| Loop Id: 1281 | Module: exec | Source: stl_algobase.h:924-924 | Coverage: 0.08% |
|---|
| Loop Id: 1281 | Module: exec | Source: stl_algobase.h:924-924 | Coverage: 0.08% |
|---|
0x4498e0 ST1B {Z0.B}, P0, [X0, X8] [1] |
0x4498e4 INCP X8, P0.B |
0x4498e8 WHILELO P0.B, X8, X2 |
0x4498ec B.MI 4498e0 |
/usr/lib/gcc/aarch64-linux-gnu/11/../../../../include/c++/11/bits/stl_algobase.h: 924 - 924 |
-------------------------------------------------------------------------------- |
924: *__first = __tmp; |
| Coverage (%) | Name | Source Location | Module |
|---|---|---|---|
| ►87.50+ | qmcplusplus::DistanceTableAA<d[...] | DistanceTableAA.h:53 | exec |
| ○ | qmcplusplus::createDistanceTab[...] | ostream:611 | exec |
| ○ | qmcplusplus::ParticleSet::addT[...] | vector.tcc:112 | exec |
| ○ | qmcplusplus::build_WaveFunctio[...] | WaveFunction.cpp:79 | exec |
| ○ | .omp_outlined. | miniqmc.cpp:389 | exec |
| ○ | __kmp_invoke_microtask | libomp.so | |
| ►12.50+ | qmcplusplus::DistanceTableBA<d[...] | stl_vector.h:919 | exec |
| ○ | qmcplusplus::createDistanceTab[...] | ostream:611 | exec |
| ○ | qmcplusplus::ParticleSet::addT[...] | vector.tcc:112 | exec |
| ○ | qmcplusplus::build_WaveFunctio[...] | WaveFunction.cpp:79 | exec |
| ○ | .omp_outlined. | miniqmc.cpp:389 | exec |
| ○ | __kmp_invoke_microtask | libomp.so |
| 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 | 2.50 |
| Bottlenecks | |
| Function | qmcplusplus::Matrix |
| Source | stl_algobase.h:924-924 |
| Source loop unroll info | multi-versionned |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.00 |
| CQA cycles if no scalar integer | 5.00 |
| CQA cycles if FP arith vectorized | 5.00 |
| CQA cycles if fully vectorized | 5.00 |
| Front-end cycles | 0.50 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 0.50 |
| P1 cycles | 0.00 |
| P2 cycles | 0.00 |
| P3 cycles | 2.00 |
| P4 cycles | 0.00 |
| P5 cycles | 0.25 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.25 |
| P9 cycles | 0.50 |
| P10 cycles | 0.50 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 5 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 4.00 |
| Nb uops | 4.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 6.40 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 32.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | NA |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 100.00 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| 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 | 2.50 |
| Bottlenecks | |
| Function | qmcplusplus::Matrix |
| Source | stl_algobase.h:924-924 |
| Source loop unroll info | multi-versionned |
| Source loop unroll confidence level | max |
| Unroll/vectorization loop type | NA |
| Unroll factor | NA |
| CQA cycles | 5.00 |
| CQA cycles if no scalar integer | 5.00 |
| CQA cycles if FP arith vectorized | 5.00 |
| CQA cycles if fully vectorized | 5.00 |
| Front-end cycles | 0.50 |
| DIV/SQRT cycles | 0.50 |
| P0 cycles | 0.50 |
| P1 cycles | 0.00 |
| P2 cycles | 0.00 |
| P3 cycles | 2.00 |
| P4 cycles | 0.00 |
| P5 cycles | 0.25 |
| P6 cycles | 0.25 |
| P7 cycles | 0.25 |
| P8 cycles | 0.25 |
| P9 cycles | 0.50 |
| P10 cycles | 0.50 |
| P11 cycles | 0.00 |
| P12 cycles | 0.00 |
| P13 cycles | 0.00 |
| P14 cycles | 0.00 |
| Inter-iter dependencies cycles | 5 |
| FE+BE cycles (UFS) | NA |
| Stall cycles (UFS) | NA |
| Nb insns | 4.00 |
| Nb uops | 4.00 |
| Nb loads | NA |
| Nb stores | 1.00 |
| Nb stack references | 0.00 |
| FLOP/cycle | 0.00 |
| Nb FLOP add-sub | 0.00 |
| 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 | 6.40 |
| Bytes prefetched | 0.00 |
| Bytes loaded | 0.00 |
| Bytes stored | 32.00 |
| Stride 0 | NA |
| Stride 1 | NA |
| Stride n | NA |
| Stride unknown | NA |
| Stride indirect | NA |
| Vectorization ratio all | 100.00 |
| Vectorization ratio load | NA |
| Vectorization ratio store | 100.00 |
| Vectorization ratio mul | NA |
| Vectorization ratio add_sub | NA |
| Vectorization ratio fma | NA |
| Vectorization ratio div_sqrt | NA |
| Vectorization ratio other | NA |
| Vector-efficiency ratio all | 100.00 |
| Vector-efficiency ratio load | NA |
| Vector-efficiency ratio store | 100.00 |
| Vector-efficiency ratio mul | NA |
| Vector-efficiency ratio add_sub | NA |
| Vector-efficiency ratio fma | NA |
| Vector-efficiency ratio div_sqrt | NA |
| Vector-efficiency ratio other | NA |
| Path / |
| Function | qmcplusplus::Matrix |
| Source file and lines | stl_algobase.h:924-924 |
| Module | exec |
| nb instructions | 4 |
| loop length | 16 |
| nb stack references | 0 |
| front end | 0.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.00 | 0.00 | 2.00 | 0.00 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0.00 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.00 | 0.00 | 2.00 | 0.00 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 5.00 |
| Front-end | 0.50 |
| Data deps. | 5.00 |
| Overall L1 | 5.00 |
| all | 100% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| 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 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ST1B {Z0.B}, P0, [X0, X8] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 |
| INCP X8, P0.B | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| WHILELO P0.B, X8, X2 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 2 |
| B.MI 4498e0 <_ZN11qmcplusplus6MatrixIdNS_10MallocatorIdLm32EEEE6resizeEmm+0xc0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
| Function | qmcplusplus::Matrix |
| Source file and lines | stl_algobase.h:924-924 |
| Module | exec |
| nb instructions | 4 |
| loop length | 16 |
| nb stack references | 0 |
| front end | 0.50 cycles |
| P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | P12 | P13 | P14 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| uops | 0.50 | 0.50 | 0.00 | 0.00 | 2.00 | 0.00 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0.00 | 0.00 | 0.00 |
| cycles | 0.50 | 0.50 | 0.00 | 0.00 | 2.00 | 0.00 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0.00 | 0.00 | 0.00 |
| Cycles executing div or sqrt instructions | NA |
| Longest recurrence chain latency (RecMII) | 5.00 |
| Front-end | 0.50 |
| Data deps. | 5.00 |
| Overall L1 | 5.00 |
| all | 100% |
| load | NA (no load vectorizable/vectorized instructions) |
| store | 100% |
| mul | NA (no mul vectorizable/vectorized instructions) |
| add-sub | NA (no add-sub vectorizable/vectorized instructions) |
| fma | NA (no fma vectorizable/vectorized instructions) |
| 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 | Latency | Recip. throughput |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ST1B {Z0.B}, P0, [X0, X8] | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 | 0.25 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0 | 0 | 2 | 0.50 |
| INCP X8, P0.B | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 1 |
| WHILELO P0.B, X8, X2 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 2 |
| B.MI 4498e0 <_ZN11qmcplusplus6MatrixIdNS_10MallocatorIdLm32EEEE6resizeEmm+0xc0> | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |