Loop Id: 38 | Module: exec | Source: miniqmc.cpp:429-458 [...] | Coverage: 0.01% |
---|
Loop Id: 38 | Module: exec | Source: miniqmc.cpp:429-458 [...] | Coverage: 0.01% |
---|
0x40ae80 MOV %R14,%RDI |
0x40ae83 MOV %R12D,%ESI |
0x40ae86 CALL 461f30 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> |
0x40ae8b MOV 0x58(%RSP),%RDI [2] |
0x40ae90 MOV %R12D,%ESI |
0x40ae93 CALL 40f7e0 <_ZN11qmcplusplus12WaveFunction7restoreEi> |
0x40ae98 INC %R12 |
0x40ae9b MOV 0x28(%RSP),%R15 [2] |
0x40aea0 ADD $0x18,%R15 |
0x40aea4 CMP %R12,0xf0(%RSP) [2] |
0x40aeac JE 409af0 |
0x40aeb2 MOV %R15,0x28(%RSP) [2] |
0x40aeb7 MOV 0x28(%RBX),%RDI [3] |
0x40aebb VZEROUPPER |
0x40aebe CALL 48b590 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40aec3 LEA 0x288(%RSP),%RDI |
0x40aecb MOV 0x58(%RSP),%R15 [2] |
0x40aed0 MOV %R15,%RSI |
0x40aed3 MOV %R14,%RDX |
0x40aed6 MOV %R12D,%ECX |
0x40aed9 CALL 40f410 <_ZN11qmcplusplus12WaveFunction8evalGradERNS_11ParticleSetEi> |
0x40aede MOV 0x28(%RBX),%RDI [3] |
0x40aee2 CALL 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40aee7 MOV %R14,%RDI |
0x40aeea MOV %R12D,%ESI |
0x40aeed MOV 0x28(%RSP),%RDX [2] |
0x40aef2 MOV $0x1,%ECX |
0x40aef7 CALL 4611f0 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEEb> |
0x40aefc MOV 0x30(%RBX),%RDI [3] |
0x40af00 CALL 48b590 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40af05 VXORPD %XMM0,%XMM0,%XMM0 |
0x40af09 VMOVUPD %XMM0,0x260(%RSP) [2] |
0x40af12 MOVQ $0,0x270(%RSP) [2] |
0x40af1e MOV %R15,%RDI |
0x40af21 MOV %R14,%RSI |
0x40af24 MOV %R12D,%EDX |
0x40af27 LEA 0x260(%RSP),%RCX |
0x40af2f CALL 40f4f0 <_ZN11qmcplusplus12WaveFunction9ratioGradERNS_11ParticleSetEiRNS_10TinyVectorIdLj3EEE> |
0x40af34 MOV 0x30(%RBX),%RDI [3] |
0x40af38 CALL 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40af3d VMOVSD 0x1d0(%RSP),%XMM0 [2] |
0x40af46 MOV 0x80(%RSP),%RAX [2] |
0x40af4e VUCOMISD (%RAX,%R12,8),%XMM0 [1] |
0x40af54 JBE 40ae80 |
0x40af5a MOV 0x38(%RBX),%RDI [3] |
0x40af5e CALL 48b590 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> |
0x40af63 MOV 0x58(%RSP),%RDI [2] |
0x40af68 MOV %R14,%RSI |
0x40af6b MOV %R12D,%EDX |
0x40af6e CALL 40f6c0 <_ZN11qmcplusplus12WaveFunction10acceptMoveERNS_11ParticleSetEi> |
0x40af73 MOV 0x38(%RBX),%RDI [3] |
0x40af77 CALL 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> |
0x40af7c MOV %R14,%RDI |
0x40af7f MOV %R12D,%ESI |
0x40af82 CALL 461ab0 <_ZN11qmcplusplus11ParticleSet10acceptMoveEi> |
0x40af87 MOV 0xa0(%RSP),%RAX [2] |
0x40af8f INC %EAX |
0x40af91 MOV %RAX,0xa0(%RSP) [2] |
0x40af99 JMP 40ae98 |
/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/171-417-8059/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); |
/scratch_na/users/xoserete/qaas_runs/171-417-8059/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 62 - 62 |
-------------------------------------------------------------------------------- |
62: X[d] = T(0); |
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 | 5.76 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.33 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.49 |
Bottlenecks | |
Function | main.extracted.110 |
Source | refwrap.h:313-313,miniqmc.cpp:429-458,TinyVector.h:62-62 |
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 | 10.08 |
CQA cycles if no scalar integer | 1.75 |
CQA cycles if FP arith vectorized | 10.08 |
CQA cycles if fully vectorized | 0.89 |
Front-end cycles | 10.08 |
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) | 8.41 |
Stall cycles (UFS) | 0.00 |
Nb insns | 48.50 |
Nb uops | 60.50 |
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 | 14.25 |
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 | 6.60 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.31 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.47 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.110 |
Source | refwrap.h:313-313,miniqmc.cpp:429-458,TinyVector.h:62-62 |
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 | 11.00 |
CQA cycles if no scalar integer | 1.67 |
CQA cycles if FP arith vectorized | 11.00 |
CQA cycles if fully vectorized | 0.97 |
Front-end cycles | 11.00 |
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) | 9.16 |
Stall cycles (UFS) | 0.00 |
Nb insns | 53.00 |
Nb uops | 66.00 |
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 | 14.55 |
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 | 5.00 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 11.35 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.53 |
Bottlenecks | micro-operation queue, |
Function | main.extracted.110 |
Source | refwrap.h:313-313,miniqmc.cpp:429-458,TinyVector.h:62-62 |
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 | 9.17 |
CQA cycles if no scalar integer | 1.83 |
CQA cycles if FP arith vectorized | 9.17 |
CQA cycles if fully vectorized | 0.81 |
Front-end cycles | 9.17 |
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) | 7.67 |
Stall cycles (UFS) | 0.00 |
Nb insns | 44.00 |
Nb uops | 55.00 |
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 | 13.96 |
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 | 48.50 |
nb uops | 60.50 |
loop length | 240 |
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 | 10.08 cycles |
front end | 10.08 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 | 8.41 |
Stall cycles | 0.00 |
Front-end | 10.08 |
Dispatch | 6.75 |
Data deps. | 1.00 |
Overall L1 | 10.08 |
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 | 53 |
nb uops | 66 |
loop length | 262 |
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 | 11.00 cycles |
front end | 11.00 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 | 9.16 |
Stall cycles | 0.00 |
Front-end | 11.00 |
Dispatch | 7.50 |
Data deps. | 1.00 |
Overall L1 | 11.00 |
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 0x28(%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 |
CMP %R12,0xf0(%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 409af0 <main.extracted.110+0x6d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R15,0x28(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
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 48b590 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
LEA 0x288(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x58(%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 %R14,%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 40f410 <_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 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 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 %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x28(%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 4611f0 <_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 48b590 <_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 %XMM0,0x260(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
MOVQ $0,0x270(%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 %R14,%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 0x260(%RSP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 40f4f0 <_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 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVSD 0x1d0(%RSP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x80(%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 40ae80 <main.extracted.110+0x1a60> | 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 48b590 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x58(%RSP),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV %R14,%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 40f6c0 <_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 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 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 %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CALL 461ab0 <_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 40ae98 <main.extracted.110+0x1a78> | 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 | 44 |
nb uops | 55 |
loop length | 218 |
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 | 9.17 cycles |
front end | 9.17 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 | 7.67 |
Stall cycles | 0.00 |
Front-end | 9.17 |
Dispatch | 6.00 |
Data deps. | 1.00 |
Overall L1 | 9.17 |
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 %R14,%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 461f30 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
MOV 0x58(%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 40f7e0 <_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 0x28(%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 |
CMP %R12,0xf0(%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 409af0 <main.extracted.110+0x6d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
MOV %R15,0x28(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
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 48b590 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE5startEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
LEA 0x288(%RSP),%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
MOV 0x58(%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 %R14,%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 40f410 <_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 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 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 %R12D,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
MOV 0x28(%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 4611f0 <_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 48b590 <_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 %XMM0,0x260(%RSP) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
MOVQ $0,0x270(%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 %R14,%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 0x260(%RSP),%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
CALL 40f4f0 <_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 48b780 <_ZN11qmcplusplus9TimerTypeINSt6chrono3_V212system_clockEE4stopEv> | 2 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 1 |
VMOVSD 0x1d0(%RSP),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV 0x80(%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 40ae80 <main.extracted.110+0x1a60> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |