Loop Id: 653 | Module: exec | Source: BsplineAllocator.hpp:171-180 [...] | Coverage: 0.02% |
---|
Loop Id: 653 | Module: exec | Source: BsplineAllocator.hpp:171-180 [...] | Coverage: 0.02% |
---|
0x4364fb XOR %ECX,%ECX |
0x4364fd MOV -0x30(%RBP),%RSI |
0x436501 VPBROADCASTQ %RCX,%ZMM4 |
0x436507 VPORQ %ZMM1,%ZMM4,%ZMM4 |
0x43650d VPCMPLTUQ %ZMM0,%ZMM4,%K1 |
0x436514 VMOVUPD (%R15,%RCX,8),%ZMM4{%K1}{z} |
0x43651b VMOVAPD %ZMM4,%ZMM2{%K1} |
0x436521 VMULPD %ZMM3,%ZMM2,%ZMM3 |
0x436527 ADD %RCX,%RAX |
0x43652a MOV -0x58(%RBP),%RCX |
0x43652e VMOVUPD %ZMM3,(%RCX,%RAX,8){%K1} |
0x436535 LEA 0x1(%R12),%RAX |
0x43653a CMP -0x98(%RBP),%R12 |
0x436541 MOV %RAX,%R12 |
0x436544 JE 4366a0 |
0x43654a MOV -0x50(%RBP),%RAX |
0x43654e ADD %R12,%RAX |
0x436551 MOV %RAX,%RCX |
0x436554 OR %RDI,%RCX |
0x436557 SHR $0x20,%RCX |
0x43655b JE 436570 |
0x43655d CQTO |
0x43655f IDIV %RDI |
0x436562 MOV %RAX,%RCX |
0x436565 JMP 436577 |
0x436570 XOR %EDX,%EDX |
0x436572 DIVL -0x70(%RBP) |
0x436575 MOV %EAX,%ECX |
0x436577 MOV %RDX,%RAX |
0x43657a OR %RSI,%RAX |
0x43657d SHR $0x20,%RAX |
0x436581 JE 436590 |
0x436583 MOV %RDX,%RAX |
0x436586 CQTO |
0x436588 IDIV %RSI |
0x43658b JMP 436597 |
0x436590 MOV %EDX,%EAX |
0x436592 XOR %EDX,%EDX |
0x436594 DIVL -0x40(%RBP) |
0x436597 MOVSXD %EDX,%R11 |
0x43659a MOV -0xa0(%RBP),%RSI |
0x4365a1 IMUL %R11,%RSI |
0x4365a5 MOVSXD %EAX,%RDI |
0x4365a8 MOV -0xa8(%RBP),%RBX |
0x4365af IMUL %RDI,%RBX |
0x4365b3 ADD %RSI,%RBX |
0x4365b6 MOVSXD %ECX,%RSI |
0x4365b9 MOV -0xb0(%RBP),%RAX |
0x4365c0 IMUL %RSI,%RAX |
0x4365c4 ADD %RBX,%RAX |
0x4365c7 MOV -0x58(%RBP),%RDX |
0x4365cb LEA (%RDX,%RAX,8),%RCX |
0x4365cf CMP %RCX,-0x78(%RBP) |
0x4365d3 SETAE %R8B |
0x4365d7 LEA (%RAX,%R9,1),%RBX |
0x4365db LEA (%RDX,%RBX,8),%RBX |
0x4365df ADD $-0x8,%RBX |
0x4365e3 CMP %R15,%RBX |
0x4365e6 SETAE %R14B |
0x4365ea IMUL -0x90(%RBP),%RSI |
0x4365f2 ADD %RDI,%RSI |
0x4365f5 IMUL -0x88(%RBP),%RSI |
0x4365fd ADD %R11,%RSI |
0x436600 MOV -0x80(%RBP),%RDX |
0x436604 LEA (%RDX,%RSI,8),%RDX |
0x436608 CMP %RCX,%RDX |
0x43660b SETB %R13B |
0x43660f CMP %RDX,%RBX |
0x436612 SETB %R11B |
0x436616 TEST %R14B,%R8B |
0x436619 JNE 436670 |
0x43661b OR %R11B,%R13B |
0x43661e JE 436670 |
0x436620 VMOVSD (%RDX),%XMM3 |
0x436624 TEST %R10,%R10 |
0x436627 MOV -0x48(%RBP),%RDI |
0x43662b VBROADCASTSD %XMM3,%ZMM3 |
0x436631 JE 4364fb |
0x436637 XOR %EDX,%EDX |
0x436639 NOPL (%RAX) |
(654) 0x436640 VMULPD (%R15,%RDX,8),%ZMM3,%ZMM4 |
(654) 0x436647 VMOVUPD %ZMM4,(%RCX,%RDX,8) |
(654) 0x43664e ADD $0x8,%RDX |
(654) 0x436652 CMP %R10,%RDX |
(654) 0x436655 JL 436640 |
0x436657 MOV %R10,%RCX |
0x43665a CMP %R10,%R9 |
0x43665d MOV -0x30(%RBP),%RSI |
0x436661 JNE 436501 |
0x436667 JMP 436535 |
0x436670 XOR %EAX,%EAX |
0x436672 MOV -0x48(%RBP),%RDI |
0x436676 NOPW %CS:(%RAX,%RAX,1) |
(652) 0x436680 VMOVSD (%R15,%RAX,8),%XMM3 |
(652) 0x436686 VMULSD (%RDX),%XMM3,%XMM3 |
(652) 0x43668a VMOVSD %XMM3,(%RCX,%RAX,8) |
(652) 0x43668f INC %RAX |
(652) 0x436692 CMP %RAX,%R9 |
(652) 0x436695 JNE 436680 |
0x436697 MOV -0x30(%RBP),%RSI |
0x43669b JMP 436535 |
/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++) |
[...] |
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/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); |
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 / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 13.33 - 42.67 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.30 - 2.06 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.09 - 3.48 |
Bottlenecks | P0, |
Function | qmcplusplus::BsplineAllocator |
Source | BsplineAllocator.hpp:171-180,stl_vector.h:1126-1126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 60.00 - 192.00 |
CQA cycles if no scalar integer | 4.50 |
CQA cycles if FP arith vectorized | 60.00 - 192.00 |
CQA cycles if fully vectorized | 46.04 - 93.00 |
Front-end cycles | 55.25 |
DIV/SQRT cycles | 47.00 |
P0 cycles | 47.00 |
P1 cycles | 10.00 |
P2 cycles | 10.00 |
P3 cycles | 1.00 |
P4 cycles | 47.00 |
P5 cycles | 47.00 |
P6 cycles | 1.00 |
P7 cycles | 60.00 - 192.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 60.65 - 192.86 |
Stall cycles (UFS) | 35.85 - 168.06 |
Nb insns | 90.00 |
Nb uops | 221.00 |
Nb loads | 20.00 |
Nb stores | 1.00 |
Nb stack references | 14.00 |
FLOP/cycle | 0.13 - 0.04 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 8.00 |
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 | 1.42 - 4.53 |
Bytes prefetched | 0.00 |
Bytes loaded | 208.00 |
Bytes stored | 64.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 24.00 |
Vectorization ratio load | 12.50 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 20.00 |
Vector-efficiency ratio all | 33.00 |
Vector-efficiency ratio load | 21.88 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | 9.38 |
Vector-efficiency ratio other | 30.00 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 13.33 - 42.67 |
CQA speedup if FP arith vectorized | 1.00 |
CQA speedup if fully vectorized | 1.30 - 2.06 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.09 - 3.48 |
Bottlenecks | P0, |
Function | qmcplusplus::BsplineAllocator |
Source | BsplineAllocator.hpp:171-180,stl_vector.h:1126-1126 |
Source loop unroll info | NA |
Source loop unroll confidence level | NA |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 60.00 - 192.00 |
CQA cycles if no scalar integer | 4.50 |
CQA cycles if FP arith vectorized | 60.00 - 192.00 |
CQA cycles if fully vectorized | 46.04 - 93.00 |
Front-end cycles | 55.25 |
DIV/SQRT cycles | 47.00 |
P0 cycles | 47.00 |
P1 cycles | 10.00 |
P2 cycles | 10.00 |
P3 cycles | 1.00 |
P4 cycles | 47.00 |
P5 cycles | 47.00 |
P6 cycles | 1.00 |
P7 cycles | 60.00 - 192.00 |
Inter-iter dependencies cycles | NA |
FE+BE cycles (UFS) | 60.65 - 192.86 |
Stall cycles (UFS) | 35.85 - 168.06 |
Nb insns | 90.00 |
Nb uops | 221.00 |
Nb loads | 20.00 |
Nb stores | 1.00 |
Nb stack references | 14.00 |
FLOP/cycle | 0.13 - 0.04 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 8.00 |
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 | 1.42 - 4.53 |
Bytes prefetched | 0.00 |
Bytes loaded | 208.00 |
Bytes stored | 64.00 |
Stride 0 | NA |
Stride 1 | NA |
Stride n | NA |
Stride unknown | NA |
Stride indirect | NA |
Vectorization ratio all | 24.00 |
Vectorization ratio load | 12.50 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | NA |
Vectorization ratio div_sqrt | 0.00 |
Vectorization ratio other | 20.00 |
Vector-efficiency ratio all | 33.00 |
Vector-efficiency ratio load | 21.88 |
Vector-efficiency ratio store | 100.00 |
Vector-efficiency ratio mul | 100.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | NA |
Vector-efficiency ratio div_sqrt | 9.38 |
Vector-efficiency ratio other | 30.00 |
Path / |
Function | qmcplusplus::BsplineAllocator |
Source file and lines | BsplineAllocator.hpp:171-180 |
Module | exec |
nb instructions | 90 |
nb uops | 221 |
loop length | 359 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 5 |
nb stack references | 14 |
micro-operation queue | 55.25 cycles |
front end | 55.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 47.00 | 47.00 | 10.00 | 10.00 | 1.00 | 47.00 | 47.00 | 1.00 |
cycles | 47.00 | 47.00 | 10.00 | 10.00 | 1.00 | 47.00 | 47.00 | 1.00 |
Cycles executing div or sqrt instructions | 60.00-192.00 |
FE+BE cycles | 60.65-192.86 |
Stall cycles | 35.85-168.06 |
ROB full (events) | 37.10-170.31 |
Front-end | 55.25 |
Dispatch | 47.00 |
DIV/SQRT | 60.00-192.00 |
Overall L1 | 60.00-192.00 |
all | 10% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 66% |
load | 50% |
store | 100% |
mul | 100% |
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 | 50% |
all | 24% |
load | 12% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 20% |
all | 21% |
load | 10% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 22% |
all | 70% |
load | 56% |
store | 100% |
mul | 100% |
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 | 56% |
all | 33% |
load | 21% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 9% |
other | 30% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VPBROADCASTQ %RCX,%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPORQ %ZMM1,%ZMM4,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %ZMM0,%ZMM4,%K1 | |||||||||||
VMOVUPD (%R15,%RCX,8),%ZMM4{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVAPD %ZMM4,%ZMM2{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMULPD %ZMM3,%ZMM2,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD %ZMM3,(%RCX,%RAX,8){%K1} | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R12),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0x98(%RBP),%R12 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RAX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 4366a0 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x300> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R12,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x20,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
JE 436570 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %RDI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 436577 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1d7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
DIVL -0x70(%RBP) | 11 | 2.50 | 2.50 | 0.50 | 0.50 | 0 | 2.50 | 2.50 | 0 | 26 | 6 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x20,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
JE 436590 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %RSI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
JMP 436597 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1f7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %EDX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
DIVL -0x40(%RBP) | 11 | 2.50 | 2.50 | 0.50 | 0.50 | 0 | 2.50 | 2.50 | 0 | 26 | 6 |
MOVSXD %EDX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xa0(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R11,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVSXD %EAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xa8(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDI,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RSI,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %ECX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xb0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RSI,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RCX,-0x78(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
SETAE %R8B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%RAX,%R9,1),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RDX,%RBX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $-0x8,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R15,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETAE %R14B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IMUL -0x90(%RBP),%RSI | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL -0x88(%RBP),%RSI | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R11,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RSI,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETB %R13B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
CMP %RDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETB %R11B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST %R14B,%R8B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 436670 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
OR %R11B,%R13B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 436670 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%RDX),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R10,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM3,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
JE 4364fb <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x15b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R10,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 436501 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x161> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 436535 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x195> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 436535 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x195> | 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 | 221 |
loop length | 359 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 1 |
used ymm registers | 0 |
used zmm registers | 5 |
nb stack references | 14 |
micro-operation queue | 55.25 cycles |
front end | 55.25 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 47.00 | 47.00 | 10.00 | 10.00 | 1.00 | 47.00 | 47.00 | 1.00 |
cycles | 47.00 | 47.00 | 10.00 | 10.00 | 1.00 | 47.00 | 47.00 | 1.00 |
Cycles executing div or sqrt instructions | 60.00-192.00 |
FE+BE cycles | 60.65-192.86 |
Stall cycles | 35.85-168.06 |
ROB full (events) | 37.10-170.31 |
Front-end | 55.25 |
Dispatch | 47.00 |
DIV/SQRT | 60.00-192.00 |
Overall L1 | 60.00-192.00 |
all | 10% |
load | 0% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 11% |
all | 66% |
load | 50% |
store | 100% |
mul | 100% |
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 | 50% |
all | 24% |
load | 12% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 0% |
other | 20% |
all | 21% |
load | 10% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 22% |
all | 70% |
load | 56% |
store | 100% |
mul | 100% |
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 | 56% |
all | 33% |
load | 21% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | NA (no fma vectorizable/vectorized instructions) |
div/sqrt | 9% |
other | 30% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
XOR %ECX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VPBROADCASTQ %RCX,%ZMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
VPORQ %ZMM1,%ZMM4,%ZMM4 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VPCMPLTUQ %ZMM0,%ZMM4,%K1 | |||||||||||
VMOVUPD (%R15,%RCX,8),%ZMM4{%K1}{z} | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 5-6 | 0.50 |
VMOVAPD %ZMM4,%ZMM2{%K1} | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
VMULPD %ZMM3,%ZMM2,%ZMM3 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 4 | 0.50 |
ADD %RCX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVUPD %ZMM3,(%RCX,%RAX,8){%K1} | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
LEA 0x1(%R12),%RAX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP -0x98(%RBP),%R12 | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
MOV %RAX,%R12 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JE 4366a0 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x300> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV -0x50(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R12,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %RDI,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x20,%RCX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
JE 436570 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %RDI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
MOV %RAX,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
JMP 436577 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1d7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
DIVL -0x70(%RBP) | 11 | 2.50 | 2.50 | 0.50 | 0.50 | 0 | 2.50 | 2.50 | 0 | 26 | 6 |
MOV %EAX,%ECX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
OR %RSI,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SHR $0x20,%RAX | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
JE 436590 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1f0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
MOV %RDX,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CQTO | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IDIV %RSI | 57 | 14.25 | 14.25 | 0 | 0 | 0 | 14.25 | 14.25 | 0 | 42-95 | 24-90 |
JMP 436597 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x1f7> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
MOV %EDX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
DIVL -0x40(%RBP) | 11 | 2.50 | 2.50 | 0.50 | 0.50 | 0 | 2.50 | 2.50 | 0 | 26 | 6 |
MOVSXD %EDX,%R11 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xa0(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %R11,%RSI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVSXD %EAX,%RDI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xa8(%RBP),%RBX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RDI,%RBX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RSI,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOVSXD %ECX,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0xb0(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
IMUL %RSI,%RAX | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RBX,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x58(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RAX,8),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RCX,-0x78(%RBP) | 1 | 0.25 | 0.25 | 0.50 | 0.50 | 0 | 0.25 | 0.25 | 0 | 1 | 0.50 |
SETAE %R8B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
LEA (%RAX,%R9,1),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
LEA (%RDX,%RBX,8),%RBX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
ADD $-0x8,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
CMP %R15,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETAE %R14B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
IMUL -0x90(%RBP),%RSI | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %RDI,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
IMUL -0x88(%RBP),%RSI | 1 | 0 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 3 | 1 |
ADD %R11,%RSI | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x80(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RSI,8),%RDX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %RCX,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETB %R13B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
CMP %RDX,%RBX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
SETB %R11B | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 1 | 0.50 |
TEST %R14B,%R8B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 436670 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
OR %R11B,%R13B | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JE 436670 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x2d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
VMOVSD (%RDX),%XMM3 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
TEST %R10,%R10 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VBROADCASTSD %XMM3,%ZMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 3 | 1 |
JE 4364fb <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x15b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
XOR %EDX,%EDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
NOPL (%RAX) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV %R10,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
CMP %R10,%R9 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JNE 436501 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x161> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
JMP 436535 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x195> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |
XOR %EAX,%EAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x48(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
NOPW %CS:(%RAX,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.25 |
MOV -0x30(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
JMP 436535 <_ZN11qmcplusplus16BsplineAllocatorIdLm64ENS_10MallocatorIdLm64EEEE26setCoefficientsForOrbitalsEiiR5ArrayIdLj3EEP19multi_UBspline_3d_d.extracted+0x195> | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1-2 |