Function: qmcplusplus::WaveFunction::acceptMove(qmcplusplus::ParticleSet&, int) | Module: exec | Source: WaveFunction.cpp:225-236 [...] | Coverage: 0.01% |
---|
Function: qmcplusplus::WaveFunction::acceptMove(qmcplusplus::ParticleSet&, int) | Module: exec | Source: WaveFunction.cpp:225-236 [...] | Coverage: 0.01% |
---|
/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/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/refwrap.h: 347 - 347 |
-------------------------------------------------------------------------------- |
347: { return *_M_data; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/WaveFunction.cpp: 225 - 236 |
-------------------------------------------------------------------------------- |
225: { |
226: if (iat < nelup) |
227: Det_up->acceptMove(P, iat); |
228: else |
229: Det_dn->acceptMove(P, iat); |
230: |
231: for (size_t i = 0; i < Jastrows.size(); i++) |
232: { |
233: ScopedTimer local_timer(jastrow_timers[i]); |
234: Jastrows[i]->acceptMove(P, iat); |
235: } |
236: } |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_vector.h: 990 - 1126 |
-------------------------------------------------------------------------------- |
990: { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); } |
[...] |
1126: return *(this->_M_impl._M_start + __n); |
0x40eb00 PUSH %RBP |
0x40eb01 MOV %RSP,%RBP |
0x40eb04 PUSH %R15 |
0x40eb06 PUSH %R14 |
0x40eb08 PUSH %R13 |
0x40eb0a PUSH %R12 |
0x40eb0c PUSH %RBX |
0x40eb0d PUSH %RAX |
0x40eb0e MOV %EDX,%R15D |
0x40eb11 MOV %RSI,%R14 |
0x40eb14 MOV %RDI,%R12 |
0x40eb17 LEA 0x8(%RDI),%RAX |
0x40eb1b CMP %EDX,0x34(%RDI) |
0x40eb1e CMOVG %RDI,%RAX |
0x40eb22 MOV (%RAX),%RDI |
0x40eb25 MOV (%RDI),%RAX |
0x40eb28 CALLQ 0x28(%RAX) |
0x40eb2b MOV 0x18(%R12),%RAX |
0x40eb30 CMP 0x10(%R12),%RAX |
0x40eb35 JE 40eb84 |
0x40eb37 XOR %EBX,%EBX |
0x40eb39 NOPL (%RAX) |
(75) 0x40eb40 MOV 0x58(%R12),%RAX |
(75) 0x40eb45 MOV (%RAX,%RBX,8),%R13 |
(75) 0x40eb49 MOV %R13,%RDI |
(75) 0x40eb4c CALL 45de10 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv> |
(75) 0x40eb51 MOV 0x10(%R12),%RAX |
(75) 0x40eb56 MOV (%RAX,%RBX,8),%RDI |
(75) 0x40eb5a MOV (%RDI),%RAX |
(75) 0x40eb5d MOV %R14,%RSI |
(75) 0x40eb60 MOV %R15D,%EDX |
(75) 0x40eb63 CALLQ 0x28(%RAX) |
(75) 0x40eb66 MOV %R13,%RDI |
(75) 0x40eb69 CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
(75) 0x40eb6e INC %RBX |
(75) 0x40eb71 MOV 0x18(%R12),%RAX |
(75) 0x40eb76 SUB 0x10(%R12),%RAX |
(75) 0x40eb7b SAR $0x3,%RAX |
(75) 0x40eb7f CMP %RAX,%RBX |
(75) 0x40eb82 JB 40eb40 |
0x40eb84 ADD $0x8,%RSP |
0x40eb88 POP %RBX |
0x40eb89 POP %R12 |
0x40eb8b POP %R13 |
0x40eb8d POP %R14 |
0x40eb8f POP %R15 |
0x40eb91 POP %RBP |
0x40eb92 RET |
0x40eb93 MOV %RAX,%RDI |
0x40eb96 CALL 40b670 <__clang_call_terminate> |
0x40eb9b MOV %RAX,%R14 |
0x40eb9e MOV %R13,%RDI |
0x40eba1 CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> |
0x40eba6 MOV %R14,%RDI |
0x40eba9 CALL 404250 <_Unwind_Resume@plt> |
0x40ebae MOV %RAX,%RDI |
0x40ebb1 CALL 40b670 <__clang_call_terminate> |
0x40ebb6 NOPW %CS:(%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | main.extracted.104 | stl_vector.h:1126 | exec |
○ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | main | miniqmc.cpp:404 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | WaveFunction.cpp:225-236 |
Module | exec |
nb instructions | 40 |
nb uops | 46 |
loop length | 124 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 11.50 cycles |
front end | 11.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 8.33 | 8.33 | 12.00 | 2.00 | 6.00 | 8.33 |
cycles | 2.00 | 2.00 | 8.33 | 8.33 | 12.00 | 2.00 | 6.00 | 8.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 10.42 |
Stall cycles | 0.00 |
Front-end | 11.50 |
Dispatch | 12.00 |
Overall L1 | 12.00 |
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 | 9% |
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 | 9% |
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 %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
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 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RAX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EDX,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA 0x8(%RDI),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %EDX,0x34(%RDI) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
CMOVG %RDI,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV (%RAX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALLQ 0x28(%RAX) | 3 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 1 | 0.33 | 0 | 4 |
MOV 0x18(%R12),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x10(%R12),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40eb84 | 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) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 %R15 | 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,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 40b670 <__clang_call_terminate> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R13,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404250 <_Unwind_Resume@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 40b670 <__clang_call_terminate> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | WaveFunction.cpp:225-236 |
Module | exec |
nb instructions | 40 |
nb uops | 46 |
loop length | 124 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 11.50 cycles |
front end | 11.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.00 | 8.33 | 8.33 | 12.00 | 2.00 | 6.00 | 8.33 |
cycles | 2.00 | 2.00 | 8.33 | 8.33 | 12.00 | 2.00 | 6.00 | 8.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 10.42 |
Stall cycles | 0.00 |
Front-end | 11.50 |
Dispatch | 12.00 |
Overall L1 | 12.00 |
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 | 9% |
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 | 9% |
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 %R15 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
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 |
PUSH %R12 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH %RAX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EDX,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDI,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA 0x8(%RDI),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %EDX,0x34(%RDI) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
CMOVG %RDI,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV (%RAX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDI),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALLQ 0x28(%RAX) | 3 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 1 | 0.33 | 0 | 4 |
MOV 0x18(%R12),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x10(%R12),%RAX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 40eb84 | 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) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
ADD $0x8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
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 %R15 | 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,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 40b670 <__clang_call_terminate> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R13,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 45e030 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %R14,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404250 <_Unwind_Resume@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV %RAX,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 40b670 <__clang_call_terminate> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼qmcplusplus::WaveFunction::acceptMove(qmcplusplus::ParticleSet&, int)– | 0.01 | 0 |
○Loop 75 - WaveFunction.cpp:231-234 - exec | 0 | 0 |