Function: qmcplusplus::ParticleSet::setActive(int) | Module: exec | Source: ParticleSet.cpp:256-261 [...] | Coverage: 0.01% |
---|
Function: qmcplusplus::ParticleSet::setActive(int) | Module: exec | Source: ParticleSet.cpp:256-261 [...] | Coverage: 0.01% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.cpp: 256 - 261 |
-------------------------------------------------------------------------------- |
256: { |
257: ScopedTimer local_timer(timers[Timer_setActive]); |
258: |
259: for (size_t i = 0; i < DistTables.size(); i++) |
260: DistTables[i]->evaluate(*this, iat); |
261: } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 242 - 249 |
-------------------------------------------------------------------------------- |
242: ScopeGuard(TIMER& t) : timer(t) { timer.start(); } |
[...] |
249: ~ScopeGuard() { timer.stop(); } |
/usr/include/c++/13.1.1/bits/stl_vector.h: 990 - 990 |
-------------------------------------------------------------------------------- |
990: { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); } |
/usr/include/c++/13.1.1/bits/refwrap.h: 347 - 347 |
-------------------------------------------------------------------------------- |
347: { return *_M_data; } |
0x488750 PUSH %RBP |
0x488751 MOV %RSP,%RBP |
0x488754 PUSH %R14 |
0x488756 PUSH %R13 |
0x488758 MOV %ESI,%R13D |
0x48875b PUSH %R12 |
0x48875d MOV %RDI,%R12 |
0x488760 PUSH %RBX |
0x488761 MOV 0xaa8(%RDI),%RAX |
0x488768 MOV 0x8(%RAX),%R14 |
0x48876c MOV %R14,%RDI |
0x48876f CALL 4a40e0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> |
0x488774 MOV 0xa10(%R12),%RDX |
0x48877c CMP %RDX,0xa18(%R12) |
0x488784 JE 4887bf |
0x488786 XOR %EBX,%EBX |
0x488788 NOPL (%RAX,%RAX,1) |
(1044) 0x488790 MOV (%RDX,%RBX,8),%RDI |
(1044) 0x488794 MOV %R12,%RSI |
(1044) 0x488797 MOV %R13D,%EDX |
(1044) 0x48879a MOV (%RDI),%RCX |
(1044) 0x48879d CALLQ 0x18(%RCX) |
(1044) 0x4887a0 MOV 0xa10(%R12),%RDX |
(1044) 0x4887a8 MOV 0xa18(%R12),%RSI |
(1044) 0x4887b0 INC %RBX |
(1044) 0x4887b3 SUB %RDX,%RSI |
(1044) 0x4887b6 SAR $0x3,%RSI |
(1044) 0x4887ba CMP %RSI,%RBX |
(1044) 0x4887bd JB 488790 |
0x4887bf MOV %R14,%RDI |
0x4887c2 CALL 4a4310 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
0x4887c7 POP %RBX |
0x4887c8 POP %R12 |
0x4887ca POP %R13 |
0x4887cc POP %R14 |
0x4887ce POP %RBP |
0x4887cf RET |
0x4887d0 MOV %RAX,%R12 |
0x4887d3 JMP 405d20 |
0x4887d8 NOPL (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | main._omp_fn.1 | stl_vector.h:1126 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | ParticleSet.cpp:256-261 |
Module | exec |
nb instructions | 28 |
nb uops | 30 |
loop length | 97 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 7.50 cycles |
front end | 7.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.50 | 5.83 | 5.50 | 7.00 | 0.50 | 4.00 | 5.67 |
cycles | 1.00 | 0.50 | 5.83 | 5.50 | 7.00 | 0.50 | 4.00 | 5.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 8.10 |
Stall cycles | 0.57 |
LM full (events) | 0.57 |
Front-end | 7.50 |
Dispatch | 7.00 |
Overall L1 | 7.50 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 0% |
all | 9% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 8% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %ESI,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xaa8(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4a40e0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0xa10(%R12),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RDX,0xa18(%R12) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 4887bf | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4a4310 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 405d20 <_ZN11qmcplusplus11ParticleSet9setActiveEi.cold> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | ParticleSet.cpp:256-261 |
Module | exec |
nb instructions | 28 |
nb uops | 30 |
loop length | 97 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 7.50 cycles |
front end | 7.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.50 | 5.83 | 5.50 | 7.00 | 0.50 | 4.00 | 5.67 |
cycles | 1.00 | 0.50 | 5.83 | 5.50 | 7.00 | 0.50 | 4.00 | 5.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 8.10 |
Stall cycles | 0.57 |
LM full (events) | 0.57 |
Front-end | 7.50 |
Dispatch | 7.00 |
Overall L1 | 7.50 |
all | 0% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 0% |
all | 9% |
load | 12% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 8% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
PUSH %RBP | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RSP,%RBP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R14 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %ESI,%R13D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0xaa8(%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RAX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4a40e0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0xa10(%R12),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP %RDX,0xa18(%R12) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 4887bf | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EBX,%EBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 4a4310 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
POP %RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
POP %RBP | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 2 | 0.50 |
RET | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 405d20 <_ZN11qmcplusplus11ParticleSet9setActiveEi.cold> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPL (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼qmcplusplus::ParticleSet::setActive(int)– | 0.01 | 0 |
○Loop 1044 - stl_vector.h:990-990 - exec | 0 | 0 |