Loop Id: 45 | Module: exec | Source: miniqmc.cpp:429-458 [...] | Coverage: 0.02% |
---|
Loop Id: 45 | Module: exec | Source: miniqmc.cpp:429-458 [...] | Coverage: 0.02% |
---|
0x40b8f0 MOV %R12,%RDI |
0x40b8f3 MOV %R13D,%ESI |
0x40b8f6 CALL 460950 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> |
0x40b8fb MOV %R14,%RDI |
0x40b8fe MOV %R13D,%ESI |
0x40b901 CALL 410e00 <_ZN11qmcplusplus12WaveFunction7restoreEi> |
0x40b906 MOV %R14,%R12 |
0x40b909 INC %R13 |
0x40b90c MOV 0x18(%RSP),%R14 [3] |
0x40b911 ADD $0x18,%R14 |
0x40b915 CMP %R13,0x100(%RSP) [3] |
0x40b91d JE 40a730 |
0x40b923 MOV 0x80(%RSP),%RBX [3] |
0x40b92b MOV 0x28(%RBX),%RDI [1] |
0x40b92f VZEROUPPER |
0x40b932 CALL 48a790 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40b937 LEA 0x3b0(%RSP),%RDI |
0x40b93f MOV %R12,%RSI |
0x40b942 MOV 0x88(%RSP),%R12 [3] |
0x40b94a MOV %R12,%RDX |
0x40b94d MOV %R13D,%ECX |
0x40b950 CALL 410a30 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> |
0x40b955 MOV 0x28(%RBX),%RDI [1] |
0x40b959 CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40b95e MOV %R12,%RDI |
0x40b961 MOV %R13D,%ESI |
0x40b964 MOV %R14,0x18(%RSP) [3] |
0x40b969 MOV %R14,%RDX |
0x40b96c MOV 0x108(%RSP),%R14 [3] |
0x40b974 MOV $0x1,%ECX |
0x40b979 CALL 45fd30 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> |
0x40b97e MOV 0x30(%RBX),%RDI [1] |
0x40b982 CALL 48a790 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40b987 VXORPD %XMM0,%XMM0,%XMM0 |
0x40b98b VMOVUPD %XMM0,0x320(%RSP) [3] |
0x40b994 MOVQ $0,0x330(%RSP) [3] |
0x40b9a0 MOV %R14,%RDI |
0x40b9a3 MOV %R12,%RSI |
0x40b9a6 MOV %R13D,%EDX |
0x40b9a9 LEA 0x320(%RSP),%RCX |
0x40b9b1 CALL 410b10 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> |
0x40b9b6 MOV 0x30(%RBX),%RDI [1] |
0x40b9ba CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40b9bf MOV 0xa0(%RSP),%RAX [3] |
0x40b9c7 VMOVSD 0x1a0(%RSP),%XMM0 [3] |
0x40b9d0 VUCOMISD (%RAX,%R13,8),%XMM0 [2] |
0x40b9d6 JBE 40b8f0 |
0x40b9dc MOV 0x38(%RBX),%RDI [1] |
0x40b9e0 CALL 48a790 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40b9e5 MOV %R14,%RDI |
0x40b9e8 MOV %R12,%RSI |
0x40b9eb MOV %R13D,%EDX |
0x40b9ee CALL 410ce0 <_ZN11qmcplusplus12WaveFunction10acceptMoveERNS_11ParticleSetEi> |
0x40b9f3 MOV 0x38(%RBX),%RDI [1] |
0x40b9f7 CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40b9fc MOV %R12,%RDI |
0x40b9ff MOV %R13D,%ESI |
0x40ba02 CALL 4604d0 <_ZN11qmcplusplus11ParticleSet10acceptMoveEi> |
0x40ba07 MOV 0x68(%RSP),%RAX [3] |
0x40ba0c INC %EAX |
0x40ba0e MOV %RAX,0x68(%RSP) [3] |
0x40ba13 JMP 40b906 |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 62 - 62 |
-------------------------------------------------------------------------------- |
62: X[d] = T(0); |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1046 - 1046 |
-------------------------------------------------------------------------------- |
1046: return *(this->_M_impl._M_start + __n); |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/refwrap.h: 338 - 338 |
-------------------------------------------------------------------------------- |
338: { return *_M_data; } |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/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); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 6.05 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.69 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.57 |
Bottlenecks | |
Function | main.extracted.107 |
Source | TinyVector.h:62-62,stl_vector.h:1046-1046,refwrap.h:338-338,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 | 10.58 |
CQA cycles if no scalar integer | 1.75 |
CQA cycles if FP arith vectorized | 10.58 |
CQA cycles if fully vectorized | 0.91 |
Front-end cycles | 10.58 |
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) | 8.93 |
Stall cycles (UFS) | 0.00 |
Nb insns | 51.50 |
Nb uops | 63.50 |
Nb loads | 13.50 |
Nb stores | 3.50 |
Nb stack references | 10.50 |
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 | 13.58 |
Bytes prefetched | 0.00 |
Bytes loaded | 108.00 |
Bytes stored | 36.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 9.29 |
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 | 10.56 |
Vector-efficiency ratio all | 12.31 |
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 | 11.84 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 6.90 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.64 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.53 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.107 |
Source | TinyVector.h:62-62,stl_vector.h:1046-1046,refwrap.h:338-338,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 | 11.50 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 11.50 |
CQA cycles if fully vectorized | 0.99 |
Front-end cycles | 11.50 |
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) | 9.67 |
Stall cycles (UFS) | 0.00 |
Nb insns | 56.00 |
Nb uops | 69.00 |
Nb loads | 15.00 |
Nb stores | 4.00 |
Nb stack references | 11.00 |
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 | 13.91 |
Bytes prefetched | 0.00 |
Bytes loaded | 120.00 |
Bytes stored | 40.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 8.57 |
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 | 10.00 |
Vector-efficiency ratio all | 12.32 |
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 | 11.88 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 5.27 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.75 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.61 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.107 |
Source | TinyVector.h:62-62,stl_vector.h:1046-1046,refwrap.h:338-338,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 | 9.67 |
CQA cycles if no scalar integer | 1.83 |
CQA cycles if FP arith vectorized | 9.67 |
CQA cycles if fully vectorized | 0.82 |
Front-end cycles | 9.67 |
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) | 8.18 |
Stall cycles (UFS) | 0.00 |
Nb insns | 47.00 |
Nb uops | 58.00 |
Nb loads | 12.00 |
Nb stores | 3.00 |
Nb stack references | 10.00 |
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 | 13.24 |
Bytes prefetched | 0.00 |
Bytes loaded | 96.00 |
Bytes stored | 32.00 |
Stride 0 | 1.00 |
Stride 1 | 0.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 1.00 |
Vectorization ratio all | 10.00 |
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 | 11.11 |
Vector-efficiency ratio all | 12.29 |
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 | 11.81 |
Path / |
Function | main.extracted.107 |
Source file and lines | miniqmc.cpp:429-458 |
Module | exec |
nb instructions | 51.50 |
nb uops | 63.50 |
loop length | 255 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10.50 |
micro-operation queue | 10.58 cycles |
front end | 10.58 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 | 8.93 |
Stall cycles | 0.00 |
Front-end | 10.58 |
Dispatch | 6.75 |
Data deps. | 1.00 |
Overall L1 | 10.58 |
all | 3% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 5% |
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 | 10% |
all | 11% |
load | 12% |
store | 9% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
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.107 |
Source file and lines | miniqmc.cpp:429-458 |
Module | exec |
nb instructions | 56 |
nb uops | 69 |
loop length | 274 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 11 |
micro-operation queue | 11.50 cycles |
front end | 11.50 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 | 9.67 |
Stall cycles | 0.00 |
Front-end | 11.50 |
Dispatch | 7.50 |
Data deps. | 1.00 |
Overall L1 | 11.50 |
all | 3% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 5% |
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 | 8% |
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 | 10% |
all | 11% |
load | 12% |
store | 10% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 12% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
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 %R14,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x18(%RSP),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x18,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R13,0x100(%RSP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 40a730 <main.extracted.107+0x750> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x80(%RSP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x28(%RBX),%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 48a790 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
LEA 0x3b0(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x88(%RSP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 410a30 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x28(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R14,0x18(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x108(%RSP),%R14 | 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 45fd30 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a790 <_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 %XMM0,0x320(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
MOVQ $0,0x330(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA 0x320(%RSP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 410b10 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 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 |
VMOVSD 0x1a0(%RSP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VUCOMISD (%RAX,%R13,8),%XMM0 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JBE 40b8f0 <main.extracted.107+0x1910> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x38(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a790 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 410ce0 <_ZN11qmcplusplus12WaveFunction10acceptMoveERNS_11ParticleSetEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x38(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 4604d0 <_ZN11qmcplusplus11ParticleSet10acceptMoveEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x68(%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,0x68(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
JMP 40b906 <main.extracted.107+0x1926> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.08 |
Function | main.extracted.107 |
Source file and lines | miniqmc.cpp:429-458 |
Module | exec |
nb instructions | 47 |
nb uops | 58 |
loop length | 236 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10 |
micro-operation queue | 9.67 cycles |
front end | 9.67 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 | 8.18 |
Stall cycles | 0.00 |
Front-end | 9.67 |
Dispatch | 6.00 |
Data deps. | 1.00 |
Overall L1 | 9.67 |
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 | 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 | 11% |
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 %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 460950 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 410e00 <_ZN11qmcplusplus12WaveFunction7restoreEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %R14,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
INC %R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x18(%RSP),%R14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x18,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R13,0x100(%RSP) | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
JE 40a730 <main.extracted.107+0x750> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV 0x80(%RSP),%RBX | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x28(%RBX),%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 48a790 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
LEA 0x3b0(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x88(%RSP),%R12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 410a30 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x28(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV %R12,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R14,0x18(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x108(%RSP),%R14 | 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 45fd30 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a790 <_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 %XMM0,0x320(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
MOVQ $0,0x330(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R12,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV %R13D,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
LEA 0x320(%RSP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 410b10 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x30(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
CALL 48a970 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 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 |
VMOVSD 0x1a0(%RSP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VUCOMISD (%RAX,%R13,8),%XMM0 | 2 | 1 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 1 |
JBE 40b8f0 <main.extracted.107+0x1910> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |