Loop Id: 37 | Module: exec | Source: OperatorTags.h:53-63 [...] | Coverage: 0.37% |
---|
Loop Id: 37 | Module: exec | Source: OperatorTags.h:53-63 [...] | Coverage: 0.37% |
---|
0x40ba80 MOVSXD 0x8(%R13),%RDX [11] |
0x40ba84 MOV 0x18(%R13),%R9 [11] |
0x40ba88 ADD $0x30,%R15 |
0x40ba8c MOV -0x160(%RBP),%R11 [12] |
0x40ba93 MOV -0x150(%RBP),%ESI [12] |
0x40ba99 LEA (%RDX,%RBX,1),%RDI |
0x40ba9d VMOVSD (%R9,%R14,1),%XMM2 [3] |
0x40baa3 VMOVSD (%R11,%RBX,8),%XMM13 [4] |
0x40baa9 ADD %RDI,%RDX |
0x40baac VMOVSD (%R9,%RDX,8),%XMM14 [13] |
0x40bab2 VMOVHPD (%R9,%RDI,8),%XMM2,%XMM11 [7] |
0x40bab8 MOV -0x168(%RBP),%RDX [12] |
0x40babf VMOVDDUP %XMM13,%XMM4 |
0x40bac4 MOV -0x148(%RBP),%RDI [12] |
0x40bacb VFMSUB132SD 0x10(%RCX),%XMM14,%XMM13 [14] |
0x40bad1 VFMSUB231PD -0x18(%R15),%XMM4,%XMM11 [5] |
0x40bad7 VMOVSD %XMM13,-0x100(%RBP) [12] |
0x40badf VMOVAPD %XMM11,-0x110(%RBP) [12] |
0x40bae7 CALL 404500 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE@plt> |
0x40baec MOV 0x10(%R12),%RCX [6] |
0x40baf1 MOV (%RCX),%RSI [8] |
0x40baf4 MOV 0x20(%RSI),%RDI [2] |
0x40baf8 CALL 4044d0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> |
0x40bafd MOV -0x150(%RBP),%EDX [12] |
0x40bb03 MOV -0x148(%RBP),%RSI [12] |
0x40bb0a MOV -0x158(%RBP),%RDI [12] |
0x40bb11 CALL 4043c0 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi@plt> |
0x40bb16 MOV 0x10(%R12),%R8 [6] |
0x40bb1b MOV (%R8),%R10 [8] |
0x40bb1e MOV 0x20(%R10),%RDI [2] |
0x40bb22 CALL 4044a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> |
0x40bb27 MOV -0x150(%RBP),%ESI [12] |
0x40bb2d MOV -0x148(%RBP),%RDI [12] |
0x40bb34 CALL 404390 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi@plt> |
0x40bb39 MOV -0x160(%RBP),%RAX [12] |
0x40bb40 VMOVSD (%RAX,%RBX,8),%XMM15 [4] |
0x40bb45 MOVSXD 0x8(%R13),%RAX [11] |
0x40bb49 MOV 0x18(%R13),%R10 [11] |
0x40bb4d VMOVDDUP %XMM15,%XMM3 |
0x40bb52 MOV -0x168(%RBP),%RDX [12] |
0x40bb59 MOV -0x150(%RBP),%ESI [12] |
0x40bb5f LEA (%RAX,%RBX,1),%R11 |
0x40bb63 VMOVSD (%R10,%R14,1),%XMM0 [3] |
0x40bb69 MOV -0x148(%RBP),%RDI [12] |
0x40bb70 ADD %R11,%RAX |
0x40bb73 VMOVSD (%R10,%RAX,8),%XMM12 [1] |
0x40bb79 VMOVHPD (%R10,%R11,8),%XMM0,%XMM6 [10] |
0x40bb7f VFMSUB132PD (%R15),%XMM6,%XMM3 [9] |
0x40bb84 VFMSUB132SD 0x10(%R15),%XMM12,%XMM15 [9] |
0x40bb8a VMOVAPD %XMM3,-0x110(%RBP) [12] |
0x40bb92 VMOVSD %XMM15,-0x100(%RBP) [12] |
0x40bb9a CALL 404500 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE@plt> |
0x40bb9f MOV 0x10(%R12),%R9 [6] |
0x40bba4 MOV (%R9),%RDI [8] |
0x40bba7 MOV 0x20(%RDI),%RDI [2] |
0x40bbab CALL 4044d0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> |
0x40bbb0 MOV -0x150(%RBP),%EDX [12] |
0x40bbb6 MOV -0x148(%RBP),%RSI [12] |
0x40bbbd MOV -0x158(%RBP),%RDI [12] |
0x40bbc4 CALL 4043c0 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi@plt> |
0x40bbc9 MOV 0x10(%R12),%RSI [6] |
0x40bbce MOV (%RSI),%RDX [8] |
0x40bbd1 MOV 0x20(%RDX),%RDI [2] |
0x40bbd5 CALL 4044a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> |
0x40bbda MOV -0x150(%RBP),%ESI [12] |
0x40bbe0 MOV -0x148(%RBP),%RDI [12] |
0x40bbe7 CALL 404390 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi@plt> |
0x40bbec MOV -0x178(%RBP),%R8 [12] |
0x40bbf3 LEA 0x18(%R15),%RCX |
0x40bbf7 CMP %R8,%RCX |
0x40bbfa JNE 40ba80 |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 146 - 146 |
-------------------------------------------------------------------------------- |
146: X[i] = base[i * offset]; |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 53 - 63 |
-------------------------------------------------------------------------------- |
53: return (a - b); |
[...] |
63: return (a * b); |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVectorOps.h: 85 - 85 |
-------------------------------------------------------------------------------- |
85: ret[d] = op(lhs[d], rhs[d]); |
/home/kcamus/qaas_runs/169-390-4082/intel/miniqmc/build/miniqmc/src/Drivers/miniqmc.cpp: 478 - 488 |
-------------------------------------------------------------------------------- |
478: for (int k = 0; k < nknots; k++) |
479: { |
480: PosType deltar(dist[iat] * rOnSphere[k] - displ[iat]); |
481: |
482: els.makeMove(jel, deltar); |
483: |
484: Timers[Timer_Value].get().start(); |
485: wavefunction.ratio(els, jel); |
486: Timers[Timer_Value].get().stop(); |
487: |
488: els.rejectMove(jel); |
/usr/include/c++/13.1.1/bits/stl_vector.h: 1126 - 1126 |
-------------------------------------------------------------------------------- |
1126: return *(this->_M_impl._M_start + __n); |
/usr/include/c++/13.1.1/bits/refwrap.h: 347 - 347 |
-------------------------------------------------------------------------------- |
347: { return *_M_data; } |
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 | 2.76 |
CQA speedup if FP arith vectorized | 2.87 |
CQA speedup if fully vectorized | 7.67 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.15 |
Bottlenecks | P2, P3, |
Function | main._omp_fn.1 |
Source | TinyVector.h:146-146,OperatorTags.h:53-63,TinyVectorOps.h:85-85,miniqmc.cpp:478-488,stl_vector.h:1126-1126,refwrap.h:347-347 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 23.50 |
CQA cycles if no scalar integer | 8.50 |
CQA cycles if FP arith vectorized | 8.19 |
CQA cycles if fully vectorized | 3.06 |
Front-end cycles | 20.50 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.00 |
P1 cycles | 23.50 |
P2 cycles | 23.50 |
P3 cycles | 14.00 |
P4 cycles | 5.00 |
P5 cycles | 10.00 |
P6 cycles | 14.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 23.71 |
Stall cycles (UFS) | 5.49 |
Nb insns | 71.00 |
Nb uops | 80.00 |
Nb loads | 47.00 |
Nb stores | 4.00 |
Nb stack references | 8.00 |
FLOP/cycle | 0.51 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 6.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 17.36 |
Bytes prefetched | 0.00 |
Bytes loaded | 360.00 |
Bytes stored | 48.00 |
Stride 0 | 3.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 8.00 |
Stride indirect | 6.00 |
Vectorization ratio all | 22.22 |
Vectorization ratio load | 16.67 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 15.28 |
Vector-efficiency ratio load | 14.58 |
Vector-efficiency ratio store | 18.75 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 2.76 |
CQA speedup if FP arith vectorized | 2.87 |
CQA speedup if fully vectorized | 7.67 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.15 |
Bottlenecks | P2, P3, |
Function | main._omp_fn.1 |
Source | TinyVector.h:146-146,OperatorTags.h:53-63,TinyVectorOps.h:85-85,miniqmc.cpp:478-488,stl_vector.h:1126-1126,refwrap.h:347-347 |
Source loop unroll info | not unrolled or unrolled with no peel/tail loop |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | NA |
Unroll factor | NA |
CQA cycles | 23.50 |
CQA cycles if no scalar integer | 8.50 |
CQA cycles if FP arith vectorized | 8.19 |
CQA cycles if fully vectorized | 3.06 |
Front-end cycles | 20.50 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.00 |
P1 cycles | 23.50 |
P2 cycles | 23.50 |
P3 cycles | 14.00 |
P4 cycles | 5.00 |
P5 cycles | 10.00 |
P6 cycles | 14.00 |
P7 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 23.71 |
Stall cycles (UFS) | 5.49 |
Nb insns | 71.00 |
Nb uops | 80.00 |
Nb loads | 47.00 |
Nb stores | 4.00 |
Nb stack references | 8.00 |
FLOP/cycle | 0.51 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 6.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 17.36 |
Bytes prefetched | 0.00 |
Bytes loaded | 360.00 |
Bytes stored | 48.00 |
Stride 0 | 3.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 8.00 |
Stride indirect | 6.00 |
Vectorization ratio all | 22.22 |
Vectorization ratio load | 16.67 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 0.00 |
Vector-efficiency ratio all | 15.28 |
Vector-efficiency ratio load | 14.58 |
Vector-efficiency ratio store | 18.75 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 12.50 |
Path / |
Function | main._omp_fn.1 |
Source file and lines | OperatorTags.h:53-63 |
Module | exec |
nb instructions | 71 |
nb uops | 80 |
loop length | 384 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 10 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 20.50 cycles |
front end | 20.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.00 | 23.50 | 23.50 | 14.00 | 5.00 | 10.00 | 14.00 |
cycles | 5.00 | 5.00 | 23.50 | 23.50 | 14.00 | 5.00 | 10.00 | 14.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 23.71 |
Stall cycles | 5.49 |
LM full (events) | 11.48 |
Front-end | 20.50 |
Dispatch | 23.50 |
Data deps. | 1.00 |
Overall L1 | 23.50 |
