| Loop Id: 2697 | Module: exec | Source: ams.c:569-621 [...] | Coverage: 0.03% |
|---|
| Loop Id: 2697 | Module: exec | Source: ams.c:569-621 [...] | Coverage: 0.03% |
|---|
0x4991ee VMOVSD %XMM2,(%RSI) |
0x4991f2 LEA 0x1(%R14),%RAX |
0x4991f6 CMP -0x50(%RBP),%R14 |
0x4991fa MOV %RAX,%R14 |
0x4991fd JE 4993df |
0x499203 MOV %R11,%RDX |
0x499206 MOV -0x30(%RBP),%RAX |
0x49920a MOVQ $0,(%RAX,%R14,8) |
0x499212 MOV 0x8(%R8,%R14,8),%R11 |
0x499217 MOV %R11,%R10 |
0x49921a SUB %RDX,%R10 |
0x49921d JLE 4991f2 |
0x49921f LEA (%RAX,%R14,8),%RSI |
0x499223 LEA (%RCX,%R11,8),%RAX |
0x499227 ADD $-0x8,%RAX |
0x49922b LEA (%RCX,%RDX,8),%RBX |
0x49922f CMP %RSI,%RAX |
0x499232 JB 49925b |
0x499234 CMP %RBX,%RSI |
0x499237 JB 49925b |
0x499239 VXORPD %XMM2,%XMM2,%XMM2 |
0x49923d NOPL (%RAX) |
(2700) 0x499240 VMOVSD (%RCX,%RDX,8),%XMM3 |
(2700) 0x499245 VANDPD %XMM0,%XMM3,%XMM3 |
(2700) 0x499249 VADDSD %XMM3,%XMM2,%XMM2 |
(2700) 0x49924d VMOVSD %XMM2,(%RSI) |
(2700) 0x499251 INC %RDX |
(2700) 0x499254 CMP %RDX,%R11 |
(2700) 0x499257 JNE 499240 |
0x499259 JMP 4991f2 |
0x49925b MOV %R10,%R9 |
0x49925e AND $-0x4,%R9 |
0x499262 JE 4992a5 |
0x499264 LEA -0x1(%R9),%RDI |
0x499268 VXORPD %XMM2,%XMM2,%XMM2 |
0x49926c XOR %EAX,%EAX |
0x49926e XCHG %AX,%AX |
(2699) 0x499270 VANDPD (%RBX,%RAX,8),%YMM1,%YMM3 |
(2699) 0x499275 VADDPD %YMM3,%YMM2,%YMM2 |
(2699) 0x499279 ADD $0x4,%RAX |
(2699) 0x49927d CMP %RDI,%RAX |
(2699) 0x499280 JBE 499270 |
0x499282 VEXTRACTF128 $0x1,%YMM2,%XMM3 |
0x499288 VADDPD %XMM3,%XMM2,%XMM2 |
0x49928c VPERMILPD $0x1,%XMM2,%XMM3 |
0x499292 VADDSD %XMM3,%XMM2,%XMM2 |
0x499296 CMP %R9,%R10 |
0x499299 MOV -0x48(%RBP),%R8 |
0x49929d JE 4991ee |
0x4992a3 JMP 4992ac |
0x4992a5 VXORPD %XMM2,%XMM2,%XMM2 |
0x4992a9 XOR %R9D,%R9D |
0x4992ac ADD %R9,%RDX |
0x4992af NOP |
(2698) 0x4992b0 VMOVSD (%RCX,%RDX,8),%XMM3 |
(2698) 0x4992b5 VANDPD %XMM0,%XMM3,%XMM3 |
(2698) 0x4992b9 VADDSD %XMM3,%XMM2,%XMM2 |
(2698) 0x4992bd INC %RDX |
(2698) 0x4992c0 CMP %RDX,%R11 |
(2698) 0x4992c3 JNE 4992b0 |
0x4992c5 JMP 4991ee |
/home/kcamus/qaas_runs/169-443-9681/intel/AMG/build/AMG/AMG/parcsr_ls/ams.c: 569 - 621 |
-------------------------------------------------------------------------------- |
569: if (cf_marker != NULL) |
[...] |
602: for (i = 0; i < num_rows; i++) |
603: { |
604: l1_norm[i] = 0.0; |
605: if (cf_marker == NULL) |
606: { |
607: /* Add the l1 norm of the diag part of the ith row */ |
608: for (j = A_diag_I[i]; j < A_diag_I[i+1]; j++) |
609: l1_norm[i] += fabs(A_diag_data[j]); |
[...] |
621: for (j = A_diag_I[i]; j < A_diag_I[i+1]; j++) |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►100.00+ | hypre_BoomerAMGSetup | par_amg_setup.c:1381 | exec |
| ○ | hypre_PCGSetup | pcg.c:234 | exec |
| ○ | main | amg.c:398 | exec |
| ○ | __libc_init_first | libc.so.6 |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.39 |
| CQA speedup if FP arith vectorized | 3.21 |
| CQA speedup if fully vectorized | 11.66 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.65 |
| Bottlenecks | micro-operation queue, |
| Function | hypre_ParCSRComputeL1Norms |
| Source | ams.c:569-621 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 10.75 |
| CQA cycles if no scalar integer | 4.50 |
| CQA cycles if FP arith vectorized | 3.34 |
| CQA cycles if fully vectorized | 0.92 |
| Front-end cycles | 10.75 |
| DIV/SQRT cycles | 6.50 |
| P0 cycles | 6.50 |
| P1 cycles | 2.00 |
| P2 cycles | 2.00 |
| P3 cycles | 2.00 |
| P4 cycles | 6.50 |
| P5 cycles | 6.50 |
| P6 cycles | 2.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 12.13 |
| Stall cycles (UFS) | 0.82 |
| Nb insns | 43.00 |
| Nb uops | 43.00 |
| Nb loads | 4.00 |
| Nb stores | 2.00 |
| Nb stack references | 3.00 |
| FLOP/cycle | 0.28 |
| Nb FLOP add-sub | 3.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 4.47 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 32.00 |
| Bytes stored | 16.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 40.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 33.33 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 50.00 |
| Vector-efficiency ratio all | 17.08 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 9.38 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 16.67 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 18.75 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 2.39 |
| CQA speedup if FP arith vectorized | 3.21 |
| CQA speedup if fully vectorized | 11.66 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.65 |
| Bottlenecks | micro-operation queue, |
| Function | hypre_ParCSRComputeL1Norms |
| Source | ams.c:569-621 |
| Source loop unroll info | NA |
| Source loop unroll confidence level | NA |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 10.75 |
| CQA cycles if no scalar integer | 4.50 |
| CQA cycles if FP arith vectorized | 3.34 |
| CQA cycles if fully vectorized | 0.92 |
| Front-end cycles | 10.75 |
| DIV/SQRT cycles | 6.50 |
| P0 cycles | 6.50 |
| P1 cycles | 2.00 |
| P2 cycles | 2.00 |
| P3 cycles | 2.00 |
| P4 cycles | 6.50 |
| P5 cycles | 6.50 |
| P6 cycles | 2.00 |
| P7 cycles | 0.00 |
| Inter-iter dependencies cycles | NA |
| FE+BE cycles (UFS) | 12.13 |
| Stall cycles (UFS) | 0.82 |
| Nb insns | 43.00 |
| Nb uops | 43.00 |
| Nb loads | 4.00 |
| Nb stores | 2.00 |
| Nb stack references | 3.00 |
| FLOP/cycle | 0.28 |
| Nb FLOP add-sub | 3.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 0.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 4.47 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 32.00 |
| Bytes stored | 16.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 40.00 |
| Vectorization ratio load | 0.00 |
| Vectorization ratio store | 0.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 33.33 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 50.00 |
| Vector-efficiency ratio all | 17.08 |
| Vector-efficiency ratio load | 12.50 |
| Vector-efficiency ratio store | 9.38 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 16.67 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 18.75 |
| Path / |
| Function | hypre_ParCSRComputeL1Norms |
| Source file and lines | ams.c:569-621 |
| Module | exec |
| nb instructions | 43 |
| nb uops | 43 |
| loop length | 156 |
| used x86 registers | 12 |
| used mmx registers | 0 |
| used xmm registers | 2 |
| used ymm registers | 1 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 10.75 cycles |
| front end | 10.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 6.50 | 6.50 | 2.00 | 2.00 | 2.00 | 6.50 | 6.50 | 2.00 |
| cycles | 6.50 | 6.50 | 2.00 | 2.00 | 2.00 | 6.50 | 6.50 | 2.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 12.13 |
| Stall cycles | 0.82 |
| ROB full (events) | 1.32 |
| Front-end | 10.75 |
| Dispatch | 6.50 |
| Overall L1 | 10.75 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 75% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 40% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 33% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| all | 11% |
| load | 12% |
| store | 6% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 21% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 18% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 17% |
| load | 12% |
| store | 9% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 16% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 18% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSD %XMM2,(%RSI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| LEA 0x1(%R14),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| CMP -0x50(%RBP),%R14 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JE 4993df | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %R11,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOVQ $0,(%RAX,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
| MOV 0x8(%R8,%R14,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %R11,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| SUB %RDX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JLE 4991f2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA (%RAX,%R14,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| LEA (%RCX,%R11,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| ADD $-0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| LEA (%RCX,%RDX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JB 49925b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP %RBX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JB 49925b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| VXORPD %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JMP 4991f2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV %R10,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| AND $-0x4,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 4992a5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA -0x1(%R9),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| VXORPD %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| VEXTRACTF128 $0x1,%YMM2,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
| VADDPD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VPERMILPD $0x1,%XMM2,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| VADDSD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| CMP %R9,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JE 4991ee | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| JMP 4992ac | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| VXORPD %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| ADD %R9,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JMP 4991ee | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| Function | hypre_ParCSRComputeL1Norms |
| Source file and lines | ams.c:569-621 |
| Module | exec |
| nb instructions | 43 |
| nb uops | 43 |
| loop length | 156 |
| used x86 registers | 12 |
| used mmx registers | 0 |
| used xmm registers | 2 |
| used ymm registers | 1 |
| used zmm registers | 0 |
| nb stack references | 3 |
| micro-operation queue | 10.75 cycles |
| front end | 10.75 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
|---|---|---|---|---|---|---|---|---|
| uops | 6.50 | 6.50 | 2.00 | 2.00 | 2.00 | 6.50 | 6.50 | 2.00 |
| cycles | 6.50 | 6.50 | 2.00 | 2.00 | 2.00 | 6.50 | 6.50 | 2.00 |
| Cycles executing div or sqrt instructions | NA |
| FE+BE cycles | 12.13 |
| Stall cycles | 0.82 |
| ROB full (events) | 1.32 |
| Front-end | 10.75 |
| Dispatch | 6.50 |
| Overall L1 | 10.75 |
| all | 0% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 0% |
| all | 75% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 50% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 40% |
| load | 0% |
| store | 0% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 33% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 50% |
| all | 11% |
| load | 12% |
| store | 6% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 12% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | 12% |
| all | 21% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 12% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 18% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 25% |
| all | 17% |
| load | 12% |
| store | 9% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 16% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 18% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVSD %XMM2,(%RSI) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
| LEA 0x1(%R14),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| CMP -0x50(%RBP),%R14 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
| MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JE 4993df | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| MOV %R11,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| MOV -0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOVQ $0,(%RAX,%R14,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
| MOV 0x8(%R8,%R14,8),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| MOV %R11,%R10 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| SUB %RDX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JLE 4991f2 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA (%RAX,%R14,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| LEA (%RCX,%R11,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| ADD $-0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| LEA (%RCX,%RDX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| CMP %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JB 49925b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| CMP %RBX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JB 49925b | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| VXORPD %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JMP 4991f2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| MOV %R10,%R9 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| AND $-0x4,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| JE 4992a5 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| LEA -0x1(%R9),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
| VXORPD %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| VEXTRACTF128 $0x1,%YMM2,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
| VADDPD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| VPERMILPD $0x1,%XMM2,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
| VADDSD %XMM3,%XMM2,%XMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
| CMP %R9,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| MOV -0x48(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
| JE 4991ee | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
| JMP 4992ac | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
| VXORPD %XMM2,%XMM2,%XMM2 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| ADD %R9,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
| NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
| JMP 4991ee | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
