Function: qmcplusplus::TimerType<qmcplusplus::CPUClock>::start() | Module: exec | Source: NewTimer.cpp:38-81 [...] | Coverage: 0.07% |
---|
Function: qmcplusplus::TimerType<qmcplusplus::CPUClock>::start() | Module: exec | Source: NewTimer.cpp:38-81 [...] | Coverage: 0.07% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.cpp: 38 - 81 |
-------------------------------------------------------------------------------- |
38: { |
39: if (active) |
[...] |
53: for (int level = omp_get_level(); level > 0; level--) |
54: if (omp_get_ancestor_thread_num(level) != 0) |
55: is_true_master = false; |
56: if (is_true_master) |
57: { |
58: if (manager) |
59: { |
60: // compute current_stack_key |
61: TimerType* parent = manager->current_timer(); |
62: if (parent) |
63: { |
64: current_stack_key = parent->get_stack_key(); |
65: current_stack_key.add_id(timer_id); |
66: } |
67: else |
68: { |
69: current_stack_key = StackKey(); |
70: current_stack_key.add_id(timer_id); |
71: } |
72: |
73: manager->push_timer(this); |
74: } |
75: start_time = CLOCK()(); |
[...] |
81: } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Utilities/TimerManager.h: 92 - 93 |
-------------------------------------------------------------------------------- |
92: if (CurrentTimerStack.size() > 0) |
93: current = CurrentTimerStack.back(); |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Utilities/NewTimer.h: 90 - 97 |
-------------------------------------------------------------------------------- |
90: short_buckets[level] = c1; |
91: if (level >= max_level - 1) |
92: { |
93: timer_max_level_exceeded = true; |
94: } |
95: else |
96: { |
97: level++; |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Utilities/Clock.h: 33 - 33 |
-------------------------------------------------------------------------------- |
33: return omp_get_wtime(); |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../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); } |
0x464ec0 PUSH %RBP |
0x464ec1 MOV %RSP,%RBP |
0x464ec4 PUSH %R15 |
0x464ec6 PUSH %R14 |
0x464ec8 PUSH %R13 |
0x464eca PUSH %R12 |
0x464ecc PUSH %RBX |
0x464ecd SUB $0x18,%RSP |
0x464ed1 CMPB $0,0x38(%RDI) |
0x464ed5 JE 465072 |
0x464edb MOV %RDI,%R14 |
0x464ede CALL 404600 <omp_get_level@plt> |
0x464ee3 TEST %EAX,%EAX |
0x464ee5 JLE 464fee |
0x464eeb MOV %R14,-0x38(%RBP) |
0x464eef MOV $0x1,%R12B |
0x464ef2 MOV %RAX,-0x40(%RBP) |
0x464ef6 CMP $0x8,%EAX |
0x464ef9 JB 464f9c |
0x464eff MOV -0x40(%RBP),%RAX |
0x464f03 MOV %EAX,%ECX |
0x464f05 SHR $0x3,%ECX |
0x464f08 LEA -0x7(%RAX),%R15D |
0x464f0c MOV $0x1,%R12B |
0x464f0f NOP |
(1243) 0x464f10 MOV %ECX,-0x2c(%RBP) |
(1243) 0x464f13 LEA 0x7(%R15),%EDI |
(1243) 0x464f17 CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f1c MOV %EAX,%EBX |
(1243) 0x464f1e LEA 0x6(%R15),%EDI |
(1243) 0x464f22 CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f27 MOV %EAX,%R13D |
(1243) 0x464f2a OR %EBX,%R13D |
(1243) 0x464f2d LEA 0x5(%R15),%EDI |
(1243) 0x464f31 CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f36 MOV %EAX,%EBX |
(1243) 0x464f38 LEA 0x4(%R15),%EDI |
(1243) 0x464f3c CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f41 MOV %EAX,%R14D |
(1243) 0x464f44 OR %EBX,%R14D |
(1243) 0x464f47 OR %R13D,%R14D |
(1243) 0x464f4a LEA 0x3(%R15),%EDI |
(1243) 0x464f4e CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f53 MOV %EAX,%R13D |
(1243) 0x464f56 LEA 0x2(%R15),%EDI |
(1243) 0x464f5a CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f5f MOV %EAX,%EBX |
(1243) 0x464f61 OR %R13D,%EBX |
(1243) 0x464f64 OR %R14D,%EBX |
(1243) 0x464f67 LEA 0x1(%R15),%EDI |
(1243) 0x464f6b CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f70 MOV %EAX,%R14D |
(1243) 0x464f73 MOV %R15D,%EDI |
(1243) 0x464f76 CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1243) 0x464f7b MOV -0x2c(%RBP),%ECX |
(1243) 0x464f7e OR %R14D,%EAX |
(1243) 0x464f81 MOVZX %R12B,%R12D |
(1243) 0x464f85 OR %EBX,%EAX |
(1243) 0x464f87 MOV $0,%EAX |
(1243) 0x464f8c CMOVNE %EAX,%R12D |
(1243) 0x464f90 ADD $-0x8,%R15D |
(1243) 0x464f94 DEC %ECX |
(1243) 0x464f96 JNE 464f10 |
0x464f9c MOV -0x40(%RBP),%RBX |
0x464fa0 MOV %EBX,%EAX |
0x464fa2 AND $-0x8,%EAX |
0x464fa5 CMP %EBX,%EAX |
0x464fa7 JAE 464fe0 |
0x464fa9 SUB %EAX,%EBX |
0x464fab XOR %R15D,%R15D |
0x464fae MOV -0x38(%RBP),%R14 |
0x464fb2 NOPW %CS:(%RAX,%RAX,1) |
(1242) 0x464fc0 MOV %EBX,%EDI |
(1242) 0x464fc2 CALL 404230 <omp_get_ancestor_thread_num@plt> |
(1242) 0x464fc7 TEST %EAX,%EAX |
(1242) 0x464fc9 MOVZX %R12B,%R12D |
(1242) 0x464fcd CMOVNE %R15D,%R12D |
(1242) 0x464fd1 DEC %EBX |
(1242) 0x464fd3 JNE 464fc0 |
0x464fd5 TEST $0x1,%R12B |
0x464fd9 JNE 464fee |
0x464fdb JMP 465072 |
0x464fe0 MOV -0x38(%RBP),%R14 |
0x464fe4 TEST $0x1,%R12B |
0x464fe8 JE 465072 |
0x464fee MOV 0x48(%R14),%RAX |
0x464ff2 TEST %RAX,%RAX |
0x464ff5 JE 465068 |
0x464ff7 MOV 0x48(%RAX),%RCX |
0x464ffb CMP 0x40(%RAX),%RCX |
0x464fff JE 465039 |
0x465001 MOV -0x8(%RCX),%RAX |
0x465005 TEST %RAX,%RAX |
0x465008 JE 465039 |
0x46500a VMOVUPS 0x50(%RAX),%XMM0 |
0x46500f VMOVUPS %XMM0,0x50(%R14) |
0x465015 MOVSXD 0x60(%RAX),%RAX |
0x465019 MOV %EAX,0x60(%R14) |
0x46501d MOVZX 0x40(%R14),%ECX |
0x465022 MOV %CL,0x50(%R14,%RAX,1) |
0x465027 MOV 0x60(%R14),%EAX |
0x46502b CMP $0xf,%EAX |
0x46502e JL 465056 |
0x465030 MOVB $0x1,0x94089(%RIP) |
0x465037 JMP 46505c |
0x465039 VXORPS %XMM0,%XMM0,%XMM0 |
0x46503d VMOVUPS %XMM0,0x50(%R14) |
0x465043 MOVZX 0x40(%R14),%EAX |
0x465048 MOV %AL,0x50(%R14) |
0x46504c MOVL $0x1,0x60(%R14) |
0x465054 JMP 46505c |
0x465056 INC %EAX |
0x465058 MOV %EAX,0x60(%R14) |
0x46505c MOV 0x48(%R14),%RDI |
0x465060 MOV %R14,%RSI |
0x465063 CALL 46aa40 <_ZN11qmcplusplus12TimerManagerINS_9TimerTypeINS_8CPUClockEEEE10push_timerEPS3_> |
0x465068 CALL 4044c0 <omp_get_wtime@plt> |
0x46506d VMOVSD %XMM0,(%R14) |
0x465072 ADD $0x18,%RSP |
0x465076 POP %RBX |
0x465077 POP %R12 |
0x465079 POP %R13 |
0x46507b POP %R14 |
0x46507d POP %R15 |
0x46507f POP %RBP |
0x465080 RET |
0x465081 NOPW %CS:(%RAX,%RAX,1) |
0x46508b NOPL (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►11.11+ | qmcplusplus::ParticleSet::make[...] | ParticleSet.cpp:288 | exec |
○ | main.extracted.104 | miniqmc.cpp:482 | 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 | |
►11.11+ | main.extracted.104 | miniqmc.cpp:428 | 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 | |
►11.11+ | qmcplusplus::ParticleSet::setA[...] | stl_vector.h:990 | exec |
○ | main.extracted.104 | refwrap.h:347 | 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 | |
►11.11+ | miniqmcreference::DiracDetermi[...] | DiracDeterminantRef.cpp:199 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:214 | exec |
○ | main.extracted.104 | refwrap.h:347 | 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 | |
►11.11+ | qmcplusplus::WaveFunction::rat[...] | stl_vector.h:1126 | exec |
○ | main.extracted.104 | refwrap.h:347 | 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 | |
►11.11+ | qmcplusplus::ParticleSet::make[...] | ParticleSet.cpp:288 | exec |
○ | main.extracted.104 | refwrap.h:347 | 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 | |
►11.11+ | qmcplusplus::ParticleSet::acce[...] | ParticleSet.cpp:334 | exec |
○ | main.extracted.104 | miniqmc.cpp:447 | 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 | |
►11.11+ | qmcplusplus::WaveFunction::rat[...] | stl_vector.h:1126 | exec |
○ | main.extracted.104 | refwrap.h:347 | 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 | |
►11.11+ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:202 | exec |
○ | main.extracted.104 | refwrap.h:347 | 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 | NewTimer.cpp:38-81 |
Module | exec |
nb instructions | 83 |
nb uops | 86 |
loop length | 303 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 21.50 cycles |
front end | 21.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 9.00 | 9.00 | 14.17 | 13.83 | 20.00 | 9.00 | 9.00 | 14.00 |
cycles | 9.00 | 9.00 | 14.17 | 13.83 | 20.00 | 9.00 | 9.00 | 14.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 21.00 |
Stall cycles | 0.00 |
Front-end | 21.50 |
Dispatch | 20.00 |
Overall L1 | 21.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 80% |
load | 100% |
store | 66% |
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 | 100% |
all | 17% |
load | 25% |
store | 22% |
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 | 9% |
all | 8% |
load | 8% |
store | 7% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 8% |
all | 22% |
load | 25% |
store | 20% |
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 | 25% |
all | 11% |
load | 12% |
store | 11% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
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 |
SUB $0x18,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMPB $0,0x38(%RDI) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 465072 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404600 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 464fee | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP $0x8,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 464f9c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%ECX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA -0x7(%RAX),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EBX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %EBX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 464fe0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SUB %EAX,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %R15D,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x38(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 464fee | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 465072 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x38(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 465072 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x48(%R14),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 465068 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x48(%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x40(%RAX),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 465039 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x8(%RCX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 465039 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPS 0x50(%RAX),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM0,0x50(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD 0x60(%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EAX,0x60(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVZX 0x40(%R14),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %CL,0x50(%R14,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x60(%R14),%EAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0xf,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JL 465056 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVB $0x1,0x94089(%RIP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
JMP 46505c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPS %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPS %XMM0,0x50(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVZX 0x40(%R14),%EAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %AL,0x50(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVL $0x1,0x60(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
JMP 46505c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INC %EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EAX,0x60(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x48(%R14),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R14,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 46aa40 <_ZN11qmcplusplus12TimerManagerINS_9TimerTypeINS_8CPUClockEEEE10push_timerEPS3_> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
CALL 4044c0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD %XMM0,(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x18,%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 |
NOPW %CS:(%RAX,%RAX,1) | 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 |
Source file and lines | NewTimer.cpp:38-81 |
Module | exec |
nb instructions | 83 |
nb uops | 86 |
loop length | 303 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 2 |
micro-operation queue | 21.50 cycles |
front end | 21.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 9.00 | 9.00 | 14.17 | 13.83 | 20.00 | 9.00 | 9.00 | 14.00 |
cycles | 9.00 | 9.00 | 14.17 | 13.83 | 20.00 | 9.00 | 9.00 | 14.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 21.00 |
Stall cycles | 0.00 |
Front-end | 21.50 |
Dispatch | 20.00 |
Overall L1 | 21.50 |
all | 0% |
load | 0% |
store | 0% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 80% |
load | 100% |
store | 66% |
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 | 100% |
all | 17% |
load | 25% |
store | 22% |
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 | 9% |
all | 8% |
load | 8% |
store | 7% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 8% |
all | 22% |
load | 25% |
store | 20% |
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 | 25% |
all | 11% |
load | 12% |
store | 11% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 6% |
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 |
SUB $0x18,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMPB $0,0x38(%RDI) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 465072 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404600 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
TEST %EAX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 464fee | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R14,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP $0x8,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JB 464f9c | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x40(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SHR $0x3,%ECX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA -0x7(%RAX),%R15D | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
NOP | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x40(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EBX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x8,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %EBX,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JAE 464fe0 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
SUB %EAX,%EBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %R15D,%R15D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x38(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 464fee | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 465072 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV -0x38(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST $0x1,%R12B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 465072 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x48(%R14),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 465068 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x48(%RAX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP 0x40(%RAX),%RCX | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 465039 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x8(%RCX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 465039 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVUPS 0x50(%RAX),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPS %XMM0,0x50(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD 0x60(%RAX),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %EAX,0x60(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVZX 0x40(%R14),%ECX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %CL,0x50(%R14,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x60(%R14),%EAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMP $0xf,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JL 465056 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVB $0x1,0x94089(%RIP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
JMP 46505c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
VXORPS %XMM0,%XMM0,%XMM0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMOVUPS %XMM0,0x50(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVZX 0x40(%R14),%EAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %AL,0x50(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVL $0x1,0x60(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
JMP 46505c | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INC %EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EAX,0x60(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x48(%R14),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R14,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 46aa40 <_ZN11qmcplusplus12TimerManagerINS_9TimerTypeINS_8CPUClockEEEE10push_timerEPS3_> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
CALL 4044c0 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
VMOVSD %XMM0,(%R14) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x18,%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 |
NOPW %CS:(%RAX,%RAX,1) | 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 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼qmcplusplus::TimerType | 0.07 | 0.04 |
○Loop 1243 - NewTimer.cpp:39-54 - exec | 0 | 0 |
○Loop 1242 - NewTimer.cpp:53-54 - exec | 0 | 0 |