Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::computeU3(qmcpl ... | Module: exec | Source: TwoBodyJastrowRef.h:251-276 [...] | Coverage: 0.02% |
---|
Function: miniqmcreference::TwoBodyJastrowRef<qmcplusplus::BsplineFunctor<double> >::computeU3(qmcpl ... | Module: exec | Source: TwoBodyJastrowRef.h:251-276 [...] | Coverage: 0.02% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 251 - 276 |
-------------------------------------------------------------------------------- |
251: inline void TwoBodyJastrowRef<FT>::computeU3(const ParticleSet& P, |
[...] |
259: const int jelmax = triangle ? iat : N; |
[...] |
265: const int igt = P.GroupID[iat] * NumGroups; |
266: for (int jg = 0; jg < NumGroups; ++jg) |
267: { |
268: const FuncType& f2(*F[igt + jg]); |
269: int iStart = P.first(jg); |
270: int iEnd = std::min(jelmax, P.last(jg)); |
271: f2.evaluateVGL(iat, iStart, iEnd, dist, u, du, d2u, DistCompressed.data(), DistIndice.data()); |
272: } |
273: // u[iat]=czero; |
274: // du[iat]=czero; |
275: // d2u[iat]=czero; |
276: } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Particle/ParticleSet.h: 305 - 305 |
-------------------------------------------------------------------------------- |
305: inline int last(int igroup) const { return SubPtcl[igroup + 1]; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229 |
-------------------------------------------------------------------------------- |
229: return X[i]; |
/usr/include/c++/13.1.1/bits/stl_algobase.h: 238 - 1128 |
-------------------------------------------------------------------------------- |
238: if (__b < __a) |
[...] |
931: *__first = __tmp; |
[...] |
1123: if (__n <= 0) |
1124: return __first; |
1125: |
1126: __glibcxx_requires_can_increment(__first, __n); |
1127: |
1128: std::__fill_a(__first, __first + __n, __value); |
0x449690 PUSH %RBP |
0x449691 MOV %RSP,%RBP |
0x449694 PUSH %R15 |
0x449696 PUSH %R14 |
0x449698 MOV %RSI,%R14 |
0x44969b PUSH %R13 |
0x44969d MOV %EDX,%R13D |
0x4496a0 PUSH %R12 |
0x4496a2 PUSH %RBX |
0x4496a3 MOV %RDI,%RBX |
0x4496a6 SUB $0x38,%RSP |
0x4496aa MOV %EDX,-0x34(%RBP) |
0x4496ad CMPB $0,0x18(%RBP) |
0x4496b1 MOV %RCX,-0x50(%RBP) |
0x4496b5 MOV %R8,-0x40(%RBP) |
0x4496b9 MOV %R9,-0x48(%RBP) |
0x4496bd JNE 4496c6 |
0x4496bf MOV 0x90(%RDI),%R13D |
0x4496c6 TEST %R13D,%R13D |
0x4496c9 JLE 4496fc |
0x4496cb MOVSXD %R13D,%R12 |
0x4496ce MOV -0x40(%RBP),%RDI |
0x4496d2 XOR %ESI,%ESI |
0x4496d4 SAL $0x3,%R12 |
0x4496d8 MOV %R12,%RDX |
0x4496db CALL 404150 <memset@plt> |
0x4496e0 MOV -0x48(%RBP),%RDI |
0x4496e4 MOV %R12,%RDX |
0x4496e7 XOR %ESI,%ESI |
0x4496e9 CALL 404150 <memset@plt> |
0x4496ee MOV 0x10(%RBP),%RDI |
0x4496f2 MOV %R12,%RDX |
0x4496f5 XOR %ESI,%ESI |
0x4496f7 CALL 404150 <memset@plt> |
0x4496fc MOVSXD -0x34(%RBP),%RAX |
0x449700 MOV 0x5c0(%R14),%RDX |
0x449707 MOV 0xa0(%RBX),%R11 |
0x44970e MOV (%RDX,%RAX,4),%EDI |
0x449711 IMUL %R11D,%EDI |
0x449715 MOVSXD %EDI,%RCX |
0x449718 TEST %R11,%R11 |
0x44971b JE 4497fa |
0x449721 LEA (,%RCX,8),%R15 |
0x449729 XOR %R12D,%R12D |
0x44972c TEST $0x1,%R11B |
0x449730 JNE 449810 |
0x449736 MOV %R11,-0x60(%RBP) |
0x44973a MOV %RBX,%RAX |
0x44973d MOV %R12,%RBX |
0x449740 MOV %RAX,%R12 |
(592) 0x449743 MOV 0xa98(%R14),%RDX |
(592) 0x44974a MOV 0x200(%R12),%R8 |
(592) 0x449752 LEA 0x1(%RBX),%RDI |
(592) 0x449756 MOV -0x40(%RBP),%R9 |
(592) 0x44975a MOV -0x34(%RBP),%ESI |
(592) 0x44975d MOV %RDI,-0x58(%RBP) |
(592) 0x449761 MOV 0x4(%RDX,%RBX,4),%ECX |
(592) 0x449765 MOV (%R8,%R15,1),%RDI |
(592) 0x449769 MOV (%RDX,%RBX,4),%EDX |
(592) 0x44976c MOV -0x50(%RBP),%R8 |
(592) 0x449770 PUSHQ 0x1e8(%R12) |
(592) 0x449778 CMP %ECX,%R13D |
(592) 0x44977b CMOVLE %R13D,%ECX |
(592) 0x44977f ADD $0x2,%RBX |
(592) 0x449783 PUSHQ 0x1d0(%R12) |
(592) 0x44978b PUSHQ 0x10(%RBP) |
(592) 0x44978e PUSHQ -0x48(%RBP) |
(592) 0x449791 CALL 4476c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> |
(592) 0x449796 MOV 0xa98(%R14),%R9 |
(592) 0x44979d MOV -0x58(%RBP),%RSI |
(592) 0x4497a1 ADD $0x20,%RSP |
(592) 0x4497a5 MOV 0x200(%R12),%R10 |
(592) 0x4497ad MOV -0x50(%RBP),%R8 |
(592) 0x4497b1 MOV 0x4(%R9,%RSI,4),%ECX |
(592) 0x4497b6 MOV (%R9,%RSI,4),%EDX |
(592) 0x4497ba MOV 0x8(%R10,%R15,1),%RDI |
(592) 0x4497bf MOV -0x40(%RBP),%R9 |
(592) 0x4497c3 PUSHQ 0x1e8(%R12) |
(592) 0x4497cb CMP %ECX,%R13D |
(592) 0x4497ce MOV -0x34(%RBP),%ESI |
(592) 0x4497d1 CMOVLE %R13D,%ECX |
(592) 0x4497d5 ADD $0x10,%R15 |
(592) 0x4497d9 PUSHQ 0x1d0(%R12) |
(592) 0x4497e1 PUSHQ 0x10(%RBP) |
(592) 0x4497e4 PUSHQ -0x48(%RBP) |
(592) 0x4497e7 CALL 4476c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> |
(592) 0x4497ec ADD $0x20,%RSP |
(592) 0x4497f0 CMP %RBX,-0x60(%RBP) |
(592) 0x4497f4 JNE 449743 |
0x4497fa LEA -0x28(%RBP),%RSP |
0x4497fe POP %RBX |
0x4497ff POP %R12 |
0x449801 POP %R13 |
0x449803 POP %R14 |
0x449805 POP %R15 |
0x449807 POP %RBP |
0x449808 RET |
0x449809 NOPL (%RAX) |
0x449810 MOV 0xa98(%R14),%R8 |
0x449817 MOV 0x200(%RBX),%R10 |
0x44981e XOR %R9D,%R9D |
0x449821 MOV %R11,-0x58(%RBP) |
0x449825 MOV $0x1,%R12D |
0x44982b MOV 0x4(%R8,%R9,1),%ESI |
0x449830 MOV (%R8,%R9,1),%EDX |
0x449834 MOV (%R10,%R15,1),%RDI |
0x449838 MOV -0x40(%RBP),%R9 |
0x44983c PUSHQ 0x1e8(%RBX) |
0x449842 CMP %ESI,%R13D |
0x449845 MOV -0x50(%RBP),%R8 |
0x449849 CMOVLE %R13D,%ESI |
0x44984d ADD $0x8,%R15 |
0x449851 PUSHQ 0x1d0(%RBX) |
0x449857 MOV %ESI,%ECX |
0x449859 MOV -0x34(%RBP),%ESI |
0x44985c PUSHQ 0x10(%RBP) |
0x44985f PUSHQ -0x48(%RBP) |
0x449862 CALL 4476c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> |
0x449867 MOV -0x58(%RBP),%R11 |
0x44986b ADD $0x20,%RSP |
0x44986f CMP $0x1,%R11 |
0x449873 JNE 449736 |
0x449879 JMP 4497fa |
0x44987e XCHG %AX,%AX |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►75.00+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:300 | exec |
○ | qmcplusplus::WaveFunction::rat[...] | WaveFunction.cpp:207 | exec |
○ | main._omp_fn.1 | miniqmc.cpp:438 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
►25.00+ | miniqmcreference::TwoBodyJastr[...] | TwoBodyJastrowRef.h:312 | exec |
○ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | exec |
○ | main._omp_fn.1 | stl_vector.h:1126 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Source file and lines | TwoBodyJastrowRef.h:251-276 |
Module | exec |
nb instructions | 85 |
nb uops | 93 |
loop length | 313 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 23.25 cycles |
front end | 23.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 7.00 | 7.00 | 16.33 | 16.33 | 20.00 | 7.00 | 7.00 | 16.33 |
cycles | 7.00 | 7.00 | 16.33 | 16.33 | 20.00 | 7.00 | 7.00 | 16.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 22.40 |
Stall cycles | 0.00 |
Front-end | 23.25 |
Dispatch | 20.00 |
Overall L1 | 23.25 |
all | 0% |
load | 0% |
store | 0% |
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 | 0% |
all | 8% |
load | 5% |
store | 11% |
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 | 7% |
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 |
MOV %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EDX,%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 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB $0x38,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EDX,-0x34(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMPB $0,0x18(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RCX,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JNE 4496c6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x90(%RDI),%R13D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R13D,%R13D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4496fc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %R13D,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SAL $0x3,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404150 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404150 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404150 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD -0x34(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x5c0(%R14),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa0(%RBX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%RAX,4),%EDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R11D,%EDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVSXD %EDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST %R11,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4497fa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (,%RCX,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $0x1,%R11B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 449810 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R11,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
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 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xa98(%R14),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x200(%RBX),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R11,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x1,%R12D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x4(%R8,%R9,1),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R8,%R9,1),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R10,%R15,1),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSHQ 0x1e8(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %ESI,%R13D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x50(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMOVLE %R13D,%ESI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
ADD $0x8,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSHQ 0x1d0(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %ESI,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x34(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSHQ 0x10(%RBP) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ -0x48(%RBP) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 4476c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x1,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 449736 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4497fa | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | TwoBodyJastrowRef.h:251-276 |
Module | exec |
nb instructions | 85 |
nb uops | 93 |
loop length | 313 |
used x86 registers | 16 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 9 |
micro-operation queue | 23.25 cycles |
front end | 23.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 7.00 | 7.00 | 16.33 | 16.33 | 20.00 | 7.00 | 7.00 | 16.33 |
cycles | 7.00 | 7.00 | 16.33 | 16.33 | 20.00 | 7.00 | 7.00 | 16.33 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 22.40 |
Stall cycles | 0.00 |
Front-end | 23.25 |
Dispatch | 20.00 |
Overall L1 | 23.25 |
all | 0% |
load | 0% |
store | 0% |
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 | 0% |
all | 8% |
load | 5% |
store | 11% |
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 | 7% |
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 |
MOV %RSI,%R14 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH %R13 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %EDX,%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 |
PUSH %RBX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SUB $0x38,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %EDX,-0x34(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMPB $0,0x18(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RCX,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R8,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R9,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JNE 4496c6 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV 0x90(%RDI),%R13D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R13D,%R13D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 4496fc | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD %R13D,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x40(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
SAL $0x3,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404150 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404150 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R12,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %ESI,%ESI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CALL 404150 | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOVSXD -0x34(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x5c0(%R14),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0xa0(%RBX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RDX,%RAX,4),%EDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R11D,%EDI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVSXD %EDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
TEST %R11,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4497fa | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
LEA (,%RCX,8),%R15 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %R12D,%R12D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
TEST $0x1,%R11B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 449810 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R11,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RBX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R12,%RBX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RAX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
LEA -0x28(%RBP),%RSP | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
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 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xa98(%R14),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x200(%RBX),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R11,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x1,%R12D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x4(%R8,%R9,1),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R8,%R9,1),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R10,%R15,1),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x40(%RBP),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSHQ 0x1e8(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %ESI,%R13D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x50(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CMOVLE %R13D,%ESI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
ADD $0x8,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSHQ 0x1d0(%RBX) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %ESI,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x34(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSHQ 0x10(%RBP) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ -0x48(%RBP) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 4476c0 <_ZNK11qmcplusplus14BsplineFunctorIdE11evaluateVGLEiiiPKdPdS4_S4_S4_Pi> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x58(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP $0x1,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 449736 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 4497fa | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XCHG %AX,%AX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼miniqmcreference::TwoBodyJastrowRef | 0.02 | 0.02 |
○Loop 592 - TwoBodyJastrowRef.h:266-271 - exec | 0.02 | 0.01 |