| Loop Id: 9 | Module: exec | Source: stream.c:476-479 | Coverage: 0.12% |
|---|
| Loop Id: 9 | Module: exec | Source: stream.c:476-479 | Coverage: 0.12% |
|---|
0x402120 VMOVUPD 0x60(%R13,%RAX,8),%YMM6 [1] |
0x402127 VMOVUPD 0x80(%R13,%RAX,8),%YMM7 [1] |
0x402131 VMOVUPD 0xa0(%R13,%RAX,8),%YMM8 [1] |
0x40213b VSUBPD %YMM0,%YMM6,%YMM6 |
0x40213f VANDPD %YMM6,%YMM13,%YMM6 |
0x402143 VADDPD %YMM4,%YMM6,%YMM4 |
0x402147 VMOVUPD 0x60(%R12,%RAX,8),%YMM6 [1] |
0x40214e VMOVUPD 0x80(%R12,%RAX,8),%YMM9 [1] |
0x402158 VMOVUPD 0xa0(%R12,%RAX,8),%YMM10 [1] |
0x402162 VSUBPD %YMM1,%YMM6,%YMM6 |
0x402166 VANDPD %YMM6,%YMM13,%YMM6 |
0x40216a VADDPD %YMM5,%YMM6,%YMM5 |
0x40216e VMOVUPD 0x60(%RBX,%RAX,8),%YMM6 [1] |
0x402174 VMOVUPD 0x80(%RBX,%RAX,8),%YMM11 [1] |
0x40217d VMOVUPD 0xa0(%RBX,%RAX,8),%YMM12 [1] |
0x402186 VSUBPD %YMM2,%YMM6,%YMM6 |
0x40218a VANDPD %YMM6,%YMM13,%YMM6 |
0x40218e VADDPD %YMM3,%YMM6,%YMM3 |
0x402192 VSUBPD %YMM0,%YMM7,%YMM6 |
0x402196 VANDPD %YMM6,%YMM13,%YMM6 |
0x40219a VSUBPD %YMM1,%YMM9,%YMM7 |
0x40219e VANDPD %YMM7,%YMM13,%YMM7 |
0x4021a2 VSUBPD %YMM2,%YMM11,%YMM9 |
0x4021a6 VANDPD %YMM13,%YMM9,%YMM9 |
0x4021ab VSUBPD %YMM0,%YMM8,%YMM8 |
0x4021af VANDPD %YMM13,%YMM8,%YMM8 |
0x4021b4 VADDPD %YMM6,%YMM8,%YMM6 |
0x4021b8 VADDPD %YMM4,%YMM6,%YMM4 |
0x4021bc VSUBPD %YMM1,%YMM10,%YMM6 |
0x4021c0 VANDPD %YMM6,%YMM13,%YMM6 |
0x4021c4 VADDPD %YMM7,%YMM6,%YMM6 |
0x4021c8 VADDPD %YMM5,%YMM6,%YMM5 |
0x4021cc VSUBPD %YMM2,%YMM12,%YMM6 |
0x4021d0 VANDPD %YMM6,%YMM13,%YMM6 |
0x4021d4 VADDPD %YMM6,%YMM9,%YMM6 |
0x4021d8 VADDPD %YMM3,%YMM6,%YMM3 |
0x4021dc ADD $0xc,%RAX |
0x4021e0 CMP $0x3344fff4,%RAX |
0x4021e6 JB 402120 |
/home/eoseret/qaas_runs_CPU_9468/171-111-6305/intel/stream/build/stream/src/stream.c: 476 - 479 |
-------------------------------------------------------------------------------- |
476: for (j=0; j<STREAM_ARRAY_SIZE; j++) { |
477: aSumErr += abs(a[j] - aj); |
478: bSumErr += abs(b[j] - bj); |
479: cSumErr += abs(c[j] - cj); |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 2.00 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.02 |
| Bottlenecks | P1, |
| Function | checkSTREAMresults |
| Source | stream.c:476-479 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 9.33 |
| CQA cycles if no scalar integer | 9.33 |
| CQA cycles if FP arith vectorized | 4.67 |
| CQA cycles if fully vectorized | 4.67 |
| Front-end cycles | 6.33 |
| DIV/SQRT cycles | 9.17 |
| P0 cycles | 9.33 |
| P1 cycles | 3.00 |
| P2 cycles | 3.00 |
| P3 cycles | 0.00 |
| P4 cycles | 9.00 |
| P5 cycles | 0.50 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 3.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 6 |
| FE+BE cycles (UFS) | 9.26 |
| Stall cycles (UFS) | 2.39 |
| Nb insns | 39.00 |
| Nb uops | 38.00 |
| Nb loads | 9.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.71 |
| Nb FLOP add-sub | 72.00 |
| 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 | 30.86 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 288.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 3.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 100.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 100.00 |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 50.00 |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 2.00 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.02 |
| Bottlenecks | P1, |
| Function | checkSTREAMresults |
| Source | stream.c:476-479 |
| Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 9.33 |
| CQA cycles if no scalar integer | 9.33 |
| CQA cycles if FP arith vectorized | 4.67 |
| CQA cycles if fully vectorized | 4.67 |
| Front-end cycles | 6.33 |
| DIV/SQRT cycles | 9.17 |
| P0 cycles | 9.33 |
| P1 cycles | 3.00 |
| P2 cycles | 3.00 |
| P3 cycles | 0.00 |
| P4 cycles | 9.00 |
| P5 cycles | 0.50 |
| P6 cycles | 0.00 |
| P7 cycles | 0.00 |
| P8 cycles | 0.00 |
| P9 cycles | 0.00 |
| P10 cycles | 3.00 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 6 |
| FE+BE cycles (UFS) | 9.26 |
| Stall cycles (UFS) | 2.39 |
| Nb insns | 39.00 |
| Nb uops | 38.00 |
| Nb loads | 9.00 |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 7.71 |
| Nb FLOP add-sub | 72.00 |
| 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 | 30.86 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 288.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 3.00 |
| Stride n | 0.00 |
| Stride unknown | 0.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 100.00 |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | 100.00 |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | 50.00 |
| Path / |
| Function | checkSTREAMresults |
| Source file and lines | stream.c:476-479 |
| Module | exec |
| nb instructions | 39 |
| nb uops | 38 |
| loop length | 204 |
| used x86 registers | 4 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 14 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 6.33 cycles |
| front end | 6.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 9.17 | 9.33 | 3.00 | 3.00 | 0.00 | 9.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
| cycles | 9.17 | 9.33 | 3.00 | 3.00 | 0.00 | 9.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 6.00 |
| FE+BE cycles | 9.26 |
| Stall cycles | 2.39 |
| RS full (events) | 6.51 |
| Front-end | 6.33 |
| Dispatch | 9.33 |
| Data deps. | 6.00 |
| Overall L1 | 9.33 |
| all | 100% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 50% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 50% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD 0x60(%R13,%RAX,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x80(%R13,%RAX,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0xa0(%R13,%RAX,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VSUBPD %YMM0,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM4,%YMM6,%YMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VMOVUPD 0x60(%R12,%RAX,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x80(%R12,%RAX,8),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0xa0(%R12,%RAX,8),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VSUBPD %YMM1,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM5,%YMM6,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VMOVUPD 0x60(%RBX,%RAX,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x80(%RBX,%RAX,8),%YMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0xa0(%RBX,%RAX,8),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VSUBPD %YMM2,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM3,%YMM6,%YMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VSUBPD %YMM0,%YMM7,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VSUBPD %YMM1,%YMM9,%YMM7 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM7,%YMM13,%YMM7 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VSUBPD %YMM2,%YMM11,%YMM9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM13,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VSUBPD %YMM0,%YMM8,%YMM8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM13,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM6,%YMM8,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %YMM4,%YMM6,%YMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VSUBPD %YMM1,%YMM10,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM7,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %YMM5,%YMM6,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VSUBPD %YMM2,%YMM12,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM6,%YMM9,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %YMM3,%YMM6,%YMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| ADD $0xc,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP $0x3344fff4,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 402120 <checkSTREAMresults+0xd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | checkSTREAMresults |
| Source file and lines | stream.c:476-479 |
| Module | exec |
| nb instructions | 39 |
| nb uops | 38 |
| loop length | 204 |
| used x86 registers | 4 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 14 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 6.33 cycles |
| front end | 6.33 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 9.17 | 9.33 | 3.00 | 3.00 | 0.00 | 9.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
| cycles | 9.17 | 9.33 | 3.00 | 3.00 | 0.00 | 9.00 | 0.50 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 6.00 |
| FE+BE cycles | 9.26 |
| Stall cycles | 2.39 |
| RS full (events) | 6.51 |
| Front-end | 6.33 |
| Dispatch | 9.33 |
| Data deps. | 6.00 |
| Overall L1 | 9.33 |
| all | 100% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 100% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | 100% |
| all | 50% |
| load | 50% |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 50% |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD 0x60(%R13,%RAX,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x80(%R13,%RAX,8),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0xa0(%R13,%RAX,8),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VSUBPD %YMM0,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM4,%YMM6,%YMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VMOVUPD 0x60(%R12,%RAX,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x80(%R12,%RAX,8),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0xa0(%R12,%RAX,8),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VSUBPD %YMM1,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM5,%YMM6,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VMOVUPD 0x60(%RBX,%RAX,8),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0x80(%RBX,%RAX,8),%YMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VMOVUPD 0xa0(%RBX,%RAX,8),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VSUBPD %YMM2,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM3,%YMM6,%YMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VSUBPD %YMM0,%YMM7,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VSUBPD %YMM1,%YMM9,%YMM7 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM7,%YMM13,%YMM7 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VSUBPD %YMM2,%YMM11,%YMM9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM13,%YMM9,%YMM9 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VSUBPD %YMM0,%YMM8,%YMM8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM13,%YMM8,%YMM8 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM6,%YMM8,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %YMM4,%YMM6,%YMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VSUBPD %YMM1,%YMM10,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM7,%YMM6,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %YMM5,%YMM6,%YMM5 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VSUBPD %YMM2,%YMM12,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VANDPD %YMM6,%YMM13,%YMM6 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
| VADDPD %YMM6,%YMM9,%YMM6 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| VADDPD %YMM3,%YMM6,%YMM3 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
| ADD $0xc,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP $0x3344fff4,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JB 402120 <checkSTREAMresults+0xd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
