Loop Id: 489 | Module: libqmcwfs.so | Source: TwoBodyJastrowRef.h:344-347 | Coverage: 0.56% |
---|
Loop Id: 489 | Module: libqmcwfs.so | Source: TwoBodyJastrowRef.h:344-347 | Coverage: 0.56% |
---|
0x4c828 VMOVUPD (%R9,%RDX,1),%YMM9 [5] |
0x4c82e VMOVUPD (%RAX,%RDX,1),%YMM10 [3] |
0x4c833 VFMADD132PD (%RBX,%RDX,1),%YMM10,%YMM9 [2] |
0x4c839 VMOVUPD (%RCX,%RDX,1),%YMM5 [6] |
0x4c83e VMOVUPD (%RDI,%RDX,1),%YMM8 [4] |
0x4c843 VMOVUPD 0x20(%RAX,%RDX,1),%YMM13 [3] |
0x4c849 VMOVUPD 0x40(%RAX,%RDX,1),%YMM4 [3] |
0x4c84f VMOVUPD 0x60(%RAX,%RDX,1),%YMM6 [3] |
0x4c855 VFMADD231PD %YMM5,%YMM8,%YMM2 |
0x4c85a VFNMADD231PD %YMM5,%YMM8,%YMM9 |
0x4c85f VMOVUPD %YMM9,(%RAX,%RDX,1) [3] |
0x4c864 VMOVUPD 0x20(%RDX,%R9,1),%YMM12 [1] |
0x4c86b VFMADD132PD 0x20(%RBX,%RDX,1),%YMM13,%YMM12 [2] |
0x4c872 VMOVUPD 0x20(%RCX,%RDX,1),%YMM7 [6] |
0x4c878 VMOVUPD 0x20(%RDI,%RDX,1),%YMM11 [4] |
0x4c87e VFNMADD231PD %YMM7,%YMM11,%YMM12 |
0x4c883 VFMADD132PD %YMM7,%YMM2,%YMM11 |
0x4c888 VMOVUPD %YMM12,0x20(%RAX,%RDX,1) [3] |
0x4c88e VMOVUPD 0x40(%RDX,%R9,1),%YMM15 [1] |
0x4c895 VFMADD132PD 0x40(%RBX,%RDX,1),%YMM4,%YMM15 [2] |
0x4c89c VMOVUPD 0x40(%RCX,%RDX,1),%YMM14 [6] |
0x4c8a2 VMOVUPD 0x40(%RDI,%RDX,1),%YMM2 [4] |
0x4c8a8 VFNMADD231PD %YMM14,%YMM2,%YMM15 |
0x4c8ad VFMADD132PD %YMM14,%YMM11,%YMM2 |
0x4c8b2 VMOVUPD %YMM15,0x40(%RAX,%RDX,1) [3] |
0x4c8b8 VMOVUPD 0x60(%RDX,%R9,1),%YMM3 [1] |
0x4c8bf VFMADD132PD 0x60(%RBX,%RDX,1),%YMM6,%YMM3 [2] |
0x4c8c6 VMOVUPD 0x60(%RCX,%RDX,1),%YMM8 [6] |
0x4c8cc VMOVUPD 0x60(%RDI,%RDX,1),%YMM5 [4] |
0x4c8d2 VFMADD231PD %YMM8,%YMM5,%YMM2 |
0x4c8d7 VFNMADD231PD %YMM8,%YMM5,%YMM3 |
0x4c8dc VMOVUPD %YMM3,0x60(%RAX,%RDX,1) [3] |
0x4c8e2 SUB $-0x80,%RDX |
0x4c8e6 CMP %R15,%RDX |
0x4c8e9 JNE 4c828 |
/scratch_na/users/xoserete/qaas_runs/171-417-3180/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 344 - 347 |
-------------------------------------------------------------------------------- |
344: const valT newg = cur_du_pt[jat] * new_dX[jat]; |
345: const valT dg = newg - old_du_pt[jat] * old_dX[jat]; |
346: save_g[jat] -= dg; |
347: cur_g += newg; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►97.92+ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | libqmcwfs.so |
○ | main._omp_fn.1 | stl_vector.h:1121 | exec |
○ | gomp_thread_start | team.c:130 | libgomp.so.1.0.0 |
►2.08+ | qmcplusplus::WaveFunction::acc[...] | NewTimer.h:249 | libqmcwfs.so |
○ | main._omp_fn.1 | stl_vector.h:1121 | exec |
○ | GOMP_parallel | libgomp.h:985 | libgomp.so.1.0.0 |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.23 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.40 |
Bottlenecks | |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:344-347 |
Source loop unroll info | unrolled by 2 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 2 |
CQA cycles | 16.00 |
CQA cycles if no scalar integer | 16.00 |
CQA cycles if FP arith vectorized | 13.03 |
CQA cycles if fully vectorized | 8.00 |
Front-end cycles | 6.33 |
DIV/SQRT cycles | 6.00 |
P0 cycles | 6.00 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 2.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 0.00 |
P10 cycles | 6.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 16 |
FE+BE cycles (UFS) | 16.11 |
Stall cycles (UFS) | 9.17 |
Nb insns | 35.00 |
Nb uops | 34.00 |
Nb loads | 20.00 |
Nb stores | 4.00 |
Nb stack references | 0.00 |
FLOP/cycle | 6.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 48.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 48.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 640.00 |
Bytes stored | 128.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 50.00 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 50.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.23 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 2.40 |
Bottlenecks | |
Function | miniqmcreference::TwoBodyJastrowRef |
Source | TwoBodyJastrowRef.h:344-347 |
Source loop unroll info | unrolled by 2 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 2 |
CQA cycles | 16.00 |
CQA cycles if no scalar integer | 16.00 |
CQA cycles if FP arith vectorized | 13.03 |
CQA cycles if fully vectorized | 8.00 |
Front-end cycles | 6.33 |
DIV/SQRT cycles | 6.00 |
P0 cycles | 6.00 |
P1 cycles | 6.67 |
P2 cycles | 6.67 |
P3 cycles | 2.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 2.00 |
P7 cycles | 2.00 |
P8 cycles | 2.00 |
P9 cycles | 0.00 |
P10 cycles | 6.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 16 |
FE+BE cycles (UFS) | 16.11 |
Stall cycles (UFS) | 9.17 |
Nb insns | 35.00 |
Nb uops | 34.00 |
Nb loads | 20.00 |
Nb stores | 4.00 |
Nb stack references | 0.00 |
FLOP/cycle | 6.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 48.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 48.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 640.00 |
Bytes stored | 128.00 |
Stride 0 | 0.00 |
Stride 1 | 4.00 |
Stride n | 2.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | 100.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 50.00 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | 50.00 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 50.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:344-347 |
Module | libqmcwfs.so |
nb instructions | 35 |
nb uops | 34 |
loop length | 199 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 14 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 6.33 cycles |
front end | 6.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.00 | 6.00 | 6.67 | 6.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.67 |
cycles | 6.00 | 6.00 | 6.67 | 6.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 16.00 |
FE+BE cycles | 16.11 |
Stall cycles | 9.17 |
LB full (events) | 11.33 |
LM full (events) | 0.16 |
Front-end | 6.33 |
Dispatch | 6.67 |
Data deps. | 16.00 |
