Copyright (C) 1995-2018 FinalWire Ltd. All rights reserved. aida_bench32.dll build: 4.3.15794.0 Oct 31 2018 16:23:44 MS915G Arch:X64 CPUCount:2 NUMA:0 Freq: 3196.12MHz Priority:080 OS:6.1.7600 Memory: 1047928KB AllocGran:0x00010000 P:0x00001000 LP:0x00200000 Memory To Test:16384KB 4K DTLB: 32 2M DTLB: 32 CLFlush:64 ProcMask: 0x00000003 Features: X86,TSC,X87,CMOV,MMX,SSE,SSE2,SSE3,CMPX8,HTT,CLFLUSH,LNOP,PSE, CPU#000 Vendor: GenuineIntel Family: f Model: 04 Stepping: 3 CoreType:0x20000f43 CPU#000 Type: " Intel(R) Pentium(R) 4 CPU 3.20GHz" CPU#000 AffMask: 0x00000001 CPU#000 PhysMask:0x00000003 CPU#000 APIC_ID:0x00000000 Phys_ID:000 Core_ID:00 SMT_ID:00 CPU#000 L1I cache: 12K uops trace, 8 way, SMask:00000003 CPU#000 L1D cache: 16KB, 64 byte cache line, 8 way, SMask:00000003 CPU#000 L2 cache: 2048KB, 64 byte cache line, 8 way, SMask:00000003, inclusive CPU#000 L1D 4K+2M TLB: 64 entries, full, SMask:00000003 CPU#000 L1I 4K+2M TLB: 64 entries, full, SMask:00000003 CPU#001 Vendor: GenuineIntel Family: f Model: 04 Stepping: 3 CoreType:0x20000f43 CPU#001 Type: " Intel(R) Pentium(R) 4 CPU 3.20GHz" CPU#001 AffMask: 0x00000002 CPU#001 PhysMask:0x00000003 CPU#001 APIC_ID:0x00000001 Phys_ID:000 Core_ID:00 SMT_ID:01 CPU#001 L1I cache: 12K uops trace, 8 way, SMask:00000003 CPU#001 L1D cache: 16KB, 64 byte cache line, 8 way, SMask:00000003 CPU#001 L2 cache: 2048KB, 64 byte cache line, 8 way, SMask:00000003, inclusive CPU#001 L1D 4K+2M TLB: 64 entries, full, SMask:00000003 CPU#001 L1I 4K+2M TLB: 64 entries, full, SMask:00000003 Instruction Latency: Used CPUs: 1 ProcMask: 0x00000002 0 X86 :NOP L: [no true dep.] T: 0.11ns= 0.36c 1 X86 :0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 2 X86 : 2x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 3 X86 : 3x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 4 X86 : 4x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 5 X86 : 5x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 6 X86 : 6x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 7 X86 : 7x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 8 X86 : 8x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 9 X86 : 9x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 10 X86 :10x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 11 X86 :11x 0x66 NOP L: [no true dep.] T: 0.27ns= 0.85c 12 X86 :12x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 13 X86 :13x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 14 X86 :14x 0x66 NOP L: [no true dep.] T: 0.11ns= 0.35c 15 SSE2 :PAUSE L: [no true dep.] T: 16.97ns= 54.25c 16 X86 :MOV r8, imm8 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 17 X86 :MOV r16, imm16 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 18 X86 :MOV r32, imm32 L: 0.12ns= 0.4c T: 0.12ns= 0.38c 20 X86 :MOV r8, r8 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 21 X86 :MOV r16, r16 L: 0.31ns= 1.0c T: 0.25ns= 0.81c 22 X86 :MOV r32, r32 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 24 X86 :MOV r8, [m8] L: 1.56ns= 5.0c T: 0.31ns= 1.00c 25 X86 :MOV r16, [m16] L: 1.56ns= 5.0c T: 0.31ns= 1.00c 26 X86 :MOV r32, [m32] L: 1.25ns= 4.0c T: 0.31ns= 1.00c 28 X86 :MOV [m8], r8 L: [memory dep.] T: 0.55ns= 1.75c 29 X86 :MOV [m16], r16 L: [memory dep.] T: 0.57ns= 1.83c 30 X86 :MOV [m32], r32 L: [memory dep.] T: 0.57ns= 1.83c 31 X86 :MOV [m32 + 8], r32 L: [memory dep.] T: 0.57ns= 1.83c 34 X86 :MOV r8,[m8]+MOV [m8],r8 L: 2.50ns= 8.0c T: 0.34ns= 1.08c 35 X86 :MOV r16,[m16]+MOV [m16],r16 L: 2.50ns= 8.0c T: 0.57ns= 1.83c 36 X86 :MOV r32,[m32]+MOV [m32],r32 L: 1.96ns= 6.3c T: 0.39ns= 1.25c 38 SSE2 :MOVNTI [m32], r32 L: [memory dep.] T: 1.67ns= 1.67c 40 CMOV :CMOVNZ r16, r16 L: 2.97ns= 9.5c T: 0.16ns= 0.50c 41 CMOV :CMOVNZ r32, r32 L: 2.97ns= 9.5c T: 0.16ns= 0.51c 43 X86 :MOVSX r16, r8 L: 0.63ns= 2.0c T: 0.39ns= 1.25c 44 X86 :MOVSX r32, r8 L: 0.31ns= 1.0c T: 0.16ns= 0.51c 46 X86 :MOVSX r32, r16 L: 0.31ns= 1.0c T: 0.26ns= 0.82c 49 X86 :MOVZX r16, r8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 50 X86 :MOVZX r32, r8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 52 X86 :MOVZX r32, r16 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 54 X86 :XCHG r8, r8 L: 0.63ns= 2.0c T: 0.34ns= 1.08c 55 X86 :XCHG r16, r16 L: 0.63ns= 2.0c T: 0.37ns= 1.17c 56 X86 :XCHG r32, r32 L: 0.63ns= 2.0c T: 0.34ns= 1.08c 58 X86 :XCHG r1_8, r2_8 L: 4.38ns= 14.0c T: 0.31ns= 1.00c 59 X86 :XCHG r1_16, r2_16 L: 0.47ns= 1.5c T: 0.37ns= 1.17c 60 X86 :XCHG r1_32, r2_32 L: 0.47ns= 1.5c T: 0.47ns= 1.50c 62 X86 :XCHG r8, [m8] L: 26.31ns= 84.1c T: 29.07ns= 92.92c 63 X86 :XCHG r16, [m16] L: 25.50ns= 81.5c T: 28.76ns= 91.92c 64 X86 :XCHG r32, [m32] L: 25.50ns= 81.5c T: 28.78ns= 92.00c 66 X86 :ADD r32, 0x04000 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 67 X86 :ADD r32, 0x08000 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 68 X86 :ADD r32, 0x10000 L: 0.31ns= 1.0c T: 0.22ns= 0.69c 69 X86 :ADD r32, 0x20000 L: 0.31ns= 1.0c T: 0.22ns= 0.69c 70 X86 :ADD r8, r8 L: 0.31ns= 1.0c T: 0.27ns= 0.86c 71 X86 :ADD r16, r16 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 72 X86 :ADD r32, r32 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 74 X86 :ADD r8, [m8] L: 1.56ns= 5.0c T: 0.31ns= 1.00c 75 X86 :ADD r16, [m16] L: 1.56ns= 5.0c T: 0.63ns= 2.00c 76 X86 :ADD r32, [m32] L: 1.56ns= 5.0c T: 0.31ns= 1.00c 78 X86 :ADD [m8], r8 L: 1.56ns= 5.0c T: 0.44ns= 1.42c 79 X86 :ADD [m16], r16 L: 1.56ns= 5.0c T: 0.50ns= 1.58c 80 X86 :ADD [m32], r32 L: 1.77ns= 5.7c T: 0.55ns= 1.75c 81 X86 :ADD [m32 + 8], r32 L: 1.56ns= 5.0c T: 0.55ns= 1.75c 84 X86 :LOCK ADD [m8], r8 L: 28.47ns= 91.0c T: 28.37ns= 90.67c 85 X86 :LOCK ADD [m16], r16 L: 27.74ns= 88.7c T: 27.90ns= 89.17c 86 X86 :LOCK ADD [m32], r32 L: 27.72ns= 88.6c T: 27.66ns= 88.42c 87 X86 :LOCK ADD [m32 + 8], r32 L: 27.72ns= 88.6c T: 27.61ns= 88.25c 90 X86 :ADD r8, imm8 L: 0.31ns= 1.0c T: 0.12ns= 0.37c 91 X86 :ADD r16, imm8 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 92 X86 :ADD r32, imm8 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 94 X86 :ADD r16, imm16 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 95 X86 :ADD r32, imm32 L: 0.31ns= 1.0c T: 0.12ns= 0.39c 97 X86 :ADD [m8], imm8 L: 1.56ns= 5.0c T: 0.52ns= 1.67c 98 X86 :ADD [m16], imm8 L: 1.80ns= 5.8c T: 0.52ns= 1.67c 99 X86 :ADD [m32], imm8 L: 1.56ns= 5.0c T: 0.52ns= 1.67c 101 X86 :ADD [m16], imm16 L: 1.56ns= 5.0c T: 0.55ns= 1.75c 102 X86 :ADD [m32], imm32 L: 1.56ns= 5.0c T: 0.57ns= 1.83c 104 X86 :ADD al, imm8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 105 X86 :ADD ax, imm16 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 106 X86 :ADD eax, imm32 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 108 X86 :SUB r8, r8 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 109 X86 :SUB r16, r16 L: 0.31ns= 1.0c T: 0.11ns= 0.35c 110 X86 :SUB r32, r32 L: 0.11ns= 0.3c T: 0.11ns= 0.34c 112 X86 :SUB r1_8, r2_8 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 113 X86 :SUB r1_16, r2_16 L: 0.34ns= 1.1c T: 0.25ns= 0.81c 114 X86 :SUB r1_32, r2_32 L: 0.31ns= 1.0c T: 0.10ns= 0.32c 116 X86 :ADC r8, r8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 117 X86 :ADC r16, r16 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 118 X86 :ADC r32, r32 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 120 X86 :SBB r8, r8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 121 X86 :SBB r16, r16 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 122 X86 :SBB r32, r32 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 124 X86 :SBB r1_8, r2_8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 125 X86 :SBB r1_16, r2_16 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 126 X86 :SBB r1_32, r2_32 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 128 X86 :CMP r8, r8 L: [no true dep.] T: 0.12ns= 0.39c 129 X86 :CMP r16, r16 L: [no true dep.] T: 0.12ns= 0.39c 130 X86 :CMP r32, r32 L: [no true dep.] T: 0.12ns= 0.39c 132 X86 :CMP r1_8, r2_8 L: [no true dep.] T: 0.13ns= 0.42c 133 X86 :CMP r1_16, r2_16 L: [no true dep.] T: 0.17ns= 0.55c 134 X86 :CMP r1_32, r2_32 L: [no true dep.] T: 0.12ns= 0.39c 136 X86 :AND r8, r8 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 137 X86 :AND r16, r16 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 138 X86 :AND r32, r32 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 140 X86 :AND r1_8, r2_8 L: 0.31ns= 1.0c T: 0.13ns= 0.42c 141 X86 :AND r1_16, r2_16 L: 0.31ns= 1.0c T: 0.14ns= 0.46c 142 X86 :AND r1_32, r2_32 L: 0.31ns= 1.0c T: 0.14ns= 0.46c 144 X86 :OR r8, r8 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 145 X86 :OR r16, r16 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 146 X86 :OR r32, r32 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 148 X86 :OR r1_8, r2_8 L: 0.31ns= 1.0c T: 0.29ns= 0.92c 149 X86 :OR r1_16, r2_16 L: 0.31ns= 1.0c T: 0.14ns= 0.46c 150 X86 :OR r1_32, r2_32 L: 0.31ns= 1.0c T: 0.14ns= 0.46c 152 X86 :XOR r8, r8 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 153 X86 :XOR r16, r16 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 154 X86 :XOR r32, r32 L: 0.16ns= 0.5c T: 0.16ns= 0.50c 156 X86 :XOR r1_8, r2_8 L: 0.31ns= 1.0c T: 0.14ns= 0.46c 157 X86 :XOR r1_16, r2_16 L: 0.31ns= 1.0c T: 0.14ns= 0.46c 158 X86 :XOR r1_32, r2_32 L: 0.39ns= 1.3c T: 0.16ns= 0.51c 160 X86 :NEG r8 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 161 X86 :NEG r16 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 162 X86 :NEG r32 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 164 X86 :NOT r8 L: 0.31ns= 1.0c T: 0.18ns= 0.59c 165 X86 :NOT r16 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 166 X86 :NOT r32 L: 0.31ns= 1.0c T: 0.19ns= 0.59c 168 X86 :TEST r8, r8 L: [no true dep.] T: 0.18ns= 0.58c 169 X86 :TEST r16, r16 L: [no true dep.] T: 0.18ns= 0.59c 170 X86 :TEST r32, r32 L: [no true dep.] T: 0.18ns= 0.59c 172 X86 :TEST r1_8, r2_8 L: [no true dep.] T: 0.19ns= 0.60c 173 X86 :TEST r1_16, r2_16 L: [no true dep.] T: 0.26ns= 0.82c 174 X86 :TEST r1_32, r2_32 L: [no true dep.] T: 0.18ns= 0.59c 176 X86 :BT r16, r16 L: [no true dep.] T: 2.82ns= 9.00c 177 X86 :BT r32, r32 L: [no true dep.] T: 2.82ns= 9.00c 179 X86 :BT r16, imm8 L: [no true dep.] T: 2.50ns= 8.00c 180 X86 :BT r32, imm8 L: [no true dep.] T: 2.50ns= 8.00c 182 X86 :BTC r16, r16 L: 2.82ns= 9.0c T: 2.82ns= 9.00c 183 X86 :BTC r32, r32 L: 2.82ns= 9.0c T: 2.82ns= 9.00c 185 X86 :BTC r16, imm8 L: 2.50ns= 8.0c T: 2.50ns= 8.00c 186 X86 :BTC r32, imm8 L: 2.50ns= 8.0c T: 2.50ns= 8.00c 188 X86 :BTR r16, r16 L: 2.82ns= 9.0c T: 2.82ns= 9.00c 189 X86 :BTR r32, r32 L: 2.82ns= 9.0c T: 2.82ns= 9.00c 191 X86 :BTR r16, imm8 L: 2.50ns= 8.0c T: 2.50ns= 8.00c 192 X86 :BTR r32, imm8 L: 2.53ns= 8.1c T: 2.50ns= 8.00c 194 X86 :BTS r16, r16 L: 2.82ns= 9.0c T: 2.82ns= 9.00c 195 X86 :BTS r32, r32 L: 2.82ns= 9.0c T: 2.82ns= 9.00c 197 X86 :BTS r16, imm8 L: 2.50ns= 8.0c T: 2.50ns= 8.00c 198 X86 :BTS r32, imm8 L: 2.50ns= 8.0c T: 2.50ns= 8.00c 200 X86 :SETC r8 L: 0.42ns= 1.3c T: 0.42ns= 1.33c 201 X86 :INC r8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 202 X86 :INC r16 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 203 X86 :INC r32 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 205 X86 :LEA r16, [r32 + r32] L: 1.25ns= 4.0c T: 0.65ns= 2.08c 206 X86 :LEA r32, [r32 + r32] L: 0.31ns= 1.0c T: 0.11ns= 0.36c 208 X86 :LEA r16, [r32 + r32 + disp8] L: 1.25ns= 4.0c T: 0.70ns= 2.25c 209 X86 :LEA r32, [r32 + r32 + disp8] L: 0.63ns= 2.0c T: 0.24ns= 0.77c 211 X86 :LEA r16, [r32 + r32 * 8] L: 1.25ns= 4.0c T: 0.65ns= 2.08c 212 X86 :LEA r32, [r32 + r32 * 8] L: 0.63ns= 2.0c T: 0.25ns= 0.81c 214 X86 :LEA r16, [r32 + r32 * 8 + disp8] L: 1.25ns= 4.0c T: 0.70ns= 2.25c 215 X86 :LEA r32, [r32 + r32 * 8 + disp8] L: 0.94ns= 3.0c T: 0.39ns= 1.25c 217 X86 :SHL r8, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 218 X86 :SHL r16, 1 L: 0.31ns= 1.0c T: 0.21ns= 0.68c 219 X86 :SHL r32, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 221 X86 :SHL r8, imm8 L: 0.44ns= 1.4c T: 0.29ns= 0.92c 222 X86 :SHL r16, imm8 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 223 X86 :SHL r32, imm8 L: 0.44ns= 1.4c T: 0.37ns= 1.17c 225 X86 :SHL r8, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 226 X86 :SHL r16, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 227 X86 :SHL r32, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 229 X86 :SHR r8, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 230 X86 :SHR r16, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 231 X86 :SHR r32, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 233 X86 :SHR r8, imm8 L: 0.44ns= 1.4c T: 0.39ns= 1.25c 234 X86 :SHR r16, imm8 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 235 X86 :SHR r32, imm8 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 237 X86 :SHR r8, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 238 X86 :SHR r16, cl L: 0.65ns= 2.1c T: 0.63ns= 2.00c 239 X86 :SHR r32, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 241 X86 :SAR r8, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 242 X86 :SAR r16, 1 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 243 X86 :SAR r32, 1 L: 0.37ns= 1.2c T: 0.21ns= 0.68c 245 X86 :SAR r8, imm8 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 246 X86 :SAR r16, imm8 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 247 X86 :SAR r32, imm8 L: 0.31ns= 1.0c T: 0.18ns= 0.58c 249 X86 :SAR r8, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 250 X86 :SAR r16, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 251 X86 :SAR r32, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 253 X86 :SHLD r1_16, r1_16, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 254 X86 :SHLD r1_32, r1_32, imm8 L: 2.82ns= 9.0c T: 2.19ns= 7.00c 256 X86 :SHLD r1_16, r1_16, cl L: 3.75ns= 12.0c T: 3.75ns= 12.00c 257 X86 :SHLD r1_32, r1_32, cl L: 2.82ns= 9.0c T: 2.50ns= 8.00c 259 X86 :SHRD r1_16, r1_16, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 260 X86 :SHRD r1_32, r1_32, imm8 L: 2.82ns= 9.0c T: 2.19ns= 7.00c 262 X86 :SHRD r1_16, r1_16, cl L: 3.75ns= 12.0c T: 3.75ns= 12.00c 263 X86 :SHRD r1_32, r1_32, cl L: 2.82ns= 9.0c T: 2.50ns= 8.00c 265 X86 :ROL r8, 1 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 266 X86 :ROL r16, 1 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 267 X86 :ROL r32, 1 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 269 X86 :ROL r8, imm8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 270 X86 :ROL r16, imm8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 271 X86 :ROL r32, imm8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 273 X86 :ROL r8, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 274 X86 :ROL r16, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 275 X86 :ROL r32, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 277 X86 :ROR r8, 1 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 278 X86 :ROR r16, 1 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 279 X86 :ROR r32, 1 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 281 X86 :ROR r8, imm8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 282 X86 :ROR r16, imm8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 283 X86 :ROR r32, imm8 L: 0.37ns= 1.2c T: 0.29ns= 0.92c 285 X86 :ROR r8, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 286 X86 :ROR r16, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 287 X86 :ROR r32, cl L: 0.63ns= 2.0c T: 0.63ns= 2.00c 289 X86 :RCL r8, 1 L: 2.19ns= 7.0c T: 2.19ns= 7.00c 290 X86 :RCL r16, 1 L: 2.19ns= 7.0c T: 2.19ns= 7.00c 291 X86 :RCL r32, 1 L: 2.19ns= 7.0c T: 2.19ns= 7.00c 293 X86 :RCL r8, imm8 L: 7.82ns= 25.0c T: 7.82ns= 25.00c 294 X86 :RCL r16, imm8 L: 7.82ns= 25.0c T: 7.82ns= 25.00c 295 X86 :RCL r32, imm8 L: 7.82ns= 25.0c T: 7.82ns= 25.00c 297 X86 :RCL r8, cl L: 7.93ns= 25.3c T: 7.93ns= 25.33c 298 X86 :RCL r16, cl L: 7.93ns= 25.3c T: 7.82ns= 25.00c 299 X86 :RCL r32, cl L: 7.93ns= 25.3c T: 7.93ns= 25.33c 301 X86 :RCR r8, 1 L: 2.19ns= 7.0c T: 2.19ns= 7.00c 302 X86 :RCR r16, 1 L: 2.19ns= 7.0c T: 2.19ns= 7.00c 303 X86 :RCR r32, 1 L: 2.22ns= 7.1c T: 2.19ns= 7.00c 305 X86 :RCR r8, imm8 L: 7.82ns= 25.0c T: 7.82ns= 25.00c 306 X86 :RCR r16, imm8 L: 7.82ns= 25.0c T: 7.82ns= 25.00c 307 X86 :RCR r32, imm8 L: 7.82ns= 25.0c T: 7.82ns= 25.00c 309 X86 :RCR r8, cl L: 7.93ns= 25.3c T: 7.93ns= 25.33c 310 X86 :RCR r16, cl L: 7.93ns= 25.3c T: 7.82ns= 25.00c 311 X86 :RCR r32, cl L: 7.93ns= 25.3c T: 7.82ns= 25.00c 313 X86 :BSF r16, r16 L: 5.01ns= 16.0c T: 0.31ns= 1.00c 314 X86 :BSF r32, r32 L: 5.01ns= 16.0c T: 0.31ns= 1.00c 316 X86 :BSR r16, r16 L: 5.01ns= 16.0c T: 0.31ns= 1.00c 317 X86 :BSR r32, r32 L: 5.01ns= 16.0c T: 0.31ns= 1.00c 319 X86 :BSWAP r32 L: 0.31ns= 1.0c T: 0.16ns= 0.50c 327 X86 :IMUL r16, r16 L: 3.13ns= 10.0c T: 0.31ns= 1.00c 328 X86 :IMUL r32, r32 L: 3.13ns= 10.0c T: 0.31ns= 1.00c 330 X86 :IMUL r16, r16, imm8 L: 3.44ns= 11.0c T: 0.21ns= 0.67c 331 X86 :IMUL r32, r32, imm8 L: 3.13ns= 10.0c T: 0.31ns= 1.00c 333 X86 :IMUL r16, r16, imm16 L: 3.44ns= 11.0c T: 0.52ns= 1.67c 334 X86 :IMUL r32, r32, imm32 L: 3.13ns= 10.0c T: 0.31ns= 1.00c 336 X86 :IMUL r8 (ah) L: 3.44ns= 11.0c T: 3.13ns= 10.00c 337 X86 :IMUL r16 (dx) L: 3.75ns= 12.0c T: 3.47ns= 11.08c 338 X86 :IMUL r32 (edx) L: 3.44ns= 11.0c T: 3.44ns= 11.00c 340 X86 :MUL r8 (ah) L: 3.44ns= 11.0c T: 3.13ns= 10.00c 341 X86 :MUL r16 (dx) L: 3.75ns= 12.0c T: 3.44ns= 11.00c 342 X86 :MUL r32 (edx) L: 3.44ns= 11.0c T: 3.44ns= 11.00c 344 X86 :IMUL r8 (al) L: 3.13ns= 10.0c T: 3.13ns= 10.00c 345 X86 :IMUL r16 (ax) L: 3.44ns= 11.0c T: 3.44ns= 11.00c 346 X86 :IMUL r32 (eax) L: 3.75ns= 12.0c T: 3.44ns= 11.00c 348 X86 :MUL r8 (al) L: 3.13ns= 10.0c T: 3.13ns= 10.00c 349 X86 :MUL r16 (ax) L: 3.44ns= 11.0c T: 3.44ns= 11.00c 350 X86 :MUL r32 (eax) L: 3.75ns= 12.0c T: 3.44ns= 11.00c 352 X86 :IDIV r8 14/ 7b (full) L: 24.90ns= 79.6c T: 24.17ns= 77.25c 353 X86 :IDIV r8 12/ 7b ax upd L: 24.40ns= 78.0c T: 24.09ns= 77.00c 354 X86 :IDIV r8 7/ 7b ax upd L: 24.40ns= 78.0c T: 24.09ns= 77.00c 355 X86 :IDIV r8 4/ 7b ax upd L: [no true dep.] T: 24.09ns= 77.00c 356 X86 :IDIV r8 0/ 7b L: [no true dep.] T: 23.78ns= 76.00c 357 X86 :IDIV r8 11/ 4b ax upd L: 24.40ns= 78.0c T: 24.09ns= 77.00c 358 X86 :IDIV r8 8/ 4b ax upd L: [no true dep.] T: 24.09ns= 77.00c 359 X86 :IDIV r8 4/ 4b ax upd L: 24.40ns= 78.0c T: 24.09ns= 77.00c 360 X86 :IDIV r8 0/ 4b L: [no true dep.] T: 23.78ns= 76.00c 361 X86 :IDIV r8 2^12/2^6 ax upd L: [no true dep.] T: 24.09ns= 77.00c 362 X86 :IDIV r8 1/1 L: 24.09ns= 77.0c T: 23.78ns= 76.00c 363 X86 :IDIV r8 1/1 ax upd L: 24.40ns= 78.0c T: 24.09ns= 77.00c 364 X86 :IDIV r16 30/15b (full) L: 25.03ns= 80.0c T: 24.72ns= 79.00c 365 X86 :IDIV r16 24/15b ax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 366 X86 :IDIV r16 15/15b ax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 367 X86 :IDIV r16 8/15b ax/dx upd L: [no true dep.] T: 25.03ns= 80.00c 368 X86 :IDIV r16 0/15b L: [no true dep.] T: 24.72ns= 79.00c 369 X86 :IDIV r16 23/ 8b ax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 370 X86 :IDIV r16 16/ 8b ax upd L: [no true dep.] T: 24.72ns= 79.00c 371 X86 :IDIV r16 8/ 8b ax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 372 X86 :IDIV r16 0/ 8b L: [no true dep.] T: 24.72ns= 79.00c 373 X86 :IDIV r16 2^28/2^14 ax/dx L: [no true dep.] T: 25.03ns= 80.00c 374 X86 :IDIV r16 1/1 L: 25.03ns= 80.0c T: 24.72ns= 79.00c 375 X86 :IDIV r16 1/1 ax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 376 X86 :IDIV r16 1/1 ax/dx upd L: 25.34ns= 81.0c T: 25.03ns= 80.00c 377 X86 :IDIV r32 62/31b (full) L: 25.03ns= 80.0c T: 24.72ns= 79.00c 378 X86 :IDIV r32 62/31b 0 rem. L: 25.03ns= 80.0c T: 24.72ns= 79.00c 379 X86 :IDIV r32 48/31b eax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 380 X86 :IDIV r32 31/31b eax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 381 X86 :IDIV r32 16/31b eax/edx L: [no true dep.] T: 10.64ns= 34.00c 382 X86 :IDIV r32 0/31b L: [no true dep.] T: 24.72ns= 79.00c 383 X86 :IDIV r32 47/16b eax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 384 X86 :IDIV r32 32/16b eax upd L: [no true dep.] T: 24.72ns= 79.00c 385 X86 :IDIV r32 16/16b eax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 386 X86 :IDIV r32 0/16b L: [no true dep.] T: 24.72ns= 79.00c 387 X86 :IDIV r32 2^60/2^30 eax/edx L: [no true dep.] T: 10.64ns= 34.00c 388 X86 :IDIV r32 1/1 L: 25.03ns= 80.0c T: 24.72ns= 79.00c 389 X86 :IDIV r32 1/1 eax upd L: 24.72ns= 79.0c T: 24.72ns= 79.00c 390 X86 :IDIV r32 1/1 eax/edx upd L: 10.64ns= 34.0c T: 10.64ns= 34.00c 405 X86 :DIV r8 16/ 8b (full) L: 23.94ns= 76.5c T: 23.73ns= 75.83c 406 X86 :DIV r8 12/ 8b ax upd L: 23.78ns= 76.0c T: 23.52ns= 75.17c 407 X86 :DIV r8 8/ 8b ax upd L: 23.78ns= 76.0c T: 23.52ns= 75.17c 408 X86 :DIV r8 4/ 8b ax upd L: [no true dep.] T: 23.52ns= 75.17c 409 X86 :DIV r8 0/ 8b L: [no true dep.] T: 23.15ns= 74.00c 410 X86 :DIV r8 12/ 4b ax upd L: 23.78ns= 76.0c T: 23.52ns= 75.17c 411 X86 :DIV r8 8/ 4b ax upd L: [no true dep.] T: 23.52ns= 75.17c 412 X86 :DIV r8 4/ 4b ax upd L: 23.78ns= 76.0c T: 23.52ns= 75.17c 413 X86 :DIV r8 0/ 4b L: [no true dep.] T: 23.15ns= 74.00c 414 X86 :DIV r8 2^14/2^7 ax upd L: [no true dep.] T: 23.52ns= 75.17c 415 X86 :DIV r8 1/1 L: 23.47ns= 75.0c T: 23.15ns= 74.00c 416 X86 :DIV r8 1/1 ax upd L: 23.78ns= 76.0c T: 23.52ns= 75.17c 417 X86 :DIV r16 32/16b (full) L: 22.84ns= 73.0c T: 22.84ns= 73.00c 418 X86 :DIV r16 30/15b 0 rem. L: 22.84ns= 73.0c T: 22.84ns= 73.00c 419 X86 :DIV r16 24/16b ax upd L: 22.84ns= 73.0c T: 22.84ns= 73.00c 420 X86 :DIV r16 16/16b ax upd L: 22.84ns= 73.0c T: 22.84ns= 73.00c 421 X86 :DIV r16 8/16b ax/dx upd L: [no true dep.] T: 23.15ns= 74.00c 422 X86 :DIV r16 0/16b L: [no true dep.] T: 22.84ns= 73.00c 423 X86 :DIV r16 24/ 8b ax upd L: 22.84ns= 73.0c T: 22.84ns= 73.00c 424 X86 :DIV r16 16/ 8b ax upd L: [no true dep.] T: 23.15ns= 74.00c 425 X86 :DIV r16 8/ 8b ax upd L: 22.84ns= 73.0c T: 22.84ns= 73.00c 426 X86 :DIV r16 0/ 8b L: [no true dep.] T: 22.84ns= 73.00c 427 X86 :DIV r16 1/1 L: 22.84ns= 73.0c T: 22.84ns= 73.00c 428 X86 :DIV r16 1/1 ax upd L: 22.84ns= 73.0c T: 22.84ns= 73.00c 429 X86 :DIV r16 1/1 ax/dx upd L: 23.15ns= 74.0c T: 23.15ns= 74.00c 430 X86 :DIV r32 64/32b (full) L: 23.78ns= 76.0c T: 23.78ns= 76.00c 431 X86 :DIV r32 62/31b 0 rem. L: 23.78ns= 76.0c T: 23.78ns= 76.00c 432 X86 :DIV r32 48/32b eax upd L: 23.78ns= 76.0c T: 23.78ns= 76.00c 433 X86 :DIV r32 32/32b eax upd L: 23.78ns= 76.0c T: 23.78ns= 76.00c 434 X86 :DIV r32 16/32b eax/edx L: [no true dep.] T: 10.64ns= 34.00c 435 X86 :DIV r32 0/32b L: [no true dep.] T: 23.78ns= 76.00c 436 X86 :DIV r32 48/16b eax upd L: 23.78ns= 76.0c T: 23.78ns= 76.00c 437 X86 :DIV r32 32/16b eax upd L: [no true dep.] T: 23.78ns= 76.00c 438 X86 :DIV r32 16/16b eax upd L: 23.78ns= 76.0c T: 23.78ns= 76.00c 439 X86 :DIV r32 0/16b L: [no true dep.] T: 23.78ns= 76.00c 440 X86 :DIV r32 2^62/2^31 eax/edx L: [no true dep.] T: 10.64ns= 34.00c 441 X86 :DIV r32 1/1 L: 23.78ns= 76.0c T: 23.78ns= 76.00c 442 X86 :DIV r32 1/1 eax upd L: 23.78ns= 76.0c T: 23.78ns= 76.00c 443 X86 :DIV r32 1/1 eax/edx upd L: 10.64ns= 34.0c T: 10.64ns= 34.00c 458 X86 :CBW L: 0.63ns= 2.0c T: 0.63ns= 2.00c 459 X86 :CWDE L: 0.63ns= 2.0c T: 0.63ns= 2.00c 461 X86 :CWD L: 0.31ns= 1.0c T: 0.31ns= 1.00c 462 X86 :CDQ L: 0.18ns= 0.6c T: 0.18ns= 0.58c 464 X86 :CLC L: 2.48ns= 7.9c T: 2.48ns= 7.92c 465 X86 :STC L: 2.53ns= 8.1c T: 2.50ns= 8.00c 466 X86 :CMC L: 4.67ns= 14.9c T: 4.67ns= 14.92c 467 X86 :CLD L: 16.90ns= 54.0c T: 16.90ns= 54.00c 468 X86 :STD L: 16.90ns= 54.0c T: 16.90ns= 54.00c 469 X86 :AAA L: 8.13ns= 26.0c T: 8.13ns= 26.00c 470 X86 :AAD L: 2.01ns= 6.4c T: 2.01ns= 6.42c 471 X86 :AAM L: 11.11ns= 35.5c T: 11.11ns= 35.50c 472 X86 :AAS L: 8.13ns= 26.0c T: 8.13ns= 26.00c 473 X86 :DAA L: 9.07ns= 29.0c T: 9.07ns= 29.00c 474 X86 :DAS L: 9.07ns= 29.0c T: 9.07ns= 29.00c 475 X86 :LAHF L: 9.07ns= 29.0c T: 9.07ns= 29.00c 476 X86 :SAHF L: 9.07ns= 29.0c T: 9.07ns= 29.00c 477 X86 :PUSHA L: [no true dep.] T: 4.77ns= 15.25c 478 X86 :POPA L: [no true dep.] T: 4.38ns= 14.00c 479 X86 :PUSHA + POPA L: 8.13ns= 26.0c T: 8.32ns= 26.58c 480 X86 :PUSHAD L: [no true dep.] T: 4.75ns= 15.17c 481 X86 :POPAD L: [no true dep.] T: 4.46ns= 14.25c 482 X86 :PUSHAD + POPAD L: 8.13ns= 26.0c T: 8.16ns= 26.08c 483 X86 :PUSH r16 L: [no true dep.] T: 0.57ns= 1.83c 484 X86 :POP r16 L: [no true dep.] T: 0.37ns= 1.17c 485 X86 :PUSH r16 + POP r16 L: 1.88ns= 6.0c T: 0.63ns= 2.00c 486 X86 :PUSH r32 L: [no true dep.] T: 0.60ns= 1.92c 487 X86 :POP r32 L: [no true dep.] T: 0.31ns= 1.00c 488 X86 :PUSH r32 + POP r32 L: 1.59ns= 5.1c T: 0.73ns= 2.33c 489 X86 :PUSH imm8 L: [no true dep.] T: 0.60ns= 1.92c 490 X86 :PUSH imm8 + POP r32 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 491 X86 :PUSH imm32 L: [no true dep.] T: 0.60ns= 1.92c 492 X86 :PUSH imm32 + POP r32 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 493 X86 :PUSH [m16] L: [no true dep.] T: 0.57ns= 1.83c 494 X86 :POP [m16] L: [no true dep.] T: 3.15ns= 10.08c 495 X86 :PUSH [m16] + POP [m16] L: 7.48ns= 23.9c T: 3.21ns= 10.25c 496 X86 :PUSH [m32] L: [no true dep.] T: 0.60ns= 1.92c 497 X86 :POP [m32] L: [no true dep.] T: 3.15ns= 10.08c 498 X86 :PUSH [m32] + POP [m32] L: 7.46ns= 23.8c T: 3.21ns= 10.25c 499 X86 :PUSHF L: [no true dep.] T: 2.50ns= 8.00c 501 X86 :PUSHF + POPF L: 30.82ns= 98.5c T: 29.96ns= 95.75c 502 X86 :PUSHFD L: [no true dep.] T: 2.50ns= 8.00c 503 X86 :POPFD L: [no true dep.] T: 21.90ns= 70.00c 504 X86 :PUSHFD + POPFD L: 30.04ns= 96.0c T: 29.98ns= 95.83c 505 X86 :CMPSB L: 3.13ns= 10.0c T: 3.13ns= 10.00c 506 X86 :CMPSW L: 3.13ns= 10.0c T: 3.13ns= 10.00c 507 X86 :CMPSD L: 3.13ns= 10.0c T: 3.13ns= 10.00c 509 X86 :REPE CMPSB BW in L1D: 0.49 B/c 1572MiB/s 510 X86 :REPE CMPSW BW in L1D: 0.97 B/c 3109MiB/s 511 X86 :REPE CMPSD BW in L1D: 1.89 B/c 6035MiB/s 513 X86 :LODSB L: 2.50ns= 8.0c T: 2.50ns= 8.00c 514 X86 :LODSW L: 2.50ns= 8.0c T: 2.50ns= 8.00c 515 X86 :LODSD L: 2.50ns= 8.0c T: 2.56ns= 8.17c 517 X86 :REP LODSB BW in L1D: 0.25 B/c 798MiB/s 518 X86 :REP LODSW BW in L1D: 0.50 B/c 1595MiB/s 519 X86 :REP LODSD BW in L1D: 1.00 B/c 3183MiB/s 521 X86 :STOSB L: 2.50ns= 8.0c T: 2.50ns= 8.00c 522 X86 :STOSW L: 2.50ns= 8.0c T: 2.50ns= 8.00c 523 X86 :STOSD L: 2.50ns= 8.0c T: 2.50ns= 8.00c 525 X86 :REP STOSB BW in L1D: 3.33 B/c 10628MiB/s 526 X86 :REP STOSW BW in L1D: 3.44 B/c 11006MiB/s 527 X86 :REP STOSD BW in L1D: 3.43 B/c 10960MiB/s 529 X86 :MOVSB L: 2.50ns= 8.0c T: 2.50ns= 8.00c 530 X86 :MOVSW L: 2.50ns= 8.0c T: 2.53ns= 8.08c 531 X86 :MOVSD L: 2.50ns= 8.0c T: 2.50ns= 8.00c 533 X86 :REP MOVSB BW in L1D: 6.20 B/c 19805MiB/s 534 X86 :REP MOVSW BW in L1D: 6.63 B/c 21192MiB/s 535 X86 :REP MOVSD BW in L1D: 6.50 B/c 20763MiB/s 537 X86 :SCASB L: 2.50ns= 8.0c T: 2.50ns= 8.00c 538 X86 :SCASW L: 2.50ns= 8.0c T: 2.50ns= 8.00c 539 X86 :SCASD L: 2.50ns= 8.0c T: 2.50ns= 8.00c 541 X86 :REPNE SCASB BW in L1D: 0.24 B/c 768MiB/s 542 X86 :REPNE SCASW BW in L1D: 0.50 B/c 1594MiB/s 543 X86 :REPNE SCASD BW in L1D: 1.00 B/c 3181MiB/s 545 X86 :XADD r8, r8 L: 0.63ns= 2.0c T: 0.34ns= 1.08c 546 X86 :XADD r16, r16 L: 0.63ns= 2.0c T: 0.37ns= 1.17c 547 X86 :XADD r32, r32 L: 0.86ns= 2.8c T: 0.37ns= 1.17c 549 X86 :CMPXCHG r8, r8 L: 8.45ns= 27.0c T: 3.42ns= 10.92c 550 X86 :CMPXCHG r16, r16 L: 5.94ns= 19.0c T: 3.13ns= 10.00c 551 X86 :CMPXCHG r32, r32 L: 5.94ns= 19.0c T: 3.13ns= 10.00c 553 CMPX8 :CMPXCHG8B L: 9.13ns= 29.2c T: 5.94ns= 19.00c 555 X86 :RDTSC L: [no true dep.] T: 31.97ns=102.17c 556 X86 :CPUID (EAX = 0) L: 106.38ns=340.0c T: 106.38ns=340.00c 557 X86 :CPUID (EAX = 1) L: 128.91ns=412.0c T: 128.91ns=412.00c 569 X87 :FNOP L: [no true dep.] T: 0.31ns= 1.00c 570 X87 :FXCH st(i) L: 0.31ns= 1.0c T: 0.31ns= 1.00c 571 X87 :FCHS L: 0.94ns= 3.0c T: 0.94ns= 3.00c 572 X87 :FABS L: 0.94ns= 3.0c T: 0.94ns= 3.00c 573 X87 :FTST L: [no true dep.] T: 0.31ns= 1.00c 574 X87 :FXAM L: [no true dep.] T: 0.31ns= 1.00c 575 CMOV :FCMOVE st, st(i) L: 2.19ns= 7.0c T: 1.25ns= 4.00c 576 X87 :FADD st(i), st (st = 0.0) L: 1.88ns= 6.0c T: 0.31ns= 1.00c 577 X87 :FADD st(i), st L: 1.88ns= 6.0c T: 0.31ns= 1.00c 578 X87 :FADD st, st(i), FXCH st(i) L: 1.88ns= 6.0c T: 0.29ns= 0.92c 579 X87 :FMUL st(i), st (st = 0.0) L: 2.50ns= 8.0c T: 0.63ns= 2.00c 580 X87 :FMUL st(i), st L: 2.50ns= 8.0c T: 0.63ns= 2.00c 581 X87 :FMUL st, st(i), FXCH st(i) L: 2.50ns= 8.0c T: 0.63ns= 2.00c 582 X87 :FMUL + FADD st, st(i) L: 4.38ns= 14.0c T: [not enough reg] 583 X87 :FMUL st(2i) FADD st(2i+1) L: 2.53ns= 8.1c T: [not enough reg] 584 X87 :FDIV32 st(i), st L: 10.01ns= 32.0c T: 10.01ns= 32.00c 585 X87 :FDIV64 st(i), st L: 12.52ns= 40.0c T: 12.98ns= 41.50c 586 X87 :FDIV80 st(i), st L: 14.08ns= 45.0c T: 14.08ns= 45.00c 587 X87 :FDIV80 (0.0l/x) L: 10.33ns= 33.0c T: 10.33ns= 33.00c 588 X87 :FDIV80 (x/1.0l) L: 14.08ns= 45.0c T: 14.08ns= 45.00c 589 X87 :FDIV80 (x/2.0l) L: 14.08ns= 45.0c T: 14.08ns= 45.00c 590 X87 :FDIV80 (x/0.5l) L: 14.08ns= 45.0c T: 14.08ns= 45.00c 591 X87 :FSQRT32 st L: 10.01ns= 32.0c T: 10.01ns= 32.00c 592 X87 :FSQRT64 st L: 12.54ns= 40.1c T: 12.52ns= 40.00c 593 X87 :FSQRT80 st L: 14.08ns= 45.0c T: 14.08ns= 45.00c 594 X87 :FSQRT80 (0.0l) L: 10.33ns= 33.0c T: 10.33ns= 33.00c 595 X87 :FSQRT80 (1.0l) L: 14.08ns= 45.0c T: 14.08ns= 45.00c 596 X87 :FDECSTP L: [no true dep.] T: 0.31ns= 1.00c 597 X87 :FINCSTP L: [no true dep.] T: 0.31ns= 1.00c 598 X87 :FCOM st(i) L: [no true dep.] T: 0.31ns= 1.00c 599 CMOV :FCOMI st, st(i) L: [no true dep.] T: 0.68ns= 2.17c 600 X87 :FSIN80 (0.0) L: 43.28ns=138.3c T: 41.35ns=132.17c 601 X87 :FSIN80 (0.0) + FADD L: 40.57ns=129.7c T: 41.30ns=132.00c 602 X87 :FSIN80 (1.0) + FADD L: 56.63ns=181.0c T: 46.41ns=148.33c 603 X87 :FSIN80 (4Pi) + FADD L: 63.83ns=204.0c T: 58.20ns=186.00c 604 X87 :FSIN80 (2Pi) + FADD L: 63.83ns=204.0c T: 58.22ns=186.08c 605 X87 :FSIN80 (Pi) + FADD L: 63.83ns=204.0c T: 58.22ns=186.08c 606 X87 :FSIN80 (Pi/2) + FADD L: 62.26ns=199.0c T: 59.45ns=190.00c 607 X87 :FSIN80 (Pi/4) + FADD L: 56.63ns=181.0c T: 46.41ns=148.33c 608 X87 :FSIN80 (Pi/8) + FADD L: 55.69ns=178.0c T: 47.61ns=152.17c 609 X87 :FSIN80 (Pi/16) + FADD L: 63.83ns=204.0c T: 58.20ns=186.00c 610 X87 :FSIN80 (Pi/32) + FADD L: 63.83ns=204.0c T: 58.20ns=186.00c 611 X87 :FCOS80 (0.73908513...) L: 54.44ns=174.0c T: 45.18ns=144.42c 612 X87 :FCOS80 (0.73908513...)+FADD L: 56.32ns=180.0c T: 45.18ns=144.42c 613 X87 :FCOS80 (0.0) + FADD L: 41.30ns=132.0c T: 41.30ns=132.00c 614 X87 :FCOS80 (1.0) + FADD L: 55.38ns=177.0c T: 45.71ns=146.08c 615 X87 :FCOS80 (4Pi) + FADD L: 61.95ns=198.0c T: 59.42ns=189.92c 616 X87 :FCOS80 (2Pi) + FADD L: 61.95ns=198.0c T: 59.42ns=189.92c 617 X87 :FCOS80 (Pi) + FADD L: 61.95ns=198.0c T: 59.45ns=190.00c 618 X87 :FCOS80 (Pi/2) + FADD L: 63.51ns=203.0c T: 56.53ns=180.67c 619 X87 :FCOS80 (Pi/4) + FADD L: 55.38ns=177.0c T: 45.71ns=146.08c 620 X87 :FCOS80 (Pi/8) + FADD L: 56.32ns=180.0c T: 45.18ns=144.42c 621 X87 :FCOS80 (Pi/16) + FADD L: 61.95ns=198.0c T: 59.45ns=190.00c 622 X87 :FCOS80 (Pi/32) + FADD L: 61.95ns=198.0c T: 59.45ns=190.00c 623 MMX :EMMS L: 3.75ns= 12.0c T: 3.75ns= 12.00c 624 MMX :MOVD r32, mm L: [diff. reg. set] T: 0.31ns= 1.00c 625 MMX :MOVD mm, r32 L: [diff. reg. set] T: 0.31ns= 1.00c 626 MMX :MOVD r32, mm+MOVD mm, r32 L: 3.44ns= 11.0c T: 0.63ns= 2.00c 630 MMX :MOVD mm, [m32] L: [memory dep.] T: 0.31ns= 1.00c 631 MMX :MOVD [m32], mm L: [memory dep.] T: 0.52ns= 1.67c 632 MMX :MOVD mm,[m32]+MOVD [m32],mm L: 6.26ns= 20.0c T: 0.29ns= 0.92c 633 MMX :MOVQ mm, mm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 634 MMX :MOVQ mm, [m64] L: [memory dep.] T: 0.31ns= 1.00c 635 MMX :MOVQ [m64], mm L: [memory dep.] T: 0.52ns= 1.67c 636 MMX :MOVQ mm,[m64]+MOVQ [m64],mm L: 6.26ns= 20.0c T: 0.08ns= 0.27c 637 SSE :MOVNTQ [m64], mm L: [memory dep.] T: 2.00ns= 2.00c 638 SSE :PMOVMSKB r32, mm L: [diff. reg. set] T: 0.83ns= 2.67c 640 SSE :MASKMOVQ mm, mm L: [memory dep.] T: 8.00ns= 8.00c 641 MMX :PADDB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 642 MMX :PADDW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 643 MMX :PADDD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 644 SSE2 :PADDQ mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 645 MMX :PADDSB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 646 MMX :PADDSW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 647 MMX :PADDUSB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 648 MMX :PADDUSW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 649 MMX :PSUBB mm, mm L: 0.31ns= 1.0c T: 0.31ns= 1.00c 650 MMX :PSUBB mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 651 MMX :PSUBW mm, mm L: 0.31ns= 1.0c T: 0.31ns= 1.00c 652 MMX :PSUBW mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 653 MMX :PSUBD mm, mm L: 0.31ns= 1.0c T: 0.31ns= 1.00c 654 MMX :PSUBD mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 655 SSE2 :PSUBQ mm, mm L: 0.31ns= 1.0c T: 0.31ns= 1.00c 656 SSE2 :PSUBQ mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 657 MMX :PSUBSB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 658 MMX :PSUBSB mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 659 MMX :PSUBSW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 660 MMX :PSUBSW mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 661 MMX :PSUBUSB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 662 MMX :PSUBUSB mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 663 MMX :PSUBUSW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 664 MMX :PSUBUSW mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 665 MMX :PCMPEQB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 666 MMX :PCMPEQB mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 667 MMX :PCMPEQW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 668 MMX :PCMPEQW mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 669 MMX :PCMPEQD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 670 MMX :PCMPEQD mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 671 MMX :PCMPGTB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 672 MMX :PCMPGTB mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 673 MMX :PCMPGTW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 674 MMX :PCMPGTW mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 675 MMX :PCMPGTD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 676 MMX :PCMPGTD mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 677 MMX :PAND mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 678 MMX :PAND mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 679 MMX :PANDN mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 680 MMX :PANDN mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 681 MMX :POR mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 682 MMX :POR mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 683 MMX :PXOR mm, mm L: 0.31ns= 1.0c T: 0.31ns= 1.00c 684 MMX :PXOR mm1, mm2 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 685 MMX :PMULHW mm, mm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 686 SSE :PMULHUW mm, mm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 689 MMX :PMULLW mm, mm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 690 SSE2 :PMULUDQ mm, mm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 692 MMX :PMADDWD mm, mm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 693 MMX :PSLLW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 694 MMX :PSLLW mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 695 MMX :PSLLD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 696 MMX :PSLLD mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 697 MMX :PSLLQ mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 698 MMX :PSLLQ mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 699 MMX :PSRAW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 700 MMX :PSRAW mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 701 MMX :PSRAD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 702 MMX :PSRAD mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 703 MMX :PSRLW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 704 MMX :PSRLW mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 705 MMX :PSRLD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 706 MMX :PSRLD mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 707 MMX :PSRLQ mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 708 MMX :PSRLQ mm, imm8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 709 MMX :PUNPCKHBW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 710 MMX :PUNPCKHWD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 711 MMX :PUNPCKHDQ mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 712 MMX :PUNPCKLBW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 713 MMX :PUNPCKLWD mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 714 MMX :PUNPCKLDQ mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 715 MMX :PACKSSWB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 716 MMX :PACKUSWB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 717 MMX :PACKSSDW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 753 SSE :PAVGB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 754 SSE :PAVGW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 755 SSE :PEXTRW r32, mm, im8 L: [diff. reg. set] T: 0.63ns= 2.00c 756 SSE :PINSRW mm, r32, im8 L: [diff. reg. set] T: 0.63ns= 2.00c 757 SSE :PEXTRW + PINSRW r32 L: 1.56ns= 5.0c T: 1.56ns= 5.00c 761 SSE :PMAXSW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 762 SSE :PMAXUB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 763 SSE :PMINSW mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 764 SSE :PMINUB mm, mm L: 0.63ns= 2.0c T: 0.31ns= 1.00c 765 SSE :PSADBW mm, mm L: 1.25ns= 4.0c T: 0.31ns= 1.00c 766 SSE :PSHUFW mm, mm, im8 L: 0.63ns= 2.0c T: 0.31ns= 1.00c 767 SSE :PREFETCHNTA [mem] L: [memory dep.] T: 0.31ns= 1.00c 768 SSE :PREFETCHT0 [mem] L: [memory dep.] T: 0.31ns= 1.00c 769 SSE :PREFETCHT1 [mem] L: [memory dep.] T: 0.31ns= 1.00c 770 SSE :PREFETCHT2 [mem] L: [memory dep.] T: 0.31ns= 1.00c 771 SSE :SFENCE L: 16.97ns= 54.3c T: 16.97ns= 54.25c 772 SSE2 :LFENCE L: 16.27ns= 52.0c T: 16.27ns= 52.00c 773 SSE2 :MFENCE L: 38.80ns=124.0c T: 38.80ns=124.00c 788 SSE :MOVHLPS xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 789 SSE :MOVHLPS xmm1, xmm2 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 792 SSE :MOVSS xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 794 SSE :MOVSS xmm, [m32] L: [memory dep.] T: 0.31ns= 1.00c 795 SSE :MOVSS [m32], xmm L: [memory dep.] T: 0.52ns= 1.67c 796 SSE :MOVSS LS pair L: 6.44ns= 20.6c T: 0.14ns= 0.45c 800 SSE :MOVLPS xmm, [m32] L: [memory dep.] T: 0.63ns= 2.00c 801 SSE :MOVLPS [m32], xmm L: [memory dep.] T: 0.52ns= 1.67c 802 SSE :MOVLPS LS pair L: 7.82ns= 25.0c T: 0.14ns= 0.43c 806 SSE :MOVHPS xmm, [m32] L: [memory dep.] T: 0.63ns= 2.00c 807 SSE :MOVHPS [m32], xmm L: [memory dep.] T: 0.52ns= 1.67c 808 SSE :MOVHPS LS pair L: 7.20ns= 23.0c T: 0.15ns= 0.47c 812 SSE :MOVAPS xmm, xmm L: 2.24ns= 7.2c T: 0.31ns= 1.00c 813 SSE :MOVAPS xmm, [m128] L: [memory dep.] T: 0.31ns= 1.00c 814 SSE :MOVAPS [m128], xmm L: [memory dep.] T: 0.52ns= 1.67c 815 SSE :MOVAPS LS pair L: 6.26ns= 20.0c T: 0.09ns= 0.28c 820 SSE :MOVUPS xmm, xmm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 821 SSE :MOVUPS xmm, [m128] L: [memory dep.] T: 0.81ns= 2.58c 822 SSE :MOVUPS [m128], xmm L: [memory dep.] T: 2.50ns= 8.00c 823 SSE :MOVUPS aligned LS pair L: 7.51ns= 24.0c T: 2.92ns= 9.33c 824 SSE :MOVUPS xmm, [m128 + 4] L: [memory dep.] T: 0.57ns= 1.83c 825 SSE :MOVUPS [m128 + 4], xmm L: [memory dep.] T: 1.83ns= 5.83c 826 SSE :MOVUPS unaligned LS pair L: 7.51ns= 24.0c T: 8.32ns= 26.58c 835 SSE :MOVNTPS [m128], xmm L: [memory dep.] T: 1.67ns= 1.67c 837 SSE :MOVMSKPS r32, xmm L: [diff. reg. set] T: 0.83ns= 2.67c 842 SSE :UNPCKLPS xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 844 SSE :UNPCKHPS xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 846 SSE :SHUFPS xmm, xmm, imm8 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 850 SSE :COMISS xmm, xmm L: [no true dep.] T: 0.83ns= 2.67c 852 SSE :UCOMISS xmm, xmm L: [no true dep.] T: 0.83ns= 2.67c 854 SSE :CMPSS xmm, xmm, imm8 L: 1.56ns= 5.0c T: 0.63ns= 2.00c 855 SSE :CMPPS xmm, xmm, imm8 L: 1.56ns= 5.0c T: 0.63ns= 2.00c 858 SSE :SUBSS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 860 SSE :SUBPS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 862 SSE :ADDSS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 864 SSE :ADDPS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 866 SSE :MULSS xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 868 SSE :MULPS xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 870 SSE :MULSS+ADDSS xmm, xmm L: 3.75ns= 12.0c T: [not enough reg] 872 SSE :MULPS+ADDPS xmm, xmm L: 3.75ns= 12.0c T: [not enough reg] 874 SSE :MULSS xm1,xm1 ADDSS xm2,xm2 L: 2.19ns= 7.0c T: [not enough reg] 876 SSE :MULPS xm1,xm1 ADDPS xm2,xm2 L: 2.19ns= 7.0c T: [not enough reg] 878 SSE :MAXSS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 880 SSE :MAXPS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 882 SSE :MINSS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 884 SSE :MINPS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 886 SSE :ANDNPS xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 887 SSE :ANDNPS xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 890 SSE :ANDPS xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 891 SSE :ANDPS xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 894 SSE :ORPS xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 895 SSE :ORPS xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 898 SSE :XORPS xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 899 SSE :XORPS xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 902 SSE :DIVSS xmm, xmm L: 10.01ns= 32.0c T: 10.01ns= 32.00c 903 SSE :DIVSS (0.0f/x) L: 10.01ns= 32.0c T: 10.40ns= 33.25c 904 SSE :DIVSS (x/1.0f) L: 10.04ns= 32.1c T: 10.48ns= 33.50c 905 SSE :DIVSS (x/2.0f) L: 10.01ns= 32.0c T: 10.01ns= 32.00c 906 SSE :DIVSS (x/0.5f) L: 10.01ns= 32.0c T: 10.01ns= 32.00c 912 SSE :DIVPS xmm, xmm L: 12.85ns= 41.1c T: 13.45ns= 43.00c 913 SSE :DIVPS (0.0f/x) L: 12.83ns= 41.0c T: 13.04ns= 41.67c 914 SSE :DIVPS (x/1.0f) L: 12.83ns= 41.0c T: 12.83ns= 41.00c 915 SSE :DIVPS (x/2.0f) L: 12.85ns= 41.1c T: 12.83ns= 41.00c 916 SSE :DIVPS (x/0.5f) L: 12.85ns= 41.1c T: 12.83ns= 41.00c 922 SSE :SQRTSS xmm, xmm L: 10.01ns= 32.0c T: 10.46ns= 33.42c 923 SSE :SQRTSS (0.0f) L: 10.01ns= 32.0c T: 10.01ns= 32.00c 924 SSE :SQRTSS (1.0f) L: 10.01ns= 32.0c T: 10.01ns= 32.00c 928 SSE :SQRTPS xmm, xmm L: 12.83ns= 41.0c T: 12.83ns= 41.00c 929 SSE :SQRTPS (0.0f) L: 12.83ns= 41.0c T: 12.83ns= 41.00c 930 SSE :SQRTPS (1.0f) L: 12.83ns= 41.0c T: 12.83ns= 41.00c 934 SSE :RCPSS xmm, xmm L: 1.56ns= 5.0c T: 0.94ns= 3.00c 936 SSE :RCPPS xmm, xmm L: 1.88ns= 6.0c T: 1.25ns= 4.00c 938 SSE :RSQRTSS xmm, xmm L: 1.56ns= 5.0c T: 0.94ns= 3.00c 940 SSE :RSQRTPS xmm, xmm L: 1.88ns= 6.0c T: 1.25ns= 4.00c 942 SSE :CVTPI2PS xmm, mm L: [diff. reg. set] T: 1.59ns= 5.08c 943 SSE :CVTPS2PI mm, xmm L: [diff. reg. set] T: 0.78ns= 2.50c 944 SSE :CVTPS2PI + CVTPI2PS L: 6.26ns= 20.0c T: 2.06ns= 6.58c 945 SSE :CVTTPS2PI mm, xmm L: [diff. reg. set] T: 0.78ns= 2.50c 946 SSE :CVTTPS2PI + CVTPI2PS L: 6.26ns= 20.0c T: 2.06ns= 6.58c 947 SSE :CVTSI2SS xmm, r32 L: [diff. reg. set] T: 1.25ns= 4.00c 948 SSE :CVTSS2SI r32, xmm L: [diff. reg. set] T: 1.25ns= 4.00c 949 SSE :CVTSS2SI + CVTSI2SS r32 L: 8.45ns= 27.0c T: 1.90ns= 6.08c 950 SSE :CVTTSS2SI r32, xmm L: [diff. reg. set] T: 1.25ns= 4.00c 951 SSE :CVTTSS2SI + CVTSI2SS r32 L: 8.45ns= 27.0c T: 1.90ns= 6.08c 967 SSE :STMXCSR [mem] L: [memory dep.] T: 0.63ns= 2.00c 968 SSE :LDMXCSR [mem] L: [memory dep.] T: 3.75ns= 12.00c 969 SSE :STMXCSR + LDMXCSR L: 4.46ns= 14.3c T: 4.48ns= 14.33c 970 SSE2 :MOVSD xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 971 SSE2 :MOVSD xmm, [m64] L: [memory dep.] T: 0.31ns= 1.00c 972 SSE2 :MOVSD [m64], xmm L: [memory dep.] T: 0.52ns= 1.67c 973 SSE2 :MOVSD LS pair L: 6.26ns= 20.0c T: 0.07ns= 0.23c 978 SSE2 :MOVLPD xmm, [m64] L: [memory dep.] T: 0.65ns= 2.08c 979 SSE2 :MOVLPD [m64], xmm L: [memory dep.] T: 0.52ns= 1.67c 980 SSE2 :MOVLPD LS pair L: 7.82ns= 25.0c T: 1.07ns= 3.42c 984 SSE2 :MOVHPD xmm, [m64] L: [memory dep.] T: 0.63ns= 2.00c 985 SSE2 :MOVHPD [m64], xmm L: [memory dep.] T: 0.52ns= 1.67c 986 SSE2 :MOVHPD LS pair L: 7.20ns= 23.0c T: 0.18ns= 0.57c 990 SSE2 :MOVAPD xmm, xmm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 991 SSE2 :MOVAPD xmm, [m128] L: [memory dep.] T: 0.31ns= 1.00c 992 SSE2 :MOVAPD [m128], xmm L: [memory dep.] T: 0.52ns= 1.67c 993 SSE2 :MOVAPD LS pair L: 6.26ns= 20.0c T: 0.08ns= 0.25c 998 SSE2 :MOVUPD xmm, xmm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 999 SSE2 :MOVUPD xmm, [m128] L: [memory dep.] T: 0.76ns= 2.42c 1000 SSE2 :MOVUPD [m128], xmm L: [memory dep.] T: 2.50ns= 8.00c 1001 SSE2 :MOVUPD aligned LS pair L: 7.51ns= 24.0c T: 3.10ns= 9.92c 1002 SSE2 :MOVUPD xmm, [m128 + 4] L: [memory dep.] T: 0.60ns= 1.92c 1003 SSE2 :MOVUPD [m128 + 4], xmm L: [memory dep.] T: 1.83ns= 5.83c 1004 SSE2 :MOVUPD unaligned LS pair L: 7.51ns= 24.0c T: 8.32ns= 26.58c 1013 SSE2 :MOVNTPD [m128], xmm L: [memory dep.] T: 3.83ns= 3.83c 1015 SSE2 :MOVMSKPD r32, xmm L: [diff. reg. set] T: 0.83ns= 2.67c 1020 SSE2 :UNPCKLPD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1022 SSE2 :UNPCKHPD xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1024 SSE2 :SHUFPD xmm, xmm, imm8 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1028 SSE2 :COMISD xmm, xmm L: [no true dep.] T: 0.83ns= 2.67c 1030 SSE2 :UCOMISD xmm, xmm L: [no true dep.] T: 0.83ns= 2.67c 1032 SSE2 :CMPSD xmm, xmm, imm8 L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1033 SSE2 :CMPPD xmm, xmm, imm8 L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1036 SSE2 :SUBSD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1038 SSE2 :SUBPD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1040 SSE2 :ADDSD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1042 SSE2 :ADDPD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1044 SSE2 :MULSD xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1046 SSE2 :MULPD xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1048 SSE2 :MULSD+ADDSD xmm, xmm L: 3.75ns= 12.0c T: [not enough reg] 1050 SSE2 :MULPD+ADDPD xmm, xmm L: 3.75ns= 12.0c T: [not enough reg] 1052 SSE2 :MULSD xm1,xm1 ADDSD xm2,xm2 L: 2.19ns= 7.0c T: [not enough reg] 1054 SSE2 :MULPD xm1,xm1 ADDPD xm2,xm2 L: 2.19ns= 7.0c T: [not enough reg] 1056 SSE2 :MAXSD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1058 SSE2 :MAXPD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1060 SSE2 :MINSD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1062 SSE2 :MINPD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1064 SSE2 :ANDNPD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1065 SSE2 :ANDNPD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1068 SSE2 :ANDPD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1069 SSE2 :ANDPD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1072 SSE2 :ORPD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1073 SSE2 :ORPD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1076 SSE2 :XORPD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1077 SSE2 :XORPD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1080 SSE2 :DIVSD xmm, xmm L: 12.52ns= 40.0c T: 12.78ns= 40.83c 1081 SSE2 :DIVSD (0.0/x) L: 12.52ns= 40.0c T: 12.91ns= 41.25c 1082 SSE2 :DIVSD (x/1.0) L: 12.52ns= 40.0c T: 12.72ns= 40.67c 1083 SSE2 :DIVSD (x/2.0) L: 12.52ns= 40.0c T: 12.52ns= 40.00c 1084 SSE2 :DIVSD (x/0.5) L: 12.52ns= 40.0c T: 12.52ns= 40.00c 1090 SSE2 :DIVPD xmm, xmm L: 23.02ns= 73.6c T: 23.02ns= 73.58c 1091 SSE2 :DIVPD (0.0/x) L: 22.21ns= 71.0c T: 22.21ns= 71.00c 1092 SSE2 :DIVPD (x/1.0) L: 22.21ns= 71.0c T: 22.21ns= 71.00c 1093 SSE2 :DIVPD (x/2.0) L: 22.24ns= 71.1c T: 22.21ns= 71.00c 1094 SSE2 :DIVPD (x/0.5) L: 22.24ns= 71.1c T: 22.21ns= 71.00c 1100 SSE2 :SQRTSD xmm, xmm L: 12.54ns= 40.1c T: 13.09ns= 41.83c 1101 SSE2 :SQRTSD (0.0) L: 12.52ns= 40.0c T: 12.91ns= 41.25c 1102 SSE2 :SQRTSD (1.0) L: 12.52ns= 40.0c T: 12.52ns= 40.00c 1106 SSE2 :SQRTPD xmm, xmm L: 23.02ns= 73.6c T: 22.87ns= 73.08c 1107 SSE2 :SQRTPD (0.0) L: 22.21ns= 71.0c T: 22.21ns= 71.00c 1108 SSE2 :SQRTPD (1.0) L: 22.21ns= 71.0c T: 22.21ns= 71.00c 1112 SSE2 :CVTPI2PD xmm, mm L: [diff. reg. set] T: 1.56ns= 5.00c 1113 SSE2 :CVTPD2PI mm, xmm L: [diff. reg. set] T: 1.25ns= 4.00c 1114 SSE2 :CVTPD2PI + CVTPI2PD L: 7.82ns= 25.0c T: 2.45ns= 7.83c 1115 SSE2 :CVTTPD2PI mm, xmm L: [diff. reg. set] T: 1.25ns= 4.00c 1116 SSE2 :CVTTPD2PI + CVTPI2PD L: 7.82ns= 25.0c T: 2.50ns= 8.00c 1117 SSE2 :CVTSI2SD xmm, r32 L: [diff. reg. set] T: 1.62ns= 5.17c 1118 SSE2 :CVTSD2SI r32, xmm L: [diff. reg. set] T: 1.25ns= 4.00c 1119 SSE2 :CVTSD2SI + CVTSI2SD r32 L: 10.01ns= 32.0c T: 2.32ns= 7.42c 1120 SSE2 :CVTTSD2SI r32, xmm L: [diff. reg. set] T: 1.30ns= 4.17c 1121 SSE2 :CVTTSD2SI + CVTSI2SD r32 L: 10.01ns= 32.0c T: 2.32ns= 7.42c 1137 SSE2 :CVTDQ2PD xmm, xmm L: 3.78ns= 12.1c T: 1.25ns= 4.00c 1138 SSE2 :CVTPD2DQ xmm, xmm L: 3.44ns= 11.0c T: 0.94ns= 3.00c 1139 SSE2 :CVTPD2DQ + CVTDQ2PD L: 6.57ns= 21.0c T: 1.83ns= 5.83c 1140 SSE2 :CVTTPD2DQ xmm, xmm L: 3.44ns= 11.0c T: 0.94ns= 3.00c 1141 SSE2 :CVTTPD2DQ + CVTDQ2PD L: 6.57ns= 21.0c T: 1.83ns= 5.83c 1147 SSE2 :CVTDQ2PS xmm, xmm L: 4.25ns= 13.6c T: 0.63ns= 2.00c 1148 SSE2 :CVTPS2DQ xmm, xmm L: 4.54ns= 14.5c T: 0.63ns= 2.00c 1149 SSE2 :CVTPS2DQ + CVTDQ2PS L: 3.13ns= 10.0c T: 1.25ns= 4.00c 1150 SSE2 :CVTTPS2DQ xmm, xmm L: 4.33ns= 13.8c T: 0.63ns= 2.00c 1151 SSE2 :CVTTPS2DQ + CVTDQ2PS L: 3.13ns= 10.0c T: 1.25ns= 4.00c 1157 SSE2 :CVTPS2PD xmm, xmm L: 3.34ns= 10.7c T: 0.63ns= 2.00c 1158 SSE2 :CVTPD2PS xmm, xmm L: 3.44ns= 11.0c T: 0.94ns= 3.00c 1159 SSE2 :CVTPD2PS + CVTPS2PD L: 4.38ns= 14.0c T: 0.47ns= 1.50c 1160 SSE2 :CVTSS2SD xmm, xmm L: 2.82ns= 9.0c T: 1.25ns= 4.00c 1161 SSE2 :CVTSD2SS xmm, xmm L: 4.12ns= 13.2c T: 1.33ns= 4.25c 1162 SSE2 :CVTSD2SS + CVTSS2SD L: 6.88ns= 22.0c T: 1.96ns= 6.25c 1169 SSE2 :MOVD r32, xmm L: [diff. reg. set] T: 0.31ns= 1.00c 1170 SSE2 :MOVD xmm, r32 L: [diff. reg. set] T: 0.63ns= 2.00c 1171 SSE2 :MOVD r32, xmm+MOVD xmm, r32 L: 4.07ns= 13.0c T: 0.76ns= 2.42c 1181 SSE2 :MOVD xmm, [m32] L: [memory dep.] T: 0.31ns= 1.00c 1182 SSE2 :MOVD [m32], xmm L: [memory dep.] T: 0.52ns= 1.67c 1183 SSE2 :MOVD LS pair L: 6.26ns= 20.0c T: 0.13ns= 0.42c 1187 SSE2 :MOVQ xmm, [m64] L: [memory dep.] T: 0.31ns= 1.00c 1188 SSE2 :MOVQ [m64], xmm L: [memory dep.] T: 0.52ns= 1.67c 1189 SSE2 :MOVQ LS pair L: 6.26ns= 20.0c T: 0.11ns= 0.34c 1193 SSE2 :MOVDQ2Q mm, xmm L: [diff. reg. set] T: 0.63ns= 2.00c 1194 SSE2 :MOVQ2DQ xmm, mm L: [diff. reg. set] T: 0.63ns= 2.00c 1195 SSE2 :MOVDQ2Q + MOVQ2DQ xmm, mm L: 6.26ns= 20.0c T: 0.94ns= 3.00c 1196 SSE2 :MOVDQA xmm, xmm L: 2.22ns= 7.1c T: 0.31ns= 1.00c 1197 SSE2 :MOVDQA xmm, [m128] L: [memory dep.] T: 0.31ns= 1.00c 1198 SSE2 :MOVDQA [m128], xmm L: [memory dep.] T: 0.52ns= 1.67c 1199 SSE2 :MOVDQA LS pair L: 6.26ns= 20.0c T: 0.09ns= 0.29c 1204 SSE2 :MOVDQU xmm, xmm L: 2.19ns= 7.0c T: 0.31ns= 1.00c 1205 SSE2 :MOVDQU xmm, [m128] L: [memory dep.] T: 0.76ns= 2.42c 1206 SSE2 :MOVDQU [m128], xmm L: [memory dep.] T: 2.50ns= 8.00c 1207 SSE2 :MOVDQU aligned LS pair L: 7.51ns= 24.0c T: 2.92ns= 9.33c 1208 SSE2 :MOVDQU xmm, [m128 + 4] L: [memory dep.] T: 0.60ns= 1.92c 1209 SSE2 :MOVDQU [m128 + 4], xmm L: [memory dep.] T: 2.03ns= 6.50c 1210 SSE2 :MOVDQU unaligned LS pair L: 7.51ns= 24.0c T: 8.29ns= 26.50c 1219 SSE2 :MOVNTDQ [m128], xmm L: [memory dep.] T: 1.67ns= 1.67c 1224 SSE2 :PMOVMSKB r32, xmm L: [diff. reg. set] T: 0.83ns= 2.67c 1228 SSE2 :MASKMOVDQU xmm, xmm L: [memory dep.] T: 10.00ns= 10.00c 1230 SSE2 :PADDB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1232 SSE2 :PADDW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1234 SSE2 :PADDD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1236 SSE2 :PADDQ xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1238 SSE2 :PADDSB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1240 SSE2 :PADDSW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1242 SSE2 :PADDUSB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1244 SSE2 :PADDUSW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1246 SSE2 :PSUBB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1247 SSE2 :PSUBB xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1250 SSE2 :PSUBW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1251 SSE2 :PSUBW xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1254 SSE2 :PSUBD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1255 SSE2 :PSUBD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1258 SSE2 :PSUBQ xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1259 SSE2 :PSUBQ xmm1, xmm2 L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1262 SSE2 :PSUBSB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1263 SSE2 :PSUBSB xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1266 SSE2 :PSUBSW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1267 SSE2 :PSUBSW xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1270 SSE2 :PSUBUSB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1271 SSE2 :PSUBUSB xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1274 SSE2 :PSUBUSW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1275 SSE2 :PSUBUSW xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1278 SSE2 :PCMPEQB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1279 SSE2 :PCMPEQB xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1282 SSE2 :PCMPEQW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1283 SSE2 :PCMPEQW xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1286 SSE2 :PCMPEQD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1287 SSE2 :PCMPEQD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1294 SSE2 :PCMPGTB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1295 SSE2 :PCMPGTB xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1298 SSE2 :PCMPGTW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1299 SSE2 :PCMPGTW xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1302 SSE2 :PCMPGTD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1303 SSE2 :PCMPGTD xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1310 SSE2 :PAND xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1311 SSE2 :PAND xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1314 SSE2 :PANDN xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1315 SSE2 :PANDN xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1318 SSE2 :POR xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1319 SSE2 :POR xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1322 SSE2 :PXOR xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1323 SSE2 :PXOR xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1326 SSE2 :PMULHW xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1328 SSE2 :PMULHUW xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1332 SSE2 :PMULLW xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1338 SSE2 :PMULUDQ xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1342 SSE2 :PMADDWD xmm, xmm L: 2.19ns= 7.0c T: 0.63ns= 2.00c 1344 SSE2 :PSLLW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1346 SSE2 :PSLLW xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1348 SSE2 :PSLLD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1350 SSE2 :PSLLD xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1352 SSE2 :PSLLQ xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1354 SSE2 :PSLLQ xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1356 SSE2 :PSLLDQ xmm, imm8 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1358 SSE2 :PSRAW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1360 SSE2 :PSRAW xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1362 SSE2 :PSRAD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1364 SSE2 :PSRAD xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1366 SSE2 :PSRLW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1368 SSE2 :PSRLW xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1370 SSE2 :PSRLD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1372 SSE2 :PSRLD xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1374 SSE2 :PSRLQ xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1376 SSE2 :PSRLQ xmm, imm8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1378 SSE2 :PSRLDQ xmm, imm8 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1380 SSE2 :PUNPCKHBW xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1382 SSE2 :PUNPCKHWD xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1384 SSE2 :PUNPCKHDQ xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1386 SSE2 :PUNPCKHQDQ xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1388 SSE2 :PUNPCKLBW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1390 SSE2 :PUNPCKLWD xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1392 SSE2 :PUNPCKLDQ xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1394 SSE2 :PUNPCKLQDQ xmm, xmm L: 0.94ns= 3.0c T: 0.63ns= 2.00c 1396 SSE2 :PACKSSWB xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1398 SSE2 :PACKUSWB xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1400 SSE2 :PACKSSDW xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1404 SSE2 :PAVGB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1406 SSE2 :PAVGW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1418 SSE2 :PEXTRW r32, xmm, im8 L: [diff. reg. set] T: 0.78ns= 2.50c 1419 SSE2 :PINSRW xmm, r32, im8 L: [diff. reg. set] T: 0.65ns= 2.08c 1420 SSE2 :PEXTRW + PINSRW r32 L: 5.32ns= 17.0c T: 1.33ns= 4.25c 1450 SSE2 :PMAXUB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1456 SSE2 :PMAXSW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1462 SSE2 :PMINUB xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1468 SSE2 :PMINSW xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1474 SSE2 :PSADBW xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1478 SSE2 :PSHUFLW xmm, xmm, im8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1480 SSE2 :PSHUFHW xmm, xmm, im8 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1482 SSE2 :PSHUFD xmm, xmm, im8 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1484 SSE3 :ADDSUBPS xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1486 SSE3 :ADDSUBPD xmm, xmm L: 1.56ns= 5.0c T: 0.63ns= 2.00c 1488 SSE3 :HADDPS xmm, xmm L: 4.07ns= 13.0c T: 1.72ns= 5.50c 1490 SSE3 :HADDPD xmm, xmm L: 4.07ns= 13.0c T: 1.46ns= 4.67c 1492 SSE3 :HSUBPS xmm, xmm L: 4.07ns= 13.0c T: 1.72ns= 5.50c 1494 SSE3 :HSUBPD xmm, xmm L: 4.07ns= 13.0c T: 1.46ns= 4.67c 1496 SSE3 :MOVSLDUP xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1498 SSE3 :MOVSHDUP xmm, xmm L: 1.25ns= 4.0c T: 0.63ns= 2.00c 1500 SSE3 :MOVDDUP xmm, xmm L: 0.63ns= 2.0c T: 0.63ns= 2.00c 1502 SSE3 :LDDQU xmm, [m128 + 4] L: [memory dep.] T: 0.76ns= 2.42c 1974 X86 :MOV+ADD r8, r8 L: 0.63ns= 2.0c T: 0.23ns= 0.75c 1975 X86 :MOV+ADD r16, r16 L: 0.65ns= 2.1c T: 0.25ns= 0.79c 1976 X86 :MOV+ADD r32, r32 L: 0.63ns= 2.0c T: 0.25ns= 0.79c 1978 MMX :MOVQ+PADDB mm, mm L: 3.13ns= 10.0c T: 0.31ns= 1.00c 1979 MMX :MOVQ+PADDW mm, mm L: 3.13ns= 10.0c T: 0.31ns= 1.00c 1980 MMX :MOVQ+PADDD mm, mm L: 3.13ns= 10.0c T: 0.31ns= 1.00c 1981 SSE2 :MOVQ+PADDQ mm, mm L: 3.13ns= 10.0c T: 0.31ns= 1.00c 1983 SSE :MOVSS+ADDSS xmm, xmm L: 2.82ns= 9.0c T: 0.96ns= 3.08c 1985 SSE :MOVAPS+ADDPS xmm, xmm L: 4.07ns= 13.0c T: 0.47ns= 1.50c 1987 SSE2 :MOVSD+ADDSD xmm, xmm L: 3.44ns= 11.0c T: 1.10ns= 3.50c 1989 SSE2 :MOVAPD+ADDPD xmm, xmm L: 4.07ns= 13.0c T: 0.47ns= 1.50c 1991 SSE2 :MOVDQA+PADDB xmm, xmm L: 3.13ns= 10.0c T: 0.63ns= 2.00c 1992 SSE2 :MOVDQA+PADDW xmm, xmm L: 3.13ns= 10.0c T: 0.63ns= 2.00c 1993 SSE2 :MOVDQA+PADDD xmm, xmm L: 3.13ns= 10.0c T: 0.63ns= 2.00c 1994 SSE2 :MOVDQA+PADDQ xmm, xmm L: 4.12ns= 13.2c T: 0.63ns= 2.00c 2238 CLFLUSH :CLFLUSH [mem] L: [memory dep.] T: 71.02ns=227.00c 2248 X86 :MOV r1_8, r2_8 L: 0.31ns= 1.0c T: 0.21ns= 0.67c 2249 X86 :MOV r1_16, r2_16 L: 0.31ns= 1.0c T: 0.25ns= 0.79c 2250 X86 :MOV r1_32, r2_32 L: 0.12ns= 0.4c T: 0.12ns= 0.38c 2252 X86 :MOVSX r1_16, r2_8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2253 X86 :MOVSX r1_32, r2_8 L: 0.18ns= 0.6c T: 0.18ns= 0.58c 2255 X86 :MOVSX r1_32, r2_16 L: 0.18ns= 0.6c T: 0.18ns= 0.58c 2258 X86 :MOVZX r1_16, r2_8 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2259 X86 :MOVZX r1_32, r2_8 L: 0.12ns= 0.4c T: 0.12ns= 0.38c 2261 X86 :MOVZX r1_32, r2_16 L: 0.12ns= 0.4c T: 0.12ns= 0.38c 2263 MMX :MOVQ mm1, mm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2264 SSE :MOVSS xmm1, xmm2 L: 0.63ns= 2.0c T: 0.63ns= 2.00c 2266 SSE :MOVAPS xmm1, xmm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2268 SSE :MOVUPS xmm1, xmm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2270 SSE2 :MOVSD xmm1, xmm2 L: 1.25ns= 4.0c T: 0.63ns= 2.00c 2272 SSE2 :MOVAPD xmm1, xmm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2274 SSE2 :MOVUPD xmm1, xmm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2276 SSE2 :MOVDQA xmm1, xmm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2278 SSE2 :MOVDQU xmm1, xmm2 L: 0.31ns= 1.0c T: 0.31ns= 1.00c 2290 SSE :4xADDPS xm1,xm1 4x xm2,xm2 L: 6.26ns= 20.0c T: 6.26ns= 20.00c 2291 SSE :4xMULPS xm1,xm1 4x xm2,xm2 L: 8.76ns= 28.0c T: 8.76ns= 28.00c 2292 SSE2 :4xADDPD xm1,xm1 4x xm2,xm2 L: 6.26ns= 20.0c T: 6.26ns= 20.00c 2293 SSE2 :4xMULPD xm1,xm1 4x xm2,xm2 L: 8.76ns= 28.0c T: 8.76ns= 28.00c 2294 LNOP :LNOP3 [eax], eax L: [no true dep.] T: 0.11ns= 0.35c 2295 LNOP :LNOP4 [eax+disp8], eax L: [no true dep.] T: 0.11ns= 0.35c 2296 LNOP :LNOP5 [SIB+disp8], eax L: [no true dep.] T: 0.11ns= 0.35c 2297 LNOP :LNOP6 [SIB+disp8], ax L: [no true dep.] T: 0.11ns= 0.35c 2298 LNOP :LNOP7 [eax+disp32], eax L: [no true dep.] T: 0.11ns= 0.35c 2299 LNOP :LNOP8 [SIB+disp32], eax L: [no true dep.] T: 0.27ns= 0.85c 2300 LNOP :LNOP9 [SIB+disp32], ax L: [no true dep.] T: 0.11ns= 0.35c 2301 LNOP :2x66 LNOPA [SIB+disp32], ax L: [no true dep.] T: 0.11ns= 0.35c 2302 LNOP :3x66 LNOPB [SIB+disp32], ax L: [no true dep.] T: 0.11ns= 0.35c 2303 LNOP :4x66 LNOPC [SIB+disp32], ax L: [no true dep.] T: 0.11ns= 0.35c 2304 LNOP :5x66 LNOPD [SIB+disp32], ax L: [no true dep.] T: 0.16ns= 0.52c 2305 LNOP :6x66 LNOPE [SIB+disp32], ax L: [no true dep.] T: 0.11ns= 0.35c 2306 LNOP :7x66 LNOPF [SIB+disp32], ax L: [no true dep.] T: 0.11ns= 0.35c 4354 X86 :SHLD r1_16, r2_16, imm8 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4355 X86 :SHLD r1_32, r2_32, imm8 L: 2.50ns= 8.0c T: 2.14ns= 6.83c 4357 X86 :SHLD r1_16, r2_16, cl L: 3.75ns= 12.0c T: 3.75ns= 12.00c 4358 X86 :SHLD r1_32, r2_32, cl L: 2.82ns= 9.0c T: 2.50ns= 8.00c 4360 X86 :SHRD r1_16, r2_16, imm8 L: 3.13ns= 10.0c T: 3.18ns= 10.17c 4361 X86 :SHRD r1_32, r2_32, imm8 L: 2.50ns= 8.0c T: 2.14ns= 6.83c 4363 X86 :SHRD r1_16, r2_16, cl L: 3.75ns= 12.0c T: 3.78ns= 12.08c 4364 X86 :SHRD r1_32, r2_32, cl L: 2.82ns= 9.0c T: 2.50ns= 8.00c 4366 X86 :ADC r8, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4367 X86 :ADC r16, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4368 X86 :ADC r32, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4370 X86 :ADC r16, imm16 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4371 X86 :ADC r32, imm32 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4373 X86 :ADC al, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4374 X86 :ADC ax, imm16 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4375 X86 :ADC eax, imm32 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4377 X86 :ADC r8, imm8_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4378 X86 :ADC r16, imm8_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4379 X86 :ADC r32, imm8_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4381 X86 :ADC r16, imm16_0 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4382 X86 :ADC r32, imm32_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4384 X86 :ADC al, imm8_0 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4385 X86 :ADC ax, imm16_0 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4386 X86 :ADC eax, imm32_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4388 X86 :SBB r8, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4389 X86 :SBB r16, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4390 X86 :SBB r32, imm8 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4392 X86 :SBB r16, imm16 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4393 X86 :SBB r32, imm32 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4395 X86 :SBB al, imm8 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4396 X86 :SBB ax, imm16 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4397 X86 :SBB eax, imm32 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4399 X86 :SBB r8, imm8_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4400 X86 :SBB r16, imm8_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4401 X86 :SBB r32, imm8_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4403 X86 :SBB r16, imm16_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4404 X86 :SBB r32, imm32_0 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4406 X86 :SBB al, imm8_0 L: 3.13ns= 10.0c T: 3.15ns= 10.08c 4407 X86 :SBB ax, imm16_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4408 X86 :SBB eax, imm32_0 L: 3.13ns= 10.0c T: 3.13ns= 10.00c 4410 X86 :LEA r16, [disp32] L: 0.65ns= 2.1c T: 0.65ns= 2.08c 4411 X86 :LEA r32, [disp32] L: 0.25ns= 0.8c T: 0.25ns= 0.80c 4413 X86 :LEA r16, [r32] L: 0.94ns= 3.0c T: 0.68ns= 2.17c 4414 X86 :LEA r32, [r32] L: 0.31ns= 1.0c T: 0.12ns= 0.39c 4416 X86 :LEA r16, [r32+disp8] L: 0.94ns= 3.0c T: 0.65ns= 2.08c 4417 X86 :LEA r32, [r32+disp8] L: 0.31ns= 1.0c T: 0.21ns= 0.66c 4419 X86 :LEA r16, [r32+disp32] L: 0.94ns= 3.0c T: 0.65ns= 2.08c 4420 X86 :LEA r32, [r32+disp32] L: 0.31ns= 1.0c T: 0.12ns= 0.39c 4422 X86 :LEA r16, [r32 + r32] L: 1.30ns= 4.2c T: 0.65ns= 2.08c 4423 X86 :LEA r32, [r32 + r32] L: 0.31ns= 1.0c T: 0.11ns= 0.36c 4425 X86 :LEA r16, [r32 + r32 + disp8] L: 1.25ns= 4.0c T: 0.70ns= 2.25c 4426 X86 :LEA r32, [r32 + r32 + disp8] L: 0.63ns= 2.0c T: 0.63ns= 2.00c 4428 X86 :LEA r16, [r32 + r32 + disp32] L: 1.25ns= 4.0c T: 0.65ns= 2.08c 4429 X86 :LEA r32, [r32 + r32 + disp32] L: 0.63ns= 2.0c T: 0.25ns= 0.80c 4431 X86 :LEA r16, [r32 + r32 * 8] L: 1.25ns= 4.0c T: 0.65ns= 2.08c 4432 X86 :LEA r32, [r32 + r32 * 8] L: 0.65ns= 2.1c T: 0.25ns= 0.81c 4434 X86 :LEA r16, [r32 + r32 * 8 + disp8] L: 1.25ns= 4.0c T: 0.70ns= 2.25c 4435 X86 :LEA r32, [r32 + r32 * 8 + disp8] L: 0.94ns= 3.0c T: 0.39ns= 1.25c 4437 X86 :LEA r16, [r32 + r32 * 8 + disp32] L: 1.25ns= 4.0c T: 0.65ns= 2.08c 4438 X86 :LEA r32, [r32 + r32 * 8 + disp32] L: 0.94ns= 3.0c T: 0.39ns= 1.25c