Loop Id: 36 | Module: exec | Source: miniqmc.cpp:429-458 [...] | Coverage: 0.01% |
---|
Loop Id: 36 | Module: exec | Source: miniqmc.cpp:429-458 [...] | Coverage: 0.01% |
---|
0x40d500 MOV %RBX,%RDI |
0x40d503 MOV %R12D,%ESI |
0x40d506 CALL 47c350 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> |
0x40d50b MOV 0x78(%RSP),%RDI [1] |
0x40d510 MOV %R12D,%ESI |
0x40d513 CALL 413a50 <_ZN11qmcplusplus12WaveFunction7restoreEi> |
0x40d518 INC %R12 |
0x40d51b MOV 0x38(%RSP),%R15 [1] |
0x40d520 ADD $0x18,%R15 |
0x40d524 MOV 0x110(%RSP),%RAX [1] |
0x40d52c CMP %R12,%RAX |
0x40d52f JE 40c140 |
0x40d535 MOV %R15,0x38(%RSP) [1] |
0x40d53a MOV 0x28(%R14),%RDI [2] |
0x40d53e VZEROUPPER |
0x40d541 CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40d546 LEA 0x240(%RSP),%RDI |
0x40d54e MOV 0x78(%RSP),%R15 [1] |
0x40d553 MOV %R15,%RSI |
0x40d556 MOV %RBX,%RDX |
0x40d559 MOV %R12D,%ECX |
0x40d55c CALL 4133d0 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> |
0x40d561 MOV 0x28(%R14),%RDI [2] |
0x40d565 CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40d56a MOV %RBX,%RDI |
0x40d56d MOV %R12D,%ESI |
0x40d570 MOV 0x38(%RSP),%RDX [1] |
0x40d575 MOV $0x1,%ECX |
0x40d57a CALL 47b0a0 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> |
0x40d57f MOV 0x30(%R14),%RDI [2] |
0x40d583 CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40d588 VXORPD %XMM0,%XMM0,%XMM0 |
0x40d58c VMOVUPD %XMM0,0x220(%RSP) [1] |
0x40d595 MOVQ $0,0x230(%RSP) [1] |
0x40d5a1 MOV %R15,%RDI |
0x40d5a4 MOV %RBX,%RSI |
0x40d5a7 MOV %R12D,%EDX |
0x40d5aa LEA 0x220(%RSP),%RCX |
0x40d5b2 CALL 413550 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> |
0x40d5b7 MOV 0x30(%R14),%RDI [2] |
0x40d5bb CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40d5c0 VMOVSD 0x190(%RSP),%XMM0 [1] |
0x40d5c9 MOV 0xb0(%RSP),%RAX [1] |
0x40d5d1 VUCOMISD (%RAX,%R12,8),%XMM0 [3] |
0x40d5d7 JBE 40d500 |
0x40d5dd MOV 0x38(%R14),%RDI [2] |
0x40d5e1 CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40d5e6 MOV 0x78(%RSP),%RDI [1] |
0x40d5eb MOV %RBX,%RSI |
0x40d5ee MOV %R12D,%EDX |
0x40d5f1 CALL 413810 <_ZN11qmcplusplus12WaveFunction10acceptMoveERNS_11ParticleSetEi> |
0x40d5f6 MOV 0x38(%R14),%RDI [2] |
0x40d5fa CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40d5ff MOV %RBX,%RDI |
0x40d602 MOV %R12D,%ESI |
0x40d605 CALL 47bd60 <_ZN11qmcplusplus11ParticleSet10acceptMoveEi> |
0x40d60a MOV 0xa0(%RSP),%RAX [1] |
0x40d612 INC %EAX |
0x40d614 MOV %RAX,0xa0(%RSP) [1] |
0x40d61c JMP 40d518 |
/usr/lib/gcc/x86_64-redhat-linux/8/../../../../include/c++/8/bits/refwrap.h: 313 - 313 |
-------------------------------------------------------------------------------- |
313: { return *_M_data; } |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 62 - 62 |
-------------------------------------------------------------------------------- |
62: X[d] = T(0); |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/Drivers/miniqmc.cpp: 429 - 458 |
-------------------------------------------------------------------------------- |
429: for (int iel = 0; iel < nels; ++iel) |
430: { |
431: // Compute gradient at the current position |
432: Timers[Timer_evalGrad].get().start(); |
433: PosType grad_now = wavefunction.evalGrad(els, iel); |
434: Timers[Timer_evalGrad].get().stop(); |
435: |
436: // Construct trial move |
437: els.makeMove(iel, delta[iel]); |
438: |
439: // Compute gradient at the trial position |
440: Timers[Timer_ratioGrad].get().start(); |
441: PosType grad_new; |
442: wavefunction.ratioGrad(els, iel, grad_new); |
443: Timers[Timer_ratioGrad].get().stop(); |
444: |
445: // Accept/reject the trial move |
446: if (ur[iel] < accept) // MC |
447: { |
448: // Update position, and update temporary storage |
449: Timers[Timer_Update].get().start(); |
450: wavefunction.acceptMove(els, iel); |
451: Timers[Timer_Update].get().stop(); |
452: els.acceptMove(iel); |
453: my_accepted++; |
454: } |
455: else |
456: { |
457: els.rejectMove(iel); |
458: wavefunction.restore(iel); |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 5.35 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.40 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.52 |
Bottlenecks | |
Function | main.extracted.110 |
Source | refwrap.h:313-313,TinyVector.h:62-62,miniqmc.cpp:429-458 |
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 | 10.25 |
CQA cycles if no scalar integer | 1.92 |
CQA cycles if FP arith vectorized | 10.25 |
CQA cycles if fully vectorized | 0.90 |
Front-end cycles | 10.25 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.90 |
P1 cycles | 4.50 |
P2 cycles | 4.50 |
P3 cycles | 6.75 |
P4 cycles | 0.80 |
P5 cycles | 1.50 |
P6 cycles | 6.75 |
P7 cycles | 6.75 |
P8 cycles | 6.75 |
P9 cycles | 0.80 |
P10 cycles | 4.50 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 8.59 |
Stall cycles (UFS) | 0.00 |
Nb insns | 49.50 |
Nb uops | 61.50 |
Nb loads | 13.50 |
Nb stores | 3.50 |
Nb stack references | 8.50 |
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 | 14.02 |
Bytes prefetched | 0.00 |
Bytes loaded | 108.00 |
Bytes stored | 36.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 9.90 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 29.17 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 12.55 |
Vector-efficiency ratio all | 12.29 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 14.32 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 11.72 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 6.70 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.37 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.49 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.110 |
Source | refwrap.h:313-313,TinyVector.h:62-62,miniqmc.cpp:429-458 |
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 | 11.17 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 11.17 |
CQA cycles if fully vectorized | 0.98 |
Front-end cycles | 11.17 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 1.00 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 7.50 |
P4 cycles | 1.00 |
P5 cycles | 1.50 |
P6 cycles | 7.50 |
P7 cycles | 7.50 |
P8 cycles | 7.50 |
P9 cycles | 1.00 |
P10 cycles | 5.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 9.33 |
Stall cycles (UFS) | 0.00 |
Nb insns | 54.00 |
Nb uops | 67.00 |
Nb loads | 15.00 |
Nb stores | 4.00 |
Nb stack references | 9.00 |
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 | 14.33 |
Bytes prefetched | 0.00 |
Bytes loaded | 120.00 |
Bytes stored | 40.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 9.09 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 25.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 11.76 |
Vector-efficiency ratio all | 12.31 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 14.06 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 11.76 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 4.31 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.43 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.56 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.110 |
Source | refwrap.h:313-313,TinyVector.h:62-62,miniqmc.cpp:429-458 |
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 | 2.17 |
CQA cycles if FP arith vectorized | 9.33 |
CQA cycles if fully vectorized | 0.82 |
Front-end cycles | 9.33 |
DIV/SQRT cycles | 1.50 |
P0 cycles | 0.80 |
P1 cycles | 4.00 |
P2 cycles | 4.00 |
P3 cycles | 6.00 |
P4 cycles | 0.60 |
P5 cycles | 1.50 |
P6 cycles | 6.00 |
P7 cycles | 6.00 |
P8 cycles | 6.00 |
P9 cycles | 0.60 |
P10 cycles | 4.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 7.84 |
Stall cycles (UFS) | 0.00 |
Nb insns | 45.00 |
Nb uops | 56.00 |
Nb loads | 12.00 |
Nb stores | 3.00 |
Nb stack references | 8.00 |
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 | 13.71 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
Bytes stored | 32.00 |
Stride 0 | 2.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 10.71 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 33.33 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 13.33 |
Vector-efficiency ratio all | 12.28 |
Vector-efficiency ratio load | 12.50 |
Vector-efficiency ratio store | 14.58 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 12.50 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 11.67 |
Path / |
Function | main.extracted.110 |
Source file and lines | miniqmc.cpp:429-458 |
Module | exec |
nb instructions | 49.50 |
nb uops | 61.50 |
loop length | 243 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8.50 |
micro-operation queue | 10.25 cycles |
front end | 10.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.90 | 4.50 | 4.50 | 6.75 | 0.80 | 1.50 | 6.75 | 6.75 | 6.75 | 0.80 | 4.50 |
cycles | 1.50 | 0.90 | 4.50 | 4.50 | 6.75 | 0.80 | 1.50 | 6.75 | 6.75 | 6.75 | 0.80 | 4.50 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 8.59 |
Stall cycles | 0.00 |
Front-end | 10.25 |
Dispatch | 6.75 |
Data deps. | 1.00 |
Overall L1 | 10.25 |
all | 3% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 7% |
all | 50% |
load | 0% |
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 | 50% |
all | 9% |
load | 0% |
store | 29% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
all | 11% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 10% |
all | 18% |
load | 12% |
store | 25% |
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 | 18% |
all | 12% |
load | 12% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 11% |
Function | main.extracted.110 |
Source file and lines | miniqmc.cpp:429-458 |
Module | exec |
nb instructions | 54 |
nb uops | 67 |
loop length | 265 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 11.17 cycles |
front end | 11.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 1.00 | 5.00 | 5.00 | 7.50 | 1.00 | 1.50 | 7.50 | 7.50 | 7.50 | 1.00 | 5.00 |
cycles | 1.50 | 1.00 | 5.00 | 5.00 | 7.50 | 1.00 | 1.50 | 7.50 | 7.50 | 7.50 | 1.00 | 5.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 9.33 |
Stall cycles | 0.00 |
Front-end | 11.17 |
Dispatch | 7.50 |
Data deps. | 1.00 |
Overall L1 | 11.17 |
all | 3% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 6% |
all | 50% |
load | 0% |
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 | 50% |
all | 9% |
load | 0% |
store | 25% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 11% |
all | 11% |
load | 12% |
store | 10% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 10% |
all | 18% |
load | 12% |
store | 25% |
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 | 18% |
all | 12% |
load | 12% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 11% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
INC %R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x38(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x18,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x110(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %R12,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JE 40c140 <main.extracted.110+0x790> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R15,0x38(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x28(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VZEROUPPER | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
LEA 0x240(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x78(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R15,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RBX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 4133d0 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x28(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %RBX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x38(%RSP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV $0x1,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CALL 47b0a0 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVUPD %XMM0,0x220(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
MOVQ $0,0x230(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R15,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA 0x220(%RSP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 413550 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVSD 0x190(%RSP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xb0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VUCOMISD (%RAX,%R12,8),%XMM0 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JBE 40d500 <main.extracted.110+0x1b50> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x38(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x78(%RSP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 413810 <_ZN11qmcplusplus12WaveFunction10acceptMoveERNS_11ParticleSetEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x38(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %RBX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 47bd60 <_ZN11qmcplusplus11ParticleSet10acceptMoveEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0xa0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
INC %EAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
MOV %RAX,0xa0(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 40d518 <main.extracted.110+0x1b68> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | main.extracted.110 |
Source file and lines | miniqmc.cpp:429-458 |
Module | exec |
nb instructions | 45 |
nb uops | 56 |
loop length | 221 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 9.33 cycles |
front end | 9.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.50 | 0.80 | 4.00 | 4.00 | 6.00 | 0.60 | 1.50 | 6.00 | 6.00 | 6.00 | 0.60 | 4.00 |
cycles | 1.50 | 0.80 | 4.00 | 4.00 | 6.00 | 0.60 | 1.50 | 6.00 | 6.00 | 6.00 | 0.60 | 4.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 7.84 |
Stall cycles | 0.00 |
Front-end | 9.33 |
Dispatch | 6.00 |
Data deps. | 1.00 |
Overall L1 | 9.33 |
all | 4% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 7% |
all | 50% |
load | 0% |
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 | 50% |
all | 10% |
load | 0% |
store | 33% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 13% |
all | 11% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 10% |
all | 18% |
load | 12% |
store | 25% |
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 | 18% |
all | 12% |
load | 12% |
store | 14% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 11% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV %RBX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 47c350 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x78(%RSP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 413a50 <_ZN11qmcplusplus12WaveFunction7restoreEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
INC %R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x38(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x18,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x110(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CMP %R12,%RAX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JE 40c140 <main.extracted.110+0x790> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R15,0x38(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x28(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VZEROUPPER | 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
LEA 0x240(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x78(%RSP),%R15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R15,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RBX,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 4133d0 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x28(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %RBX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x38(%RSP),%RDX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV $0x1,%ECX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
CALL 47b0a0 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bf800 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VXORPD %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VMOVUPD %XMM0,0x220(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
MOVQ $0,0x230(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R15,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %RBX,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA 0x220(%RSP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 413550 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%R14),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 4bfa80 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVSD 0x190(%RSP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0xb0(%RSP),%RAX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VUCOMISD (%RAX,%R12,8),%XMM0 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JBE 40d500 <main.extracted.110+0x1b50> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |