Loop Id: 655 | Module: exec | Source: BsplineAllocator.hpp:171-180 [...] | Coverage: 0.01% |
---|
Loop Id: 655 | Module: exec | Source: BsplineAllocator.hpp:171-180 [...] | Coverage: 0.01% |
---|
0x450430 CMP %R14D,-0x38(%RBP) |
0x450434 JLE 4505ec |
0x45043a MOVSXD -0x40(%RBP),%R8 |
0x45043e MOV 0x8(%RBX),%R12 |
0x450442 MOVSXD %EDX,%RAX |
0x450445 MOVSXD %R9D,%RCX |
0x450448 MOV 0x18(%RBX),%RDI |
0x45044c MOV -0x68(%RBP),%RSI |
0x450450 IMUL %R8,%R12 |
0x450454 ADD %RAX,%R12 |
0x450457 IMUL 0x10(%RBX),%R12 |
0x45045c ADD %RCX,%R12 |
0x45045f LEA (%RDI,%R12,8),%RDI |
0x450463 MOV -0x60(%RBP),%R12 |
0x450467 ADD (%R12),%RSI |
0x45046b MOV -0x48(%RBP),%R12 |
0x45046f IMUL %R12,%R8 |
0x450473 MOV -0x50(%RBP),%R12 |
0x450477 IMUL %R12,%RAX |
0x45047b LEA -0x8(%R10),%R12 |
0x45047f SHR $0x3,%R12 |
0x450483 INC %R12 |
0x450486 ADD %R8,%RAX |
0x450489 MOV -0x58(%RBP),%R8 |
0x45048d IMUL %R8,%RCX |
0x450491 ADD %RCX,%RAX |
0x450494 MOV 0x8(%R13),%RCX |
0x450498 ADD %R15,%RAX |
0x45049b LEA (%RCX,%RAX,8),%RCX |
0x45049f XOR %EAX,%EAX |
0x4504a1 AND $0x7,%R12D |
0x4504a5 JE 450559 |
0x4504ab CMP $0x1,%R12 |
0x4504af JE 45053e |
0x4504b5 CMP $0x2,%R12 |
0x4504b9 JE 45052c |
0x4504bb CMP $0x3,%R12 |
0x4504bf JE 45051a |
0x4504c1 CMP $0x4,%R12 |
0x4504c5 JE 450508 |
0x4504c7 CMP $0x5,%R12 |
0x4504cb JE 4504f6 |
0x4504cd CMP $0x6,%R12 |
0x4504d1 JE 4504e4 |
0x4504d3 VMOVSD (%RDI),%XMM0 |
0x4504d7 MOV $0x8,%EAX |
0x4504dc VMULSD (%RSI),%XMM0,%XMM1 |
0x4504e0 VMOVSD %XMM1,(%RCX) |
0x4504e4 VMOVSD (%RDI),%XMM2 |
0x4504e8 VMULSD (%RSI,%RAX,1),%XMM2,%XMM3 |
0x4504ed VMOVSD %XMM3,(%RCX,%RAX,1) |
0x4504f2 ADD $0x8,%RAX |
0x4504f6 VMOVSD (%RDI),%XMM4 |
0x4504fa VMULSD (%RSI,%RAX,1),%XMM4,%XMM5 |
0x4504ff VMOVSD %XMM5,(%RCX,%RAX,1) |
0x450504 ADD $0x8,%RAX |
0x450508 VMOVSD (%RDI),%XMM6 |
0x45050c VMULSD (%RSI,%RAX,1),%XMM6,%XMM7 |
0x450511 VMOVSD %XMM7,(%RCX,%RAX,1) |
0x450516 ADD $0x8,%RAX |
0x45051a VMOVSD (%RDI),%XMM8 |
0x45051e VMULSD (%RSI,%RAX,1),%XMM8,%XMM9 |
0x450523 VMOVSD %XMM9,(%RCX,%RAX,1) |
0x450528 ADD $0x8,%RAX |
0x45052c VMOVSD (%RDI),%XMM10 |
0x450530 VMULSD (%RSI,%RAX,1),%XMM10,%XMM11 |
0x450535 VMOVSD %XMM11,(%RCX,%RAX,1) |
0x45053a ADD $0x8,%RAX |
0x45053e VMOVSD (%RDI),%XMM12 |
0x450542 VMULSD (%RSI,%RAX,1),%XMM12,%XMM13 |
0x450547 VMOVSD %XMM13,(%RCX,%RAX,1) |
0x45054c ADD $0x8,%RAX |
0x450550 CMP %RAX,%R10 |
0x450553 JE 4505ec |
0x450559 MOV -0x34(%RBP),%R8D |
(656) 0x45055d VMOVSD (%RDI),%XMM14 |
(656) 0x450561 VMULSD (%RSI,%RAX,1),%XMM14,%XMM15 |
(656) 0x450566 VMOVSD %XMM15,(%RCX,%RAX,1) |
(656) 0x45056b VMOVSD (%RDI),%XMM0 |
(656) 0x45056f VMULSD 0x8(%RSI,%RAX,1),%XMM0,%XMM1 |
(656) 0x450575 VMOVSD %XMM1,0x8(%RCX,%RAX,1) |
(656) 0x45057b VMOVSD (%RDI),%XMM2 |
(656) 0x45057f VMULSD 0x10(%RSI,%RAX,1),%XMM2,%XMM3 |
(656) 0x450585 VMOVSD %XMM3,0x10(%RCX,%RAX,1) |
(656) 0x45058b VMOVSD (%RDI),%XMM4 |
(656) 0x45058f VMULSD 0x18(%RSI,%RAX,1),%XMM4,%XMM5 |
(656) 0x450595 VMOVSD %XMM5,0x18(%RCX,%RAX,1) |
(656) 0x45059b VMOVSD (%RDI),%XMM6 |
(656) 0x45059f VMULSD 0x20(%RSI,%RAX,1),%XMM6,%XMM7 |
(656) 0x4505a5 VMOVSD %XMM7,0x20(%RCX,%RAX,1) |
(656) 0x4505ab VMOVSD (%RDI),%XMM8 |
(656) 0x4505af VMULSD 0x28(%RSI,%RAX,1),%XMM8,%XMM9 |
(656) 0x4505b5 VMOVSD %XMM9,0x28(%RCX,%RAX,1) |
(656) 0x4505bb VMOVSD (%RDI),%XMM10 |
(656) 0x4505bf VMULSD 0x30(%RSI,%RAX,1),%XMM10,%XMM11 |
(656) 0x4505c5 VMOVSD %XMM11,0x30(%RCX,%RAX,1) |
(656) 0x4505cb VMOVSD (%RDI),%XMM12 |
(656) 0x4505cf VMULSD 0x38(%RSI,%RAX,1),%XMM12,%XMM13 |
(656) 0x4505d5 VMOVSD %XMM13,0x38(%RCX,%RAX,1) |
(656) 0x4505db ADD $0x40,%RAX |
(656) 0x4505df CMP %RAX,%R10 |
(656) 0x4505e2 JNE 45055d |
0x4505e8 MOV %R8D,-0x34(%RBP) |
0x4505ec CMP %R11D,-0x3c(%RBP) |
0x4505f0 JE 450608 |
0x4505f2 INC %R9D |
0x4505f5 CMP %R9D,-0x34(%RBP) |
0x4505f9 JLE 450620 |
0x4505fb INC %R11D |
0x4505fe JMP 450430 |
0x450620 INC %EDX |
0x450622 XOR %R9D,%R9D |
0x450625 CMP %EDX,-0x6c(%RBP) |
0x450628 JG 4505fb |
0x45062a INCL -0x40(%RBP) |
0x45062d XOR %EDX,%EDX |
0x45062f JMP 4505fb |
/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]; |
/usr/include/c++/13.1.1/bits/stl_vector.h: 1126 - 1126 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
/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)]; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
○100.00 | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.18 |
CQA speedup if FP arith vectorized | 2.08 |
CQA speedup if fully vectorized | 11.90 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.58 |
Bottlenecks | micro-operation queue, |
Function | qmcplusplus::BsplineAllocator |
Source | BsplineAllocator.hpp:171-180,stl_vector.h:1126-1126,OhmmsArray.h:156-156 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 24.50 |
CQA cycles if no scalar integer | 11.25 |
CQA cycles if FP arith vectorized | 11.76 |
CQA cycles if fully vectorized | 2.06 |
Front-end cycles | 24.50 |
DIV/SQRT cycles | 15.50 |
P0 cycles | 15.50 |
P1 cycles | 15.50 |
P2 cycles | 15.50 |
P3 cycles | 9.00 |
P4 cycles | 15.50 |
P5 cycles | 15.50 |
P6 cycles | 9.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 24.49 |
Stall cycles (UFS) | 0.00 |
Nb insns | 90.00 |
Nb uops | 92.00 |
Nb loads | 31.00 |
Nb stores | 9.00 |
Nb stack references | 10.00 |
FLOP/cycle | 0.29 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 7.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 11.59 |
Bytes prefetched | 0.00 |
Bytes loaded | 220.00 |
Bytes stored | 64.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 10.86 |
Vector-efficiency ratio load | 11.01 |
Vector-efficiency ratio store | 11.72 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.62 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.18 |
CQA speedup if FP arith vectorized | 2.08 |
CQA speedup if fully vectorized | 11.90 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.58 |
Bottlenecks | micro-operation queue, |
Function | qmcplusplus::BsplineAllocator |
Source | BsplineAllocator.hpp:171-180,stl_vector.h:1126-1126,OhmmsArray.h:156-156 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 24.50 |
CQA cycles if no scalar integer | 11.25 |
CQA cycles if FP arith vectorized | 11.76 |
CQA cycles if fully vectorized | 2.06 |
Front-end cycles | 24.50 |
DIV/SQRT cycles | 15.50 |
P0 cycles | 15.50 |
P1 cycles | 15.50 |
P2 cycles | 15.50 |
P3 cycles | 9.00 |
P4 cycles | 15.50 |
P5 cycles | 15.50 |
P6 cycles | 9.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 24.49 |
Stall cycles (UFS) | 0.00 |
Nb insns | 90.00 |
Nb uops | 92.00 |
Nb loads | 31.00 |
Nb stores | 9.00 |
Nb stack references | 10.00 |
FLOP/cycle | 0.29 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 7.00 |
Nb FLOP fma | 0.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 11.59 |
Bytes prefetched | 0.00 |
Bytes loaded | 220.00 |
Bytes stored | 64.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 0.00 |
Vectorization ratio load | 0.00 |
Vectorization ratio store | 0.00 |
Vectorization ratio mul | 0.00 |
Vectorization ratio add_sub | 0.00 |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 10.86 |
Vector-efficiency ratio load | 11.01 |
Vector-efficiency ratio store | 11.72 |
Vector-efficiency ratio mul | 12.50 |
Vector-efficiency ratio add_sub | 6.25 |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 9.62 |
Path / |
Function | qmcplusplus::BsplineAllocator |
Source file and lines | BsplineAllocator.hpp:171-180 |
Module | exec |
nb instructions | 90 |
nb uops | 92 |
loop length | 345 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 14 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10 |
micro-operation queue | 24.50 cycles |
front end | 24.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 15.50 | 15.50 | 15.50 | 15.50 | 9.00 | 15.50 | 15.50 | 9.00 |
cycles | 15.50 | 15.50 | 15.50 | 15.50 | 9.00 | 15.50 | 15.50 | 9.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 24.49 |
Stall cycles | 0.00 |
Front-end | 24.50 |
Dispatch | 15.50 |
Overall L1 | 24.50 |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 9% |
load | 8% |
store | 6% |
mul | 12% |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 10% |
load | 11% |
store | 11% |
mul | 12% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
CMP %R14D,-0x38(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4505ec <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2ac> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD -0x40(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RBX),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %EDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %R9D,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x18(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RAX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL 0x10(%RBX),%R12 | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RCX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RDI,%R12,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x60(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD (%R12),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R12,%R8 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV -0x50(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R12,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x8(%R10),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SHR $0x3,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R15,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RCX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $0x7,%R12D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 450559 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x219> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45053e <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1fe> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45052c <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1ec> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x3,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45051a <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1da> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x4,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 450508 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1c8> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x5,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4504f6 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1b6> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x6,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4504e4 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1a4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x8,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMULSD (%RSI),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM1,(%RCX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD (%RDI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM2,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM4,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM5,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM7,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM10,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM12,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4505ec <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2ac> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x34(%RBP),%R8D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8D,-0x34(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %R11D,-0x3c(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 450608 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2c8> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R9D,-0x34(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 450620 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %R11D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 450430 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0xf0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INC %EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %EDX,-0x6c(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JG 4505fb <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2bb> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INCL -0x40(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4505fb <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2bb> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
Function | qmcplusplus::BsplineAllocator |
Source file and lines | BsplineAllocator.hpp:171-180 |
Module | exec |
nb instructions | 90 |
nb uops | 92 |
loop length | 345 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 14 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 10 |
micro-operation queue | 24.50 cycles |
front end | 24.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 15.50 | 15.50 | 15.50 | 15.50 | 9.00 | 15.50 | 15.50 | 9.00 |
cycles | 15.50 | 15.50 | 15.50 | 15.50 | 9.00 | 15.50 | 15.50 | 9.00 |
Cycles executing div or sqrt instructions | NA |
FE+BE cycles | 24.49 |
Stall cycles | 0.00 |
Front-end | 24.50 |
Dispatch | 15.50 |
Overall L1 | 24.50 |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 0% |
all | 0% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 0% |
load | 0% |
store | 0% |
mul | 0% |
add-sub | 0% |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 0% |
all | 9% |
load | 8% |
store | 6% |
mul | 12% |
add-sub | 6% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 9% |
all | 12% |
load | 12% |
store | 12% |
mul | 12% |
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 | NA (no other vectorizable/vectorized instructions) |
all | 10% |
load | 11% |
store | 11% |
mul | 12% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
CMP %R14D,-0x38(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 4505ec <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2ac> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOVSXD -0x40(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x8(%RBX),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD %EDX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %R9D,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x18(%RBX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x68(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%R12 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RAX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL 0x10(%RBX),%R12 | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RCX,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RDI,%R12,8),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV -0x60(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD (%R12),%RSI | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV -0x48(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R12,%R8 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOV -0x50(%RBP),%R12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R12,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
