Copyright (C) 1995-2020 FinalWire Ltd. All rights reserved. aida_bench64.dll build: 4.5.825.8 Apr 29 2020 15:31:36 Arch:X64 CPUCount:4 NUMA:0 Freq: 1828.31MHz Priority:080 OS:6.3.18363 Memory: 7810752KB AllocGran:0x00010000 P:0x00001000 LP:0x0000000000200000 Memory To Test:16384KB 4K DTLB: 96 2M DTLB: 32 CLFlush:64 ProcMask: 0x000000000000000f Features: X86,TSC,X87,CMOV,MMX,SSE,SSE2,SSE3,AMD64,SSSE3,ABM,SSE4.1,SSE4.2,POPCNT,VIAAES,LAHF,CMPX8,CMPX16,AESNI,CLMUL,AVX,MOVBE,F16C,VIAHASH,VIARNG,RDRAND,FSGSBASE,BMI,CLFLUSH,RDTSCP,3DNOWPREF,LNOP,AVX2,BMI2,XRNG2,PSE,RDSEED,ADX,PAGE1GB, CPU#000 Vendor: CentaurHauls Family: 6 Model: 0f Stepping: e CoreType:0x300006fe CPU#000 Type: " ZHAOXIN KaiXian ZX-C+ C4580@1.83GHz" CPU#000 AffMask: 0x0000000000000001 CPU#000 PhysMask:0x000000000000000f CPU#000 APIC_ID:0x00000000 Phys_ID:000 Core_ID:00 SMT_ID:00 CPU#000 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000001 CPU#000 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000001 CPU#000 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:000000000000000f, Nano L2 CPU#000 L1D 4K TLB: 96 entries, 6 way, SMask:0000000000000001 CPU#000 L1D 2M TLB: 32 entries, 4 way, SMask:0000000000000001 CPU#000 L1I 4K TLB: 96 entries, 6 way, SMask:0000000000000001 CPU#000 L1I 2M TLB: 32 entries, 4 way, SMask:0000000000000001 CPU#001 Vendor: CentaurHauls Family: 6 Model: 0f Stepping: e CoreType:0x300006fe CPU#001 Type: " ZHAOXIN KaiXian ZX-C+ C4580@1.83GHz" CPU#001 AffMask: 0x0000000000000002 CPU#001 PhysMask:0x000000000000000f CPU#001 APIC_ID:0x00000001 Phys_ID:000 Core_ID:01 SMT_ID:00 CPU#001 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000002 CPU#001 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000002 CPU#001 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:000000000000000f, Nano L2 CPU#001 L1D 4K TLB: 96 entries, 6 way, SMask:0000000000000002 CPU#001 L1D 2M TLB: 32 entries, 4 way, SMask:0000000000000002 CPU#001 L1I 4K TLB: 96 entries, 6 way, SMask:0000000000000002 CPU#001 L1I 2M TLB: 32 entries, 4 way, SMask:0000000000000002 CPU#002 Vendor: CentaurHauls Family: 6 Model: 0f Stepping: e CoreType:0x300006fe CPU#002 Type: " ZHAOXIN KaiXian ZX-C+ C4580@1.83GHz" CPU#002 AffMask: 0x0000000000000004 CPU#002 PhysMask:0x000000000000000f CPU#002 APIC_ID:0x00000002 Phys_ID:000 Core_ID:02 SMT_ID:00 CPU#002 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000004 CPU#002 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000004 CPU#002 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:000000000000000f, Nano L2 CPU#002 L1D 4K TLB: 96 entries, 6 way, SMask:0000000000000004 CPU#002 L1D 2M TLB: 32 entries, 4 way, SMask:0000000000000004 CPU#002 L1I 4K TLB: 96 entries, 6 way, SMask:0000000000000004 CPU#002 L1I 2M TLB: 32 entries, 4 way, SMask:0000000000000004 CPU#003 Vendor: CentaurHauls Family: 6 Model: 0f Stepping: e CoreType:0x300006fe CPU#003 Type: " ZHAOXIN KaiXian ZX-C+ C4580@1.83GHz" CPU#003 AffMask: 0x0000000000000008 CPU#003 PhysMask:0x000000000000000f CPU#003 APIC_ID:0x00000003 Phys_ID:000 Core_ID:03 SMT_ID:00 CPU#003 L1I cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000008 CPU#003 L1D cache: 32KB, 64 byte cache line, 8 way, SMask:0000000000000008 CPU#003 L2 cache: 2048KB, 64 byte cache line, 16 way, SMask:000000000000000f, Nano L2 CPU#003 L1D 4K TLB: 96 entries, 6 way, SMask:0000000000000008 CPU#003 L1D 2M TLB: 32 entries, 4 way, SMask:0000000000000008 CPU#003 L1I 4K TLB: 96 entries, 6 way, SMask:0000000000000008 CPU#003 L1I 2M TLB: 32 entries, 4 way, SMask:0000000000000008 Instruction Latency: Used CPUs: 1 ProcMask: 0x0000000000000008 0 X86 :NOP L: [no true dep.] T: 0.21ns= 0.38c 1 X86 :0x66 NOP L: [no true dep.] T: 0.20ns= 0.37c 2 X86 : 2x 0x66 NOP L: [no true dep.] T: 0.21ns= 0.38c 3 X86 : 3x 0x66 NOP L: [no true dep.] T: 0.27ns= 0.50c 4 X86 : 4x 0x66 NOP L: [no true dep.] T: 0.34ns= 0.63c 5 X86 : 5x 0x66 NOP L: [no true dep.] T: 0.29ns= 0.53c 6 X86 : 6x 0x66 NOP L: [no true dep.] T: 0.31ns= 0.56c 7 X86 : 7x 0x66 NOP L: [no true dep.] T: 0.27ns= 0.50c 8 X86 : 8x 0x66 NOP L: [no true dep.] T: 0.31ns= 0.56c 9 X86 : 9x 0x66 NOP L: [no true dep.] T: 0.34ns= 0.62c 10 X86 :10x 0x66 NOP L: [no true dep.] T: 0.38ns= 0.69c 11 X86 :11x 0x66 NOP L: [no true dep.] T: 0.41ns= 0.75c 12 X86 :12x 0x66 NOP L: [no true dep.] T: 0.44ns= 0.81c 13 X86 :13x 0x66 NOP L: [no true dep.] T: 0.48ns= 0.88c 14 X86 :14x 0x66 NOP L: [no true dep.] T: 0.50ns= 0.92c 15 SSE2 :PAUSE L: [no true dep.] T: 8.20ns= 15.00c 16 X86 :MOV r8, imm8 L: 0.55ns= 1.0c T: 0.33ns= 0.60c 17 X86 :MOV r16, imm16 L: 1.23ns= 2.3c T: 1.23ns= 2.25c 18 X86 :MOV r32, imm32 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 19 AMD64 :MOV r64, imm64 L: 1.41ns= 2.6c T: 1.41ns= 2.58c 20 X86 :MOV r8, r8 L: 0.55ns= 1.0c T: 0.33ns= 0.60c 21 X86 :MOV r16, r16 L: 0.55ns= 1.0c T: 0.33ns= 0.60c 22 X86 :MOV r32, r32 L: 0.46ns= 0.8c T: 0.26ns= 0.48c 23 AMD64 :MOV r64, r64 L: 0.46ns= 0.8c T: 0.28ns= 0.50c 24 X86 :MOV r8, [m8] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 25 X86 :MOV r16, [m16] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 26 X86 :MOV r32, [m32] L: 2.19ns= 4.0c T: 0.73ns= 1.33c 27 AMD64 :MOV r64, [m64] L: 2.19ns= 4.0c T: 0.73ns= 1.33c 28 X86 :MOV [m8], r8 L: [memory dep.] T: 0.87ns= 1.58c 29 X86 :MOV [m16], r16 L: [memory dep.] T: 0.91ns= 1.67c 30 X86 :MOV [m32], r32 L: [memory dep.] T: 0.87ns= 1.58c 31 X86 :MOV [m32 + 8], r32 L: [memory dep.] T: 0.87ns= 1.58c 32 AMD64 :MOV [m64], r64 L: [memory dep.] T: 0.87ns= 1.58c 33 AMD64 :MOV [m64 + 16], r64 L: [memory dep.] T: 0.87ns= 1.58c 34 X86 :MOV r8,[m8]+MOV [m8],r8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 35 X86 :MOV r16,[m16]+MOV [m16],r16 L: 3.28ns= 6.0c T: 0.77ns= 1.42c 36 X86 :MOV r32,[m32]+MOV [m32],r32 L: 2.73ns= 5.0c T: 0.64ns= 1.17c 37 AMD64 :MOV r64,[m64]+MOV [m64],r64 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 38 SSE2 :MOVNTI [m32], r32 L: [memory dep.] T: 1.50ns= 1.50c 39 AMD64 :MOVNTI [m64], r64 L: [memory dep.] T: 1.50ns= 1.50c 40 CMOV :CMOVNZ r16, r16 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 41 CMOV :CMOVNZ r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 42 AMD64 :CMOVNZ r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 43 X86 :MOVSX r16, r8 L: 0.55ns= 1.0c T: 0.25ns= 0.45c 44 X86 :MOVSX r32, r8 L: 0.55ns= 1.0c T: 0.26ns= 0.47c 45 AMD64 :MOVSX r64, r8 L: 0.55ns= 1.0c T: 0.27ns= 0.49c 46 X86 :MOVSX r32, r16 L: 0.55ns= 1.0c T: 0.33ns= 0.60c 47 AMD64 :MOVSX r64, r16 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 48 AMD64 :MOVSXD r64, r32 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 49 X86 :MOVZX r16, r8 L: 0.55ns= 1.0c T: 0.25ns= 0.45c 50 X86 :MOVZX r32, r8 L: 0.55ns= 1.0c T: 0.25ns= 0.45c 51 AMD64 :MOVZX r64, r8 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 52 X86 :MOVZX r32, r16 L: 0.55ns= 1.0c T: 0.33ns= 0.60c 53 AMD64 :MOVZX r64, r16 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 54 X86 :XCHG r8, r8 L: 1.37ns= 2.5c T: 0.77ns= 1.42c 55 X86 :XCHG r16, r16 L: 1.37ns= 2.5c T: 0.82ns= 1.50c 56 X86 :XCHG r32, r32 L: 1.23ns= 2.3c T: 0.82ns= 1.50c 57 AMD64 :XCHG r64, r64 L: 1.23ns= 2.3c T: 0.82ns= 1.50c 58 X86 :XCHG r1_8, r2_8 L: 1.60ns= 2.9c T: 0.59ns= 1.08c 59 X86 :XCHG r1_16, r2_16 L: 1.46ns= 2.7c T: 0.50ns= 0.92c 60 X86 :XCHG r1_32, r2_32 L: 1.46ns= 2.7c T: 0.50ns= 0.92c 61 AMD64 :XCHG r1_64, r2_64 L: 1.46ns= 2.7c T: 0.82ns= 1.50c 62 X86 :XCHG r8, [m8] L: 8.20ns= 15.0c T: 8.75ns= 16.00c 63 X86 :XCHG r16, [m16] L: 8.20ns= 15.0c T: 8.20ns= 15.00c 64 X86 :XCHG r32, [m32] L: 8.20ns= 15.0c T: 8.20ns= 15.00c 65 AMD64 :XCHG r64, [m64] L: 8.20ns= 15.0c T: 8.20ns= 15.00c 66 X86 :ADD r32, 0x04000 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 67 X86 :ADD r32, 0x08000 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 68 X86 :ADD r32, 0x10000 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 69 X86 :ADD r32, 0x20000 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 70 X86 :ADD r8, r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 71 X86 :ADD r16, r16 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 72 X86 :ADD r32, r32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 73 AMD64 :ADD r64, r64 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 74 X86 :ADD r8, [m8] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 75 X86 :ADD r16, [m16] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 76 X86 :ADD r32, [m32] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 77 AMD64 :ADD r64, [m64] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 78 X86 :ADD [m8], r8 L: 2.73ns= 5.0c T: 1.09ns= 2.00c 79 X86 :ADD [m16], r16 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 80 X86 :ADD [m32], r32 L: 2.73ns= 5.0c T: 0.96ns= 1.75c 81 X86 :ADD [m32 + 8], r32 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 82 AMD64 :ADD [m64], r64 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 83 AMD64 :ADD [m64 + 16], r64 L: 2.73ns= 5.0c T: 0.82ns= 1.50c 84 X86 :LOCK ADD [m8], r8 L: 8.30ns= 15.2c T: 8.30ns= 15.17c 85 X86 :LOCK ADD [m16], r16 L: 8.30ns= 15.2c T: 8.30ns= 15.17c 86 X86 :LOCK ADD [m32], r32 L: 8.30ns= 15.2c T: 8.30ns= 15.17c 87 X86 :LOCK ADD [m32 + 8], r32 L: 8.30ns= 15.2c T: 8.30ns= 15.17c 88 AMD64 :LOCK ADD [m64], r64 L: 8.30ns= 15.2c T: 8.30ns= 15.17c 89 AMD64 :LOCK ADD [m64 + 16], r64 L: 8.30ns= 15.2c T: 8.30ns= 15.17c 90 X86 :ADD r8, imm8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 91 X86 :ADD r16, imm8 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 92 X86 :ADD r32, imm8 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 93 AMD64 :ADD r64, imm8 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 94 X86 :ADD r16, imm16 L: 1.28ns= 2.3c T: 1.28ns= 2.33c 95 X86 :ADD r32, imm32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 96 AMD64 :ADD r64, imm32 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 97 X86 :ADD [m8], imm8 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 98 X86 :ADD [m16], imm8 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 99 X86 :ADD [m32], imm8 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 100 AMD64 :ADD [m64], imm8 L: 2.73ns= 5.0c T: 0.87ns= 1.58c 101 X86 :ADD [m16], imm16 L: 2.73ns= 5.0c T: 1.28ns= 2.33c 102 X86 :ADD [m32], imm32 L: 2.73ns= 5.0c T: 0.91ns= 1.67c 103 AMD64 :ADD [m64], imm32 L: 2.73ns= 5.0c T: 0.87ns= 1.58c 104 X86 :ADD al, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 105 X86 :ADD ax, imm16 L: 1.23ns= 2.3c T: 1.23ns= 2.25c 106 X86 :ADD eax, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 107 AMD64 :ADD rax, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 108 X86 :SUB r8, r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 109 X86 :SUB r16, r16 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 110 X86 :SUB r32, r32 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 111 AMD64 :SUB r64, r64 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 112 X86 :SUB r1_8, r2_8 L: 0.55ns= 1.0c T: 0.36ns= 0.66c 113 X86 :SUB r1_16, r2_16 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 114 X86 :SUB r1_32, r2_32 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 115 AMD64 :SUB r1_64, r2_64 L: 0.55ns= 1.0c T: 0.28ns= 0.51c 116 X86 :ADC r8, r8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 117 X86 :ADC r16, r16 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 118 X86 :ADC r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 119 AMD64 :ADC r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 120 X86 :SBB r8, r8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 121 X86 :SBB r16, r16 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 122 X86 :SBB r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 123 AMD64 :SBB r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 124 X86 :SBB r1_8, r2_8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 125 X86 :SBB r1_16, r2_16 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 126 X86 :SBB r1_32, r2_32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 127 AMD64 :SBB r1_64, r2_64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 128 X86 :CMP r8, r8 L: [no true dep.] T: 0.27ns= 0.50c 129 X86 :CMP r16, r16 L: [no true dep.] T: 0.27ns= 0.50c 130 X86 :CMP r32, r32 L: [no true dep.] T: 0.27ns= 0.50c 131 AMD64 :CMP r64, r64 L: [no true dep.] T: 0.27ns= 0.50c 132 X86 :CMP r1_8, r2_8 L: [no true dep.] T: 0.27ns= 0.50c 133 X86 :CMP r1_16, r2_16 L: [no true dep.] T: 0.27ns= 0.50c 134 X86 :CMP r1_32, r2_32 L: [no true dep.] T: 0.27ns= 0.50c 135 AMD64 :CMP r1_64, r2_64 L: [no true dep.] T: 0.27ns= 0.50c 136 X86 :AND r8, r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 137 X86 :AND r16, r16 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 138 X86 :AND r32, r32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 139 AMD64 :AND r64, r64 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 140 X86 :AND r1_8, r2_8 L: 0.55ns= 1.0c T: 0.36ns= 0.66c 141 X86 :AND r1_16, r2_16 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 142 X86 :AND r1_32, r2_32 L: 0.55ns= 1.0c T: 0.34ns= 0.63c 143 AMD64 :AND r1_64, r2_64 L: 0.55ns= 1.0c T: 0.28ns= 0.51c 144 X86 :OR r8, r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 145 X86 :OR r16, r16 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 146 X86 :OR r32, r32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 147 AMD64 :OR r64, r64 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 148 X86 :OR r1_8, r2_8 L: 0.55ns= 1.0c T: 0.36ns= 0.66c 149 X86 :OR r1_16, r2_16 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 150 X86 :OR r1_32, r2_32 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 151 AMD64 :OR r1_64, r2_64 L: 0.55ns= 1.0c T: 0.28ns= 0.51c 152 X86 :XOR r8, r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 153 X86 :XOR r16, r16 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 154 X86 :XOR r32, r32 L: 0.28ns= 0.5c T: 0.27ns= 0.50c 155 AMD64 :XOR r64, r64 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 156 X86 :XOR r1_8, r2_8 L: 0.55ns= 1.0c T: 0.36ns= 0.66c 157 X86 :XOR r1_16, r2_16 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 158 X86 :XOR r1_32, r2_32 L: 0.55ns= 1.0c T: 0.34ns= 0.62c 159 AMD64 :XOR r1_64, r2_64 L: 0.55ns= 1.0c T: 0.28ns= 0.51c 160 X86 :NEG r8 L: 0.59ns= 1.1c T: 0.55ns= 1.00c 161 X86 :NEG r16 L: 0.59ns= 1.1c T: 0.55ns= 1.00c 162 X86 :NEG r32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 163 AMD64 :NEG r64 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 164 X86 :NOT r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 165 X86 :NOT r16 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 166 X86 :NOT r32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 167 AMD64 :NOT r64 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 168 X86 :TEST r8, r8 L: [no true dep.] T: 0.27ns= 0.50c 169 X86 :TEST r16, r16 L: [no true dep.] T: 0.27ns= 0.50c 170 X86 :TEST r32, r32 L: [no true dep.] T: 0.27ns= 0.50c 171 AMD64 :TEST r64, r64 L: [no true dep.] T: 0.27ns= 0.50c 172 X86 :TEST r1_8, r2_8 L: [no true dep.] T: 0.27ns= 0.50c 173 X86 :TEST r1_16, r2_16 L: [no true dep.] T: 0.27ns= 0.50c 174 X86 :TEST r1_32, r2_32 L: [no true dep.] T: 0.27ns= 0.50c 175 AMD64 :TEST r1_64, r2_64 L: [no true dep.] T: 0.27ns= 0.50c 176 X86 :BT r16, r16 L: [no true dep.] T: 0.55ns= 1.00c 177 X86 :BT r32, r32 L: [no true dep.] T: 0.55ns= 1.00c 178 AMD64 :BT r64, r64 L: [no true dep.] T: 0.55ns= 1.00c 179 X86 :BT r16, imm8 L: [no true dep.] T: 0.55ns= 1.00c 180 X86 :BT r32, imm8 L: [no true dep.] T: 0.55ns= 1.00c 181 AMD64 :BT r64, imm8 L: [no true dep.] T: 0.55ns= 1.00c 182 X86 :BTC r16, r16 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 183 X86 :BTC r32, r32 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 184 AMD64 :BTC r64, r64 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 185 X86 :BTC r16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 186 X86 :BTC r32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 187 AMD64 :BTC r64, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 188 X86 :BTR r16, r16 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 189 X86 :BTR r32, r32 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 190 AMD64 :BTR r64, r64 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 191 X86 :BTR r16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 192 X86 :BTR r32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 193 AMD64 :BTR r64, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 194 X86 :BTS r16, r16 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 195 X86 :BTS r32, r32 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 196 AMD64 :BTS r64, r64 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 197 X86 :BTS r16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 198 X86 :BTS r32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 199 AMD64 :BTS r64, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 200 X86 :SETC r8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 201 X86 :INC r8 L: 0.55ns= 1.0c T: 0.28ns= 0.52c 202 X86 :INC r16 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 203 X86 :INC r32 L: 0.55ns= 1.0c T: 0.32ns= 0.59c 204 AMD64 :INC r64 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 205 AMD64 :LEA r16, [r64 + r64] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 206 AMD64 :LEA r32, [r64 + r64] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 207 AMD64 :LEA r64, [r64 + r64] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 208 AMD64 :LEA r16, [r64 + r64 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 209 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 210 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 211 AMD64 :LEA r16, [r64 + r64 * 8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 212 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 213 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 214 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 215 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 216 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 217 X86 :SHL r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 218 X86 :SHL r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 219 X86 :SHL r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 220 AMD64 :SHL r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 221 X86 :SHL r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 222 X86 :SHL r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 223 X86 :SHL r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 224 AMD64 :SHL r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 225 X86 :SHL r8, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 226 X86 :SHL r16, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 227 X86 :SHL r32, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 228 AMD64 :SHL r64, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 229 X86 :SHR r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 230 X86 :SHR r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 231 X86 :SHR r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 232 AMD64 :SHR r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 233 X86 :SHR r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 