Overall L1 | 16.00 |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 50% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%R9,%RDX,1),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD (%RAX,%RDX,1),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD (%RBX,%RDX,1),%YMM10,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD (%RCX,%RDX,1),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD (%RDI,%RDX,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%RAX,%RDX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%RAX,%RDX,1),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%RAX,%RDX,1),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD231PD %YMM5,%YMM8,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231PD %YMM5,%YMM8,%YMM9 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM9,(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPD 0x20(%RDX,%R9,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD 0x20(%RBX,%RDX,1),%YMM13,%YMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD 0x20(%RCX,%RDX,1),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%RDI,%RDX,1),%YMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFNMADD231PD %YMM7,%YMM11,%YMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD %YMM7,%YMM2,%YMM11 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM12,0x20(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPD 0x40(%RDX,%R9,1),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD 0x40(%RBX,%RDX,1),%YMM4,%YMM15 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD 0x40(%RCX,%RDX,1),%YMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%RDI,%RDX,1),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFNMADD231PD %YMM14,%YMM2,%YMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD %YMM14,%YMM11,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM15,0x40(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPD 0x60(%RDX,%R9,1),%YMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD 0x60(%RBX,%RDX,1),%YMM6,%YMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD 0x60(%RCX,%RDX,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%RDI,%RDX,1),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD231PD %YMM8,%YMM5,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231PD %YMM8,%YMM5,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM3,0x60(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
SUB $-0x80,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R15,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 4c828 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x588> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | miniqmcreference::TwoBodyJastrowRef |
Source file and lines | TwoBodyJastrowRef.h:344-347 |
Module | libqmcwfs.so |
nb instructions | 35 |
nb uops | 34 |
loop length | 199 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 14 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 6.33 cycles |
front end | 6.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 6.00 | 6.00 | 6.67 | 6.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.67 |
cycles | 6.00 | 6.00 | 6.67 | 6.67 | 2.00 | 0.00 | 1.00 | 2.00 | 2.00 | 2.00 | 0.00 | 6.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 16.00 |
FE+BE cycles | 16.11 |
Stall cycles | 9.17 |
LB full (events) | 11.33 |
LM full (events) | 0.16 |
Front-end | 6.33 |
Dispatch | 6.67 |
Data deps. | 16.00 |
Overall L1 | 16.00 |
all | 100% |
load | 100% |
store | 100% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 50% |
load | 50% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%R9,%RDX,1),%YMM9 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD (%RAX,%RDX,1),%YMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD (%RBX,%RDX,1),%YMM10,%YMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD (%RCX,%RDX,1),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD (%RDI,%RDX,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%RAX,%RDX,1),%YMM13 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%RAX,%RDX,1),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%RAX,%RDX,1),%YMM6 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD231PD %YMM5,%YMM8,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231PD %YMM5,%YMM8,%YMM9 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM9,(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPD 0x20(%RDX,%R9,1),%YMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD 0x20(%RBX,%RDX,1),%YMM13,%YMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD 0x20(%RCX,%RDX,1),%YMM7 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x20(%RDI,%RDX,1),%YMM11 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFNMADD231PD %YMM7,%YMM11,%YMM12 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD %YMM7,%YMM2,%YMM11 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM12,0x20(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPD 0x40(%RDX,%R9,1),%YMM15 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD 0x40(%RBX,%RDX,1),%YMM4,%YMM15 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD 0x40(%RCX,%RDX,1),%YMM14 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x40(%RDI,%RDX,1),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFNMADD231PD %YMM14,%YMM2,%YMM15 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMADD132PD %YMM14,%YMM11,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM15,0x40(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVUPD 0x60(%RDX,%R9,1),%YMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD132PD 0x60(%RBX,%RDX,1),%YMM6,%YMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD 0x60(%RCX,%RDX,1),%YMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD 0x60(%RDI,%RDX,1),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD231PD %YMM8,%YMM5,%YMM2 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFNMADD231PD %YMM8,%YMM5,%YMM3 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVUPD %YMM3,0x60(%RAX,%RDX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
SUB $-0x80,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R15,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 4c828 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x588> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |