Function: qmcplusplus::BsplineAllocator<double, 64ul, qmcplusplus::Mallocator<double, 64ul> >::setCo ... | Module: exec | Source: BsplineAllocator.hpp:171-180 [...] | Coverage: 0.22% |
---|
Function: qmcplusplus::BsplineAllocator<double, 64ul, qmcplusplus::Mallocator<double, 64ul> >::setCo ... | Module: exec | Source: BsplineAllocator.hpp:171-180 [...] | Coverage: 0.22% |
---|
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/BsplineAllocator.hpp: 171 - 180 |
-------------------------------------------------------------------------------- |
171: #pragma omp parallel for collapse(3) |
172: for (int ix = 0; ix < spline->x_grid.num + 3; ix++) |
173: for (int iy = 0; iy < spline->y_grid.num + 3; iy++) |
174: for (int iz = 0; iz < spline->z_grid.num + 3; iz++) |
175: { |
176: intptr_t xs = spline->x_stride; |
177: intptr_t ys = spline->y_stride; |
178: intptr_t zs = spline->z_stride; |
179: for (int ind = first; ind < last; ind++) |
180: spline->coefs[ix * xs + iy * ys + iz * zs + ind] = coeff(ix, iy, iz) * prefactor[ind]; |
/home/kcamus/qaas_runs/169-451-1869/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsArray.h: 156 - 156 |
-------------------------------------------------------------------------------- |
156: return X[k + Length[2] * (j + Length[1] * i)]; |
/usr/lib64/gcc/x86_64-pc-linux-gnu/13.1.1/../../../../include/c++/13.1.1/bits/stl_vector.h: 1126 - 1126 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
0x43a2b0 PUSH %RBP |
0x43a2b1 MOV %RSP,%RBP |
0x43a2b4 PUSH %R15 |
0x43a2b6 PUSH %R14 |
0x43a2b8 PUSH %R13 |
0x43a2ba PUSH %R12 |
0x43a2bc PUSH %RBX |
0x43a2bd SUB $0xa8,%RSP |
0x43a2c4 MOV %RCX,%R15 |
0x43a2c7 MOV 0x30(%RBP),%RAX |
0x43a2cb MOV 0x20(%RBP),%RCX |
0x43a2cf MOV %RCX,-0x30(%RBP) |
0x43a2d3 MOV 0x18(%RBP),%RBX |
0x43a2d7 MOV 0x10(%RBP),%R14 |
0x43a2db MOVL $0,-0x40(%RBP) |
0x43a2e2 TEST %RAX,%RAX |
0x43a2e5 JS 43a608 |
0x43a2eb MOV %R9,%R12 |
0x43a2ee MOV %R8,%R13 |
0x43a2f1 MOV (%RDI),%ESI |
0x43a2f3 MOVQ $0,-0x60(%RBP) |
0x43a2fb MOV %RAX,-0x58(%RBP) |
0x43a2ff MOVQ $0x1,-0xc8(%RBP) |
0x43a30a SUB $0x8,%RSP |
0x43a30e LEA -0xc8(%RBP),%RAX |
0x43a315 LEA -0x40(%RBP),%RCX |
0x43a319 LEA -0x60(%RBP),%R8 |
0x43a31d LEA -0x58(%RBP),%R9 |
0x43a321 MOV $0x4e7890,%EDI |
0x43a326 MOV %ESI,-0x3c(%RBP) |
0x43a329 MOV $0x22,%EDX |
0x43a32e PUSH $0x1 |
0x43a330 PUSH $0x1 |
0x43a332 PUSH %RAX |
0x43a333 CALL 404400 <__kmpc_for_static_init_8@plt> |
0x43a338 ADD $0x20,%RSP |
0x43a33c MOV -0x60(%RBP),%RCX |
0x43a340 MOV -0x58(%RBP),%RAX |
0x43a344 MOV %RCX,-0x48(%RBP) |
0x43a348 CMP %RAX,%RCX |
0x43a34b JA 43a5e7 |
0x43a351 TEST %R15D,%R15D |
0x43a354 JLE 43a5e7 |
0x43a35a MOV -0x30(%RBP),%RDX |
0x43a35e IMUL %EDX,%EBX |
0x43a361 MOV %RBX,-0x68(%RBP) |
0x43a365 MOVSXD %EBX,%RBX |
0x43a368 MOV 0x10(%R12),%RCX |
0x43a36d MOV %RCX,-0xb0(%RBP) |
0x43a374 MOV 0x18(%R12),%RCX |
0x43a379 MOV %RCX,-0xa8(%RBP) |
0x43a380 MOV 0x20(%R12),%RCX |
0x43a385 MOV %RCX,-0xa0(%RBP) |
0x43a38c MOV 0x8(%R13),%RCX |
0x43a390 MOV %RCX,-0x98(%RBP) |
0x43a397 MOV 0x10(%R13),%RCX |
0x43a39b MOV %RCX,-0x90(%RBP) |
0x43a3a2 MOV 0x18(%R13),%RCX |
0x43a3a6 MOV %RCX,-0x88(%RBP) |
0x43a3ad MOV 0x8(%R12),%RCX |
0x43a3b2 MOV %RCX,-0x50(%RBP) |
0x43a3b6 MOV -0x48(%RBP),%RSI |
0x43a3ba LEA 0x1(%RSI),%RCX |
0x43a3be INC %RAX |
0x43a3c1 CMP %RAX,%RCX |
0x43a3c4 CMOVG %RCX,%RAX |
0x43a3c8 NOT %RSI |
0x43a3cb ADD %RAX,%RSI |
0x43a3ce MOV %RSI,-0x80(%RBP) |
0x43a3d2 MOVSXD %EDX,%RDI |
0x43a3d5 MOVSXD %R15D,%R13 |
0x43a3d8 LEA (%R14,%R13,8),%RAX |
0x43a3dc ADD $-0x8,%RAX |
0x43a3e0 MOV %RAX,-0x70(%RBP) |
0x43a3e4 MOV %R13,%R15 |
0x43a3e7 AND $-0x4,%R15 |
0x43a3eb XOR %EDX,%EDX |
0x43a3ed MOV %RBX,-0x38(%RBP) |
0x43a3f1 MOV %RDI,-0x78(%RBP) |
0x43a3f5 JMP 43a419 |
0x43a3f7 NOPW (%RAX,%RAX,1) |
(810) 0x43a400 MOV -0xc0(%RBP),%RCX |
(810) 0x43a407 LEA 0x1(%RCX),%RDX |
(810) 0x43a40b CMP -0x80(%RBP),%RCX |
(810) 0x43a40f MOV -0x78(%RBP),%RDI |
(810) 0x43a413 JE 43a5e7 |
(810) 0x43a419 MOV -0x48(%RBP),%RAX |
(810) 0x43a41d ADD %RDX,%RAX |
(810) 0x43a420 MOV %RAX,%RCX |
(810) 0x43a423 OR %RBX,%RCX |
(810) 0x43a426 SHR $0x20,%RCX |
(810) 0x43a42a MOV %RDX,-0xc0(%RBP) |
(810) 0x43a431 JE 43a470 |
(810) 0x43a433 CQTO |
(810) 0x43a435 IDIV %RBX |
(810) 0x43a438 MOV %RDX,%RBX |
(810) 0x43a43b MOV %RAX,%R8 |
(810) 0x43a43e MOV %RBX,%RSI |
(810) 0x43a441 OR %RDI,%RSI |
(810) 0x43a444 SHR $0x20,%RSI |
(810) 0x43a448 JE 43a486 |
(810) 0x43a44a MOV %RBX,%RAX |
(810) 0x43a44d CQTO |
(810) 0x43a44f IDIV %RDI |
(810) 0x43a452 MOV %RAX,%RCX |
(810) 0x43a455 TEST %RSI,%RSI |
(810) 0x43a458 JE 43a494 |
(810) 0x43a45a MOV %RBX,%RAX |
(810) 0x43a45d CQTO |
(810) 0x43a45f IDIV %RDI |
(810) 0x43a462 JMP 43a49b |
0x43a464 NOPW %CS:(%RAX,%RAX,1) |
(810) 0x43a470 XOR %EDX,%EDX |
(810) 0x43a472 DIVL -0x68(%RBP) |
(810) 0x43a475 MOV %EDX,%EBX |
(810) 0x43a477 MOV %EAX,%R8D |
(810) 0x43a47a MOV %RBX,%RSI |
(810) 0x43a47d OR %RDI,%RSI |
(810) 0x43a480 SHR $0x20,%RSI |
(810) 0x43a484 JNE 43a44a |
(810) 0x43a486 MOV %EBX,%EAX |
(810) 0x43a488 XOR %EDX,%EDX |
(810) 0x43a48a DIVL -0x30(%RBP) |
(810) 0x43a48d MOV %EAX,%ECX |
(810) 0x43a48f TEST %RSI,%RSI |
(810) 0x43a492 JNE 43a45a |
(810) 0x43a494 MOV %EBX,%EAX |
(810) 0x43a496 XOR %EDX,%EDX |
(810) 0x43a498 DIVL -0x30(%RBP) |
(810) 0x43a49b MOVSXD %EDX,%R12 |
(810) 0x43a49e MOV -0xa0(%RBP),%RAX |
(810) 0x43a4a5 IMUL %R12,%RAX |
(810) 0x43a4a9 MOVSXD %ECX,%RDX |
(810) 0x43a4ac MOV -0xa8(%RBP),%RCX |
(810) 0x43a4b3 IMUL %RDX,%RCX |
(810) 0x43a4b7 MOV %RCX,-0xb8(%RBP) |
(810) 0x43a4be LEA (%RAX,%RCX,1),%RDI |
(810) 0x43a4c2 MOVSXD %R8D,%RBX |
(810) 0x43a4c5 MOV -0xb0(%RBP),%R8 |
(810) 0x43a4cc IMUL %RBX,%R8 |
(810) 0x43a4d0 ADD %R8,%RDI |
(810) 0x43a4d3 MOV -0x50(%RBP),%RCX |
(810) 0x43a4d7 LEA (%RCX,%RDI,8),%RSI |
(810) 0x43a4db CMP %RSI,-0x70(%RBP) |
(810) 0x43a4df SETAE %R9B |
(810) 0x43a4e3 ADD %R13,%RDI |
(810) 0x43a4e6 LEA (%RCX,%RDI,8),%R10 |
(810) 0x43a4ea ADD $-0x8,%R10 |
(810) 0x43a4ee CMP %R14,%R10 |
(810) 0x43a4f1 SETAE %R11B |
(810) 0x43a4f5 IMUL -0x98(%RBP),%RBX |
(810) 0x43a4fd ADD %RDX,%RBX |
(810) 0x43a500 IMUL -0x90(%RBP),%RBX |
(810) 0x43a508 ADD %R12,%RBX |
(810) 0x43a50b MOV -0x88(%RBP),%RDX |
(810) 0x43a512 LEA (%RDX,%RBX,8),%RDI |
(810) 0x43a516 CMP %RSI,%RDI |
(810) 0x43a519 SETB %BL |
(810) 0x43a51c CMP %RDI,%R10 |
(810) 0x43a51f SETB %DL |
(810) 0x43a522 TEST %R11B,%R9B |
(810) 0x43a525 JNE 43a570 |
(810) 0x43a527 OR %DL,%BL |
(810) 0x43a529 JE 43a570 |
(810) 0x43a52b VMOVSD (%RDI),%XMM0 |
(810) 0x43a52f TEST %R15,%R15 |
(810) 0x43a532 JE 43a59c |
(810) 0x43a534 VBROADCASTSD %XMM0,%YMM1 |
(810) 0x43a539 XOR %EDI,%EDI |
(810) 0x43a53b NOPL (%RAX,%RAX,1) |
(812) 0x43a540 VMULPD (%R14,%RDI,8),%YMM1,%YMM2 |
(812) 0x43a546 VMOVUPD %YMM2,(%RSI,%RDI,8) |
(812) 0x43a54b ADD $0x4,%RDI |
(812) 0x43a54f CMP %R15,%RDI |
(812) 0x43a552 JL 43a540 |
(810) 0x43a554 MOV %R15,%RDI |
(810) 0x43a557 CMP %R15,%R13 |
(810) 0x43a55a MOV -0x38(%RBP),%RBX |
(810) 0x43a55e JE 43a400 |
(810) 0x43a564 JMP 43a5a2 |
0x43a566 NOPW %CS:(%RAX,%RAX,1) |
(810) 0x43a570 XOR %EAX,%EAX |
(810) 0x43a572 MOV -0x38(%RBP),%RBX |
(810) 0x43a576 NOPW %CS:(%RAX,%RAX,1) |
(809) 0x43a580 VMOVSD (%R14,%RAX,8),%XMM0 |
(809) 0x43a586 VMULSD (%RDI),%XMM0,%XMM0 |
(809) 0x43a58a VMOVSD %XMM0,(%RSI,%RAX,8) |
(809) 0x43a58f INC %RAX |
(809) 0x43a592 CMP %RAX,%R13 |
(809) 0x43a595 JNE 43a580 |
(810) 0x43a597 JMP 43a400 |
(810) 0x43a59c XOR %EDI,%EDI |
(810) 0x43a59e MOV -0x38(%RBP),%RBX |
(810) 0x43a5a2 MOV %R13,%RSI |
(810) 0x43a5a5 SUB %RDI,%RSI |
(810) 0x43a5a8 ADD %RDI,%RAX |
(810) 0x43a5ab ADD -0xb8(%RBP),%RAX |
(810) 0x43a5b2 ADD %R8,%RAX |
(810) 0x43a5b5 MOV -0x50(%RBP),%RCX |
(810) 0x43a5b9 LEA (%RCX,%RAX,8),%RAX |
(810) 0x43a5bd LEA (%R14,%RDI,8),%RCX |
(810) 0x43a5c1 XOR %EDX,%EDX |
(810) 0x43a5c3 NOPW %CS:(%RAX,%RAX,1) |
(811) 0x43a5d0 VMULSD (%RCX,%RDX,8),%XMM0,%XMM1 |
(811) 0x43a5d5 VMOVSD %XMM1,(%RAX,%RDX,8) |
(811) 0x43a5da INC %RDX |
(811) 0x43a5dd CMP %RDX,%RSI |
(811) 0x43a5e0 JNE 43a5d0 |
(810) 0x43a5e2 JMP 43a400 |
0x43a5e7 MOV $0x4e78b0,%EDI |
0x43a5ec MOV -0x3c(%RBP),%ESI |
0x43a5ef ADD $0xa8,%RSP |
0x43a5f6 POP %RBX |
0x43a5f7 POP %R12 |
0x43a5f9 POP %R13 |
0x43a5fb POP %R14 |
0x43a5fd POP %R15 |
0x43a5ff POP %RBP |
0x43a600 VZEROUPPER |
0x43a603 JMP 404820 |
0x43a608 ADD $0xa8,%RSP |
0x43a60f POP %RBX |
0x43a610 POP %R12 |
0x43a612 POP %R13 |
0x43a614 POP %R14 |
0x43a616 POP %R15 |
0x43a618 POP %RBP |
0x43a619 RET |
0x43a61a NOPW (%RAX,%RAX,1) |
0x44b227 NOPW (%RAX,%RAX,1) |
0x44b294 NOPW %CS:(%RAX,%RAX,1) |
0x44b396 NOPW %CS:(%RAX,%RAX,1) |
0x44b44a NOPW (%RAX,%RAX,1) |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_fork_call | libiomp5.so | |
○ | __kmpc_fork_call | libiomp5.so | |
○ | miniqmcreference::einspline_sp[...] | BsplineAllocator.hpp:171 | exec |
○ | qmcplusplus::build_SPOSet(bool[...] | SPOSet_builder.cpp:31 | exec |
○ | main | miniqmc.cpp:358 | exec |
○ | __libc_init_first | libc.so.6 |
Path / |
Source file and lines | BsplineAllocator.hpp:171-180 |
Module | exec |
nb instructions | 107 |
nb uops | 111 |
loop length | 452 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 23 |
micro-operation queue | 27.75 cycles |
front end | 27.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 8.75 | 8.75 | 19.83 | 19.50 | 29.00 | 8.75 | 8.75 | 19.67 |
cycles | 8.75 | 9.00 | 19.83 | 19.50 | 29.00 | 8.75 | 8.75 | 19.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 28.14 |
Stall cycles | 0.86 |
SB full (events) | 2.07 |
Front-end | 27.75 |
Dispatch | 29.00 |
Overall L1 | 29.00 |
all | 2% |
load | 0% |
store | 0% |
mul | 0% |
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% |
all | 11% |
load | 12% |
store | 11% |
mul | 6% |
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 | 11% |
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 $0xa8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x18(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVL $0,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JS 43a608 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x358> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RDI),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %RAX,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0x1,-0xc8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
SUB $0x8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0xc8(%RBP),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x40(%RBP),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x60(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x58(%RBP),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x4e7890,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %ESI,-0x3c(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x22,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH $0x1 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH $0x1 | 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 |
CALL 404400 <__kmpc_for_static_init_8@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JA 43a5e7 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x337> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %R15D,%R15D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 43a5e7 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x337> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %EDX,%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RBX,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %EBX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x10(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x18(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x10(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x18(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x48(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%RSI),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVG %RCX,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
NOT %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %EDX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %R15D,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R14,%R13,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $-0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R13,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RBX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JMP 43a419 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x169> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x4e78b0,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x3c(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0xa8,%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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JMP 404820 <__kmpc_for_static_fini@plt> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
ADD $0xa8,%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 (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Source file and lines | BsplineAllocator.hpp:171-180 |
Module | exec |
nb instructions | 107 |
nb uops | 111 |
loop length | 452 |
used x86 registers | 14 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 23 |
micro-operation queue | 27.75 cycles |
front end | 27.75 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 8.75 | 8.75 | 19.83 | 19.50 | 29.00 | 8.75 | 8.75 | 19.67 |
cycles | 8.75 | 9.00 | 19.83 | 19.50 | 29.00 | 8.75 | 8.75 | 19.67 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 28.14 |
Stall cycles | 0.86 |
SB full (events) | 2.07 |
Front-end | 27.75 |
Dispatch | 29.00 |
Overall L1 | 29.00 |
all | 2% |
load | 0% |
store | 0% |
mul | 0% |
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% |
all | 11% |
load | 12% |
store | 11% |
mul | 6% |
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 | 11% |
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 $0xa8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RCX,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV 0x30(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x30(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x18(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x10(%RBP),%R14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVL $0,-0x40(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
TEST %RAX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JS 43a608 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x358> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %R9,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R8,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV (%RDI),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVQ $0,-0x60(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
MOV %RAX,-0x58(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVQ $0x1,-0xc8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 2 | 1 |
SUB $0x8,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA -0xc8(%RBP),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x40(%RBP),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x60(%RBP),%R8 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA -0x58(%RBP),%R9 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV $0x4e7890,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %ESI,-0x3c(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV $0x22,%EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
PUSH $0x1 | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
PUSH $0x1 | 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 |
CALL 404400 <__kmpc_for_static_init_8@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
ADD $0x20,%RSP | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x60(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x58(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x48(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JA 43a5e7 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x337> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
TEST %R15D,%R15D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JLE 43a5e7 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x337> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x30(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %EDX,%EBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV %RBX,-0x68(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %EBX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x10(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xb0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x18(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xa8(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x20(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0xa0(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x98(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x10(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x90(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x18(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x88(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV 0x8(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %RCX,-0x50(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV -0x48(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x1(%RSI),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
INC %RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMOVG %RCX,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
NOT %RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %RAX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RSI,-0x80(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOVSXD %EDX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %R15D,%R13 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%R14,%R13,8),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $-0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,-0x70(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %R13,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $-0x4,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RBX,-0x38(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
MOV %RDI,-0x78(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
JMP 43a419 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x169> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV $0x4e78b0,%EDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x3c(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0xa8,%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 |
VZEROUPPER | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
JMP 404820 <__kmpc_for_static_fini@plt> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
ADD $0xa8,%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 (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPW (%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
Name | Coverage (%) | Time (s) |
---|---|---|
▼qmcplusplus::BsplineAllocator | 0.22 | 0.14 |
▼Loop 810 - BsplineAllocator.hpp:171-180 - exec– | 0 | 0 |
○Loop 812 - BsplineAllocator.hpp:179-180 - exec | 0.22 | 0.14 |
○Loop 811 - BsplineAllocator.hpp:179-180 - exec | 0 | 0 |
○Loop 809 - BsplineAllocator.hpp:179-180 - exec | 0 | 0 |