234 X86 :SHR r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 235 X86 :SHR r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 236 AMD64 :SHR r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 237 X86 :SHR r8, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 238 X86 :SHR r16, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 239 X86 :SHR r32, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 240 AMD64 :SHR r64, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 241 X86 :SAR r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 242 X86 :SAR r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 243 X86 :SAR r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 244 AMD64 :SAR r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 245 X86 :SAR r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 246 X86 :SAR r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 247 X86 :SAR r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 248 AMD64 :SAR r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 249 X86 :SAR r8, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 250 X86 :SAR r16, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 251 X86 :SAR r32, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 252 AMD64 :SAR r64, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 253 X86 :SHLD r1_16, r1_16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 254 X86 :SHLD r1_32, r1_32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 255 AMD64 :SHLD r1_64, r1_64, imm8 L: 20.78ns= 38.0c T: 20.78ns= 38.00c 256 X86 :SHLD r1_16, r1_16, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 257 X86 :SHLD r1_32, r1_32, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 258 AMD64 :SHLD r1_64, r1_64, cl L: 15.31ns= 28.0c T: 15.31ns= 28.00c 259 X86 :SHRD r1_16, r1_16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 260 X86 :SHRD r1_32, r1_32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 261 AMD64 :SHRD r1_64, r1_64, imm8 L: 18.41ns= 33.7c T: 18.41ns= 33.67c 262 X86 :SHRD r1_16, r1_16, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 263 X86 :SHRD r1_32, r1_32, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 264 AMD64 :SHRD r1_64, r1_64, cl L: 15.31ns= 28.0c T: 15.31ns= 28.00c 265 X86 :ROL r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 266 X86 :ROL r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 267 X86 :ROL r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 268 AMD64 :ROL r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 269 X86 :ROL r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 270 X86 :ROL r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 271 X86 :ROL r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 272 AMD64 :ROL r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 273 X86 :ROL r8, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 274 X86 :ROL r16, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 275 X86 :ROL r32, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 276 AMD64 :ROL r64, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 277 X86 :ROR r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 278 X86 :ROR r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 279 X86 :ROR r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 280 AMD64 :ROR r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 281 X86 :ROR r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 282 X86 :ROR r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 283 X86 :ROR r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 284 AMD64 :ROR r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 285 X86 :ROR r8, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 286 X86 :ROR r16, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 287 X86 :ROR r32, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 288 AMD64 :ROR r64, cl L: 0.55ns= 1.0c T: 0.55ns= 1.00c 289 X86 :RCL r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 290 X86 :RCL r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 291 X86 :RCL r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 292 AMD64 :RCL r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 293 X86 :RCL r8, imm8 L: 19.14ns= 35.0c T: 19.14ns= 35.00c 294 X86 :RCL r16, imm8 L: 19.69ns= 36.0c T: 19.69ns= 36.00c 295 X86 :RCL r32, imm8 L: 20.24ns= 37.0c T: 20.24ns= 37.00c 296 AMD64 :RCL r64, imm8 L: 20.24ns= 37.0c T: 20.24ns= 37.00c 297 X86 :RCL r8, cl L: 14.77ns= 27.0c T: 14.77ns= 27.00c 298 X86 :RCL r16, cl L: 14.22ns= 26.0c T: 14.22ns= 26.00c 299 X86 :RCL r32, cl L: 14.22ns= 26.0c T: 14.22ns= 26.00c 300 AMD64 :RCL r64, cl L: 14.22ns= 26.0c T: 14.22ns= 26.00c 301 X86 :RCR r8, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 302 X86 :RCR r16, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 303 X86 :RCR r32, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 304 AMD64 :RCR r64, 1 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 305 X86 :RCR r8, imm8 L: 19.14ns= 35.0c T: 19.14ns= 35.00c 306 X86 :RCR r16, imm8 L: 19.69ns= 36.0c T: 19.69ns= 36.00c 307 X86 :RCR r32, imm8 L: 20.24ns= 37.0c T: 20.24ns= 37.00c 308 AMD64 :RCR r64, imm8 L: 20.24ns= 37.0c T: 20.24ns= 37.00c 309 X86 :RCR r8, cl L: 14.77ns= 27.0c T: 14.77ns= 27.00c 310 X86 :RCR r16, cl L: 14.22ns= 26.0c T: 14.22ns= 26.00c 311 X86 :RCR r32, cl L: 14.22ns= 26.0c T: 14.22ns= 26.00c 312 AMD64 :RCR r64, cl L: 14.22ns= 26.0c T: 14.22ns= 26.00c 313 X86 :BSF r16, r16 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 314 X86 :BSF r32, r32 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 315 AMD64 :BSF r64, r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 316 X86 :BSR r16, r16 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 317 X86 :BSR r32, r32 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 318 AMD64 :BSR r64, r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 319 X86 :BSWAP r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 320 AMD64 :BSWAP r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 321 MOVBE :MOVBE r16, [m16] L: 8.20ns= 15.0c T: 0.68ns= 1.25c 322 MOVBE :MOVBE r32, [m32] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 323 MOVBE :MOVBE r64, [m64] L: 2.73ns= 5.0c T: 0.68ns= 1.25c 324 MOVBE :MOVBE [m16], r16 L: [memory dep.] T: 0.91ns= 1.67c 325 MOVBE :MOVBE [m32], r32 L: [memory dep.] T: 0.91ns= 1.67c 326 MOVBE :MOVBE [m64], r64 L: [memory dep.] T: 0.91ns= 1.67c 327 X86 :IMUL r16, r16 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 328 X86 :IMUL r32, r32 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 329 AMD64 :IMUL r64, r64 L: 5.47ns= 10.0c T: 1.09ns= 2.00c 330 X86 :IMUL r16, r16, imm8 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 331 X86 :IMUL r32, r32, imm8 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 332 AMD64 :IMUL r64, r64, imm8 L: 4.92ns= 9.0c T: 1.09ns= 2.00c 333 X86 :IMUL r16, r16, imm16 L: 1.28ns= 2.3c T: 1.28ns= 2.33c 334 X86 :IMUL r32, r32, imm32 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 335 AMD64 :IMUL r64, r64, imm32 L: 4.92ns= 9.0c T: 1.09ns= 2.00c 336 X86 :IMUL r8 (ah) L: 1.09ns= 2.0c T: 1.09ns= 2.00c 337 X86 :IMUL r16 (dx) L: 1.87ns= 3.4c T: 1.46ns= 2.67c 338 X86 :IMUL r32 (edx) L: 1.87ns= 3.4c T: 1.46ns= 2.67c 339 AMD64 :IMUL r64 (rdx) L: 7.11ns= 13.0c T: 6.56ns= 12.00c 340 X86 :MUL r8 (ah) L: 1.09ns= 2.0c T: 1.09ns= 2.00c 341 X86 :MUL r16 (dx) L: 1.87ns= 3.4c T: 1.46ns= 2.67c 342 X86 :MUL r32 (edx) L: 1.87ns= 3.4c T: 1.46ns= 2.67c 343 AMD64 :MUL r64 (rdx) L: 7.11ns= 13.0c T: 6.56ns= 12.00c 344 X86 :IMUL r8 (al) L: 1.09ns= 2.0c T: 1.09ns= 2.00c 345 X86 :IMUL r16 (ax) L: 1.55ns= 2.8c T: 1.55ns= 2.83c 346 X86 :IMUL r32 (eax) L: 1.55ns= 2.8c T: 1.55ns= 2.83c 347 AMD64 :IMUL r64 (rax) L: 7.11ns= 13.0c T: 6.56ns= 12.00c 348 X86 :MUL r8 (al) L: 1.09ns= 2.0c T: 1.09ns= 2.00c 349 X86 :MUL r16 (ax) L: 1.55ns= 2.8c T: 1.55ns= 2.83c 350 X86 :MUL r32 (eax) L: 1.55ns= 2.8c T: 1.55ns= 2.83c 351 AMD64 :MUL r64 (rax) L: 7.11ns= 13.0c T: 6.56ns= 12.00c 352 X86 :IDIV r8 14/ 7b (full) L: 13.26ns= 24.3c T: 12.90ns= 23.58c 353 X86 :IDIV r8 12/ 7b ax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 354 X86 :IDIV r8 7/ 7b ax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 355 X86 :IDIV r8 4/ 7b ax upd L: [no true dep.] T: 11.49ns= 21.00c 356 X86 :IDIV r8 0/ 7b L: [no true dep.] T: 10.94ns= 20.00c 357 X86 :IDIV r8 11/ 4b ax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 358 X86 :IDIV r8 8/ 4b ax upd L: [no true dep.] T: 11.49ns= 21.00c 359 X86 :IDIV r8 4/ 4b ax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 360 X86 :IDIV r8 0/ 4b L: [no true dep.] T: 11.76ns= 21.50c 361 X86 :IDIV r8 2^12/2^6 ax upd L: [no true dep.] T: 11.49ns= 21.00c 362 X86 :IDIV r8 1/1 L: 12.03ns= 22.0c T: 11.76ns= 21.50c 363 X86 :IDIV r8 1/1 ax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 364 X86 :IDIV r16 30/15b (full) L: 14.22ns= 26.0c T: 14.22ns= 26.00c 365 X86 :IDIV r16 24/15b ax upd L: 14.04ns= 25.7c T: 14.04ns= 25.67c 366 X86 :IDIV r16 15/15b ax upd L: 12.31ns= 22.5c T: 12.31ns= 22.50c 367 X86 :IDIV r16 8/15b ax/dx upd L: [no true dep.] T: 12.58ns= 23.00c 368 X86 :IDIV r16 0/15b L: [no true dep.] T: 10.94ns= 20.00c 369 X86 :IDIV r16 23/ 8b ax upd L: 14.77ns= 27.0c T: 14.36ns= 26.25c 370 X86 :IDIV r16 16/ 8b ax upd L: [no true dep.] T: 13.45ns= 24.58c 371 X86 :IDIV r16 8/ 8b ax upd L: 12.31ns= 22.5c T: 12.31ns= 22.50c 372 X86 :IDIV r16 0/ 8b L: [no true dep.] T: 10.94ns= 20.00c 373 X86 :IDIV r16 2^28/2^14 ax/dx L: [no true dep.] T: 15.36ns= 28.08c 374 X86 :IDIV r16 1/1 L: 12.03ns= 22.0c T: 12.03ns= 22.00c 375 X86 :IDIV r16 1/1 ax upd L: 12.31ns= 22.5c T: 12.31ns= 22.50c 376 X86 :IDIV r16 1/1 ax/dx upd L: 13.13ns= 24.0c T: 13.04ns= 23.83c 377 X86 :IDIV r32 62/31b (full) L: 14.90ns= 27.3c T: 14.81ns= 27.08c 378 X86 :IDIV r32 62/31b 0 rem. L: 14.90ns= 27.3c T: 14.81ns= 27.08c 379 X86 :IDIV r32 48/31b eax upd L: 13.63ns= 24.9c T: 13.17ns= 24.08c 380 X86 :IDIV r32 31/31b eax upd L: 10.94ns= 20.0c T: 10.94ns= 20.00c 381 X86 :IDIV r32 16/31b eax/edx L: [no true dep.] T: 8.75ns= 16.00c 382 X86 :IDIV r32 0/31b L: [no true dep.] T: 10.39ns= 19.00c 383 X86 :IDIV r32 47/16b eax upd L: 15.31ns= 28.0c T: 15.31ns= 28.00c 384 X86 :IDIV r32 32/16b eax upd L: [no true dep.] T: 13.08ns= 23.92c 385 X86 :IDIV r32 16/16b eax upd L: 10.94ns= 20.0c T: 10.94ns= 20.00c 386 X86 :IDIV r32 0/16b L: [no true dep.] T: 10.39ns= 19.00c 387 X86 :IDIV r32 2^60/2^30 eax/edx L: [no true dep.] T: 10.94ns= 20.00c 388 X86 :IDIV r32 1/1 L: 10.57ns= 19.3c T: 10.57ns= 19.33c 389 X86 :IDIV r32 1/1 eax upd L: 10.94ns= 20.0c T: 10.94ns= 20.00c 390 X86 :IDIV r32 1/1 eax/edx upd L: 8.75ns= 16.0c T: 8.75ns= 16.00c 391 AMD64 :IDIV r64 126/63b (full) L: 116.50ns=213.0c T: 116.50ns=213.00c 392 AMD64 :IDIV r64 126/63b 0 rem. L: 116.50ns=213.0c T: 116.50ns=213.00c 393 AMD64 :IDIV r64 96/63b rax upd L: 115.41ns=211.0c T: 115.41ns=211.00c 394 AMD64 :IDIV r64 63/63b rax upd L: 107.75ns=197.0c T: 107.75ns=197.00c 395 AMD64 :IDIV r64 32/63b rax/rdx L: [no true dep.] T: 107.29ns=196.17c 396 AMD64 :IDIV r64 0/63b L: [no true dep.] T: 106.70ns=195.08c 397 AMD64 :IDIV r64 95/32b rax upd L: 117.05ns=214.0c T: 117.05ns=214.00c 398 AMD64 :IDIV r64 64/32b rax upd L: [no true dep.] T: 108.34ns=198.08c 399 AMD64 :IDIV r64 32/32b rax upd L: 107.75ns=197.0c T: 107.75ns=197.00c 400 AMD64 :IDIV r64 0/32b L: [no true dep.] T: 106.70ns=195.08c 401 AMD64 :IDIV r64 2^124/2^62 rax/rdx L: [no true dep.] T: 112.22ns=205.17c 402 AMD64 :IDIV r64 1/1 L: 107.20ns=196.0c T: 107.20ns=196.00c 403 AMD64 :IDIV r64 1/1 rax upd L: 107.75ns=197.0c T: 107.75ns=197.00c 404 AMD64 :IDIV r64 1/1 rax/rdx upd L: 107.75ns=197.0c T: 107.75ns=197.00c 405 X86 :DIV r8 16/ 8b (full) L: 13.17ns= 24.1c T: 12.81ns= 23.42c 406 X86 :DIV r8 12/ 8b ax upd L: 12.31ns= 22.5c T: 11.81ns= 21.58c 407 X86 :DIV r8 8/ 8b ax upd L: 12.31ns= 22.5c T: 12.26ns= 22.42c 408 X86 :DIV r8 4/ 8b ax upd L: [no true dep.] T: 11.76ns= 21.50c 409 X86 :DIV r8 0/ 8b L: [no true dep.] T: 11.12ns= 20.33c 410 X86 :DIV r8 12/ 4b ax upd L: 12.31ns= 22.5c T: 12.26ns= 22.42c 411 X86 :DIV r8 8/ 4b ax upd L: [no true dep.] T: 12.26ns= 22.42c 412 X86 :DIV r8 4/ 4b ax upd L: 12.31ns= 22.5c T: 12.26ns= 22.42c 413 X86 :DIV r8 0/ 4b L: [no true dep.] T: 11.85ns= 21.67c 414 X86 :DIV r8 2^14/2^7 ax upd L: [no true dep.] T: 11.81ns= 21.58c 415 X86 :DIV r8 1/1 L: 12.08ns= 22.1c T: 11.85ns= 21.67c 416 X86 :DIV r8 1/1 ax upd L: 12.31ns= 22.5c T: 12.26ns= 22.42c 417 X86 :DIV r16 32/16b (full) L: 15.41ns= 28.2c T: 15.31ns= 28.00c 418 X86 :DIV r16 30/15b 0 rem. L: 15.45ns= 28.3c T: 15.31ns= 28.00c 419 X86 :DIV r16 24/16b ax upd L: 14.49ns= 26.5c T: 14.49ns= 26.50c 420 X86 :DIV r16 16/16b ax upd L: 13.40ns= 24.5c T: 13.40ns= 24.50c 421 X86 :DIV r16 8/16b ax/dx upd L: [no true dep.] T: 13.95ns= 25.50c 422 X86 :DIV r16 0/16b L: [no true dep.] T: 12.63ns= 23.08c 423 X86 :DIV r16 24/ 8b ax upd L: 15.50ns= 28.3c T: 15.45ns= 28.25c 424 X86 :DIV r16 16/ 8b ax upd L: [no true dep.] T: 14.49ns= 26.50c 425 X86 :DIV r16 8/ 8b ax upd L: 13.40ns= 24.5c T: 13.40ns= 24.50c 426 X86 :DIV r16 0/ 8b L: [no true dep.] T: 12.63ns= 23.08c 427 X86 :DIV r16 1/1 L: 13.13ns= 24.0c T: 13.13ns= 24.00c 428 X86 :DIV r16 1/1 ax upd L: 13.40ns= 24.5c T: 13.40ns= 24.50c 429 X86 :DIV r16 1/1 ax/dx upd L: 14.08ns= 25.8c T: 14.08ns= 25.75c 430 X86 :DIV r32 64/32b (full) L: 15.86ns= 29.0c T: 15.86ns= 29.00c 431 X86 :DIV r32 62/31b 0 rem. L: 15.86ns= 29.0c T: 15.86ns= 29.00c 432 X86 :DIV r32 48/32b eax upd L: 13.67ns= 25.0c T: 13.67ns= 25.00c 433 X86 :DIV r32 32/32b eax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 434 X86 :DIV r32 16/32b eax/edx L: [no true dep.] T: 9.30ns= 17.00c 435 X86 :DIV r32 0/32b L: [no true dep.] T: 10.94ns= 20.00c 436 X86 :DIV r32 48/16b eax upd L: 15.86ns= 29.0c T: 15.86ns= 29.00c 437 X86 :DIV r32 32/16b eax upd L: [no true dep.] T: 13.67ns= 25.00c 438 X86 :DIV r32 16/16b eax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 439 X86 :DIV r32 0/16b L: [no true dep.] T: 10.94ns= 20.00c 440 X86 :DIV r32 2^62/2^31 eax/edx L: [no true dep.] T: 10.94ns= 20.00c 441 X86 :DIV r32 1/1 L: 11.58ns= 21.2c T: 11.49ns= 21.00c 442 X86 :DIV r32 1/1 eax upd L: 11.49ns= 21.0c T: 11.49ns= 21.00c 443 X86 :DIV r32 1/1 eax/edx upd L: 9.30ns= 17.0c T: 9.30ns= 17.00c 444 AMD64 :DIV r64 128/64b (full) L: 96.26ns=176.0c T: 96.26ns=176.00c 445 AMD64 :DIV r64 126/63b 0 rem. L: 94.08ns=172.0c T: 94.08ns=172.00c 446 AMD64 :DIV r64 96/64b rax upd L: 85.32ns=156.0c T: 85.32ns=156.00c 447 AMD64 :DIV r64 64/64b rax upd L: 85.32ns=156.0c T: 85.32ns=156.00c 448 AMD64 :DIV r64 32/64b rax/rdx L: [no true dep.] T: 84.82ns=155.08c 449 AMD64 :DIV r64 0/64b L: [no true dep.] T: 84.28ns=154.08c 450 AMD64 :DIV r64 96/32b rax upd L: 94.62ns=173.0c T: 94.62ns=173.00c 451 AMD64 :DIV r64 64/32b rax upd L: [no true dep.] T: 85.92ns=157.08c 452 AMD64 :DIV r64 32/32b rax upd L: 85.32ns=156.0c T: 85.32ns=156.00c 453 AMD64 :DIV r64 0/32b L: [no true dep.] T: 84.23ns=154.00c 454 AMD64 :DIV r64 2^126/2^63 rax/rdx L: [no true dep.] T: 89.75ns=164.08c 455 AMD64 :DIV r64 1/1 L: 84.78ns=155.0c T: 84.78ns=155.00c 456 AMD64 :DIV r64 1/1 rax upd L: 85.32ns=156.0c T: 85.32ns=156.00c 457 AMD64 :DIV r64 1/1 rax/rdx upd L: 85.32ns=156.0c T: 85.32ns=156.00c 458 X86 :CBW L: 0.55ns= 1.0c T: 0.55ns= 1.00c 459 X86 :CWDE L: 0.55ns= 1.0c T: 0.55ns= 1.00c 460 AMD64 :CDQE L: 0.55ns= 1.0c T: 0.55ns= 1.00c 461 X86 :CWD L: 0.55ns= 1.0c T: 0.55ns= 1.00c 462 X86 :CDQ L: 0.55ns= 1.0c T: 0.55ns= 1.00c 463 AMD64 :CQO L: 0.55ns= 1.0c T: 0.55ns= 1.00c 464 X86 :CLC L: 1.64ns= 3.0c T: 1.64ns= 3.00c 465 X86 :STC L: 1.64ns= 3.0c T: 1.64ns= 3.00c 466 X86 :CMC L: 1.64ns= 3.0c T: 1.64ns= 3.00c 467 X86 :CLD L: 1.64ns= 3.0c T: 1.64ns= 3.00c 468 X86 :STD L: 1.64ns= 3.0c T: 1.64ns= 3.00c 475 LAHF :LAHF L: 0.55ns= 1.0c T: 0.55ns= 1.00c 476 LAHF :SAHF L: 0.55ns= 1.0c T: 0.55ns= 1.00c 483 X86 :PUSH r16 L: [no true dep.] T: 0.91ns= 1.67c 484 X86 :POP r16 L: [no true dep.] T: 0.68ns= 1.25c 485 X86 :PUSH r16 + POP r16 L: 4.97ns= 9.1c T: 1.09ns= 2.00c 486 AMD64 :PUSH r64 L: [no true dep.] T: 0.91ns= 1.67c 487 AMD64 :POP r64 L: [no true dep.] T: 0.68ns= 1.25c 488 AMD64 :PUSH r64 + POP r64 L: 4.97ns= 9.1c T: 1.09ns= 2.00c 489 AMD64 :PUSH imm8 L: [no true dep.] T: 0.91ns= 1.67c 490 AMD64 :PUSH imm8 + POP r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 491 AMD64 :PUSH imm32 L: [no true dep.] T: 0.91ns= 1.67c 492 AMD64 :PUSH imm32 + POP r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 493 X86 :PUSH [m16] L: [no true dep.] T: 0.96ns= 1.75c 494 X86 :POP [m16] L: [no true dep.] T: 1.09ns= 2.00c 495 X86 :PUSH [m16] + POP [m16] L: 5.47ns= 10.0c T: 1.82ns= 3.33c 496 AMD64 :PUSH [m64] L: [no true dep.] T: 0.87ns= 1.58c 497 AMD64 :POP [m64] L: [no true dep.] T: 1.09ns= 2.00c 498 AMD64 :PUSH [m64] + POP [m64] L: 5.47ns= 10.0c T: 1.91ns= 3.50c 499 X86 :PUSHF L: [no true dep.] T: 0.96ns= 1.75c 501 X86 :PUSHF + POPF L: 5.79ns= 10.6c T: 5.47ns= 10.00c 502 AMD64 :PUSHFQ L: [no true dep.] T: 0.96ns= 1.75c 504 AMD64 :PUSHFQ + POPFQ L: 21.33ns= 39.0c T: 21.33ns= 39.00c 505 X86 :CMPSB L: 3.83ns= 7.0c T: 3.83ns= 7.00c 506 X86 :CMPSW L: 3.83ns= 7.0c T: 3.83ns= 7.00c 507 X86 :CMPSD L: 3.83ns= 7.0c T: 3.83ns= 7.00c 508 AMD64 :CMPSQ L: 3.83ns= 7.0c T: 3.83ns= 7.00c 509 X86 :REPE CMPSB BW in L1D: 0.67 B/c 1217MiB/s 510 X86 :REPE CMPSW BW in L1D: 1.33 B/c 2432MiB/s 511 X86 :REPE CMPSD BW in L1D: 2.59 B/c 4736MiB/s 512 AMD64 :REPE CMPSQ BW in L1D: 4.93 B/c 9023MiB/s 513 X86 :LODSB L: 0.68ns= 1.3c T: 0.68ns= 1.25c 514 X86 :LODSW L: 0.68ns= 1.3c T: 0.68ns= 1.25c 515 X86 :LODSD L: 0.68ns= 1.3c T: 0.96ns= 1.75c 516 AMD64 :LODSQ L: 1.28ns= 2.3c T: 1.28ns= 2.33c 517 X86 :REP LODSB BW in L1D: 0.25 B/c 457MiB/s 518 X86 :REP LODSW BW in L1D: 0.50 B/c 914MiB/s 519 X86 :REP LODSD BW in L1D: 1.00 B/c 1827MiB/s 520 AMD64 :REP LODSQ BW in L1D: 2.00 B/c 3650MiB/s 521 X86 :STOSB L: 0.91ns= 1.7c T: 0.91ns= 1.67c 522 X86 :STOSW L: 0.91ns= 1.7c T: 1.00ns= 1.83c 523 X86 :STOSD L: 0.91ns= 1.7c T: 1.09ns= 2.00c 524 AMD64 :STOSQ L: 1.19ns= 2.2c T: 1.19ns= 2.17c 525 X86 :REP STOSB BW in L1D: 7.52 B/c 13741MiB/s 526 X86 :REP STOSW BW in L1D: 7.51 B/c 13722MiB/s 527 X86 :REP STOSD BW in L1D: 7.52 B/c 13741MiB/s 528 AMD64 :REP STOSQ BW in L1D: 7.51 B/c 13735MiB/s 529 X86 :MOVSB L: 0.96ns= 1.8c T: 1.00ns= 1.83c 530 X86 :MOVSW L: 0.91ns= 1.7c T: 1.05ns= 1.92c 531 X86 :MOVSD L: 0.96ns= 1.8c T: 1.14ns= 2.08c 532 AMD64 :MOVSQ L: 1.37ns= 2.5c T: 1.41ns= 2.58c 533 X86 :REP MOVSB BW in L1D:14.19 B/c 25946MiB/s 534 X86 :REP MOVSW BW in L1D:14.15 B/c 25879MiB/s 535 X86 :REP MOVSD BW in L1D:14.20 B/c 25958MiB/s 536 AMD64 :REP MOVSQ BW in L1D:14.19 B/c 25946MiB/s 537 X86 :SCASB L: 0.64ns= 1.2c T: 0.64ns= 1.17c 538 X86 :SCASW L: 0.64ns= 1.2c T: 0.68ns= 1.25c 539 X86 :SCASD L: 0.64ns= 1.2c T: 1.05ns= 1.92c 540 AMD64 :SCASQ L: 1.37ns= 2.5c T: 1.37ns= 2.50c 541 X86 :REPNE SCASB BW in L1D: 0.44 B/c 812MiB/s 542 X86 :REPNE SCASW BW in L1D: 0.89 B/c 1623MiB/s 543 X86 :REPNE SCASD BW in L1D: 1.76 B/c 3210MiB/s 544 AMD64 :REPNE SCASQ BW in L1D: 3.46 B/c 6327MiB/s 545 X86 :XADD r8, r8 L: 1.19ns= 2.2c T: 1.19ns= 2.17c 546 X86 :XADD r16, r16 L: 1.09ns= 2.0c T: 0.82ns= 1.50c 547 X86 :XADD r32, r32 L: 1.09ns= 2.0c T: 0.82ns= 1.50c 548 AMD64 :XADD r64, r64 L: 1.09ns= 2.0c T: 0.82ns= 1.50c 549 X86 :CMPXCHG r8, r8 L: 8.07ns= 14.8c T: 2.37ns= 4.33c 550 X86 :CMPXCHG r16, r16 L: 7.84ns= 14.3c T: 4.24ns= 7.75c 551 X86 :CMPXCHG r32, r32 L: 6.02ns= 11.0c T: 6.02ns= 11.00c 552 AMD64 :CMPXCHG r64, r64 L: 4.38ns= 8.0c T: 4.38ns= 8.00c 553 CMPX8 :CMPXCHG8B L: 7.11ns= 13.0c T: 7.11ns= 13.00c 554 CMPX16 :CMPXCHG16B L: 32.27ns= 59.0c T: 7.66ns= 14.00c 555 X86 :RDTSC L: [no true dep.] T: 33.36ns= 61.00c 556 X86 :CPUID (EAX = 0) L: 40.47ns= 74.0c T: 40.47ns= 74.00c 557 X86 :CPUID (EAX = 1) L: 124.16ns=227.0c T: 124.16ns=227.00c 558 POPCNT :POPCNT r16, r16 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 559 POPCNT :POPCNT r32, r32 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 560 POPCNT :POPCNT r64, r64 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 561 ABM :LZCNT r16, r16 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 562 ABM :LZCNT r32, r32 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 563 ABM :LZCNT r64, r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 564 SSE4.2 :CRC32 r32, r8 L: 4.38ns= 8.0c T: 4.38ns= 8.00c 565 SSE4.2 :CRC32 r32, r16 L: 6.56ns= 12.0c T: 6.56ns= 12.00c 566 SSE4.2 :CRC32 r32, r32 L: 10.39ns= 19.0c T: 10.39ns= 19.00c 567 SSE4.2 :CRC32 r64, r8 L: 4.38ns= 8.0c T: 4.38ns= 8.00c 568 SSE4.2 :CRC32 r64, r16 L: 19.69ns= 36.0c T: 19.69ns= 36.00c 569 X87 :FNOP L: [no true dep.] T: 0.55ns= 1.00c 570 X87 :FXCH st(i) L: 0.55ns= 1.0c T: 0.55ns= 1.00c 571 X87 :FCHS L: 0.55ns= 1.0c T: 0.55ns= 1.00c 572 X87 :FABS L: 0.55ns= 1.0c T: 0.55ns= 1.00c 573 X87 :FTST L: [no true dep.] T: 0.55ns= 1.00c 574 X87 :FXAM L: [no true dep.] T: 34.46ns= 63.00c 575 CMOV :FCMOVE st, st(i) L: 1.64ns= 3.0c T: 1.64ns= 3.00c 576 X87 :FADD st(i), st (st = 0.0) L: 1.64ns= 3.0c T: 0.55ns= 1.00c 577 X87 :FADD st(i), st L: 1.64ns= 3.0c T: 0.55ns= 1.00c 578 X87 :FADD st, st(i), FXCH st(i) L: 1.64ns= 3.0c T: 0.55ns= 1.00c 579 X87 :FMUL st(i), st (st = 0.0) L: 2.19ns= 4.0c T: 1.09ns= 2.00c 580 X87 :FMUL st(i), st L: 2.19ns= 4.0c T: 1.09ns= 2.00c 581 X87 :FMUL st, st(i), FXCH st(i) L: 2.19ns= 4.0c T: 1.09ns= 2.00c 582 X87 :FMUL + FADD st, st(i) L: 3.83ns= 7.0c T: [not enough reg] 583 X87 :FMUL st(2i) FADD st(2i+1) L: 2.19ns= 4.0c T: [not enough reg] 584 X87 :FDIV32 st(i), st L: 7.11ns= 13.0c T: 7.11ns= 13.00c 585 X87 :FDIV64 st(i), st L: 10.94ns= 20.0c T: 10.94ns= 20.00c 586 X87 :FDIV80 st(i), st L: 12.58ns= 23.0c T: 12.58ns= 23.00c 587 X87 :FDIV80 (0.0l/x) L: 7.66ns= 14.0c T: 7.66ns= 14.00c 588 X87 :FDIV80 (x/1.0l) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 589 X87 :FDIV80 (x/2.0l) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 590 X87 :FDIV80 (x/0.5l) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 591 X87 :FSQRT32 st L: 18.05ns= 33.0c T: 18.05ns= 33.00c 592 X87 :FSQRT64 st L: 33.91ns= 62.0c T: 33.91ns= 62.00c 593 X87 :FSQRT80 st L: 39.93ns= 73.0c T: 39.93ns= 73.00c 594 X87 :FSQRT80 (0.0l) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 595 X87 :FSQRT80 (1.0l) L: 39.93ns= 73.0c T: 39.93ns= 73.00c 596 X87 :FDECSTP L: [no true dep.] T: 0.55ns= 1.00c 597 X87 :FINCSTP L: [no true dep.] T: 0.55ns= 1.00c 598 X87 :FCOM st(i) L: [no true dep.] T: 0.55ns= 1.00c 599 CMOV :FCOMI st, st(i) L: [no true dep.] T: 0.55ns= 1.00c 600 X87 :FSIN80 (0.0) L: 41.02ns= 75.0c T: 41.57ns= 76.00c 601 X87 :FSIN80 (0.0) + FADD L: 41.57ns= 76.0c T: 42.12ns= 77.00c 602 X87 :FSIN80 (1.0) + FADD L: 138.93ns=254.0c T: 139.61ns=255.25c 603 X87 :FSIN80 (4Pi) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 604 X87 :FSIN80 (2Pi) + FADD L: 91.89ns=168.0c T: 92.43ns=169.00c 605 X87 :FSIN80 (Pi) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 606 X87 :FSIN80 (Pi/2) + FADD L: 91.89ns=168.0c T: 92.43ns=169.00c 607 X87 :FSIN80 (Pi/4) + FADD L: 99.55ns=182.0c T: 100.09ns=183.00c 608 X87 :FSIN80 (Pi/8) + FADD L: 99.55ns=182.0c T: 100.14ns=183.08c 609 X87 :FSIN80 (Pi/16) + FADD L: 99.55ns=182.0c T: 100.14ns=183.08c 610 X87 :FSIN80 (Pi/32) + FADD L: 90.25ns=165.0c T: 90.79ns=166.00c 611 X87 :FCOS80 (0.73908513...) L: 91.34ns=167.0c T: 91.93ns=168.08c 612 X87 :FCOS80 (0.73908513...)+FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 613 X87 :FCOS80 (0.0) + FADD L: 42.66ns= 78.0c T: 43.21ns= 79.00c 614 X87 :FCOS80 (1.0) + FADD L: 147.13ns=269.0c T: 147.81ns=270.25c 615 X87 :FCOS80 (4Pi) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 616 X87 :FCOS80 (2Pi) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 617 X87 :FCOS80 (Pi) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 618 X87 :FCOS80 (Pi/2) + FADD L: 91.89ns=168.0c T: 92.43ns=169.00c 619 X87 :FCOS80 (Pi/4) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 620 X87 :FCOS80 (Pi/8) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 621 X87 :FCOS80 (Pi/16) + FADD L: 91.89ns=168.0c T: 92.48ns=169.08c 622 X87 :FCOS80 (Pi/32) + FADD L: 89.15ns=163.0c T: 89.70ns=164.00c 623 MMX :EMMS L: 0.55ns= 1.0c T: 0.55ns= 1.00c 624 MMX :MOVD r32, mm L: [diff. reg. set] T: 0.55ns= 1.00c 625 MMX :MOVD mm, r32 L: [diff. reg. set] T: 0.55ns= 1.00c 626 MMX :MOVD r32, mm+MOVD mm, r32 L: 4.38ns= 8.0c T: 0.55ns= 1.00c 627 AMD64 :MOVD r64, mm L: [diff. reg. set] T: 0.55ns= 1.00c 628 AMD64 :MOVD mm, r64 L: [diff. reg. set] T: 0.55ns= 1.00c 629 AMD64 :MOVD r64, mm+MOVD mm, r64 L: 4.38ns= 8.0c T: 0.55ns= 1.00c 630 MMX :MOVD mm, [m32] L: [memory dep.] T: 0.73ns= 1.33c 631 MMX :MOVD [m32], mm L: [memory dep.] T: 0.87ns= 1.58c 632 MMX :MOVD mm,[m32]+MOVD [m32],mm L: 2.73ns= 5.0c T: 0.87ns= 1.58c 633 MMX :MOVQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 634 MMX :MOVQ mm, [m64] L: [memory dep.] T: 0.73ns= 1.33c 635 MMX :MOVQ [m64], mm L: [memory dep.] T: 0.91ns= 1.67c 636 MMX :MOVQ mm,[m64]+MOVQ [m64],mm L: 2.73ns= 5.0c T: 0.87ns= 1.58c 637 SSE :MOVNTQ [m64], mm L: [memory dep.] T: 1.50ns= 1.50c 638 SSE :PMOVMSKB r32, mm L: [diff. reg. set] T: 0.55ns= 1.00c 639 AMD64 :PMOVMSKB r64, mm L: [diff. reg. set] T: 0.55ns= 1.00c 640 SSE :MASKMOVQ mm, mm L: [memory dep.] T: 1.75ns= 1.75c 641 MMX :PADDB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 642 MMX :PADDW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 643 MMX :PADDD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 644 SSE2 :PADDQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 645 MMX :PADDSB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 646 MMX :PADDSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 647 MMX :PADDUSB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 648 MMX :PADDUSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 649 MMX :PSUBB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 650 MMX :PSUBB mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 651 MMX :PSUBW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 652 MMX :PSUBW mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 653 MMX :PSUBD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 654 MMX :PSUBD mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 655 SSE2 :PSUBQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 656 SSE2 :PSUBQ mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 657 MMX :PSUBSB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 658 MMX :PSUBSB mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 659 MMX :PSUBSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 660 MMX :PSUBSW mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 661 MMX :PSUBUSB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 662 MMX :PSUBUSB mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 663 MMX :PSUBUSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 664 MMX :PSUBUSW mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 665 MMX :PCMPEQB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 666 MMX :PCMPEQB mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 667 MMX :PCMPEQW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 668 MMX :PCMPEQW mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 669 MMX :PCMPEQD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 670 MMX :PCMPEQD mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 671 MMX :PCMPGTB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 672 MMX :PCMPGTB mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 673 MMX :PCMPGTW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 674 MMX :PCMPGTW mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 675 MMX :PCMPGTD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 676 MMX :PCMPGTD mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 677 MMX :PAND mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 678 MMX :PAND mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 679 MMX :PANDN mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 680 MMX :PANDN mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 681 MMX :POR mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 682 MMX :POR mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 683 MMX :PXOR mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 684 MMX :PXOR mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 685 MMX :PMULHW mm, mm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 686 SSE :PMULHUW mm, mm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 688 SSSE3 :PMULHRSW mm, mm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 689 MMX :PMULLW mm, mm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 690 SSE2 :PMULUDQ mm, mm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 691 SSSE3 :PMADDUBSW mm, mm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 692 MMX :PMADDWD mm, mm L: 2.19ns= 4.0c T: 0.55ns= 1.00c 693 MMX :PSLLW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 694 MMX :PSLLW mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 695 MMX :PSLLD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 696 MMX :PSLLD mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 697 MMX :PSLLQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 698 MMX :PSLLQ mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 699 MMX :PSRAW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 700 MMX :PSRAW mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 701 MMX :PSRAD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 702 MMX :PSRAD mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 703 MMX :PSRLW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 704 MMX :PSRLW mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 705 MMX :PSRLD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 706 MMX :PSRLD mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 707 MMX :PSRLQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 708 MMX :PSRLQ mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 709 MMX :PUNPCKHBW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 710 MMX :PUNPCKHWD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 711 MMX :PUNPCKHDQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 712 MMX :PUNPCKLBW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 713 MMX :PUNPCKLWD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 714 MMX :PUNPCKLDQ mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 715 MMX :PACKSSWB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 716 MMX :PACKUSWB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 717 MMX :PACKSSDW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 746 3DNOWPREF :PREFETCHW [mem] L: [memory dep.] T: 0.73ns= 1.33c 753 SSE :PAVGB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 754 SSE :PAVGW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 755 SSE :PEXTRW r32, mm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 756 SSE :PINSRW mm, r32, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 757 SSE :PEXTRW + PINSRW r32 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 758 AMD64 :PEXTRW r64, mm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 759 AMD64 :PINSRW mm, r64, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 760 AMD64 :PEXTRW + PINSRW r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 761 SSE :PMAXSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 762 SSE :PMAXUB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 763 SSE :PMINSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 764 SSE :PMINUB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 765 SSE :PSADBW mm, mm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 766 SSE :PSHUFW mm, mm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 767 SSE :PREFETCHNTA [mem] L: [memory dep.] T: 0.73ns= 1.33c 768 SSE :PREFETCHT0 [mem] L: [memory dep.] T: 0.73ns= 1.33c 769 SSE :PREFETCHT1 [mem] L: [memory dep.] T: 0.73ns= 1.33c 770 SSE :PREFETCHT2 [mem] L: [memory dep.] T: 0.73ns= 1.33c 771 SSE :SFENCE L: 6.75ns= 12.3c T: 6.75ns= 12.33c 772 SSE2 :LFENCE L: 6.75ns= 12.3c T: 6.75ns= 12.33c 773 SSE2 :MFENCE L: 6.75ns= 12.3c T: 6.75ns= 12.33c 774 SSSE3 :PABSB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 775 SSSE3 :PABSW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 776 SSSE3 :PABSD mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 777 SSSE3 :PALIGNR mm, mm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 778 SSSE3 :PHADDW mm, mm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 779 SSSE3 :PHADDD mm, mm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 780 SSSE3 :PHADDSW mm, mm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 781 SSSE3 :PHSUBW mm, mm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 782 SSSE3 :PHSUBD mm, mm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 783 SSSE3 :PHSUBSW mm, mm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 784 SSSE3 :PSHUFB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 785 SSSE3 :PSIGNB mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 786 SSSE3 :PSIGNW mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 787 SSSE3 :PSIGND mm, mm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 788 SSE :MOVHLPS xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 789 SSE :MOVHLPS xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 790 AVX :VMOVHLPS xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 791 AVX :VMOVHLPS xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 792 SSE :MOVSS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 793 AVX :VMOVSS xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 794 SSE :MOVSS xmm, [m32] L: [memory dep.] T: 0.73ns= 1.33c 795 SSE :MOVSS [m32], xmm L: [memory dep.] T: 0.87ns= 1.58c 796 SSE :MOVSS LS pair L: 2.73ns= 5.0c T: 0.77ns= 1.42c 797 AVX :VMOVSS xmm, [m32] L: [memory dep.] T: 0.68ns= 1.25c 798 AVX :VMOVSS [m32], xmm L: [memory dep.] T: 0.87ns= 1.58c 799 AVX :VMOVSS LS pair L: 2.73ns= 5.0c T: 0.64ns= 1.17c 800 SSE :MOVLPS xmm, [m32] L: [memory dep.] T: 0.68ns= 1.25c 801 SSE :MOVLPS [m32], xmm L: [memory dep.] T: 0.91ns= 1.67c 802 SSE :MOVLPS LS pair L: 4.38ns= 8.0c T: 2.46ns= 4.50c 803 AVX :VMOVLPS xmm, xmm, [m32] L: [memory dep.] T: 0.59ns= 1.08c 804 AVX :VMOVLPS [m32], xmm L: [memory dep.] T: 0.87ns= 1.58c 805 AVX :VMOVLPS LS pair L: 4.38ns= 8.0c T: 0.77ns= 1.42c 806 SSE :MOVHPS xmm, [m32] L: [memory dep.] T: 0.68ns= 1.25c 807 SSE :MOVHPS [m32], xmm L: [memory dep.] T: 0.91ns= 1.67c 808 SSE :MOVHPS LS pair L: 5.06ns= 9.3c T: 1.78ns= 3.25c 809 AVX :VMOVHPS xmm, xmm, [m32] L: [memory dep.] T: 0.59ns= 1.08c 810 AVX :VMOVHPS [m32], xmm L: [memory dep.] T: 0.91ns= 1.67c 811 AVX :VMOVHPS LS pair L: 5.10ns= 9.3c T: 1.09ns= 2.00c 812 SSE :MOVAPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 813 SSE :MOVAPS xmm, [m128] L: [memory dep.] T: 0.73ns= 1.33c 814 SSE :MOVAPS [m128], xmm L: [memory dep.] T: 0.91ns= 1.67c 815 SSE :MOVAPS LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 816 AVX :VMOVAPS xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 817 AVX :VMOVAPS xmm, [m128] L: [memory dep.] T: 0.68ns= 1.25c 818 AVX :VMOVAPS [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 819 AVX :VMOVAPS LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 820 SSE :MOVUPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.62c 821 SSE :MOVUPS xmm, [m128] L: [memory dep.] T: 0.73ns= 1.33c 822 SSE :MOVUPS [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 823 SSE :MOVUPS aligned LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 824 SSE :MOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.73ns= 1.33c 825 SSE :MOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.73ns= 1.33c 826 SSE :MOVUPS unaligned LS pair L: 2.73ns= 5.0c T: 0.77ns= 1.42c 827 AVX :VMOVUPS xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 828 AVX :VMOVUPS xmm, [m128] L: [memory dep.] T: 0.68ns= 1.25c 829 AVX :VMOVUPS [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 830 AVX :VMOVUPS aligned LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 831 AVX :VMOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.68ns= 1.25c 832 AVX :VMOVUPS [m128 + 4], xmm L: [memory dep.] T: 0.73ns= 1.33c 833 AVX :VMOVUPS unaligned LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 835 SSE :MOVNTPS [m128], xmm L: [memory dep.] T: 1.50ns= 1.50c 836 AVX :VMOVNTPS [m128], xmm L: [memory dep.] T: 1.50ns= 1.50c 837 SSE :MOVMSKPS r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 838 AVX :VMOVMSKPS r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 839 AVX :VMASKMOVPS xmm,xmm,[m128+4] L: [memory dep.] T: 54.70ns=100.00c 840 AVX :VMASKMOVPS [m128+4],xmm,xmm L: [memory dep.] T: 14.77ns= 27.00c 841 AVX :VMASKMOVPS unaligned LSpair L: 70.01ns=128.0c T: 70.01ns=128.00c 842 SSE :UNPCKLPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 843 AVX :VUNPCKLPS xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 844 SSE :UNPCKHPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 845 AVX :VUNPCKHPS xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 846 SSE :SHUFPS xmm, xmm, imm8 L: 0.64ns= 1.2c T: 0.33ns= 0.61c 847 AVX :VSHUFPS xmm, xmm, xmm, imm8 L: 1.00ns= 1.8c T: 0.50ns= 0.92c 848 AVX :VPERMILPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 849 AVX :VPERMILPS xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 850 SSE :COMISS xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 851 AVX :VCOMISS xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 852 SSE :UCOMISS xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 853 AVX :VUCOMISS xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 854 SSE :CMPSS xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 855 SSE :CMPPS xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 856 AVX :VCMPSS xmm, xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 857 AVX :VCMPPS xmm, xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 858 SSE :SUBSS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 859 AVX :VSUBSS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 860 SSE :SUBPS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 861 AVX :VSUBPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 862 SSE :ADDSS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 863 AVX :VADDSS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 864 SSE :ADDPS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 865 AVX :VADDPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 866 SSE :MULSS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 867 AVX :VMULSS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 868 SSE :MULPS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 869 AVX :VMULPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 870 SSE :MULSS+ADDSS xmm, xmm L: 3.28ns= 6.0c T: 0.55ns= 1.00c 871 AVX :VMULSS+VADDSS xmm, xmm, xmm L: 3.28ns= 6.0c T: 1.09ns= 2.00c 872 SSE :MULPS+ADDPS xmm, xmm L: 3.28ns= 6.0c T: 0.55ns= 1.00c 873 AVX :VMULPS+VADDPS xmm, xmm, xmm L: 3.28ns= 6.0c T: 1.09ns= 2.00c 874 SSE :MULSS xm1,xm1 ADDSS xm2,xm2 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 875 AVX :VMULSS xmm1.. VADDSS xmm2.. L: 1.64ns= 3.0c T: 1.09ns= 2.00c 876 SSE :MULPS xm1,xm1 ADDPS xm2,xm2 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 877 AVX :VMULPS xmm1.. VADDPS xmm2.. L: 1.64ns= 3.0c T: 1.09ns= 2.00c 878 SSE :MAXSS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 879 AVX :VMAXSS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 880 SSE :MAXPS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 881 AVX :VMAXPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 882 SSE :MINSS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 883 AVX :VMINSS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 884 SSE :MINPS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 885 AVX :VMINPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 886 SSE :ANDNPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 887 SSE :ANDNPS xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 888 AVX :VANDNPS xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 889 AVX :VANDNPS xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 890 SSE :ANDPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 891 SSE :ANDPS xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 892 AVX :VANDPS xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 893 AVX :VANDPS xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 894 SSE :ORPS xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.62c 895 SSE :ORPS xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 896 AVX :VORPS xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.55ns= 1.00c 897 AVX :VORPS xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 898 SSE :XORPS xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 899 SSE :XORPS xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 900 AVX :VXORPS xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 901 AVX :VXORPS xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 902 SSE :DIVSS xmm, xmm L: 7.11ns= 13.0c T: 7.11ns= 13.00c 903 SSE :DIVSS (0.0f/x) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 904 SSE :DIVSS (x/1.0f) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 905 SSE :DIVSS (x/2.0f) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 906 SSE :DIVSS (x/0.5f) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 907 AVX :VDIVSS xmm, xmm, xmm L: 7.11ns= 13.0c T: 7.11ns= 13.00c 908 AVX :VDIVSS (0.0f/x) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 909 AVX :VDIVSS (x/1.0f) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 910 AVX :VDIVSS (x/2.0f) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 911 AVX :VDIVSS (x/0.5f) L: 7.11ns= 13.0c T: 7.11ns= 13.00c 912 SSE :DIVPS xmm, xmm L: 13.13ns= 24.0c T: 13.13ns= 24.00c 913 SSE :DIVPS (0.0f/x) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 914 SSE :DIVPS (x/1.0f) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 915 SSE :DIVPS (x/2.0f) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 916 SSE :DIVPS (x/0.5f) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 917 AVX :VDIVPS xmm, xmm, xmm L: 13.13ns= 24.0c T: 13.13ns= 24.00c 918 AVX :VDIVPS (0.0f/x) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 919 AVX :VDIVPS (x/1.0f) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 920 AVX :VDIVPS (x/2.0f) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 921 AVX :VDIVPS (x/0.5f) L: 13.13ns= 24.0c T: 13.13ns= 24.00c 922 SSE :SQRTSS xmm, xmm L: 18.05ns= 33.0c T: 18.05ns= 33.00c 923 SSE :SQRTSS (0.0f) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 924 SSE :SQRTSS (1.0f) L: 18.05ns= 33.0c T: 18.05ns= 33.00c 925 AVX :VSQRTSS xmm, xmm, xmm L: 18.05ns= 33.0c T: 18.05ns= 33.00c 926 AVX :VSQRTSS (0.0f) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 927 AVX :VSQRTSS (1.0f) L: 18.05ns= 33.0c T: 18.05ns= 33.00c 928 SSE :SQRTPS xmm, xmm L: 35.00ns= 64.0c T: 35.00ns= 64.00c 929 SSE :SQRTPS (0.0f) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 930 SSE :SQRTPS (1.0f) L: 35.00ns= 64.0c T: 35.00ns= 64.00c 931 AVX :VSQRTPS xmm, xmm L: 35.00ns= 64.0c T: 35.00ns= 64.00c 932 AVX :VSQRTPS (0.0f) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 933 AVX :VSQRTPS (1.0f) L: 35.00ns= 64.0c T: 35.00ns= 64.00c 934 SSE :RCPSS xmm, xmm L: 2.73ns= 5.0c T: 2.73ns= 5.00c 935 AVX :VRCPSS xmm, xmm, xmm L: 2.73ns= 5.0c T: 2.73ns= 5.00c 936 SSE :RCPPS xmm, xmm L: 7.11ns= 13.0c T: 5.47ns= 10.00c 937 AVX :VRCPPS xmm, xmm, xmm L: 7.11ns= 13.0c T: 5.47ns= 10.00c 938 SSE :RSQRTSS xmm, xmm L: 2.73ns= 5.0c T: 2.73ns= 5.00c 939 AVX :VRSQRTSS xmm, xmm, xmm L: 2.73ns= 5.0c T: 2.73ns= 5.00c 940 SSE :RSQRTPS xmm, xmm L: 7.11ns= 13.0c T: 5.47ns= 10.00c 941 AVX :VRSQRTPS xmm, xmm, xmm L: 7.11ns= 13.0c T: 5.47ns= 10.00c 942 SSE :CVTPI2PS xmm, mm L: [diff. reg. set] T: 0.82ns= 1.50c 943 SSE :CVTPS2PI mm, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 944 SSE :CVTPS2PI + CVTPI2PS L: 4.92ns= 9.0c T: 1.23ns= 2.25c 945 SSE :CVTTPS2PI mm, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 946 SSE :CVTTPS2PI + CVTPI2PS L: 4.92ns= 9.0c T: 1.23ns= 2.25c 947 SSE :CVTSI2SS xmm, r32 L: [diff. reg. set] T: 0.55ns= 1.00c 948 SSE :CVTSS2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 949 SSE :CVTSS2SI + CVTSI2SS r32 L: 6.02ns= 11.0c T: 0.55ns= 1.00c 950 SSE :CVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 951 SSE :CVTTSS2SI + CVTSI2SS r32 L: 6.02ns= 11.0c T: 0.55ns= 1.00c 952 AVX :VCVTSI2SS xmm, xmm, r32 L: [diff. reg. set] T: 0.68ns= 1.25c 953 AVX :VCVTSS2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 954 AVX :VCVTSS2SI + VCVTSI2SS r32 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 955 AVX :VCVTTSS2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 956 AVX :VCVTTSS2SI + VCVTSI2SS r32 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 957 AMD64 :CVTSI2SS xmm, r64 L: [diff. reg. set] T: 1.09ns= 2.00c 958 AMD64 :CVTSS2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 959 AMD64 :CVTSS2SI + CVTSI2SS r64 L: 7.66ns= 14.0c T: 1.82ns= 3.33c 960 AMD64 :CVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 961 AMD64 :CVTTSS2SI + CVTSI2SS r64 L: 7.66ns= 14.0c T: 1.82ns= 3.33c 962 AVX :VCVTSI2SS xmm, xmm, r64 L: [diff. reg. set] T: 0.68ns= 1.25c 963 AVX :VCVTSS2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 964 AVX :VCVTSS2SI + VCVTSI2SS r64 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 965 AVX :VCVTTSS2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 966 AVX :VCVTTSS2SI + VCVTSI2SS r64 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 967 SSE :STMXCSR [mem] L: [memory dep.] T: 6.56ns= 12.00c 968 SSE :LDMXCSR [mem] L: [memory dep.] T: 15.31ns= 28.00c 969 SSE :STMXCSR + LDMXCSR L: 32.82ns= 60.0c T: 32.82ns= 60.00c 970 SSE2 :MOVSD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 971 SSE2 :MOVSD xmm, [m64] L: [memory dep.] T: 0.73ns= 1.33c 972 SSE2 :MOVSD [m64], xmm L: [memory dep.] T: 0.87ns= 1.58c 973 SSE2 :MOVSD LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 974 AVX :VMOVSD xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 975 AVX :VMOVSD xmm, [m64] L: [memory dep.] T: 0.68ns= 1.25c 976 AVX :VMOVSD [m64], xmm L: [memory dep.] T: 0.87ns= 1.58c 977 AVX :VMOVSD LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 978 SSE2 :MOVLPD xmm, [m64] L: [memory dep.] T: 0.68ns= 1.25c 979 SSE2 :MOVLPD [m64], xmm L: [memory dep.] T: 0.91ns= 1.67c 980 SSE2 :MOVLPD LS pair L: 4.38ns= 8.0c T: 2.83ns= 5.17c 981 AVX :VMOVLPD xmm, [m64] L: [memory dep.] T: 0.59ns= 1.08c 982 AVX :VMOVLPD [m64], xmm L: [memory dep.] T: 0.87ns= 1.58c 983 AVX :VMOVLPD LS pair L: 4.38ns= 8.0c T: 0.77ns= 1.42c 984 SSE2 :MOVHPD xmm, [m64] L: [memory dep.] T: 0.68ns= 1.25c 985 SSE2 :MOVHPD [m64], xmm L: [memory dep.] T: 0.91ns= 1.67c 986 SSE2 :MOVHPD LS pair L: 5.06ns= 9.3c T: 1.82ns= 3.33c 987 AVX :VMOVHPD xmm, [m64] L: [memory dep.] T: 0.59ns= 1.08c 988 AVX :VMOVHPD [m64], xmm L: [memory dep.] T: 0.91ns= 1.67c 989 AVX :VMOVHPD LS pair L: 5.10ns= 9.3c T: 1.09ns= 2.00c 990 SSE2 :MOVAPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 991 SSE2 :MOVAPD xmm, [m128] L: [memory dep.] T: 0.73ns= 1.33c 992 SSE2 :MOVAPD [m128], xmm L: [memory dep.] T: 0.91ns= 1.67c 993 SSE2 :MOVAPD LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 994 AVX :VMOVAPD xmm, xmm L: 1.00ns= 1.8c T: 0.55ns= 1.00c 995 AVX :VMOVAPD xmm, [m128] L: [memory dep.] T: 0.68ns= 1.25c 996 AVX :VMOVAPD [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 997 AVX :VMOVAPD LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 998 SSE2 :MOVUPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 999 SSE2 :MOVUPD xmm, [m128] L: [memory dep.] T: 0.73ns= 1.33c 1000 SSE2 :MOVUPD [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 1001 SSE2 :MOVUPD aligned LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 1002 SSE2 :MOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.73ns= 1.33c 1003 SSE2 :MOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.73ns= 1.33c 1004 SSE2 :MOVUPD unaligned LS pair L: 2.73ns= 5.0c T: 0.68ns= 1.25c 1005 AVX :VMOVUPD xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1006 AVX :VMOVUPD xmm, [m128] L: [memory dep.] T: 0.68ns= 1.25c 1007 AVX :VMOVUPD [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 1008 AVX :VMOVUPD aligned LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 1009 AVX :VMOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.68ns= 1.25c 1010 AVX :VMOVUPD [m128 + 4], xmm L: [memory dep.] T: 0.73ns= 1.33c 1011 AVX :VMOVUPD unaligned LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 1013 SSE2 :MOVNTPD [m128], xmm L: [memory dep.] T: 1.50ns= 1.50c 1014 AVX :VMOVNTPD [m128], xmm L: [memory dep.] T: 1.50ns= 1.50c 1015 SSE2 :MOVMSKPD r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1016 AVX :VMOVMSKPD r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1017 AVX :VMASKMOVPD xmm,xmm,[m128+4] L: [memory dep.] T: 26.80ns= 49.00c 1018 AVX :VMASKMOVPD [m128+4],xmm,xmm L: [memory dep.] T: 14.22ns= 26.00c 1019 AVX :VMASKMOVPD unaligned LSpair L: 41.57ns= 76.0c T: 41.57ns= 76.00c 1020 SSE2 :UNPCKLPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.62c 1021 AVX :VUNPCKLPD xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1022 SSE2 :UNPCKHPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 1023 AVX :VUNPCKHPD xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1024 SSE2 :SHUFPD xmm, xmm, imm8 L: 0.64ns= 1.2c T: 0.34ns= 0.63c 1025 AVX :VSHUFPD xmm, xmm, xmm, imm8 L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1026 AVX :VPERMILPD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1027 AVX :VPERMILPD xmm, xmm, imm8 L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1028 SSE2 :COMISD xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1029 AVX :VCOMISD xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1030 SSE2 :UCOMISD xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1031 AVX :VUCOMISD xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1032 SSE2 :CMPSD xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1033 SSE2 :CMPPD xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1034 AVX :VCMPSD xmm, xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1035 AVX :VCMPPD xmm, xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1036 SSE2 :SUBSD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1037 AVX :VSUBSD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1038 SSE2 :SUBPD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1039 AVX :VSUBPD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1040 SSE2 :ADDSD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1041 AVX :VADDSD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1042 SSE2 :ADDPD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1043 AVX :VADDPD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1044 SSE2 :MULSD xmm, xmm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1045 AVX :VMULSD xmm, xmm, xmm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1046 SSE2 :MULPD xmm, xmm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1047 AVX :VMULPD xmm, xmm, xmm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1048 SSE2 :MULSD+ADDSD xmm, xmm L: 3.83ns= 7.0c T: 1.09ns= 2.00c 1049 AVX :VMULSD+VADDSD xmm, xmm, xmm L: 3.83ns= 7.0c T: 1.37ns= 2.50c 1050 SSE2 :MULPD+ADDPD xmm, xmm L: 3.83ns= 7.0c T: 1.09ns= 2.00c 1051 AVX :VMULPD+VADDPD xmm, xmm, xmm L: 3.83ns= 7.0c T: 1.37ns= 2.50c 1052 SSE2 :MULSD xm1,xm1 ADDSD xm2,xm2 L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1053 AVX :VMULSD xmm1.. VADDSD xmm2.. L: 2.19ns= 4.0c T: 1.37ns= 2.50c 1054 SSE2 :MULPD xm1,xm1 ADDPD xm2,xm2 L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1055 AVX :VMULPD xmm1.. VADDPD xmm2.. L: 2.19ns= 4.0c T: 1.37ns= 2.50c 1056 SSE2 :MAXSD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1057 AVX :VMAXSD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1058 SSE2 :MAXPD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1059 AVX :VMAXPD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1060 SSE2 :MINSD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1061 AVX :VMINSD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1062 SSE2 :MINPD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1063 AVX :VMINPD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1064 SSE2 :ANDNPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.62c 1065 SSE2 :ANDNPD xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 1066 AVX :VANDNPD xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.55ns= 1.00c 1067 AVX :VANDNPD xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 1068 SSE2 :ANDPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.62c 1069 SSE2 :ANDPD xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 1070 AVX :VANDPD xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.55ns= 1.00c 1071 AVX :VANDPD xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 1072 SSE2 :ORPD xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 1073 SSE2 :ORPD xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 1074 AVX :VORPD xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.55ns= 1.00c 1075 AVX :VORPD xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 1076 SSE2 :XORPD xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1077 SSE2 :XORPD xmm1, xmm2 L: 0.64ns= 1.2c T: 0.39ns= 0.71c 1078 AVX :VXORPD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1079 AVX :VXORPD xmm1, xmm1, xmm2 L: 1.00ns= 1.8c T: 0.49ns= 0.90c 1080 SSE2 :DIVSD xmm, xmm L: 10.94ns= 20.0c T: 10.94ns= 20.00c 1081 SSE2 :DIVSD (0.0/x) L: 7.66ns= 14.0c T: 7.66ns= 14.00c 1082 SSE2 :DIVSD (x/1.0) L: 10.94ns= 20.0c T: 10.94ns= 20.00c 1083 SSE2 :DIVSD (x/2.0) L: 10.94ns= 20.0c T: 10.94ns= 20.00c 1084 SSE2 :DIVSD (x/0.5) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1085 AVX :VDIVSD xmm, xmm, xmm L: 10.94ns= 20.0c T: 10.94ns= 20.00c 1086 AVX :VDIVSD (0.0/x) L: 7.66ns= 14.0c T: 7.66ns= 14.00c 1087 AVX :VDIVSD (x/1.0) L: 10.94ns= 20.0c T: 10.94ns= 20.00c 1088 AVX :VDIVSD (x/2.0) L: 10.94ns= 20.0c T: 10.94ns= 20.00c 1089 AVX :VDIVSD (x/0.5) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1090 SSE2 :DIVPD xmm, xmm L: 20.78ns= 38.0c T: 20.78ns= 38.00c 1091 SSE2 :DIVPD (0.0/x) L: 12.03ns= 22.0c T: 12.03ns= 22.00c 1092 SSE2 :DIVPD (x/1.0) L: 20.78ns= 38.0c T: 20.78ns= 38.00c 1093 SSE2 :DIVPD (x/2.0) L: 20.78ns= 38.0c T: 20.78ns= 38.00c 1094 SSE2 :DIVPD (x/0.5) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 1095 AVX :VDIVPD xmm, xmm, xmm L: 20.78ns= 38.0c T: 20.78ns= 38.00c 1096 AVX :VDIVPD (0.0/x) L: 12.03ns= 22.0c T: 12.03ns= 22.00c 1097 AVX :VDIVPD (x/1.0) L: 20.78ns= 38.0c T: 20.78ns= 38.00c 1098 AVX :VDIVPD (x/2.0) L: 20.78ns= 38.0c T: 20.78ns= 38.00c 1099 AVX :VDIVPD (x/0.5) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 1100 SSE2 :SQRTSD xmm, xmm L: 33.91ns= 62.0c T: 33.91ns= 62.00c 1101 SSE2 :SQRTSD (0.0) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1102 SSE2 :SQRTSD (1.0) L: 33.91ns= 62.0c T: 33.91ns= 62.00c 1103 AVX :VSQRTSD xmm, xmm, xmm L: 33.91ns= 62.0c T: 33.91ns= 62.00c 1104 AVX :VSQRTSD (0.0) L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1105 AVX :VSQRTSD (1.0) L: 33.91ns= 62.0c T: 33.91ns= 62.00c 1106 SSE2 :SQRTPD xmm, xmm L: 66.73ns=122.0c T: 66.73ns=122.00c 1107 SSE2 :SQRTPD (0.0) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 1108 SSE2 :SQRTPD (1.0) L: 66.73ns=122.0c T: 66.73ns=122.00c 1109 AVX :VSQRTPD xmm, xmm L: 66.73ns=122.0c T: 66.73ns=122.00c 1110 AVX :VSQRTPD (0.0) L: 12.58ns= 23.0c T: 12.58ns= 23.00c 1111 AVX :VSQRTPD (1.0) L: 66.73ns=122.0c T: 66.73ns=122.00c 1112 SSE2 :CVTPI2PD xmm, mm L: [diff. reg. set] T: 0.55ns= 1.00c 1113 SSE2 :CVTPD2PI mm, xmm L: [diff. reg. set] T: 0.82ns= 1.50c 1114 SSE2 :CVTPD2PI + CVTPI2PD L: 5.29ns= 9.7c T: 1.73ns= 3.17c 1115 SSE2 :CVTTPD2PI mm, xmm L: [diff. reg. set] T: 0.82ns= 1.50c 1116 SSE2 :CVTTPD2PI + CVTPI2PD L: 5.29ns= 9.7c T: 1.73ns= 3.17c 1117 SSE2 :CVTSI2SD xmm, r32 L: [diff. reg. set] T: 0.55ns= 1.00c 1118 SSE2 :CVTSD2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1119 SSE2 :CVTSD2SI + CVTSI2SD r32 L: 6.02ns= 11.0c T: 0.55ns= 1.00c 1120 SSE2 :CVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1121 SSE2 :CVTTSD2SI + CVTSI2SD r32 L: 6.02ns= 11.0c T: 0.55ns= 1.00c 1122 AVX :VCVTSI2SD xmm, xmm, r32 L: [diff. reg. set] T: 0.68ns= 1.25c 1123 AVX :VCVTSD2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1124 AVX :VCVTSD2SI + VCVTSI2SD r32 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 1125 AVX :VCVTTSD2SI r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1126 AVX :VCVTTSD2SI + VCVTSI2SD r32 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 1127 AMD64 :CVTSI2SD xmm, r64 L: [diff. reg. set] T: 1.09ns= 2.00c 1128 AMD64 :CVTSD2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1129 AMD64 :CVTSD2SI + CVTSI2SD r64 L: 7.66ns= 14.0c T: 1.82ns= 3.33c 1130 AMD64 :CVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1131 AMD64 :CVTTSD2SI + CVTSI2SD r64 L: 7.66ns= 14.0c T: 1.82ns= 3.33c 1132 AVX :VCVTSI2SD xmm, xmm, r64 L: [diff. reg. set] T: 0.68ns= 1.25c 1133 AVX :VCVTSD2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1134 AVX :VCVTSD2SI + VCVTSI2SD r64 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 1135 AVX :VCVTTSD2SI r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1136 AVX :VCVTTSD2SI + VCVTSI2SD r64 L: 6.02ns= 11.0c T: 0.59ns= 1.08c 1137 SSE2 :CVTDQ2PD xmm, xmm L: 3.19ns= 5.8c T: 0.59ns= 1.08c 1138 SSE2 :CVTPD2DQ xmm, xmm L: 3.19ns= 5.8c T: 0.73ns= 1.33c 1139 SSE2 :CVTPD2DQ + CVTDQ2PD L: 5.29ns= 9.7c T: 1.73ns= 3.17c 1140 SSE2 :CVTTPD2DQ xmm, xmm L: 3.19ns= 5.8c T: 0.73ns= 1.33c 1141 SSE2 :CVTTPD2DQ + CVTDQ2PD L: 5.29ns= 9.7c T: 1.73ns= 3.17c 1142 AVX :VCVTDQ2PD xmm, xmm L: 3.24ns= 5.9c T: 0.82ns= 1.50c 1143 AVX :VCVTPD2DQ xmm, xmm L: 3.24ns= 5.9c T: 0.96ns= 1.75c 1144 AVX :VCVTPD2DQ + VCVTDQ2PD L: 5.52ns= 10.1c T: 3.78ns= 6.92c 1145 AVX :VCVTTPD2DQ xmm, xmm L: 3.24ns= 5.9c T: 0.96ns= 1.75c 1146 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 5.52ns= 10.1c T: 3.78ns= 6.92c 1147 SSE2 :CVTDQ2PS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1148 SSE2 :CVTPS2DQ xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1149 SSE2 :CVTPS2DQ + CVTDQ2PS L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1150 SSE2 :CVTTPS2DQ xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1151 SSE2 :CVTTPS2DQ + CVTDQ2PS L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1152 AVX :VCVTDQ2PS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1153 AVX :VCVTPS2DQ xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1154 AVX :VCVTPS2DQ + VCVTDQ2PS L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1155 AVX :VCVTTPS2DQ xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1156 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1157 SSE2 :CVTPS2PD xmm, xmm L: 3.19ns= 5.8c T: 0.41ns= 0.75c 1158 SSE2 :CVTPD2PS xmm, xmm L: 3.19ns= 5.8c T: 0.73ns= 1.33c 1159 SSE2 :CVTPD2PS + CVTPS2PD L: 5.29ns= 9.7c T: 1.14ns= 2.08c 1160 SSE2 :CVTSS2SD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1161 SSE2 :CVTSD2SS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1162 SSE2 :CVTSD2SS + CVTSS2SD L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1163 AVX :VCVTPS2PD xmm, xmm L: 3.24ns= 5.9c T: 0.73ns= 1.33c 1164 AVX :VCVTPD2PS xmm, xmm L: 3.24ns= 5.9c T: 0.96ns= 1.75c 1165 AVX :VCVTPD2PS + VCVTPS2PD L: 5.52ns= 10.1c T: 1.87ns= 3.42c 1166 AVX :VCVTSS2SD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1167 AVX :VCVTSD2SS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1168 AVX :VCVTSD2SS + VCVTSS2SD L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1169 SSE2 :MOVD r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1170 SSE2 :MOVD xmm, r32 L: [diff. reg. set] T: 0.55ns= 1.00c 1171 SSE2 :MOVD r32, xmm+MOVD xmm, r32 L: 4.38ns= 8.0c T: 0.55ns= 1.00c 1172 AVX :VMOVD r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1173 AVX :VMOVD xmm, r32 L: [diff. reg. set] T: 0.55ns= 1.00c 1174 AVX :VMOVD r32,xmm+VMOVD xmm,r32 L: 4.38ns= 8.0c T: 0.35ns= 0.65c 1175 AMD64 :MOVD r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1176 AMD64 :MOVD xmm, r64 L: [diff. reg. set] T: 0.55ns= 1.00c 1177 AMD64 :MOVD r64, xmm+MOVD xmm, r64 L: 4.38ns= 8.0c T: 0.55ns= 1.00c 1178 AVX :VMOVD r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1179 AVX :VMOVD xmm, r64 L: [diff. reg. set] T: 0.55ns= 1.00c 1180 AVX :VMOVD r64,xmm+VMOVD xmm,r64 L: 4.38ns= 8.0c T: 0.59ns= 1.08c 1181 SSE2 :MOVD xmm, [m32] L: [memory dep.] T: 0.73ns= 1.33c 1182 SSE2 :MOVD [m32], xmm L: [memory dep.] T: 0.87ns= 1.58c 1183 SSE2 :MOVD LS pair L: 2.73ns= 5.0c T: 0.77ns= 1.42c 1184 AVX :VMOVD xmm, [m32] L: [memory dep.] T: 0.68ns= 1.25c 1185 AVX :VMOVD [m32], xmm L: [memory dep.] T: 0.87ns= 1.58c 1186 AVX :VMOVD LS pair L: 2.73ns= 5.0c T: 0.68ns= 1.25c 1187 SSE2 :MOVQ xmm, [m64] L: [memory dep.] T: 0.73ns= 1.33c 1188 SSE2 :MOVQ [m64], xmm L: [memory dep.] T: 0.87ns= 1.58c 1189 SSE2 :MOVQ LS pair L: 2.73ns= 5.0c T: 0.77ns= 1.42c 1190 AVX :VMOVQ xmm, [m64] L: [memory dep.] T: 0.68ns= 1.25c 1191 AVX :VMOVQ [m64], xmm L: [memory dep.] T: 0.87ns= 1.58c 1192 AVX :VMOVQ LS pair L: 2.73ns= 5.0c T: 0.77ns= 1.42c 1193 SSE2 :MOVDQ2Q mm, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1194 SSE2 :MOVQ2DQ xmm, mm L: [diff. reg. set] T: 0.55ns= 1.00c 1195 SSE2 :MOVDQ2Q + MOVQ2DQ xmm, mm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1196 SSE2 :MOVDQA xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1197 SSE2 :MOVDQA xmm, [m128] L: [memory dep.] T: 0.73ns= 1.33c 1198 SSE2 :MOVDQA [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 1199 SSE2 :MOVDQA LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 1200 AVX :VMOVDQA xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1201 AVX :VMOVDQA xmm, [m128] L: [memory dep.] T: 0.68ns= 1.25c 1202 AVX :VMOVDQA [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 1203 AVX :VMOVDQA LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 1204 SSE2 :MOVDQU xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1205 SSE2 :MOVDQU xmm, [m128] L: [memory dep.] T: 0.73ns= 1.33c 1206 SSE2 :MOVDQU [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 1207 SSE2 :MOVDQU aligned LS pair L: 2.73ns= 5.0c T: 0.82ns= 1.50c 1208 SSE2 :MOVDQU xmm, [m128 + 4] L: [memory dep.] T: 3.19ns= 5.83c 1209 SSE2 :MOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.73ns= 1.33c 1210 SSE2 :MOVDQU unaligned LS pair L: 2.73ns= 5.0c T: 0.64ns= 1.17c 1211 AVX :VMOVDQU xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1212 AVX :VMOVDQU xmm, [m128] L: [memory dep.] T: 0.68ns= 1.25c 1213 AVX :VMOVDQU [m128], xmm L: [memory dep.] T: 0.87ns= 1.58c 1214 AVX :VMOVDQU aligned LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 1215 AVX :VMOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.68ns= 1.25c 1216 AVX :VMOVDQU [m128 + 4], xmm L: [memory dep.] T: 0.73ns= 1.33c 1217 AVX :VMOVDQU unaligned LS pair L: 2.73ns= 5.0c T: 0.87ns= 1.58c 1218 SSE4.1 :MOVNTDQA xmm, [m128] L: [memory dep.] T: 1.33ns= 1.33c 1219 SSE2 :MOVNTDQ [m128], xmm L: [memory dep.] T: 1.50ns= 1.50c 1220 SSE4.1 :MOVNTDQA + MOVNTDQ L: 163.22ns=298.4c T: 298.42ns=298.42c 1221 AVX :VMOVNTDQA xmm, [m128] L: [memory dep.] T: 1.25ns= 1.25c 1222 AVX :VMOVNTDQ [m128], xmm L: [memory dep.] T: 1.50ns= 1.50c 1223 AVX :VMOVNTDQA + VMOVNTDQ L: 163.22ns=298.4c T: 298.42ns=298.42c 1224 SSE2 :PMOVMSKB r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1225 AMD64 :PMOVMSKB r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1226 AVX :VPMOVMSKB r32, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1227 AVX :VPMOVMSKB r64, xmm L: [diff. reg. set] T: 0.55ns= 1.00c 1228 SSE2 :MASKMOVDQU xmm, xmm L: [memory dep.] T: 37.00ns= 37.00c 1229 AVX :VMASKMOVDQU xmm, xmm L: [memory dep.] T: 37.00ns= 37.00c 1230 SSE2 :PADDB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1231 AVX :VPADDB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1232 SSE2 :PADDW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1233 AVX :VPADDW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1234 SSE2 :PADDD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1235 AVX :VPADDD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1236 SSE2 :PADDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1237 AVX :VPADDQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1238 SSE2 :PADDSB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1239 AVX :VPADDSB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1240 SSE2 :PADDSW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1241 AVX :VPADDSW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1242 SSE2 :PADDUSB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1243 AVX :VPADDUSB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1244 SSE2 :PADDUSW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1245 AVX :VPADDUSW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1246 SSE2 :PSUBB xmm, xmm L: 0.28ns= 0.5c T: 0.27ns= 0.50c 1247 SSE2 :PSUBB xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1248 AVX :VPSUBB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1249 AVX :VPSUBB xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1250 SSE2 :PSUBW xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1251 SSE2 :PSUBW xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1252 AVX :VPSUBW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1253 AVX :VPSUBW xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1254 SSE2 :PSUBD xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1255 SSE2 :PSUBD xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1256 AVX :VPSUBD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1257 AVX :VPSUBD xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1258 SSE2 :PSUBQ xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1259 SSE2 :PSUBQ xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1260 AVX :VPSUBQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1261 AVX :VPSUBQ xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1262 SSE2 :PSUBSB xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1263 SSE2 :PSUBSB xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1264 AVX :VPSUBSB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1265 AVX :VPSUBSB xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1266 SSE2 :PSUBSW xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1267 SSE2 :PSUBSW xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1268 AVX :VPSUBSW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1269 AVX :VPSUBSW xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1270 SSE2 :PSUBUSB xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1271 SSE2 :PSUBUSB xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1272 AVX :VPSUBUSB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1273 AVX :VPSUBUSB xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1274 SSE2 :PSUBUSW xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1275 SSE2 :PSUBUSW xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1276 AVX :VPSUBUSW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1277 AVX :VPSUBUSW xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1278 SSE2 :PCMPEQB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1279 SSE2 :PCMPEQB xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1280 AVX :VPCMPEQB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1281 AVX :VPCMPEQB xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1282 SSE2 :PCMPEQW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1283 SSE2 :PCMPEQW xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1284 AVX :VPCMPEQW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1285 AVX :VPCMPEQW xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1286 SSE2 :PCMPEQD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1287 SSE2 :PCMPEQD xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1288 AVX :VPCMPEQD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1289 AVX :VPCMPEQD xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1290 SSE4.1 :PCMPEQQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1291 SSE4.1 :PCMPEQQ xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1292 AVX :VPCMPEQQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1293 AVX :VPCMPEQQ xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1294 SSE2 :PCMPGTB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1295 SSE2 :PCMPGTB xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1296 AVX :VPCMPGTB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1297 AVX :VPCMPGTB xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1298 SSE2 :PCMPGTW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1299 SSE2 :PCMPGTW xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1300 AVX :VPCMPGTW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1301 AVX :VPCMPGTW xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1302 SSE2 :PCMPGTD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1303 SSE2 :PCMPGTD xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1304 AVX :VPCMPGTD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1305 AVX :VPCMPGTD xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1306 SSE4.2 :PCMPGTQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1307 SSE4.2 :PCMPGTQ xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1308 AVX :VPCMPGTQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1309 AVX :VPCMPGTQ xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1310 SSE2 :PAND xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1311 SSE2 :PAND xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1312 AVX :VPAND xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1313 AVX :VPAND xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1314 SSE2 :PANDN xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1315 SSE2 :PANDN xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1316 AVX :VPANDN xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1317 AVX :VPANDN xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1318 SSE2 :POR xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1319 SSE2 :POR xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1320 AVX :VPOR xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1321 AVX :VPOR xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1322 SSE2 :PXOR xmm, xmm L: 0.27ns= 0.5c T: 0.27ns= 0.50c 1323 SSE2 :PXOR xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1324 AVX :VPXOR xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1325 AVX :VPXOR xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1326 SSE2 :PMULHW xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1327 AVX :VPMULHW xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1328 SSE2 :PMULHUW xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1329 AVX :VPMULHUW xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1330 SSSE3 :PMULHRSW xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1331 AVX :VPMULHRSW xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1332 SSE2 :PMULLW xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1333 AVX :VPMULLW xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1334 SSE4.1 :PMULLD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1335 AVX :VPMULLD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1336 SSE4.1 :PMULDQ xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1337 AVX :VPMULDQ xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1338 SSE2 :PMULUDQ xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1339 AVX :VPMULUDQ xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1340 SSSE3 :PMADDUBSW xmm, xmm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 1341 AVX :VPMADDUBSW xmm, xmm, xmm L: 5.47ns= 10.0c T: 5.47ns= 10.00c 1342 SSE2 :PMADDWD xmm, xmm L: 2.19ns= 4.0c T: 0.55ns= 1.00c 1343 AVX :VPMADDWD xmm, xmm, xmm L: 2.19ns= 4.0c T: 0.55ns= 1.00c 1344 SSE2 :PSLLW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1345 AVX :VPSLLW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1346 SSE2 :PSLLW xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1347 AVX :VPSLLW xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1348 SSE2 :PSLLD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1349 AVX :VPSLLD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1350 SSE2 :PSLLD xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1351 AVX :VPSLLD xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1352 SSE2 :PSLLQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1353 AVX :VPSLLQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1354 SSE2 :PSLLQ xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1355 AVX :VPSLLQ xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1356 SSE2 :PSLLDQ xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1357 AVX :VPSLLDQ xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1358 SSE2 :PSRAW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1359 AVX :VPSRAW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1360 SSE2 :PSRAW xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1361 AVX :VPSRAW xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1362 SSE2 :PSRAD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1363 AVX :VPSRAD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1364 SSE2 :PSRAD xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1365 AVX :VPSRAD xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1366 SSE2 :PSRLW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1367 AVX :VPSRLW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1368 SSE2 :PSRLW xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1369 AVX :VPSRLW xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1370 SSE2 :PSRLD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1371 AVX :VPSRLD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1372 SSE2 :PSRLD xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1373 AVX :VPSRLD xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1374 SSE2 :PSRLQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1375 AVX :VPSRLQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1376 SSE2 :PSRLQ xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1377 AVX :VPSRLQ xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1378 SSE2 :PSRLDQ xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1379 AVX :VPSRLDQ xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1380 SSE2 :PUNPCKHBW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1381 AVX :VPUNPCKHBW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1382 SSE2 :PUNPCKHWD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1383 AVX :VPUNPCKHWD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1384 SSE2 :PUNPCKHDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1385 AVX :VPUNPCKHDQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1386 SSE2 :PUNPCKHQDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1387 AVX :VPUNPCKHQDQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1388 SSE2 :PUNPCKLBW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1389 AVX :VPUNPCKLBW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1390 SSE2 :PUNPCKLWD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1391 AVX :VPUNPCKLWD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1392 SSE2 :PUNPCKLDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1393 AVX :VPUNPCKLDQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1394 SSE2 :PUNPCKLQDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1395 AVX :VPUNPCKLQDQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1396 SSE2 :PACKSSWB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1397 AVX :VPACKSSWB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1398 SSE2 :PACKUSWB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1399 AVX :VPACKUSWB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1400 SSE2 :PACKSSDW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1401 AVX :VPACKSSDW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1402 SSE4.1 :PACKUSDW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1403 AVX :VPACKUSDW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1404 SSE2 :PAVGB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1405 AVX :VPAVGB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1406 SSE2 :PAVGW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1407 AVX :VPAVGW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1408 SSE4.1 :PEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1409 SSE4.1 :PINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1410 SSE4.1 :PEXTRB + PINSRB r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1411 AVX :VPEXTRB r32, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1412 AVX :VPINSRB xmm, r32, im8 L: [diff. reg. set] T: 0.59ns= 1.08c 1413 AVX :VPEXTRB + VPINSRB r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1414 SSE4.1 :PEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1415 SSE4.1 :PEXTRB r64 + PINSRB r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1416 AVX :VPEXTRB r64, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1417 AVX :VPEXTRB r64 + VPINSRB r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1418 SSE2 :PEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1419 SSE2 :PINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1420 SSE2 :PEXTRW + PINSRW r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1421 AVX :VPEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1422 AVX :VPINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.59ns= 1.08c 1423 AVX :VPEXTRW + VPINSRW r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1424 AMD64 :PEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1425 AMD64 :PEXTRW r64 + PINSRW r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1426 AVX :VPEXTRW r64, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1427 AVX :VPEXTRW r64 + VPINSRW r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1428 SSE4.1 :PEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1429 SSE4.1 :PINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1430 SSE4.1 :PEXTRD + PINSRD r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1431 AVX :VPEXTRD r32, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1432 AVX :VPINSRD xmm, r32, im8 L: [diff. reg. set] T: 0.59ns= 1.08c 1433 AVX :VPEXTRD + VPINSRD r32 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1434 SSE4.1 :PEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1435 SSE4.1 :PINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1436 SSE4.1 :PEXTRD + PINSRD r64 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1437 AVX :VPEXTRQ r64, xmm, im8 L: [diff. reg. set] T: 0.55ns= 1.00c 1438 AVX :VPINSRQ xmm, r64, im8 L: [diff. reg. set] T: 0.59ns= 1.08c 1439 AVX :VPEXTRQ + VPINSRQ r64 L: 4.92ns= 9.0c T: 0.59ns= 1.08c 1440 SSE4.1 :EXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.27ns= 0.50c 1441 AVX :VEXTRACTPS r32, xmm, im8 L: [diff. reg. set] T: 0.27ns= 0.50c 1442 SSE4.1 :EXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.27ns= 0.50c 1443 AVX :VEXTRACTPS r64, xmm, im8 L: [diff. reg. set] T: 0.27ns= 0.50c 1444 SSE4.1 :INSERTPS xmm, xmm, im8 L: 0.64ns= 1.2c T: 0.34ns= 0.62c 1445 AVX :VINSERTPS xmm, xmm, im8 L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1450 SSE2 :PMAXUB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1451 AVX :VPMAXUB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1452 SSE4.1 :PMAXSB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1453 AVX :VPMAXSB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1454 SSE4.1 :PMAXUW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1455 AVX :VPMAXUW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1456 SSE2 :PMAXSW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1457 AVX :VPMAXSW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1458 SSE4.1 :PMAXUD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1459 AVX :VPMAXUD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1460 SSE4.1 :PMAXSD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1461 AVX :VPMAXSD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1462 SSE2 :PMINUB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1463 AVX :VPMINUB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1464 SSE4.1 :PMINSB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1465 AVX :VPMINSB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1466 SSE4.1 :PMINUW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1467 AVX :VPMINUW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1468 SSE2 :PMINSW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1469 AVX :VPMINSW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1470 SSE4.1 :PMINUD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1471 AVX :VPMINUD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1472 SSE4.1 :PMINSD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1473 AVX :VPMINSD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1474 SSE2 :PSADBW xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1475 AVX :VPSADBW xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1476 SSSE3 :PSHUFB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1477 AVX :VPSHUFB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1478 SSE2 :PSHUFLW xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1479 AVX :VPSHUFLW xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1480 SSE2 :PSHUFHW xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1481 AVX :VPSHUFHW xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1482 SSE2 :PSHUFD xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1483 AVX :VPSHUFD xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1484 SSE3 :ADDSUBPS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1485 AVX :VADDSUBPS xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1486 SSE3 :ADDSUBPD xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1487 AVX :VADDSUBPD xmm, xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1488 SSE3 :HADDPS xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1489 AVX :VHADDPS xmm, xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1490 SSE3 :HADDPD xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1491 AVX :VHADDPD xmm, xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1492 SSE3 :HSUBPS xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1493 AVX :VHSUBPS xmm, xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1494 SSE3 :HSUBPD xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1495 AVX :VHSUBPD xmm, xmm, xmm L: 2.73ns= 5.0c T: 1.64ns= 3.00c 1496 SSE3 :MOVSLDUP xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 1497 AVX :VMOVSLDUP xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1498 SSE3 :MOVSHDUP xmm, xmm L: 0.64ns= 1.2c T: 0.35ns= 0.65c 1499 AVX :VMOVSHDUP xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1500 SSE3 :MOVDDUP xmm, xmm L: 0.64ns= 1.2c T: 0.34ns= 0.63c 1501 AVX :VMOVDDUP xmm, xmm, xmm L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1502 SSE3 :LDDQU xmm, [m128 + 4] L: [memory dep.] T: 1.55ns= 2.83c 1503 AVX :VLDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.68ns= 1.25c 1504 SSSE3 :PABSB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1505 AVX :VPABSB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1506 SSSE3 :PABSW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1507 AVX :VPABSW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1508 SSSE3 :PABSD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1509 AVX :VPABSD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1510 SSSE3 :PALIGNR xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1511 AVX :VPALIGNR xmm, xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1512 SSSE3 :PHADDW xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1513 AVX :VPHADDW xmm, xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1514 SSSE3 :PHADDD xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1515 AVX :VPHADDD xmm, xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1516 SSSE3 :PHADDSW xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1517 AVX :VPHADDSW xmm, xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1518 SSSE3 :PHSUBW xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1519 AVX :VPHSUBW xmm, xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1520 SSSE3 :PHSUBD xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1521 AVX :VPHSUBD xmm, xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1522 SSSE3 :PHSUBSW xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1523 AVX :VPHSUBSW xmm, xmm, xmm L: 1.64ns= 3.0c T: 1.64ns= 3.00c 1524 SSSE3 :PSIGNB xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1525 AVX :VPSIGNB xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1526 SSSE3 :PSIGNW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1527 AVX :VPSIGNW xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1528 SSSE3 :PSIGND xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1529 AVX :VPSIGND xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1530 SSE4.1 :BLENDPS xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1531 AVX :VBLENDPS xmm, xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1532 SSE4.1 :BLENDVPS xmm, xmm, L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1533 AVX :VBLENDVPS xmm, xmm, xmm, xm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1534 SSE4.1 :BLENDPD xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1535 AVX :VBLENDPD xmm, xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1536 SSE4.1 :BLENDVPD xmm, xmm, L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1537 AVX :VBLENDVPD xmm, xmm, xmm, xm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 1538 SSE4.1 :PBLENDW xmm, xmm, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1539 AVX :VPBLENDW xmm, xmm, xmm, im8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1540 SSE4.1 :PBLENDVB xmm, xmm, L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1541 AVX :VPBLENDVB xmm, xmm, xmm, xm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1542 SSE4.1 :DPPS xmm, xmm, imm8 L: 9.30ns= 17.0c T: 9.30ns= 17.00c 1543 AVX :VDPPS xmm, xmm, xmm, imm8 L: 9.85ns= 18.0c T: 9.85ns= 18.00c 1544 SSE4.1 :DPPD xmm, xmm, imm8 L: 5.47ns= 10.0c T: 4.38ns= 8.00c 1545 AVX :VDPPD xmm, xmm, xmm, imm8 L: 5.47ns= 10.0c T: 4.92ns= 9.00c 1546 SSE4.1 :MPSADBW xmm, xmm, imm8 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 1547 AVX :VMPSADBW xmm, xmm, imm8 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 1548 SSE4.1 :PHMINPOSUW xmm, xmm L: 1.09ns= 2.0c T: 0.55ns= 1.00c 1549 AVX :VPHMINPOSUW xmm, xmm L: 1.09ns= 2.0c T: 0.55ns= 1.00c 1550 SSE4.1 :PMOVSXBW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1551 AVX :VPMOVSXBW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1552 SSE4.1 :PMOVSXBD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1553 AVX :VPMOVSXBD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1554 SSE4.1 :PMOVSXBQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1555 AVX :VPMOVSXBQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1556 SSE4.1 :PMOVSXWD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1557 AVX :VPMOVSXWD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1558 SSE4.1 :PMOVSXWQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1559 AVX :VPMOVSXWQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1560 SSE4.1 :PMOVSXDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1561 AVX :VPMOVSXDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1562 SSE4.1 :PMOVZXBW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1563 AVX :VPMOVZXBW xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1564 SSE4.1 :PMOVZXBD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1565 AVX :VPMOVZXBD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1566 SSE4.1 :PMOVZXBQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1567 AVX :VPMOVZXBQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1568 SSE4.1 :PMOVZXWD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1569 AVX :VPMOVZXWD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1570 SSE4.1 :PMOVZXWQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1571 AVX :VPMOVZXWQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1572 SSE4.1 :PMOVZXDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1573 AVX :VPMOVZXDQ xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1574 SSE4.1 :PTEST xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1575 AVX :VPTEST xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1576 AVX :VPTESTPS xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1577 AVX :VPTESTPD xmm, xmm L: [no true dep.] T: 0.55ns= 1.00c 1578 SSE4.1 :ROUNDSS xmm, xmm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1579 AVX :VROUNDSS xmm, xmm, xmm, im8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1580 SSE4.1 :ROUNDPS xmm, xmm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1581 AVX :VROUNDPS xmm, xmm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1582 SSE4.1 :ROUNDSD xmm, xmm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1583 AVX :VROUNDSD xmm, xmm, xmm, im8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1584 SSE4.1 :ROUNDPD xmm, xmm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1585 AVX :VROUNDPD xmm, xmm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1586 AVX :VBROADCASTSS xmm, m32 L: [memory dep.] T: 1.09ns= 2.00c 1587 SSE4.2 :PCMPESTRI xmm, xmm, imm8 L: 32.82ns= 60.0c T: 32.82ns= 60.00c 1588 AVX :VPCMPESTRI xmm, xmm, imm8 L: 32.82ns= 60.0c T: 32.82ns= 60.00c 1589 SSE4.2 :PCMPESTRM xmm, xmm, imm8 L: 33.36ns= 61.0c T: 33.36ns= 61.00c 1590 AVX :VPCMPESTRM xmm, xmm, imm8 L: 33.91ns= 62.0c T: 33.91ns= 62.00c 1591 SSE4.2 :PCMPISTRI xmm, xmm, imm8 L: 47.04ns= 86.0c T: 47.04ns= 86.00c 1592 AVX :VPCMPISTRI xmm, xmm, imm8 L: 31.18ns= 57.0c T: 31.18ns= 57.00c 1593 SSE4.2 :PCMPISTRM xmm, xmm, imm8 L: 47.58ns= 87.0c T: 47.58ns= 87.00c 1594 AVX :VPCMPISTRM xmm, xmm, imm8 L: 32.27ns= 59.0c T: 32.27ns= 59.00c 1595 CLMUL :PCLMULQDQ xmm, xmm, imm8 L: 6.56ns= 12.0c T: 4.38ns= 8.00c 1596 AVX :VPCLMULQDQ xmm,xmm,xmm,im8 L: 6.56ns= 12.0c T: 4.92ns= 9.00c 1597 AESNI :AESENC xmm, xmm L: 3.83ns= 7.0c T: 0.55ns= 1.00c 1598 AVX :VAESENC xmm, xmm, xmm L: 3.83ns= 7.0c T: 0.96ns= 1.75c 1599 AESNI :AESENCLAST xmm, xmm L: 3.83ns= 7.0c T: 0.55ns= 1.00c 1600 AVX :VAESENCLAST xmm, xmm, xmm L: 3.83ns= 7.0c T: 0.91ns= 1.67c 1601 AESNI :AESDEC xmm, xmm L: 3.83ns= 7.0c T: 0.55ns= 1.00c 1602 AVX :VAESDEC xmm, xmm, xmm L: 3.83ns= 7.0c T: 0.96ns= 1.75c 1603 AESNI :AESDECLAST xmm, xmm L: 3.83ns= 7.0c T: 0.55ns= 1.00c 1604 AVX :VAESDECLAST xmm, xmm, xmm L: 3.83ns= 7.0c T: 0.96ns= 1.75c 1605 AESNI :AESIMC xmm, xmm L: 3.83ns= 7.0c T: 0.55ns= 1.00c 1606 AVX :VAESIMC xmm, xmm L: 3.83ns= 7.0c T: 0.55ns= 1.00c 1607 AESNI :AESKEYGEN xmm, xmm, imm8 L: 13.13ns= 24.0c T: 10.94ns= 20.00c 1608 AVX :VAESKEYGEN xmm, xmm, imm8 L: 13.13ns= 24.0c T: 10.94ns= 20.00c 1768 F16C :VCVTPS2PH xmm, xmm, imm8 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1769 F16C :VCVTPH2PS xmm, xmm L: 1.64ns= 3.0c T: 0.55ns= 1.00c 1770 AVX :VMOVAPS ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1771 AVX :VMOVAPS ymm, [m256] L: [memory dep.] T: 1.46ns= 2.67c 1772 AVX :VMOVAPS [m256], ymm L: [memory dep.] T: 1.78ns= 3.25c 1773 AVX :VMOVAPS LS pair L: 3.28ns= 6.0c T: 1.73ns= 3.17c 1774 AVX :VMOVUPS ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1775 AVX :VMOVUPS ymm, [m256] L: [memory dep.] T: 1.46ns= 2.67c 1776 AVX :VMOVUPS [m256], ymm L: [memory dep.] T: 1.78ns= 3.25c 1777 AVX :VMOVUPS aligned LS pair L: 3.28ns= 6.0c T: 1.73ns= 3.17c 1778 AVX :VMOVUPS ymm, [m256 + 4] L: [memory dep.] T: 7.66ns= 14.00c 1779 AVX :VMOVUPS [m256 + 4], ymm L: [memory dep.] T: 24.43ns= 44.67c 1780 AVX :VMOVUPS unaligned LS pair L: 3.28ns= 6.0c T: 20.33ns= 37.17c 1781 AVX :VMOVSLDUP ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1782 AVX :VMOVSHDUP ymm, ymm, ymm L: 1.23ns= 2.3c T: 0.55ns= 1.00c 1783 AVX :VMOVNTPS [m256], ymm L: [memory dep.] T: 2.92ns= 2.92c 1784 AVX :VMOVMSKPS r32, ymm L: [diff. reg. set] T: 3.83ns= 7.00c 1785 AVX :VMASKMOVPS ymm,ymm,[m256+4] L: [memory dep.] T: 107.20ns=196.00c 1786 AVX :VMASKMOVPS [m256+4],ymm,ymm L: [memory dep.] T: 16.41ns= 30.00c 1787 AVX :VMASKMOVPS unaligned LSpair L: 124.16ns=227.0c T: 124.25ns=227.17c 1788 AVX :VUNPCKLPS ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1789 AVX :VUNPCKHPS ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1790 AVX :VSHUFPS ymm, ymm, ymm, imm8 L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1791 AVX :VPERMILPS ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 1792 AVX :VPERMILPS ymm, ymm, imm8 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 1793 AVX :VCMPPS ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1794 AVX :VADDSUBPS ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1795 AVX :VHSUBPS ymm, ymm, ymm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 1796 AVX :VHADDPS ymm, ymm, ymm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 1797 AVX :VSUBPS ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1798 AVX :VADDPS ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1799 AVX :VMULPS ymm, ymm, ymm L: 2.73ns= 5.0c T: 1.09ns= 2.00c 1800 AVX :VMULPS+VADDPS ymm, ymm, ymm L: 5.56ns= 10.2c T: 1.91ns= 3.50c 1801 AVX :VMULPS ymm1.. VADDPS ymm2.. L: 2.78ns= 5.1c T: 1.64ns= 3.00c 1802 AVX :VMAXPS ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1803 AVX :VMINPS ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1804 AVX :VANDNPS ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1805 AVX :VANDNPS ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1806 AVX :VANDPS ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1807 AVX :VANDPS ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1808 AVX :VORPS ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1809 AVX :VORPS ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1810 AVX :VXORPS ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1811 AVX :VXORPS ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1812 AVX :VDIVPS ymm, ymm, ymm L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1813 AVX :VDIVPS (0.0f/x) L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1814 AVX :VDIVPS (x/1.0f) L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1815 AVX :VDIVPS (x/2.0f) L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1816 AVX :VDIVPS (x/0.5f) L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1817 AVX :VSQRTPS ymm, ymm L: 70.01ns=128.0c T: 70.01ns=128.00c 1818 AVX :VSQRTPS (0.0f) L: 25.16ns= 46.0c T: 25.16ns= 46.00c 1819 AVX :VSQRTPS (1.0f) L: 70.01ns=128.0c T: 70.01ns=128.00c 1820 AVX :VRCPPS ymm, ymm, ymm L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1821 AVX :VRSQRTPS ymm, ymm, ymm L: 26.25ns= 48.0c T: 26.25ns= 48.00c 1822 AVX :VBLENDPS ymm, ymm, ymm, im8 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 1823 AVX :VBLENDVPS ymm, ymm, ymm, ym L: 2.19ns= 4.0c T: 2.19ns= 4.00c 1824 AVX :VDPPS ymm, ymm, ymm, imm8 L: 16.96ns= 31.0c T: 16.96ns= 31.00c 1825 AVX :VPTESTPS ymm, ymm L: [no true dep.] T: 4.38ns= 8.00c 1826 AVX :VROUNDPS ymm, ymm, imm8 L: 4.38ns= 8.0c T: 4.38ns= 8.00c 1827 AVX :VMOVAPD ymm, ymm L: 1.23ns= 2.3c T: 0.55ns= 1.00c 1828 AVX :VMOVAPD ymm, [m256] L: [memory dep.] T: 1.46ns= 2.67c 1829 AVX :VMOVAPD [m256], ymm L: [memory dep.] T: 1.78ns= 3.25c 1830 AVX :VMOVAPD LS pair L: 3.28ns= 6.0c T: 1.73ns= 3.17c 1831 AVX :VMOVUPD ymm, ymm L: 1.23ns= 2.3c T: 0.55ns= 1.00c 1832 AVX :VMOVUPD ymm, [m256] L: [memory dep.] T: 1.46ns= 2.67c 1833 AVX :VMOVUPD [m256], ymm L: [memory dep.] T: 1.78ns= 3.25c 1834 AVX :VMOVUPD aligned LS pair L: 3.28ns= 6.0c T: 1.73ns= 3.17c 1835 AVX :VMOVUPD ymm, [m256 + 4] L: [memory dep.] T: 7.66ns= 14.00c 1836 AVX :VMOVUPD [m256 + 4], ymm L: [memory dep.] T: 24.43ns= 44.67c 1837 AVX :VMOVUPD unaligned LS pair L: 3.28ns= 6.0c T: 20.33ns= 37.17c 1838 AVX :VMOVDDUP ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1839 AVX :VMOVNTPD [m256], ymm L: [memory dep.] T: 2.92ns= 2.92c 1840 AVX :VMOVMSKPD r32, ymm L: [diff. reg. set] T: 3.83ns= 7.00c 1841 AVX :VMASKMOVPD ymm,ymm,[m256+4] L: [memory dep.] T: 50.87ns= 93.00c 1842 AVX :VMASKMOVPD [m256+4],ymm,ymm L: [memory dep.] T: 16.96ns= 31.00c 1843 AVX :VMASKMOVPD unaligned LSpair L: 67.82ns=124.0c T: 67.82ns=124.00c 1844 AVX :VUNPCKLPD ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1845 AVX :VUNPCKHPD ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1846 AVX :VSHUFPD ymm, ymm, ymm, imm8 L: 0.91ns= 1.7c T: 0.55ns= 1.00c 1847 AVX :VPERMILPD ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 1848 AVX :VPERMILPD ymm, ymm, imm8 L: 0.91ns= 1.7c T: 0.55ns= 1.00c 1849 AVX :VCMPPD ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1850 AVX :VADDSUBPD ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1851 AVX :VHSUBPD ymm, ymm, ymm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 1852 AVX :VHADDPD ymm, ymm, ymm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 1853 AVX :VSUBPD ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1854 AVX :VADDPD ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1855 AVX :VMULPD ymm, ymm, ymm L: 3.28ns= 6.0c T: 2.19ns= 4.00c 1856 AVX :VMULPD+VADDPD ymm, ymm, ymm L: 6.20ns= 11.3c T: 2.14ns= 3.92c 1857 AVX :VMULPD ymm1.. VADDPD ymm2.. L: 3.28ns= 6.0c T: 2.19ns= 4.00c 1858 AVX :VMAXPD ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1859 AVX :VMINPD ymm, ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1860 AVX :VANDNPD ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1861 AVX :VANDNPD ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1862 AVX :VANDPD ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1863 AVX :VANDPD ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1864 AVX :VORPD ymm, ymm, ymm L: 1.19ns= 2.2c T: 0.55ns= 1.00c 1865 AVX :VORPD ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1866 AVX :VXORPD ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1867 AVX :VXORPD ymm1, ymm1, ymm2 L: 1.19ns= 2.2c T: 0.47ns= 0.86c 1868 AVX :VDIVPD ymm, ymm, ymm L: 41.57ns= 76.0c T: 41.57ns= 76.00c 1869 AVX :VDIVPD (0.0/x) L: 24.07ns= 44.0c T: 24.07ns= 44.00c 1870 AVX :VDIVPD (x/1.0) L: 41.57ns= 76.0c T: 41.57ns= 76.00c 1871 AVX :VDIVPD (x/2.0) L: 41.57ns= 76.0c T: 41.57ns= 76.00c 1872 AVX :VDIVPD (x/0.5) L: 25.16ns= 46.0c T: 25.16ns= 46.00c 1873 AVX :VSQRTPD ymm, ymm L: 133.46ns=244.0c T: 133.50ns=244.08c 1874 AVX :VSQRTPD (0.0) L: 25.16ns= 46.0c T: 25.16ns= 46.00c 1875 AVX :VSQRTPD (1.0) L: 133.46ns=244.0c T: 133.50ns=244.08c 1876 AVX :VBLENDPD ymm, ymm, ymm, im8 L: 1.64ns= 3.0c T: 1.09ns= 2.00c 1877 AVX :VBLENDVPD ymm, ymm, ymm, ym L: 2.19ns= 4.0c T: 2.19ns= 4.00c 1878 AVX :VCVTDQ2PD ymm, xmm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 1879 AVX :VCVTPD2DQ xmm, ymm L: 3.83ns= 7.0c T: 3.83ns= 7.00c 1880 AVX :VCVTPD2DQ + VCVTDQ2PD L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1881 AVX :VCVTTPD2DQ xmm, ymm L: 3.83ns= 7.0c T: 3.83ns= 7.00c 1882 AVX :VCVTTPD2DQ + VCVTDQ2PD L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1883 AVX :VCVTDQ2PS ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1884 AVX :VCVTPS2DQ ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1885 AVX :VCVTPS2DQ + VCVTDQ2PS L: 6.02ns= 11.0c T: 2.73ns= 5.00c 1886 AVX :VCVTTPS2DQ ymm, ymm L: 3.01ns= 5.5c T: 1.19ns= 2.17c 1887 AVX :VCVTTPS2DQ + VCVTDQ2PS L: 6.02ns= 11.0c T: 2.73ns= 5.00c 1888 AVX :VCVTPS2PD ymm, xmm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 1889 AVX :VCVTPD2PS xmm, ymm L: 3.83ns= 7.0c T: 3.83ns= 7.00c 1890 AVX :VCVTPD2PS + VCVTPS2PD L: 8.20ns= 15.0c T: 8.20ns= 15.00c 1891 AVX :VPTESTPD ymm, ymm L: [no true dep.] T: 4.38ns= 8.00c 1892 AVX :VROUNDPD ymm, ymm, imm8 L: 4.38ns= 8.0c T: 4.38ns= 8.00c 1893 AVX :VBROADCASTSS ymm, m32 L: [memory dep.] T: 0.68ns= 1.25c 1894 AVX :VBROADCASTSD ymm, m64 L: [memory dep.] T: 0.68ns= 1.25c 1895 AVX :VBROADCASTF128 ymm, m128 L: [memory dep.] T: 0.68ns= 1.25c 1896 AVX :VEXTRACTF128 xmm, ymm, imm8 L: 1.00ns= 1.8c T: 0.50ns= 0.92c 1897 AVX :VINSERTF128 ym, ym, xm, im8 L: 1.19ns= 2.2c T: 0.50ns= 0.92c 1898 AVX :VPERM2F128 ym, ym, ym, im8 L: 2.46ns= 4.5c T: 1.09ns= 2.00c 1899 AVX :VMOVDQA ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1900 AVX :VMOVDQA ymm, [m256] L: [memory dep.] T: 1.46ns= 2.67c 1901 AVX :VMOVDQA [m256], ymm L: [memory dep.] T: 1.78ns= 3.25c 1902 AVX :VMOVDQA LS pair L: 3.28ns= 6.0c T: 1.73ns= 3.17c 1903 AVX :VMOVDQU ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1904 AVX :VMOVDQU ymm, [m256] L: [memory dep.] T: 1.46ns= 2.67c 1905 AVX :VMOVDQU [m256], ymm L: [memory dep.] T: 1.78ns= 3.25c 1906 AVX :VMOVDQU aligned LS pair L: 3.28ns= 6.0c T: 1.73ns= 3.17c 1907 AVX :VMOVDQU ymm, [m256 + 4] L: [memory dep.] T: 7.66ns= 14.00c 1908 AVX :VMOVDQU [m256 + 4], ymm L: [memory dep.] T: 24.43ns= 44.67c 1909 AVX :VMOVDQU unaligned LS pair L: 3.28ns= 6.0c T: 20.33ns= 37.17c 1910 AVX :VMOVNTDQ [m256], ymm L: [memory dep.] T: 2.92ns= 2.92c 1911 AVX :VLDDQU ymm, [m256 + 4] L: [memory dep.] T: 7.66ns= 14.00c 1912 AVX :VZEROUPPER L: [no true dep.] T: 27.89ns= 51.00c 1913 AVX :VZEROALL L: [no true dep.] T: 51.96ns= 95.00c 1967 F16C :VCVTPS2PH + VCVTPH2PS L: 3.28ns= 6.0c T: 1.09ns= 2.00c 1968 F16C :VCVTPS2PH xmm, ymm, imm8 L: 3.28ns= 6.0c T: 1.32ns= 2.42c 1969 F16C :VCVTPH2PS ymm, xmm L: 4.92ns= 9.0c T: 4.92ns= 9.00c 1970 F16C :VCVTPS2PH + VCVTPH2PS L: 7.11ns= 13.0c T: 6.02ns= 11.00c 1971 RDRAND :RDRAND r16 L: [no true dep.] T: 54.97ns=100.50c 1972 RDRAND :RDRAND r32 L: [no true dep.] T: 54.97ns=100.50c 1973 RDRAND :RDRAND r64 L: [no true dep.] T: 54.97ns=100.50c 1974 X86 :MOV+ADD r8, r8 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 1975 X86 :MOV+ADD r16, r16 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 1976 X86 :MOV+ADD r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1977 AMD64 :MOV+ADD r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 1978 MMX :MOVQ+PADDB mm, mm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1979 MMX :MOVQ+PADDW mm, mm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1980 MMX :MOVQ+PADDD mm, mm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1981 SSE2 :MOVQ+PADDQ mm, mm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1983 SSE :MOVSS+ADDSS xmm, xmm L: 3.19ns= 5.8c T: 0.41ns= 0.75c 1984 AVX :VMOVSS+VADDSS xm, xm, xm L: 3.05ns= 5.6c T: 1.09ns= 2.00c 1985 SSE :MOVAPS+ADDPS xmm, xmm L: 3.19ns= 5.8c T: 0.41ns= 0.75c 1986 AVX :VMOVAPS+VADDPS xm, xm, xm L: 3.05ns= 5.6c T: 1.09ns= 2.00c 1987 SSE2 :MOVSD+ADDSD xmm, xmm L: 3.19ns= 5.8c T: 0.41ns= 0.75c 1988 AVX :VMOVSD+VADDSD xm, xm, xm L: 3.05ns= 5.6c T: 1.09ns= 2.00c 1989 SSE2 :MOVAPD+ADDPD xmm, xmm L: 3.19ns= 5.8c T: 0.41ns= 0.75c 1990 AVX :VMOVAPD+VADDPD xm, xm, xm L: 3.05ns= 5.6c T: 1.09ns= 2.00c 1991 SSE2 :MOVDQA+PADDB xmm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1992 SSE2 :MOVDQA+PADDW xmm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1993 SSE2 :MOVDQA+PADDD xmm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1994 SSE2 :MOVDQA+PADDQ xmm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1995 AVX :VMOVDQA+VPADDB xm, xm, xm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1996 AVX :VMOVDQA+VPADDW xm, xm, xm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1997 AVX :VMOVDQA+VPADDD xm, xm, xm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1998 AVX :VMOVDQA+VPADDQ xm, xm, xm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 1999 AVX :VMOVAPS+VADDPS ym, ym, ym L: 3.65ns= 6.7c T: 1.50ns= 2.75c 2000 AVX :VMOVAPD+VADDPD ym, ym, ym L: 3.65ns= 6.7c T: 1.50ns= 2.75c 2001 RDSEED :RDSEED r16 L: [no true dep.] T: 27.26ns= 49.83c 2002 RDSEED :RDSEED r32 L: [no true dep.] T: 28.90ns= 52.83c 2003 RDSEED :RDSEED r64 L: [no true dep.] T: 27.26ns= 49.83c 2004 BMI :ANDN r32, r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2005 BMI :ANDN r64, r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2006 BMI :BEXTR r32, r32, r32 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 2007 BMI :BEXTR r64, r64, r64 L: 1.64ns= 3.0c T: 0.55ns= 1.00c 2008 BMI :BLSI r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2009 BMI :BLSI r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2010 BMI :BLSMSK r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2011 BMI :BLSMSK r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2012 BMI :BLSR r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2013 BMI :BLSR r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2014 BMI :TZCNT r16, r16 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2015 BMI :TZCNT r32, r32 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2016 BMI :TZCNT r64, r64 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2017 BMI2 :BZHI r32, r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2018 BMI2 :BZHI r64, r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2019 BMI2 :MULX r32, r32, r32 L: 1.87ns= 3.4c T: 0.91ns= 1.67c 2020 BMI2 :MULX r64, r64, r64 L: 7.11ns= 13.0c T: 3.28ns= 6.00c 2021 BMI2 :PDEP r32, r32, r32 L: 3.83ns= 7.0c T: 3.83ns= 7.00c 2022 BMI2 :PDEP r64, r64, r64 L: 6.02ns= 11.0c T: 6.02ns= 11.00c 2023 BMI2 :PEXT r32, r32, r32 L: 3.83ns= 7.0c T: 3.83ns= 7.00c 2024 BMI2 :PEXT r64, r64, r64 L: 6.02ns= 11.0c T: 6.02ns= 11.00c 2025 BMI2 :RORX r32, r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2026 BMI2 :RORX r64, r64, r64 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2027 BMI2 :SARX r32, r32, r32 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 2028 BMI2 :SARX r64, r64, r64 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 2029 BMI2 :SHLX r32, r32, r32 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 2030 BMI2 :SHLX r64, r64, r64 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 2031 BMI2 :SHRX r32, r32, r32 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 2032 BMI2 :SHRX r64, r64, r64 L: 1.09ns= 2.0c T: 0.55ns= 1.00c 2053 AVX2 :VMOVNTDQA ymm, [m256] L: [memory dep.] T: 2.67ns= 2.67c 2054 AVX2 :VMOVNTDQA + VMOVNTDQ ymm L: 170.38ns=311.5c T: 311.50ns=311.50c 2055 AVX2 :VPMOVMSKB r32, ymm L: [diff. reg. set] T: 1.09ns= 2.00c 2056 AVX2 :VPMOVMSKB r64, ymm L: [diff. reg. set] T: 1.09ns= 2.00c 2057 AVX2 :VPADDB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2058 AVX2 :VPADDW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2059 AVX2 :VPADDD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2060 AVX2 :VPADDQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2061 AVX2 :VPADDSB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2062 AVX2 :VPADDSW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2063 AVX2 :VPADDUSB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2064 AVX2 :VPADDUSW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2065 AVX2 :VPSUBB ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2066 AVX2 :VPSUBB ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2067 AVX2 :VPSUBW ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2068 AVX2 :VPSUBW ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2069 AVX2 :VPSUBD ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2070 AVX2 :VPSUBD ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2071 AVX2 :VPSUBQ ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2072 AVX2 :VPSUBQ ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2073 AVX2 :VPSUBSB ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2074 AVX2 :VPSUBSB ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2075 AVX2 :VPSUBSW ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2076 AVX2 :VPSUBSW ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2077 AVX2 :VPSUBUSB ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2078 AVX2 :VPSUBUSB ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2079 AVX2 :VPSUBUSW ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2080 AVX2 :VPSUBUSW ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2081 AVX2 :VPCMPEQB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2082 AVX2 :VPCMPEQB ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2083 AVX2 :VPCMPEQW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2084 AVX2 :VPCMPEQW ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2085 AVX2 :VPCMPEQD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2086 AVX2 :VPCMPEQD ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2087 AVX2 :VPCMPEQQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2088 AVX2 :VPCMPEQQ ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2089 AVX2 :VPCMPGTB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2090 AVX2 :VPCMPGTB ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2091 AVX2 :VPCMPGTW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2092 AVX2 :VPCMPGTW ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2093 AVX2 :VPCMPGTD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2094 AVX2 :VPCMPGTD ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2095 AVX2 :VPCMPGTQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2096 AVX2 :VPCMPGTQ ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2097 AVX2 :VPAND ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2098 AVX2 :VPAND ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2099 AVX2 :VPANDN ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2100 AVX2 :VPANDN ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2101 AVX2 :VPOR ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2102 AVX2 :VPOR ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2103 AVX2 :VPXOR ymm, ymm, ymm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2104 AVX2 :VPXOR ymm1, ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2105 AVX2 :VPMULHW ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2106 AVX2 :VPMULHUW ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2107 AVX2 :VPMULHRSW ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2108 AVX2 :VPMULLW ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2109 AVX2 :VPMULLD ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2110 AVX2 :VPMULDQ ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2111 AVX2 :VPMULUDQ ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2112 AVX2 :VPMADDUBSW ymm, ymm, ymm L: 10.94ns= 20.0c T: 10.94ns= 20.00c 2113 AVX2 :VPMADDWD ymm, ymm, ymm L: 2.19ns= 4.0c T: 1.09ns= 2.00c 2114 AVX2 :VPSLLW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2115 AVX2 :VPSLLW ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2116 AVX2 :VPSLLD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2117 AVX2 :VPSLLD ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2118 AVX2 :VPSLLQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2119 AVX2 :VPSLLQ ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2120 AVX2 :VPSLLDQ ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2121 AVX2 :VPSRAW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2122 AVX2 :VPSRAW ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2123 AVX2 :VPSRAD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2124 AVX2 :VPSRAD ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2125 AVX2 :VPSRLW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2126 AVX2 :VPSRLW ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2127 AVX2 :VPSRLD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2128 AVX2 :VPSRLD ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2129 AVX2 :VPSRLQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2130 AVX2 :VPSRLQ ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2131 AVX2 :VPSRLDQ ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2132 AVX2 :VPUNPCKHBW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2133 AVX2 :VPUNPCKHWD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2134 AVX2 :VPUNPCKHDQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2135 AVX2 :VPUNPCKHQDQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2136 AVX2 :VPUNPCKLBW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2137 AVX2 :VPUNPCKLWD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2138 AVX2 :VPUNPCKLDQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2139 AVX2 :VPUNPCKLQDQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2140 AVX2 :VPACKSSWB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2141 AVX2 :VPACKUSWB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2142 AVX2 :VPACKSSDW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2143 AVX2 :VPACKUSDW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2144 AVX2 :VPAVGB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2145 AVX2 :VPAVGW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2146 AVX2 :VPMAXUB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2147 AVX2 :VPMAXSB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2148 AVX2 :VPMAXUW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2149 AVX2 :VPMAXSW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2150 AVX2 :VPMAXUD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2151 AVX2 :VPMAXSD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2152 AVX2 :VPMINUB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2153 AVX2 :VPMINSB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2154 AVX2 :VPMINUW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2155 AVX2 :VPMINSW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2156 AVX2 :VPMINUD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2157 AVX2 :VPMINSD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2158 AVX2 :VPSADBW ymm, ymm, ymm L: 1.64ns= 3.0c T: 1.09ns= 2.00c 2159 AVX2 :VPSHUFB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2160 AVX2 :VPSHUFLW ymm, ymm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2161 AVX2 :VPSHUFHW ymm, ymm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2162 AVX2 :VPSHUFD ymm, ymm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2163 AVX2 :VPABSB ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2164 AVX2 :VPABSW ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2165 AVX2 :VPABSD ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2166 AVX2 :VPALIGNR ymm, ymm, ymm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2167 AVX2 :VPHADDW ymm, ymm, ymm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 2168 AVX2 :VPHADDD ymm, ymm, ymm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 2169 AVX2 :VPHADDSW ymm, ymm, ymm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 2170 AVX2 :VPHSUBW ymm, ymm, ymm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 2171 AVX2 :VPHSUBD ymm, ymm, ymm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 2172 AVX2 :VPHSUBSW ymm, ymm, ymm L: 4.38ns= 8.0c T: 4.38ns= 8.00c 2173 AVX2 :VPSIGNB ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2174 AVX2 :VPSIGNW ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2175 AVX2 :VPSIGND ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2176 AVX2 :VPBLENDW ymm, ymm, ymm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2177 AVX2 :VPBLENDVB ymm, ymm, ymm, ym L: 2.19ns= 4.0c T: 2.19ns= 4.00c 2178 AVX2 :VPBLENDD xmm, xmm, xmm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2179 AVX2 :VPBLENDD ymm, ymm, ymm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2180 AVX2 :VMPSADBW ymm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2181 AVX2 :VPMOVSXBW ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2182 AVX2 :VPMOVSXBD ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2183 AVX2 :VPMOVSXBQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2184 AVX2 :VPMOVSXWD ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2185 AVX2 :VPMOVSXWQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2186 AVX2 :VPMOVSXDQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2187 AVX2 :VPMOVZXBW ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2188 AVX2 :VPMOVZXBD ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2189 AVX2 :VPMOVZXBQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2190 AVX2 :VPMOVZXWD ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2191 AVX2 :VPMOVZXWQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2192 AVX2 :VPMOVZXDQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2193 AVX2 :VPMASKMOVD xmm,xmm,[m128+4] L: [memory dep.] T: 54.70ns=100.00c 2194 AVX2 :VPMASKMOVD [m128+4],xmm,xmm L: [memory dep.] T: 14.77ns= 27.00c 2195 AVX2 :VPMASKMOVD unaligned LSpair L: 70.01ns=128.0c T: 70.06ns=128.08c 2196 AVX2 :VPMASKMOVQ xmm,xmm,[m128+4] L: [memory dep.] T: 26.80ns= 49.00c 2197 AVX2 :VPMASKMOVQ [m128+4],xmm,xmm L: [memory dep.] T: 14.22ns= 26.00c 2198 AVX2 :VPMASKMOVQ unaligned LSpair L: 41.57ns= 76.0c T: 41.57ns= 76.00c 2199 AVX2 :VPMASKMOVD ymm,ymm,[m256+4] L: [memory dep.] T: 107.34ns=196.25c 2200 AVX2 :VPMASKMOVD [m256+4],ymm,ymm L: [memory dep.] T: 16.41ns= 30.00c 2201 AVX2 :VPMASKMOVD unaligned LSpair L: 124.16ns=227.0c T: 124.34ns=227.33c 2202 AVX2 :VPMASKMOVQ ymm,ymm,[m256+4] L: [memory dep.] T: 50.37ns= 92.08c 2203 AVX2 :VPMASKMOVQ [m256+4],ymm,ymm L: [memory dep.] T: 16.96ns= 31.00c 2204 AVX2 :VPMASKMOVQ unaligned LSpair L: 67.28ns=123.0c T: 67.32ns=123.08c 2205 AVX2 :VBROADCASTSS xmm, xmm L: 1.00ns= 1.8c T: 0.55ns= 1.00c 2206 AVX2 :VBROADCASTSS ymm, xmm L: 1.23ns= 2.3c T: 0.55ns= 1.00c 2207 AVX2 :VBROADCASTSD ymm, xmm L: 1.23ns= 2.3c T: 0.55ns= 1.00c 2208 AVX2 :VPBROADCASTB xmm, xmm L: 2.19ns= 4.0c T: 0.55ns= 1.00c 2209 AVX2 :VPBROADCASTB ymm, xmm L: 2.73ns= 5.0c T: 1.09ns= 2.00c 2210 AVX2 :VPBROADCASTW xmm, xmm L: 2.19ns= 4.0c T: 0.55ns= 1.00c 2211 AVX2 :VPBROADCASTW ymm, xmm L: 2.73ns= 5.0c T: 1.09ns= 2.00c 2212 AVX2 :VPBROADCASTD xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2213 AVX2 :VPBROADCASTD ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2214 AVX2 :VPBROADCASTQ xmm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2215 AVX2 :VPBROADCASTQ ymm, xmm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2216 AVX2 :VBROADCASTI128 ymm, m128 L: [memory dep.] T: 0.68ns= 1.25c 2217 AVX2 :VEXTRACTI128 xmm, ymm, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2218 AVX2 :VINSERTI128 ym, ym, xm, im8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2219 AVX2 :VPERM2I128 ym, ym, ym, im8 L: 2.19ns= 4.0c T: 2.19ns= 4.00c 2220 AVX2 :VPERMD ymm, ymm, ymm L: 3.83ns= 7.0c T: 2.19ns= 4.00c 2221 AVX2 :VPERMQ ymm, ymm, imm8 L: 3.28ns= 6.0c T: 1.09ns= 2.00c 2222 AVX2 :VPERMPS ymm, ymm, ymm L: 3.83ns= 7.0c T: 2.19ns= 4.00c 2223 AVX2 :VPERMPD ymm, ymm, imm8 L: 3.28ns= 6.0c T: 1.19ns= 2.17c 2224 AVX2 :VPSLLVD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2225 AVX2 :VPSLLVD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2226 AVX2 :VPSLLVQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2227 AVX2 :VPSLLVQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2228 AVX2 :VPSRLVD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2229 AVX2 :VPSRLVD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2230 AVX2 :VPSRLVQ xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2231 AVX2 :VPSRLVQ ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2232 AVX2 :VPSRAVD xmm, xmm, xmm L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2233 AVX2 :VPSRAVD ymm, ymm, ymm L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2234 ADX :ADCX r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2235 ADX :ADCX r64, r16 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2236 ADX :ADOX r32, r32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2237 ADX :ADOX r64, r16 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2238 CLFLUSH :CLFLUSH [mem] L: [memory dep.] T: 45.12ns= 82.50c 2248 X86 :MOV r1_8, r2_8 L: 0.55ns= 1.0c T: 0.50ns= 0.92c 2249 X86 :MOV r1_16, r2_16 L: 0.55ns= 1.0c T: 0.27ns= 0.50c 2250 X86 :MOV r1_32, r2_32 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2251 AMD64 :MOV r1_64, r2_64 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2252 X86 :MOVSX r1_16, r2_8 L: 0.55ns= 1.0c T: 0.43ns= 0.79c 2253 X86 :MOVSX r1_32, r2_8 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2254 AMD64 :MOVSX r1_64, r2_8 L: 0.28ns= 0.5c T: 0.28ns= 0.50c 2255 X86 :MOVSX r1_32, r2_16 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2256 AMD64 :MOVSX r1_64, r2_16 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2257 AMD64 :MOVSXD r1_64, r2_32 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2258 X86 :MOVZX r1_16, r2_8 L: 0.55ns= 1.0c T: 0.43ns= 0.79c 2259 X86 :MOVZX r1_32, r2_8 L: 0.55ns= 1.0c T: 0.43ns= 0.79c 2260 AMD64 :MOVZX r1_64, r2_8 L: 0.55ns= 1.0c T: 0.36ns= 0.66c 2261 X86 :MOVZX r1_32, r2_16 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2262 AMD64 :MOVZX r1_64, r2_16 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2263 MMX :MOVQ mm1, mm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2264 SSE :MOVSS xmm1, xmm2 L: 0.64ns= 1.2c T: 0.55ns= 1.00c 2265 AVX :VMOVSS xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2266 SSE :MOVAPS xmm1, xmm2 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2267 AVX :VMOVAPS xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2268 SSE :MOVUPS xmm1, xmm2 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2269 AVX :VMOVUPS xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2270 SSE2 :MOVSD xmm1, xmm2 L: 0.64ns= 1.2c T: 0.55ns= 1.00c 2271 AVX :VMOVSD xmm1, xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2272 SSE2 :MOVAPD xmm1, xmm2 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2273 AVX :VMOVAPD xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2274 SSE2 :MOVUPD xmm1, xmm2 L: 0.27ns= 0.5c T: 0.27ns= 0.50c 2275 AVX :VMOVUPD xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2276 SSE2 :MOVDQA xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2277 AVX :VMOVDQA xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2278 SSE2 :MOVDQU xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2279 AVX :VMOVDQU xmm1, xmm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2280 AVX :VMOVAPS ymm1, ymm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2281 AVX :VMOVUPS ymm1, ymm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2282 AVX :VMOVAPD ymm1, ymm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2283 AVX :VMOVUPD ymm1, ymm2 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 2284 AVX :VMOVDQA ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2285 AVX :VMOVDQU ymm1, ymm2 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 2286 AVX2 :VPADDD+VADDPS ym, ym, ym L: 4.42ns= 8.1c T: 1.23ns= 2.25c 2287 AVX2 :VPADDQ+VADDPD ym, ym, ym L: 4.42ns= 8.1c T: 1.23ns= 2.25c 2288 AVX2 :VCMPPS+VPADDD ym, ym, ym L: 4.42ns= 8.1c T: 1.50ns= 2.75c 2289 AVX2 :VCMPPD+VPADDQ ym, ym, ym L: 4.42ns= 8.1c T: 1.50ns= 2.75c 2290 SSE :4xADDPS xm1,xm1 4x xm2,xm2 L: 6.56ns= 12.0c T: 6.56ns= 12.00c 2291 SSE :4xMULPS xm1,xm1 4x xm2,xm2 L: 6.56ns= 12.0c T: 6.56ns= 12.00c 2292 SSE2 :4xADDPD xm1,xm1 4x xm2,xm2 L: 6.56ns= 12.0c T: 6.56ns= 12.00c 2293 SSE2 :4xMULPD xm1,xm1 4x xm2,xm2 L: 8.75ns= 16.0c T: 8.75ns= 16.00c 2294 LNOP :LNOP3 [eax], eax L: [no true dep.] T: 0.21ns= 0.38c 2295 LNOP :LNOP4 [eax+disp8], eax L: [no true dep.] T: 0.27ns= 0.50c 2296 LNOP :LNOP5 [SIB+disp8], eax L: [no true dep.] T: 0.24ns= 0.44c 2297 LNOP :LNOP6 [SIB+disp8], ax L: [no true dep.] T: 0.21ns= 0.38c 2298 LNOP :LNOP7 [eax+disp32], eax L: [no true dep.] T: 0.24ns= 0.44c 2299 LNOP :LNOP8 [SIB+disp32], eax L: [no true dep.] T: 0.27ns= 0.50c 2300 LNOP :LNOP9 [SIB+disp32], ax L: [no true dep.] T: 0.31ns= 0.56c 2301 LNOP :2x66 LNOPA [SIB+disp32], ax L: [no true dep.] T: 0.34ns= 0.63c 2302 LNOP :3x66 LNOPB [SIB+disp32], ax L: [no true dep.] T: 0.38ns= 0.69c 2303 LNOP :4x66 LNOPC [SIB+disp32], ax L: [no true dep.] T: 0.41ns= 0.75c 2304 LNOP :5x66 LNOPD [SIB+disp32], ax L: [no true dep.] T: 0.44ns= 0.81c 2305 LNOP :6x66 LNOPE [SIB+disp32], ax L: [no true dep.] T: 0.48ns= 0.87c 2306 LNOP :7x66 LNOPF [SIB+disp32], ax L: [no true dep.] T: 0.50ns= 0.92c 2309 AVX2 :VGATHERDPS xmm, [xm32], xmm L: 38.29ns= 70.0c T: 26.25ns= 48.00c 2310 AVX2 :VGATHERDPS ymm, [ym32], ymm L: 48.68ns= 89.0c T: 36.10ns= 66.00c 2311 AVX2 :VGATHERQPS xmm, [xm64], xmm L: 27.35ns= 50.0c T: 22.97ns= 42.00c 2312 AVX2 :VGATHERQPS xmm, [ym64], xmm L: 32.27ns= 59.0c T: 27.35ns= 50.00c 2313 AVX2 :VGATHERDPD xmm, [xm32], xmm L: 36.65ns= 67.0c T: 21.88ns= 40.00c 2314 AVX2 :VGATHERDPD ymm, [xm32], ymm L: 48.13ns= 88.0c T: 27.35ns= 50.00c 2315 AVX2 :VGATHERQPD xmm, [xm64], xmm L: 35.55ns= 65.0c T: 21.88ns= 40.00c 2316 AVX2 :VGATHERQPD ymm, [ym64], ymm L: 47.58ns= 87.0c T: 27.35ns= 50.00c 2317 AVX2 :VPGATHERDD xmm, [xm32], xmm L: 38.29ns= 70.0c T: 26.25ns= 48.00c 2318 AVX2 :VPGATHERDD ymm, [ym32], ymm L: 48.68ns= 89.0c T: 36.10ns= 66.00c 2319 AVX2 :VPGATHERQD xmm, [xm64], xmm L: 27.35ns= 50.0c T: 22.97ns= 42.00c 2320 AVX2 :VPGATHERQD xmm, [ym64], xmm L: 32.27ns= 59.0c T: 27.35ns= 50.00c 2321 AVX2 :VPGATHERDQ xmm, [xm32], xmm L: 36.65ns= 67.0c T: 21.88ns= 40.00c 2322 AVX2 :VPGATHERDQ ymm, [xm32], ymm L: 48.13ns= 88.0c T: 27.35ns= 50.00c 2323 AVX2 :VPGATHERQQ xmm, [xm64], xmm L: 35.55ns= 65.0c T: 21.88ns= 40.00c 2324 AVX2 :VPGATHERQQ ymm, [ym64], ymm L: 47.58ns= 87.0c T: 27.35ns= 50.00c 4195 AVX :VMOVAPS+VEXTRACTF128 [m128], ym, im8 L: [memory dep.] T: 1.78ns= 3.25c 4196 AVX2 :VMOVDQA+VEXTRACTI128 [m128], ym, im8 L: [memory dep.] T: 1.78ns= 3.25c 4209 AVX :VMOVAPS+VINSERTF128 ym, [m128], im8 L: [memory dep.] T: 1.32ns= 2.42c 4210 AVX2 :VMOVDQA+VINSERTI128 ym, [m128], im8 L: [memory dep.] T: 1.32ns= 2.42c 4354 X86 :SHLD r1_16, r2_16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4355 X86 :SHLD r1_32, r2_32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4356 AMD64 :SHLD r1_64, r2_64, imm8 L: 20.78ns= 38.0c T: 20.78ns= 38.00c 4357 X86 :SHLD r1_16, r2_16, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4358 X86 :SHLD r1_32, r2_32, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4359 AMD64 :SHLD r1_64, r2_64, cl L: 15.31ns= 28.0c T: 15.31ns= 28.00c 4360 X86 :SHRD r1_16, r2_16, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4361 X86 :SHRD r1_32, r2_32, imm8 L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4362 AMD64 :SHRD r1_64, r2_64, imm8 L: 18.41ns= 33.7c T: 18.41ns= 33.67c 4363 X86 :SHRD r1_16, r2_16, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4364 X86 :SHRD r1_32, r2_32, cl L: 1.09ns= 2.0c T: 1.09ns= 2.00c 4365 AMD64 :SHRD r1_64, r2_64, cl L: 15.31ns= 28.0c T: 15.31ns= 28.00c 4366 X86 :ADC r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4367 X86 :ADC r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4368 X86 :ADC r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4369 AMD64 :ADC r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4370 X86 :ADC r16, imm16 L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4371 X86 :ADC r32, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4372 AMD64 :ADC r64, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4373 X86 :ADC al, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4374 X86 :ADC ax, imm16 L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4375 X86 :ADC eax, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4376 AMD64 :ADC rax, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4377 X86 :ADC r8, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4378 X86 :ADC r16, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4379 X86 :ADC r32, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4380 AMD64 :ADC r64, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4381 X86 :ADC r16, imm16_0 L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4382 X86 :ADC r32, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4383 AMD64 :ADC r64, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4384 X86 :ADC al, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4385 X86 :ADC ax, imm16_0 L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4386 X86 :ADC eax, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4387 AMD64 :ADC rax, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4388 X86 :SBB r8, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4389 X86 :SBB r16, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4390 X86 :SBB r32, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4391 AMD64 :SBB r64, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4392 X86 :SBB r16, imm16 L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4393 X86 :SBB r32, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4394 AMD64 :SBB r64, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4395 X86 :SBB al, imm8 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4396 X86 :SBB ax, imm16 L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4397 X86 :SBB eax, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4398 AMD64 :SBB rax, imm32 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4399 X86 :SBB r8, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4400 X86 :SBB r16, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4401 X86 :SBB r32, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4402 AMD64 :SBB r64, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4403 X86 :SBB r16, imm16_0 L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4404 X86 :SBB r32, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4405 AMD64 :SBB r64, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4406 X86 :SBB al, imm8_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4407 X86 :SBB ax, imm16_0 L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4408 X86 :SBB eax, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4409 AMD64 :SBB rax, imm32_0 L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4410 AMD64 :LEA r16, [disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4411 AMD64 :LEA r32, [disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4412 AMD64 :LEA r64, [disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4413 AMD64 :LEA r16, [r64] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4414 AMD64 :LEA r32, [r64] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4415 AMD64 :LEA r64, [r64] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4416 AMD64 :LEA r16, [r64 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4417 AMD64 :LEA r32, [r64 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4418 AMD64 :LEA r64, [r64 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4419 AMD64 :LEA r16, [r64 + disp32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4420 AMD64 :LEA r32, [r64 + disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4421 AMD64 :LEA r64, [r64 + disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4422 AMD64 :LEA r16, [r64 + r64] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4423 AMD64 :LEA r32, [r64 + r64] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4424 AMD64 :LEA r64, [r64 + r64] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4425 AMD64 :LEA r16, [r64 + r64 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4426 AMD64 :LEA r32, [r64 + r64 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4427 AMD64 :LEA r64, [r64 + r64 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4428 AMD64 :LEA r16, [r64 + r64 + disp32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4429 AMD64 :LEA r32, [r64 + r64 + disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4430 AMD64 :LEA r64, [r64 + r64 + disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4431 AMD64 :LEA r16, [r64 + r64 * 8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4432 AMD64 :LEA r32, [r64 + r64 * 8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4433 AMD64 :LEA r64, [r64 + r64 * 8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4434 AMD64 :LEA r16, [r64 + r64 * 8 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4435 AMD64 :LEA r32, [r64 + r64 * 8 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4436 AMD64 :LEA r64, [r64 + r64 * 8 + disp8] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4437 AMD64 :LEA r16, [r64 + r64 * 8 + disp32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4438 AMD64 :LEA r32, [r64 + r64 * 8 + disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4439 AMD64 :LEA r64, [r64 + r64 * 8 + disp32] L: 0.55ns= 1.0c T: 0.55ns= 1.00c 4440 AMD64 :ASP LEA r16, [disp32] L: 1.41ns= 2.6c T: 1.41ns= 2.58c 4441 AMD64 :ASP LEA r32, [disp32] L: 1.37ns= 2.5c T: 1.37ns= 2.50c 4442 AMD64 :ASP LEA r64, [disp32] L: 1.41ns= 2.6c T: 1.41ns= 2.58c 4443 AMD64 :ASP LEA r16, [r32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4444 AMD64 :ASP LEA r32, [r32] L: 1.19ns= 2.2c T: 1.19ns= 2.17c 4445 AMD64 :ASP LEA r64, [r32] L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4446 AMD64 :ASP LEA r16, [r32 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4447 AMD64 :ASP LEA r32, [r32 + disp8] L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4448 AMD64 :ASP LEA r64, [r32 + disp8] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4449 AMD64 :ASP LEA r16, [r32 + disp32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4450 AMD64 :ASP LEA r32, [r32 + disp32] L: 1.32ns= 2.4c T: 1.32ns= 2.42c 4451 AMD64 :ASP LEA r64, [r32 + disp32] L: 1.37ns= 2.5c T: 1.37ns= 2.50c 4452 AMD64 :ASP LEA r16, [r32 + r32] L: 6.02ns= 11.0c T: 5.88ns= 10.75c 4453 AMD64 :ASP LEA r32, [r32 + r32] L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4454 AMD64 :ASP LEA r64, [r32 + r32] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4455 AMD64 :ASP LEA r16, [r32 + r32 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4456 AMD64 :ASP LEA r32, [r32 + r32 + disp8] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4457 AMD64 :ASP LEA r64, [r32 + r32 + disp8] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4458 AMD64 :ASP LEA r16, [r32 + r32 + disp32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4459 AMD64 :ASP LEA r32, [r32 + r32 + disp32] L: 1.37ns= 2.5c T: 1.37ns= 2.50c 4460 AMD64 :ASP LEA r64, [r32 + r32 + disp32] L: 1.41ns= 2.6c T: 1.41ns= 2.58c 4461 AMD64 :ASP LEA r16, [r32 + r32 * 8] L: 6.02ns= 11.0c T: 5.83ns= 10.67c 4462 AMD64 :ASP LEA r32, [r32 + r32 * 8] L: 1.23ns= 2.3c T: 1.23ns= 2.25c 4463 AMD64 :ASP LEA r64, [r32 + r32 * 8] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4464 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp8] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4465 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp8] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4466 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp8] L: 1.28ns= 2.3c T: 1.28ns= 2.33c 4467 AMD64 :ASP LEA r16, [r32 + r32 * 8 + disp32] L: 6.02ns= 11.0c T: 6.02ns= 11.00c 4468 AMD64 :ASP LEA r32, [r32 + r32 * 8 + disp32] L: 1.37ns= 2.5c T: 1.37ns= 2.50c 4469 AMD64 :ASP LEA r64, [r32 + r32 * 8 + disp32] L: 1.41ns= 2.6c T: 1.41ns= 2.58c