| Loop Id: 24 | Module: exec | Source: stream.c:354-356 | Coverage: 28.43% |
|---|
| Loop Id: 24 | Module: exec | Source: stream.c:354-356 | Coverage: 28.43% |
|---|
0x403110 VMOVUPD (%R15,%R12,8),%YMM1 [3] |
0x403116 VFMADD213PD (%R14,%R12,8),%YMM0,%YMM1 [2] |
0x40311c VMOVUPD %YMM1,(%R11,%R12,8) [1] |
0x403122 ADD $0x4,%R12 |
0x403126 CMP %RCX,%R12 |
0x403129 JL 403110 |
/home/eoseret/qaas_runs_CPU_9468/171-111-6305/intel/stream/build/stream/src/stream.c: 354 - 356 |
-------------------------------------------------------------------------------- |
354: #pragma omp parallel for |
355: for (j=0; j<STREAM_ARRAY_SIZE; j++) |
356: a[j] = b[j]+scalar*c[j]; |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.41 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.50 |
| Bottlenecks | micro-operation queue, P0, |
| Function | main.extracted.65 |
| Source | stream.c:354-356 |
| Source loop unroll info | unrolled by 4 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | main |
| Unroll factor | 4 |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 0.71 |
| CQA cycles if fully vectorized | 0.50 |
| Front-end cycles | 1.00 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 0.50 |
| P1 cycles | 0.67 |
| P2 cycles | 0.67 |
| P3 cycles | 0.50 |
| P4 cycles | 0.00 |
| P5 cycles | 0.50 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 0.50 |
| P9 cycles | 0.00 |
| P10 cycles | 0.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 1.16 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 6.00 |
| Nb uops | 5.00 |
| Nb loads | 2.00 |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 8.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 4.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 96.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 64.00 |
| Bytes stored | 32.00 |
| 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 | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.41 |
| CQA speedup if fully vectorized | 2.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.50 |
| Bottlenecks | micro-operation queue, P0, |
| Function | main.extracted.65 |
| Source | stream.c:354-356 |
| Source loop unroll info | unrolled by 4 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | main |
| Unroll factor | 4 |
| CQA cycles | 1.00 |
| CQA cycles if no scalar integer | 1.00 |
| CQA cycles if FP arith vectorized | 0.71 |
| CQA cycles if fully vectorized | 0.50 |
| Front-end cycles | 1.00 |
| DIV/SQRT cycles | 1.00 |
| P0 cycles | 0.50 |
| P1 cycles | 0.67 |
| P2 cycles | 0.67 |
| P3 cycles | 0.50 |
| P4 cycles | 0.00 |
| P5 cycles | 0.50 |
| P6 cycles | 0.50 |
| P7 cycles | 0.50 |
| P8 cycles | 0.50 |
| P9 cycles | 0.00 |
| P10 cycles | 0.67 |
| P11 cycles | 0.00 |
| Inter-iter dependencies cycles | 1 |
| FE+BE cycles (UFS) | 1.16 |
| Stall cycles (UFS) | 0.00 |
| Nb insns | 6.00 |
| Nb uops | 5.00 |
| Nb loads | 2.00 |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 8.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 4.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 96.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 64.00 |
| Bytes stored | 32.00 |
| 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 | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 50.00 |
| Vector-efficiency ratio load | 50.00 |
| Vector-efficiency ratio store | 50.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | 50.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | main.extracted.65 |
| Source file and lines | stream.c:354-356 |
| Module | exec |
| nb instructions | 6 |
| nb uops | 5 |
| loop length | 27 |
| used x86 registers | 5 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 2 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.00 cycles |
| front end | 1.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 0.50 | 0.67 | 0.67 | 0.50 | 0.00 | 0.50 | 0.50 | 0.50 | 0.50 | 0.00 | 0.67 |
| cycles | 1.00 | 0.50 | 0.67 | 0.67 | 0.50 | 0.00 | 0.50 | 0.50 | 0.50 | 0.50 | 0.00 | 0.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 1.16 |
| Stall cycles | 0.00 |
| Front-end | 1.00 |
| Dispatch | 1.00 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 100% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R15,%R12,8),%YMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD (%R14,%R12,8),%YMM0,%YMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM1,(%R11,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x4,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RCX,%R12 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JL 403110 <main.extracted.65+0xd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
| Function | main.extracted.65 |
| Source file and lines | stream.c:354-356 |
| Module | exec |
| nb instructions | 6 |
| nb uops | 5 |
| loop length | 27 |
| used x86 registers | 5 |
| used mmx registers | 0 |
| used xmm registers | 0 |
| used ymm registers | 2 |
| used zmm registers | 0 |
| nb stack references | 0 |
| micro-operation queue | 1.00 cycles |
| front end | 1.00 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 1.00 | 0.50 | 0.67 | 0.67 | 0.50 | 0.00 | 0.50 | 0.50 | 0.50 | 0.50 | 0.00 | 0.67 |
| cycles | 1.00 | 0.50 | 0.67 | 0.67 | 0.50 | 0.00 | 0.50 | 0.50 | 0.50 | 0.50 | 0.00 | 0.67 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 1.00 |
| FE+BE cycles | 1.16 |
| Stall cycles | 0.00 |
| Front-end | 1.00 |
| Dispatch | 1.00 |
| Data deps. | 1.00 |
| Overall L1 | 1.00 |
| all | 100% |
| load | 100% |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 100% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 50% |
| load | 50% |
| store | 50% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | 50% |
| div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VMOVUPD (%R15,%R12,8),%YMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
| VFMADD213PD (%R14,%R12,8),%YMM0,%YMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
| VMOVUPD %YMM1,(%R11,%R12,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
| ADD $0x4,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
| CMP %RCX,%R12 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
| JL 403110 <main.extracted.65+0xd0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