LEA -0x8(%R10),%R12 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
SHR $0x3,%R12 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
INC %R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
ADD %R8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R8,%RCX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV 0x8(%R13),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R15,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
LEA (%RCX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
AND $0x7,%R12D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 450559 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x219> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x1,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45053e <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1fe> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x2,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45052c <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1ec> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x3,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 45051a <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1da> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x4,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 450508 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1c8> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x5,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4504f6 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1b6> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CMP $0x6,%R12 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4504e4 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x1a4> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%RDI),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV $0x8,%EAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMULSD (%RSI),%XMM0,%XMM1 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM1,(%RCX) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD (%RDI),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM2,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM3,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM4 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM4,%XMM5 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM5,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM6,%XMM7 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM7,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM9,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM10,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM11,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%RDI),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMULSD (%RSI,%RAX,1),%XMM12,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,(%RCX,%RAX,1) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
ADD $0x8,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %RAX,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 4505ec <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2ac> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x34(%RBP),%R8D | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV %R8D,-0x34(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CMP %R11D,-0x3c(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JE 450608 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2c8> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %R9D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R9D,-0x34(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JLE 450620 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2e0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INC %R11D | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JMP 450430 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0xf0> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
INC %EDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
XOR %R9D,%R9D | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %EDX,-0x6c(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
JG 4505fb <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2bb> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
INCL -0x40(%RBP) | 3 | 0.25 | 0.25 | 0.83 | 0.83 | 1 | 0.25 | 0.25 | 0.33 | 5 | 1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 4505fb <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d._omp_fn.0+0x2bb> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |