| Loop Id: 978 | Module: exec | Source: inner_product.hpp:155-155 [...] | Coverage: 0.41% |
|---|
| Loop Id: 978 | Module: exec | Source: inner_product.hpp:155-155 [...] | Coverage: 0.41% |
|---|
0x438cec LDR Q7, [X11, X6] [1] |
0x438cf0 LDR Q16, [X18, X6] [2] |
0x438cf4 ORR X19, XZR, X7 |
0x438cf8 LD3 {V17.2D, V18.2D, V19.2D}, [X19], #80 [3] |
0x438cfc ADD X7, X7, #96 |
0x438d00 ADD X6, X6, #32 |
0x438d04 FMLA V1.2D, V17.2D, V7.2D |
0x438d08 FMLA V2.2D, V18.2D, V7.2D |
0x438d0c FMLA V3.2D, V19.2D, V7.2D |
0x438d10 LD3 {V20.2D, V21.2D, V22.2D}, [X19] [3] |
0x438d14 FMLA V4.2D, V20.2D, V16.2D |
0x438d18 FMLA V5.2D, V21.2D, V16.2D |
0x438d1c FMLA V6.2D, V22.2D, V16.2D |
0x438d20 CMP X4, X6 |
0x438d24 B.NE 438cec |
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 155 - 155 |
-------------------------------------------------------------------------------- |
155: for (int i = 0; i < n; i++) |
/home/hbollore/qaas/qaas-runs/174-135-6342/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 63 - 94 |
-------------------------------------------------------------------------------- |
63: return (a * b); |
[...] |
94: (const_cast<T1&>(a) += b); |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►50.94+ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:250 | exec |
| ○ | main.omp_outlined.63 | miniqmc.cpp:467 | exec |
| ○ | __kmp_invoke_microtask | libomp.so | |
| ►49.06+ | qmcplusplus::WaveFunction::eva[...] | WaveFunction.cpp:249 | exec |
| ○ | main.omp_outlined.63 | miniqmc.cpp:467 | exec |
| ○ | __kmp_invoke_microtask | libomp.so |
| min | med | avg | max |
|---|---|---|---|
| Percentile Index | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
|---|---|---|---|---|---|---|---|---|---|---|
| Value |
| min | med | avg | max |
|---|---|---|---|
| Percentile Index | 10 | 20 | 30 | 40 | 50 | 60 | 70 | 80 | 90 | 100 |
|---|---|---|---|---|---|---|---|---|---|---|
| Value |
| Path / |
| Metric | Value |
|---|---|
| CQA speedup if no scalar integer | 1.00 |
| CQA speedup if FP arith vectorized | 1.00 |
| CQA speedup if fully vectorized | 1.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.07 |
| Bottlenecks | P8, P9, P10, P11, |
| Function | miniqmcreference::DiracDeterminantRef |
| Source | inner_product.hpp:155-155,OperatorTags.h:63-63,OperatorTags.h:94-94 |
| Source loop unroll info | unrolled by 4 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | 4 |
| CQA cycles | 2.00 |
| CQA cycles if no scalar integer | 2.00 |
| CQA cycles if FP arith vectorized | 2.00 |
| CQA cycles if fully vectorized | 2.00 |
| Front-end cycles | 1.88 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.67 |
| P5 cycles | 0.67 |
| P6 cycles | 0.58 |
| P7 cycles | 0.58 |
| P8 cycles | 2.00 |
| P9 cycles | 2.00 |
| P10 cycles | 2.00 |
| P11 cycles | 2.00 |
| P12 cycles | 1.33 |
| P13 cycles | 1.33 |
| P14 cycles | 1.33 |
| P15 cycles | 0.00 |
| P16 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 2 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 15.00 |
| Nb uops | 15.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 12.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 12.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 64.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 2.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 90.91 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 95.45 |
| Vector-efficiency ratio load | 100.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | 100.00 |
| 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 | 1.00 |
| CQA speedup if fully vectorized | 1.00 |
| CQA speedup if no inter-iteration dependency | NA |
| CQA speedup if next bottleneck killed | 1.07 |
| Bottlenecks | P8, P9, P10, P11, |
| Function | miniqmcreference::DiracDeterminantRef |
| Source | inner_product.hpp:155-155,OperatorTags.h:63-63,OperatorTags.h:94-94 |
| Source loop unroll info | unrolled by 4 |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | 4 |
| CQA cycles | 2.00 |
| CQA cycles if no scalar integer | 2.00 |
| CQA cycles if FP arith vectorized | 2.00 |
| CQA cycles if fully vectorized | 2.00 |
| Front-end cycles | 1.88 |
| P0 cycles | 0.50 |
| P1 cycles | 0.50 |
| P2 cycles | 0.75 |
| P3 cycles | 0.75 |
| P4 cycles | 0.67 |
| P5 cycles | 0.67 |
| P6 cycles | 0.58 |
| P7 cycles | 0.58 |
| P8 cycles | 2.00 |
| P9 cycles | 2.00 |
| P10 cycles | 2.00 |
| P11 cycles | 2.00 |
| P12 cycles | 1.33 |
| P13 cycles | 1.33 |
| P14 cycles | 1.33 |
| P15 cycles | 0.00 |
| P16 cycles | 0.00 |
| DIV/SQRT cycles | 0.00 |
| Inter-iter dependencies cycles | 2 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 15.00 |
| Nb uops | 15.00 |
| Nb loads | NA |
| Nb stores | 0.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 12.00 |
| Nb FLOP add-sub | 0.00 |
| Nb FLOP mul | 0.00 |
| Nb FLOP fma | 12.00 |
| Nb FLOP div | 0.00 |
| Nb FLOP rcp | 0.00 |
| Nb FLOP sqrt | 0.00 |
| Nb FLOP rsqrt | 0.00 |
| Bytes/cycle | 64.00 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 128.00 |
| Bytes stored | 0.00 |
| Stride 0 | 0.00 |
| Stride 1 | 0.00 |
| Stride n | 2.00 |
| Stride unknown | 1.00 |
| Stride indirect | 0.00 |
| Vectorization ratio all | 90.91 |
| Vectorization ratio load | 100.00 |
| Vectorization ratio store | NA |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | 0.00 |
| Vectorization ratio fma | 100.00 |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 95.45 |
| Vector-efficiency ratio load | 100.00 |
| Vector-efficiency ratio store | NA |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | 50.00 |
| Vector-efficiency ratio fma | 100.00 |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | miniqmcreference::DiracDeterminantRef |
| Source file and lines | inner_product.hpp:155-155 |
| Module | exec |
| nb instructions | 15 |
| loop length | 60 |
| nb stack references | 0 |
| front end | 1.88 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 2.00 | 2.00 | 2.00 | 2.00 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 2.00 | 2.00 | 2.00 | 2.00 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 1.88 |
| Data deps. | 2.00 |
| Overall L1 | 2.00 |
| all | 80% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 90% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 100% |
| 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 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR Q7, [X11, X6] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| LDR Q16, [X18, X6] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| ORR X19, XZR, X7 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| LD3 {V17.2D, V18.2D, V19.2D}, [X19], #80 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.33 | 0.33 | 0.33 | 0 | 0 | 8 | 1 | vect (100.0%) |
| ADD X7, X7, #96 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (50.0%) |
| ADD X6, X6, #32 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| FMLA V1.2D, V17.2D, V7.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V2.2D, V18.2D, V7.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V3.2D, V19.2D, V7.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| LD3 {V20.2D, V21.2D, V22.2D}, [X19] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.33 | 0.33 | 0.33 | 0 | 0 | 8 | 1 | vect (100.0%) |
| FMLA V4.2D, V20.2D, V16.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V5.2D, V21.2D, V16.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V6.2D, V22.2D, V16.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| CMP X4, X6 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.NE 438cec <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x28c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |
| Function | miniqmcreference::DiracDeterminantRef |
| Source file and lines | inner_product.hpp:155-155 |
| Module | exec |
| nb instructions | 15 |
| loop length | 60 |
| nb stack references | 0 |
| front end | 1.88 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | P15 | P16 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 2.00 | 2.00 | 2.00 | 2.00 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.75 | 0.75 | 0.67 | 0.67 | 0.58 | 0.58 | 2.00 | 2.00 | 2.00 | 2.00 | 1.33 | 1.33 | 1.33 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 2.00 |
| Front-end | 1.88 |
| Data deps. | 2.00 |
| Overall L1 | 2.00 |
| all | 80% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | NA (no fma vectorizable/vectorized instructions) |
| other | NA (no other vectorizable/vectorized instructions) |
| all | 100% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | NA (no store vectorizable/vectorized instructions) |
| 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 | 90% |
| load | 100% |
| store | NA (no store vectorizable/vectorized instructions) |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | 0% |
| fma | 100% |
| 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 | P12 | P13 | P14 | P15 | P16 | Latency | Recip. throughput | Vectorization |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LDR Q7, [X11, X6] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| LDR Q16, [X18, X6] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0.33 | 0.33 | 0 | 0 | 6 | 0.33 | vect (100.0%) |
| ORR X19, XZR, X7 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| LD3 {V17.2D, V18.2D, V19.2D}, [X19], #80 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.33 | 0.33 | 0.33 | 0 | 0 | 8 | 1 | vect (100.0%) |
| ADD X7, X7, #96 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | scal (50.0%) |
| ADD X6, X6, #32 | 1 | 0 | 0 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0.17 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 | N/A |
| FMLA V1.2D, V17.2D, V7.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V2.2D, V18.2D, V7.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V3.2D, V19.2D, V7.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| LD3 {V20.2D, V21.2D, V22.2D}, [X19] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.33 | 0.33 | 0.33 | 0 | 0 | 8 | 1 | vect (100.0%) |
| FMLA V4.2D, V20.2D, V16.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V5.2D, V21.2D, V16.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| FMLA V6.2D, V22.2D, V16.2D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 4 | 0.25 | vect (100.0%) |
| CMP X4, X6 | 1 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0.25 | 0.25 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 | N/A |
| B.NE 438cec <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE10evaluateGLERNS1_11ParticleSetERNS1_14ParticleAttribINS1_10TinyVectorIdLj3EEESaIS9_EEERNS7_IdSaIdEEEb+0x28c> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 | N/A |