all | 22% |
load | 16% |
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 | 0% |
all | 15% |
load | 14% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD 0x8(%R13),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%R13),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x30,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x160(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RBX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R9,%R14,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R11,%RBX,8),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R9,%RDX,8),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%R9,%RDI,8),%XMM2,%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
MOV -0x168(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVDDUP %XMM13,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMSUB132SD 0x10(%RCX),%XMM14,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB231PD -0x18(%R15),%XMM4,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,-0x100(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVAPD %XMM11,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 404500 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RSI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044d0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x158(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4043c0 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%R10),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 404390 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x160(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RAX,%RBX,8),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD 0x8(%R13),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%R13),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVDDUP %XMM15,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV -0x168(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RBX,1),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R10,%R14,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R10,%RAX,8),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%R10,%R11,8),%XMM0,%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VFMSUB132PD (%R15),%XMM6,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD 0x10(%R15),%XMM12,%XMM15 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM3,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM15,-0x100(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 404500 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R9),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044d0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x158(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4043c0 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RDX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 404390 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x178(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x18(%R15),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 40ba80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |
Function | main._omp_fn.1 |
Source file and lines | OperatorTags.h:53-63 |
Module | exec |
nb instructions | 71 |
nb uops | 80 |
loop length | 384 |
used x86 registers | 15 |
used mmx registers | 0 |
used xmm registers | 10 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 8 |
micro-operation queue | 20.50 cycles |
front end | 20.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | |
---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.00 | 23.50 | 23.50 | 14.00 | 5.00 | 10.00 | 14.00 |
cycles | 5.00 | 5.00 | 23.50 | 23.50 | 14.00 | 5.00 | 10.00 | 14.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 23.71 |
Stall cycles | 5.49 |
LM full (events) | 11.48 |
Front-end | 20.50 |
Dispatch | 23.50 |
Data deps. | 1.00 |
Overall L1 | 23.50 |
all | 22% |
load | 16% |
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 | 0% |
all | 15% |
load | 14% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 12% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|
MOVSXD 0x8(%R13),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%R13),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD $0x30,%R15 | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
MOV -0x160(%RBP),%R11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RDX,%RBX,1),%RDI | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R9,%R14,1),%XMM2 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%R11,%RBX,8),%XMM13 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %RDI,%RDX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R9,%RDX,8),%XMM14 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%R9,%RDI,8),%XMM2,%XMM11 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
MOV -0x168(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVDDUP %XMM13,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VFMSUB132SD 0x10(%RCX),%XMM14,%XMM13 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB231PD -0x18(%R15),%XMM4,%XMM11 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVSD %XMM13,-0x100(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVAPD %XMM11,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 404500 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%RCX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RCX),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RSI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044d0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x158(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4043c0 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R8),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%R10),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 404390 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x160(%RBP),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVSD (%RAX,%RBX,8),%XMM15 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOVSXD 0x8(%R13),%RAX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x18(%R13),%R10 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVDDUP %XMM15,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 1 |
MOV -0x168(%RBP),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA (%RAX,%RBX,1),%R11 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
VMOVSD (%R10,%R14,1),%XMM0 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
ADD %R11,%RAX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
VMOVSD (%R10,%RAX,8),%XMM12 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
VMOVHPD (%R10,%R11,8),%XMM0,%XMM6 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 1 | 0 | 0 | 4 | 1 |
VFMSUB132PD (%R15),%XMM6,%XMM3 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VFMSUB132SD 0x10(%R15),%XMM12,%XMM15 | 1 | 0.50 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMOVAPD %XMM3,-0x110(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
VMOVSD %XMM15,-0x100(%RBP) | 1 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 0 | 0.33 | 3 | 1 |
CALL 404500 <_ZN11qmcplusplus11ParticleSet8makeMoveEiRKNS_10TinyVectorIdLj3EEE@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%R9 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%R9),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RDI),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044d0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE5startEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%EDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x158(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4043c0 <_ZN11qmcplusplus12WaveFunction5ratioERNS_11ParticleSetEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV 0x10(%R12),%RSI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV (%RSI),%RDX | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV 0x20(%RDX),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 4044a0 <_ZN11qmcplusplus9TimerTypeINS_8CPUClockEE4stopEv@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x150(%RBP),%ESI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
MOV -0x148(%RBP),%RDI | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
CALL 404390 <_ZN11qmcplusplus11ParticleSet10rejectMoveEi@plt> | 2 | 0 | 0 | 0.33 | 0.33 | 1 | 0 | 1 | 0.33 | 0 | 1 |
MOV -0x178(%RBP),%R8 | 1 | 0 | 0 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 4-5 | 0.50 |
LEA 0x18(%R15),%RCX | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 1 | 0.50 |
CMP %R8,%RCX | 1 | 0.25 | 0.25 | 0 | 0 | 0 | 0.25 | 0.25 | 0 | 1 | 0.25 |
JNE 40ba80 | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50-1 |