Function: qmcplusplus::DistanceTableAA<double, 3u, 39>::evaluate(qmcplusplus::ParticleSet&, int) | Module: exec | Source: DistanceTableAA.h:74-78 [...] | Coverage: 0.01% |
---|
Function: qmcplusplus::DistanceTableAA<double, 3u, 39>::evaluate(qmcplusplus::ParticleSet&, int) | Module: exec | Source: DistanceTableAA.h:74-78 [...] | Coverage: 0.01% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsMatrix.h: 217 - 217 |
-------------------------------------------------------------------------------- |
217: inline Type_t* operator[](size_type i) { return X.data() + i * D2; } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Particle/DistanceTableAA.h: 74 - 78 |
-------------------------------------------------------------------------------- |
74: inline void evaluate(ParticleSet& P, IndexType jat) |
75: { |
76: DTD_BConds<T, D, SC>::computeDistances(P.R[jat], P.RSoA, Distances[jat], Displacements[jat], 0, Ntargets, jat); |
77: Distances[jat][jat] = std::numeric_limits<T>::max(); // assign a big number |
78: } |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 223 - 248 |
-------------------------------------------------------------------------------- |
223: return X[i]; |
[...] |
248: inline pointer data() { return X; } |
/usr/include/c++/13.1.1/bits/stl_vector.h: 1126 - 1126 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
0x494430 PUSH %RBP |
0x494431 MOV %RDI,%RAX |
0x494434 MOV %RSI,%RCX |
0x494437 MOV %RSP,%RBP |
0x49443a PUSH %R14 |
0x49443c PUSH %R13 |
0x49443e PUSH %R12 |
0x494440 PUSH %RBX |
0x494441 MOVSXD %EDX,%RBX |
0x494444 LEA (%RBX,%RBX,4),%RDI |
0x494448 LEA (%RBX,%RBX,2),%R10 |
0x49444c MOV 0x50(%RAX),%RSI |
0x494450 MOV 0x40(%RAX),%R12 |
0x494454 MOV 0x610(%RCX),%R14 |
0x49445b MOV 0x600(%RCX),%R11 |
0x494462 LEA (%RSI,%RDI,8),%R8 |
0x494466 MOV 0x5e8(%RCX),%RCX |
0x49446d MOV 0x18(%RAX),%R13 |
0x494471 LEA 0xf0(%RAX),%RDI |
0x494478 MOV 0x8(%R8),%R9 |
0x49447c PUSH %RDX |
0x49447d IMUL %RBX,%R13 |
0x494481 LEA (%RCX,%R10,8),%RSI |
0x494485 MOV %R14,%RCX |
0x494488 MOV 0xc8(%RAX),%EDX |
0x49448e ADD %R13,%RBX |
0x494491 PUSH %RDX |
0x494492 MOV %R11,%RDX |
0x494495 PUSH $0 |
0x494497 PUSHQ 0x18(%R8) |
0x49449b LEA (%R12,%R13,8),%R8 |
0x49449f CALL 4917a0 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi39EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ELm64ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii.isra.0> |
0x4944a4 MOV 0x3c405(%RIP),%R9 |
0x4944ab ADD $0x20,%RSP |
0x4944af MOV %R9,(%R12,%RBX,8) |
0x4944b3 LEA -0x20(%RBP),%RSP |
0x4944b7 POP %RBX |
0x4944b8 POP %R12 |
0x4944ba POP %R13 |
0x4944bc POP %R14 |
0x4944be POP %RBP |
0x4944bf RET |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | qmcplusplus::ParticleSet::setA[...] | ParticleSet.cpp:259 | 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 | DistanceTableAA.h:74-78 |
Module | exec |
nb instructions | 42 |
nb uops | 44 |
loop length | 144 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 11.00 cycles |
front end | 11.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.50 | 4.00 | 9.17 | 8.83 | 11.00 | 4.00 | 2.50 | 9.00 |
cycles | 2.50 | 5.25 | 9.17 | 8.83 | 11.00 | 4.00 | 2.50 | 9.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 10.88 |
Stall cycles | 0.00 |
Front-end | 11.00 |
Dispatch | 11.00 |
Overall L1 | 11.00 |
all | 0% |
load | 0% |
store | 0% |
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 | 11% |
load | 11% |
store | 12% |
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 | 12% |
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 %RDI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
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 |
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 |
MOVSXD %EDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RBX,%RBX,4),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RBX,%RBX,2),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x50(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x40(%RAX),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x610(%RCX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x600(%RCX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RSI,%RDI,8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x5e8(%RCX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RAX),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0xf0(%RAX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x8(%R8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSH %RDX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
IMUL %RBX,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%RCX,%R10,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xc8(%RAX),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R13,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH %RDX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH $0 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ 0x18(%R8) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R12,%R13,8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 4917a0 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi39EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ELm64ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii.isra.0> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x3c405(%RIP),%R9 | 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 |
MOV %R9,(%R12,%RBX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x20(%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 %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 |
Source file and lines | DistanceTableAA.h:74-78 |
Module | exec |
nb instructions | 42 |
nb uops | 44 |
loop length | 144 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 11.00 cycles |
front end | 11.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 2.50 | 4.00 | 9.17 | 8.83 | 11.00 | 4.00 | 2.50 | 9.00 |
cycles | 2.50 | 5.25 | 9.17 | 8.83 | 11.00 | 4.00 | 2.50 | 9.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 10.88 |
Stall cycles | 0.00 |
Front-end | 11.00 |
Dispatch | 11.00 |
Overall L1 | 11.00 |
all | 0% |
load | 0% |
store | 0% |
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 | 11% |
load | 11% |
store | 12% |
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 | 12% |
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 %RDI,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RSI,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
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 |
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 |
MOVSXD %EDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RBX,%RBX,4),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RBX,%RBX,2),%R10 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x50(%RAX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x40(%RAX),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x610(%RCX),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x600(%RCX),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RSI,%RDI,8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x5e8(%RCX),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%RAX),%R13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0xf0(%RAX),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x8(%R8),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
PUSH %RDX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
IMUL %RBX,%R13 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA (%RCX,%R10,8),%RSI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV %R14,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0xc8(%RAX),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R13,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH %RDX | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R11,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
PUSH $0 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSHQ 0x18(%R8) | 2 | 0 | 0 | 0.83 | 0.83 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA (%R12,%R13,8),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CALL 4917a0 <_ZNK11qmcplusplus10DTD_BCondsIdLj3ELi39EE16computeDistancesINS_10TinyVectorIdLj3EEENS_18VectorSoAContainerIdLj3ELm64ENS_10MallocatorIdLm64EEEEES8_EEvRKT_RKT0_PdRT1_iii.isra.0> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x3c405(%RIP),%R9 | 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 |
MOV %R9,(%R12,%RBX,8) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA -0x20(%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 %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 |
Name | Coverage (%) | Time (s) |
---|---|---|
○qmcplusplus::DistanceTableAA | 0.01 | 0 |