymm L: 0.49ns= 2.0c T: 0.12ns= 0.49c 1900 AVX :VMOVDQA ymm, [m256] L: [memory dep.] T: 0.22ns= 0.92c 1901 AVX :VMOVDQA [m256], ymm L: [memory dep.] T: 0.47ns= 1.92c 1902 AVX :VMOVDQA LS pair L: 2.56ns= 10.5c T: 0.35ns= 1.42c 1903 AVX :VMOVDQU ymm, ymm L: 0.49ns= 2.0c T: 0.12ns= 0.50c 1904 AVX :VMOVDQU ymm, [m256] L: [memory dep.] T: 0.22ns= 0.92c 1905 AVX :VMOVDQU [m256], ymm L: [memory dep.] T: 0.47ns= 1.92c 1906 AVX :VMOVDQU aligned LS pair L: 2.56ns= 10.5c T: 0.35ns= 1.42c 1907 AVX :VMOVDQU ymm, [m256 + 4] L: [memory dep.] T: 0.77ns= 3.17c 1908 AVX :VMOVDQU [m256 + 4], ymm L: [memory dep.] T: 0.93ns= 3.83c 1909 AVX :VMOVDQU unaligned LS pair L: 2.85ns= 11.7c T: 0.57ns= 2.33c 1910 AVX :VMOVNTDQ [m256], ymm L: [memory dep.] T: 2.67ns= 2.67c 1911 AVX :VLDDQU ymm, [m256 + 4] L: [memory dep.] T: 0.79ns= 3.25c 1912 AVX :VZEROUPPER L: [no true dep.] T: 1.16ns= 4.75c 1913 AVX :VZEROALL L: [no true dep.] T: 2.32ns= 9.50c 1914 FMA4 :VFMADDPS ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1915 FMA3 :VFMADD132PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1916 FMA3 :VFMADD213PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1917 FMA3 :VFMADD231PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1918 FMA4 :VFMSUBPS ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1919 FMA3 :VFMSUB132PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1920 FMA3 :VFMSUB213PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1921 FMA3 :VFMSUB231PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1922 FMA4 :VFNMADDPS ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1923 FMA3 :VFNMADD132PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1924 FMA3 :VFNMADD213PS ymm,ymm,ymm L: 1.22ns= 5.0c T: 0.22ns= 0.92c 1925 FMA3 :VFNMADD231PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1926 FMA4 :VFNMSUBPS ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.24ns= 1.00c 1927 FMA3 :VFNMSUB132PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1928 FMA3 :VFNMSUB213PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1929 FMA3 :VFNMSUB231PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1930 FMA4 :VFMADDSUBPS ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1931 FMA3 :VFMADDSUB132PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1932 FMA3 :VFMADDSUB213PS ymm,ymm,ymm L: 1.22ns= 5.0c T: 0.22ns= 0.92c 1933 FMA3 :VFMADDSUB231PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1934 FMA4 :VFMSUBADDPS ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1935 FMA3 :VFMSUBADD132PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1936 FMA3 :VFMSUBADD213PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.24ns= 1.00c 1937 FMA3 :VFMSUBADD231PS ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1938 FMA4 :VFMADDPD ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1939 FMA3 :VFMADD132PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1940 FMA3 :VFMADD213PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1941 FMA3 :VFMADD231PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1942 FMA4 :VFMSUBPD ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1943 FMA3 :VFMSUB132PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1944 FMA3 :VFMSUB213PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1945 FMA3 :VFMSUB231PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1946 FMA4 :VFNMADDPD ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1947 FMA3 :VFNMADD132PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1948 FMA3 :VFNMADD213PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1949 FMA3 :VFNMADD231PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1950 FMA4 :VFNMSUBPD ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1951 FMA3 :VFNMSUB132PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1952 FMA3 :VFNMSUB213PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1953 FMA3 :VFNMSUB231PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1954 FMA4 :VFMADDSUBPD ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1955 FMA3 :VFMADDSUB132PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1956 FMA3 :VFMADDSUB213PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1957 FMA3 :VFMADDSUB231PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1958 FMA4 :VFMSUBADDPD ymm,ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1959 FMA3 :VFMSUBADD132PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1960 FMA3 :VFMSUBADD213PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1961 FMA3 :VFMSUBADD231PD ymm,ymm,ymm L: 1.16ns= 4.8c T: 0.22ns= 0.92c 1962 XOP :VFRCZSD ymm, ymm L: 2.32ns= 9.5c T: 0.93ns= 3.83c 1963 XOP :VFRCZPD ymm, ymm L: 2.32ns= 9.5c T: 0.93ns= 3.83c 1964 XOP :VPCMOV ymm, ymm, ymm, ymm L: 0.49ns= 2.0c T: 0.49ns= 2.00c 1965 XOP :VPERMIL2PS ym,ym,ym,ym,im L: 0.69ns= 2.8c T: 0.47ns= 1.92c 1966 XOP :VPERMIL2PD ym,ym,ym,ym,im L: 0.69ns= 2.8c T: 0.47ns= 1.92c 1967 F16C :VCVTPS2PH + VCVTPH2PS L: 3.25ns= 13.3c T: 0.93ns= 3.83c 1968 F16C :VCVTPS2PH xmm, ymm, imm8 L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1969 F16C :VCVTPH2PS ymm, xmm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1970 F16C :VCVTPS2PH + VCVTPH2PS L: 3.50ns= 14.3c T: 0.87ns= 3.58c 1974 X86 :MOV+ADD r8, r8 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 1975 X86 :MOV+ADD r16, r16 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 1976 X86 :MOV+ADD r32, r32 L: 0.47ns= 1.9c T: 0.15ns= 0.63c 1977 AMD64 :MOV+ADD r64, r64 L: 0.49ns= 2.0c T: 0.15ns= 0.63c 1978 MMX :MOVQ+PADDB mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1979 MMX :MOVQ+PADDW mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1980 MMX :MOVQ+PADDD mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1981 SSE2 :MOVQ+PADDQ mm, mm L: 0.93ns= 3.8c T: 0.22ns= 0.92c 1983 SSE :MOVSS+ADDSS xmm, xmm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1984 AVX :VMOVSS+VADDSS xm, xm, xm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1985 SSE :MOVAPS+ADDPS xmm, xmm L: 1.16ns= 4.8c T: 0.14ns= 0.56c 1986 AVX :VMOVAPS+VADDPS xm, xm, xm L: 1.16ns= 4.8c T: 0.21ns= 0.88c 1987 SSE2 :MOVSD+ADDSD xmm, xmm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1988 AVX :VMOVSD+VADDSD xm, xm, xm L: 1.87ns= 7.7c T: 0.47ns= 1.92c 1989 SSE2 :MOVAPD+ADDPD xmm, xmm L: 1.16ns= 4.8c T: 0.16ns= 0.65c 1990 AVX :VMOVAPD+VADDPD xm, xm, xm L: 1.16ns= 4.8c T: 0.17ns= 0.71c 1991 SSE2 :MOVDQA+PADDB xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1992 SSE2 :MOVDQA+PADDW xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1993 SSE2 :MOVDQA+PADDD xmm, xmm L: 0.47ns= 1.9c T: 0.12ns= 0.48c 1994 SSE2 :MOVDQA+PADDQ xmm, xmm L: 0.49ns= 2.0c T: 0.12ns= 0.47c 1995 AVX :VMOVDQA+VPADDB xm, xm, xm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1996 AVX :VMOVDQA+VPADDW xm, xm, xm L: 0.49ns= 2.0c T: 0.12ns= 0.47c 1997 AVX :VMOVDQA+VPADDD xm, xm, xm L: 0.49ns= 2.0c T: 0.12ns= 0.48c 1998 AVX :VMOVDQA+VPADDQ xm, xm, xm L: 0.49ns= 2.0c T: 0.11ns= 0.45c 1999 AVX :VMOVAPS+VADDPS ym, ym, ym L: 2.32ns= 9.5c T: 0.35ns= 1.42c 2000 AVX :VMOVAPD+VADDPD ym, ym, ym L: 2.32ns= 9.5c T: 0.35ns= 1.42c 2004 BMI :ANDN r32, r32, r32 L: 0.24ns= 1.0c T: 0.12ns= 0.48c 2005 BMI :ANDN r64, r64, r64 L: 0.24ns= 1.0c T: 0.12ns= 0.49c 2006 BMI :BEXTR r32, r32, r32 L: 0.47ns= 1.9c T: 0.15ns= 0.63c 2007 BMI :BEXTR r64, r64, r64 L: 0.47ns= 1.9c T: 0.15ns= 0.62c 2008 BMI :BLSI r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2009 BMI :BLSI r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2010 BMI :BLSMSK r32, r32 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2011 BMI :BLSMSK r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2012 BMI :BLSR r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2013 BMI :BLSR r64, r64 L: 0.49ns= 2.0c T: 0.22ns= 0.92c 2014 BMI :TZCNT r16, r16 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 2015 BMI :TZCNT r32, r32 L: 0.47ns= 1.9c T: 0.47ns= 1.92c 2016 BMI :TZCNT r64, r64 L: 0.49ns= 2.0c T: 0.47ns= 1.92c 2033 TBM :BEXTR r32, r32, imm32 L: 0.47ns= 1.9c T: 0.15ns= 0.63c 2034 TBM :BEXTR r64, r64, imm64 L: 0.47ns= 1.9c T: 0.16ns= 0.66c 2035 TBM :BLCFILL r32, r32 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2036 TBM :BLCFILL r64, r64 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 2037 TBM :BLCI r32, r32 L: 0.49ns= 2.0c T: 0.24ns= 1.00c 2038 TBM :BLCI r64, r64 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2039 TBM :BLCIC r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2040 TBM :BLCIC r64, r64 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2041 TBM :BLCMSK r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2042 TBM :BLCMSK r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2043 TBM :BLCS r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2044 TBM :BLCS r64, r64 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2045 TBM :BLSFILL r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2046 TBM :BLSFILL r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2047 TBM :BLSIC r32, r32 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2048 TBM :BLSIC r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2049 TBM :T1MSKC r32, r32 L: 0.47ns= 1.9c T: 0.24ns= 1.00c 2050 TBM :T1MSKC r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2051 TBM :TZMSK r32, r32 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2052 TBM :TZMSK r64, r64 L: 0.47ns= 1.9c T: 0.22ns= 0.92c 2238 CLFLUSH :CLFLUSH [mem] L: [memory dep.] T: 64.77ns=265.58c 2248 X86 :MOV r1_8, r2_8 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 2249 X86 :MOV r1_16, r2_16 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 2250 X86 :MOV r1_32, r2_32 L: 0.06ns= 0.3c T: 0.06ns= 0.25c 2251 AMD64 :MOV r1_64, r2_64 L: 0.06ns= 0.3c T: 0.06ns= 0.25c 2252 X86 :MOVSX r1_16, r2_8 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 2253 X86 :MOVSX r1_32, r2_8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2254 AMD64 :MOVSX r1_64, r2_8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2255 X86 :MOVSX r1_32, r2_16 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2256 AMD64 :MOVSX r1_64, r2_16 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2257 AMD64 :MOVSXD r1_64, r2_32 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2258 X86 :MOVZX r1_16, r2_8 L: 0.22ns= 0.9c T: 0.12ns= 0.48c 2259 X86 :MOVZX r1_32, r2_8 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2260 AMD64 :MOVZX r1_64, r2_8 L: 0.12ns= 0.5c T: 0.12ns= 0.50c 2261 X86 :MOVZX r1_32, r2_16 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2262 AMD64 :MOVZX r1_64, r2_16 L: 0.12ns= 0.5c T: 0.12ns= 0.50c 2263 MMX :MOVQ mm1, mm2 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2264 SSE :MOVSS xmm1, xmm2 L: 0.49ns= 2.0c T: 0.21ns= 0.84c 2265 AVX :VMOVSS xmm1, xmm1, xmm2 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2266 SSE :MOVAPS xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2267 AVX :VMOVAPS xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2268 SSE :MOVUPS xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2269 AVX :VMOVUPS xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2270 SSE2 :MOVSD xmm1, xmm2 L: 0.49ns= 2.0c T: 0.19ns= 0.79c 2271 AVX :VMOVSD xmm1, xmm1, xmm2 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2272 SSE2 :MOVAPD xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.25c 2273 AVX :VMOVAPD xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2274 SSE2 :MOVUPD xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2275 AVX :VMOVUPD xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.25c 2276 SSE2 :MOVDQA xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.25c 2277 AVX :VMOVDQA xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2278 SSE2 :MOVDQU xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.24c 2279 AVX :VMOVDQU xmm1, xmm2 L: 0.06ns= 0.3c T: 0.06ns= 0.25c 2280 AVX :VMOVAPS ymm1, ymm2 L: 0.12ns= 0.5c T: 0.12ns= 0.47c 2281 AVX :VMOVUPS ymm1, ymm2 L: 0.12ns= 0.5c T: 0.12ns= 0.47c 2282 AVX :VMOVAPD ymm1, ymm2 L: 0.12ns= 0.5c T: 0.12ns= 0.50c 2283 AVX :VMOVUPD ymm1, ymm2 L: 0.12ns= 0.5c T: 0.12ns= 0.48c 2284 AVX :VMOVDQA ymm1, ymm2 L: 0.12ns= 0.5c T: 0.12ns= 0.47c 2285 AVX :VMOVDQU ymm1, ymm2 L: 0.12ns= 0.5c T: 0.12ns= 0.50c 2290 SSE :4xADDPS xm1,xm1 4x xm2,xm2 L: 4.65ns= 19.1c T: 4.65ns= 19.08c 2291 SSE :4xMULPS xm1,xm1 4x xm2,xm2 L: 4.65ns= 19.1c T: 4.65ns= 19.08c 2292 SSE2 :4xADDPD xm1,xm1 4x xm2,xm2 L: 4.65ns= 19.1c T: 4.65ns= 19.08c 2293 SSE2 :4xMULPD xm1,xm1 4x xm2,xm2 L: 4.65ns= 19.1c T: 4.65ns= 19.08c 2294 LNOP :LNOP3 [eax], eax L: [no true dep.] T: 0.06ns= 0.24c 2295 LNOP :LNOP4 [eax+disp8], eax L: [no true dep.] T: 0.06ns= 0.24c 2296 LNOP :LNOP5 [SIB+disp8], eax L: [no true dep.] T: 0.06ns= 0.24c 2297 LNOP :LNOP6 [SIB+disp8], ax L: [no true dep.] T: 0.07ns= 0.28c 2298 LNOP :LNOP7 [eax+disp32], eax L: [no true dep.] T: 0.09ns= 0.36c 2299 LNOP :LNOP8 [SIB+disp32], eax L: [no true dep.] T: 0.09ns= 0.36c 2300 LNOP :LNOP9 [SIB+disp32], ax L: [no true dep.] T: 0.12ns= 0.48c 2301 LNOP :2x66 LNOPA [SIB+disp32], ax L: [no true dep.] T: 0.12ns= 0.48c 2302 LNOP :3x66 LNOPB [SIB+disp32], ax L: [no true dep.] T: 0.15ns= 0.61c 2303 LNOP :4x66 LNOPC [SIB+disp32], ax L: [no true dep.] T: 3.72ns= 15.25c 2304 LNOP :5x66 LNOPD [SIB+disp32], ax L: [no true dep.] T: 3.78ns= 15.50c 2305 LNOP :6x66 LNOPE [SIB+disp32], ax L: [no true dep.] T: 3.84ns= 15.75c 2306 LNOP :7x66 LNOPF [SIB+disp32], ax L: [no true dep.] T: 3.90ns= 16.00c 4195 AVX :VMOVAPS+VEXTRACTF128 [m128], ym, im8 L: [memory dep.] T: 0.47ns= 1.92c 4209 AVX :VMOVAPS+VINSERTF128 ym, [m128], im8 L: [memory dep.] T: 0.47ns= 1.92c 4354 X86 :SHLD r1_16, r2_16, imm8 L: 0.73ns= 3.0c T: 0.69ns= 2.83c 4355 X86 :SHLD r1_32, r2_32, imm8 L: 0.73ns= 3.0c T: 0.69ns= 2.83c 4356 AMD64 :SHLD r1_64, r2_64, imm8 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4357 X86 :SHLD r1_16, r2_16, cl L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4358 X86 :SHLD r1_32, r2_32, cl L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4359 AMD64 :SHLD r1_64, r2_64, cl L: 0.69ns= 2.8c T: 0.73ns= 3.00c 4360 X86 :SHRD r1_16, r2_16, imm8 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4361 X86 :SHRD r1_32, r2_32, imm8 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4362 AMD64 :SHRD r1_64, r2_64, imm8 L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4363 X86 :SHRD r1_16, r2_16, cl L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4364 X86 :SHRD r1_32, r2_32, cl L: 0.69ns= 2.8c T: 0.69ns= 2.83c 4365 AMD64 :SHRD r1_64, r2_64, cl L: 0.73ns= 3.0c T: 0.69ns= 2.83c 4366 X86 :ADC r8, imm8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4367 X86 :ADC r16, imm8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4368 X86 :ADC r32, imm8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4369 AMD64 :ADC r64, imm8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4370 X86 :ADC r16, imm16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4371 X86 :ADC r32, imm32 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4372 AMD64 :ADC r64, imm32 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4373 X86 :ADC al, imm8 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4374 X86 :ADC ax, imm16 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4375 X86 :ADC eax, imm32 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4376 AMD64 :ADC rax, imm32 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4377 X86 :ADC r8, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4378 X86 :ADC r16, imm8_0 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4379 X86 :ADC r32, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4380 AMD64 :ADC r64, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4381 X86 :ADC r16, imm16_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4382 X86 :ADC r32, imm32_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4383 AMD64 :ADC r64, imm32_0 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4384 X86 :ADC al, imm8_0 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4385 X86 :ADC ax, imm16_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4386 X86 :ADC eax, imm32_0 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4387 AMD64 :ADC rax, imm32_0 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4388 X86 :SBB r8, imm8 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4389 X86 :SBB r16, imm8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4390 X86 :SBB r32, imm8 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4391 AMD64 :SBB r64, imm8 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4392 X86 :SBB r16, imm16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4393 X86 :SBB r32, imm32 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4394 AMD64 :SBB r64, imm32 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4395 X86 :SBB al, imm8 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4396 X86 :SBB ax, imm16 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4397 X86 :SBB eax, imm32 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4398 AMD64 :SBB rax, imm32 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4399 X86 :SBB r8, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4400 X86 :SBB r16, imm8_0 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4401 X86 :SBB r32, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4402 AMD64 :SBB r64, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4403 X86 :SBB r16, imm16_0 L: 0.24ns= 1.0c T: 0.24ns= 1.00c 4404 X86 :SBB r32, imm32_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4405 AMD64 :SBB r64, imm32_0 L: 0.22ns= 0.9c T: 0.22ns= 0.92c 4406 X86 :SBB al, imm8_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4407 X86 :SBB ax, imm16_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4408 X86 :SBB eax, imm32_0 L: 0.24ns= 1.0c T: 0.22ns= 0.92c 4409 AMD64 :SBB rax, imm32_0 L: 0.22ns= 0.9c T: 0.24ns= 1.00c 4410 AMD64 :LEA r16, [disp32] L: 0.28ns= 1.2c T: 0.22ns= 0.92c 4411 AMD64 :LEA r32, [disp32] L: 0.12ns= 0.5c T: 0.12ns= 0.48c 4412 AMD64 :LEA r64, [disp32] L: 0.12ns= 0.5c T: 0.12ns= 0.50c 4413 AMD64 :LEA r16, [r64] L: 0.47ns= 1.9c T: 0.22ns= 0.92c 4414 AMD64 :LEA r32, [r64] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4415 AMD64 :LEA r64, [r64] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4416 AMD64 :LEA r16, [r64 + disp8] L: 0.47ns= 1.9c T: 0.24ns= 1.00c 4417 AMD64 :LEA r32, [r64 + disp8] L: 0.24ns= 1.0c T: 0.12ns= 0.49c 4418 AMD64 :LEA r64, [r64 + disp8] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4419 AMD64 :LEA r16, [r64 + disp32] L: 0.47ns= 1.9c T: 0.22ns= 0.92c 4420 AMD64 :LEA r32, [r64 + disp32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4421 AMD64 :LEA r64, [r64 + disp32] L: 0.22ns= 0.9c T: 0.12ns= 0.47c 4422 AMD64 :LEA r16, [r64 + r64] L: 0.47ns= 1.9c T: 0.22ns= 0.92c 4423 AMD64 :LEA r32, [r64 + r64] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4424 AMD64 :LEA r64, [r64 + r64] L: 0.24ns= 1.0c T: 0.12ns= 0.50c 4425 AMD64 :LEA r16, [r64 + r64 + disp8] L: 0.69ns= 2.8c T: 0.24ns= 1.00c 4426 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.47ns= 1.9c T: 0.13ns= 0.52c 4427 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.49c 4428 AMD64 :LEA r16, [r64 + r64 + disp32] L: 0.69ns= 2.8c T: 0.24ns= 1.00c 4429 AMD64 :LEA r32, [r64 + r64 + disp32] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4430 AMD64 :LEA r64, [r64 + r64 + disp32] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4431 AMD64 :LEA r16, [r64 + r64 * 8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4432 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4433 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.47ns= 1.9c T: 0.11ns= 0.46c 4434 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4435 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4436 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4437 AMD64 :LEA r16, [r64 + r64 * 8 + disp32] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4438 AMD64 :LEA r32, [r64 + r64 * 8 + disp32] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4439 AMD64 :LEA r64, [r64 + r64 * 8 + disp32] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4440 AMD64 :ASP LEA r16, [disp32] L: 0.28ns= 1.2c T: 0.22ns= 0.92c 4441 AMD64 :ASP LEA r32, [disp32] L: 0.12ns= 0.5c T: 0.12ns= 0.48c 4442 AMD64 :ASP LEA r64, [disp32] L: 0.12ns= 0.5c T: 0.12ns= 0.48c 4443 AMD64 :ASP LEA r16, [r32] L: 0.47ns= 1.9c T: 0.24ns= 1.00c 4444 AMD64 :ASP LEA r32, [r32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4445 AMD64 :ASP LEA r64, [r32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4446 AMD64 :ASP LEA r16, [r32 + disp8] L: 0.47ns= 1.9c T: 0.22ns= 0.92c 4447 AMD64 :ASP LEA r32, [r32 + disp8] L: 0.24ns= 1.0c T: 0.11ns= 0.47c 4448 AMD64 :ASP LEA r64, [r32 + disp8] L: 0.24ns= 1.0c T: 0.12ns= 0.49c 4449 AMD64 :ASP LEA r16, [r32 + disp32] L: 0.47ns= 1.9c T: 0.22ns= 0.92c 4450 AMD64 :ASP LEA r32, [r32 + disp32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4451 AMD64 :ASP LEA r64, [r32 + disp32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4452 AMD64 :ASP LEA r16, [r32 + r32] L: 0.47ns= 1.9c T: 0.24ns= 1.00c 4453 AMD64 :ASP LEA r32, [r32 + r32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4454 AMD64 :ASP LEA r64, [r32 + r32] L: 0.24ns= 1.0c T: 0.12ns= 0.48c 4455 AMD64 :ASP LEA r16, [r32 + r32 + disp8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4456 AMD64 :ASP LEA r32, [r32 + r32 + disp8] L: 0.49ns= 2.0c T: 0.12ns= 0.50c 4457 AMD64 :ASP LEA r64, [r32 + r32 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4458 AMD64 :ASP LEA r16, [r32 + r32 + disp32] L: 0.73ns= 3.0c T: 0.22ns= 0.92c 4459 AMD64 :ASP LEA r32, [r32 + r32 + disp32] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4460 AMD64 :ASP LEA r64, [r32 + r32 + disp32] L: 0.49ns= 2.0c T: 0.12ns= 0.48c 4461 AMD64 :ASP LEA r16, [r32 + r32 * 8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4462 AMD64 :ASP LEA r32, [r32 + r32 * 8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4463 AMD64 :ASP LEA r64, [r32 + r32 * 8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4464 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp8] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4465 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4466 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp8] L: 0.47ns= 1.9c T: 0.12ns= 0.48c 4467 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp32] L: 0.69ns= 2.8c T: 0.22ns= 0.92c 4468 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp32] L: 0.49ns= 2.0c T: 0.12ns= 0.48c 4469 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp32] L: 0.47ns= 1.9c T: 0.12ns= 0.48c