Loop Id: 78 | Module: exec | Source: NonLocalPP.hpp:131-132 [...] | Coverage: 0.01% |
---|
Loop Id: 78 | Module: exec | Source: NonLocalPP.hpp:131-132 [...] | Coverage: 0.01% |
---|
0x40d940 MOV (%R15),%RSI [10] |
0x40d943 VMOVDDUP (%RSI,%R14,8),%XMM1 [2] |
0x40d949 MOV (%RBX),%RSI [7] |
0x40d94c MOVSXD -0x10(%RBX),%RDI [7] |
0x40d950 VMOVSD (%R9,%RAX,1),%XMM2 [5] |
0x40d956 LEA (%R14,%RDI,2),%R8 |
0x40d95a VFMADD213SD (%RSI,%R8,8),%XMM1,%XMM2 [1] |
0x40d960 VPBROADCASTQ %RSI,%XMM3 |
0x40d966 VMOVQ %RDI,%XMM4 |
0x40d96b VPSLLDQ $0x8,%XMM4,%XMM4 |
0x40d970 VPADDQ %XMM4,%XMM0,%XMM4 |
0x40d974 VPSLLQ $0x3,%XMM4,%XMM4 |
0x40d979 VPADDQ %XMM4,%XMM3,%XMM3 |
0x40d97d VMOVQ %XMM3,%RSI |
0x40d982 VMOVSD (%RSI),%XMM4 [9] |
0x40d986 VPEXTRQ $0x1,%XMM3,%RSI |
0x40d98c VMOVHPD (%RSI),%XMM4,%XMM3 [12] |
0x40d990 MOV 0x40(%R10),%RSI [6] |
0x40d994 VADDSD 0x10(%RSI,%RCX,8),%XMM2,%XMM2 [4] |
0x40d99a VFMADD231PD -0x10(%R9,%RAX,1),%XMM1,%XMM3 [5] |
0x40d9a1 VADDPD (%RSI,%RCX,8),%XMM3,%XMM1 [4] |
0x40d9a6 MOV -0x60(%RBP),%RSI [8] |
0x40d9aa VMOVUPD %XMM1,-0x10(%RSI,%RAX,1) [11] |
0x40d9b0 VMOVSD %XMM2,(%RSI,%RAX,1) [11] |
0x40d9b5 MOV 0x13f0(%R12),%RSI [3] |
0x40d9bd SUB 0x13e8(%R12),%RSI [3] |
0x40d9c5 INC %RDX |
0x40d9c8 SHR $0x3,%RSI |
0x40d9cc IMUL $-0x55555555,%ESI,%ESI |
0x40d9d2 MOVSXD %ESI,%RSI |
0x40d9d5 ADD $0x18,%RAX |
0x40d9d9 CMP %RSI,%RDX |
0x40d9dc JL 40d940 |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Drivers/NonLocalPP.hpp: 131 - 132 |
-------------------------------------------------------------------------------- |
131: for (int k = 0; k < size(); k++) |
132: virtualPos[k] = dist[iat] * rOnSphere[k] + displ[iat] + els.R[jel]; |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/TinyVector.h: 145 - 145 |
-------------------------------------------------------------------------------- |
145: X[i] = base[i * offset]; |
/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 919 - 1046 |
-------------------------------------------------------------------------------- |
919: { return size_type(this->_M_impl._M_finish - this->_M_impl._M_start); } |
[...] |
1046: return *(this->_M_impl._M_start + __n); |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/VectorSoAContainer.h: 231 - 231 |
-------------------------------------------------------------------------------- |
231: inline const AoSElement_t operator[](size_t i) const { return AoSElement_t(myData + i, nGhosts); } |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Numerics/OhmmsPETE/OhmmsVector.h: 229 - 229 |
-------------------------------------------------------------------------------- |
229: return X[i]; |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 43 - 63 |
-------------------------------------------------------------------------------- |
43: return (a + b); |
[...] |
63: return (a * b); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.09 |
CQA speedup if FP arith vectorized | 1.92 |
CQA speedup if fully vectorized | 6.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.19 |
Bottlenecks | micro-operation queue, |
Function | _ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE |
Source | NonLocalPP.hpp:131-132,TinyVector.h:145-145,stl_vector.h:919-919,stl_vector.h:1046-1046,VectorSoAContainer.h:231-231,OhmmsVector.h:229-229,OperatorTags.h:43-43,OperatorTags.h:63-63 |
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 | 6.17 |
CQA cycles if no scalar integer | 5.67 |
CQA cycles if FP arith vectorized | 3.21 |
CQA cycles if fully vectorized | 0.93 |
Front-end cycles | 6.17 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.17 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 1.00 |
P4 cycles | 4.83 |
P5 cycles | 2.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 2.00 |
P10 cycles | 5.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 6.91 - 7.11 |
Stall cycles (UFS) | 0.29 - 0.44 |
Nb insns | 33.00 |
Nb uops | 33.00 |
Nb loads | 15.00 |
Nb stores | 2.00 |
Nb stack references | 1.00 |
FLOP/cycle | 1.46 |
Nb FLOP add-sub | 3.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 3.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 25.30 |
Bytes prefetched | 0.00 |
Bytes loaded | 132.00 |
Bytes stored | 24.00 |
Stride 0 | 5.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 1.00 |
Stride indirect | 3.00 |
Vectorization ratio all | 38.89 |
Vectorization ratio load | 25.00 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 75.00 |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 33.33 |
Vector-efficiency ratio all | 17.36 |
Vector-efficiency ratio load | 15.63 |
Vector-efficiency ratio store | 18.75 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 21.88 |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 16.67 |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.09 |
CQA speedup if FP arith vectorized | 1.92 |
CQA speedup if fully vectorized | 6.60 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.19 |
Bottlenecks | micro-operation queue, |
Function | _ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE |
Source | NonLocalPP.hpp:131-132,TinyVector.h:145-145,stl_vector.h:919-919,stl_vector.h:1046-1046,VectorSoAContainer.h:231-231,OhmmsVector.h:229-229,OperatorTags.h:43-43,OperatorTags.h:63-63 |
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 | 6.17 |
CQA cycles if no scalar integer | 5.67 |
CQA cycles if FP arith vectorized | 3.21 |
CQA cycles if fully vectorized | 0.93 |
Front-end cycles | 6.17 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.17 |
P1 cycles | 5.00 |
P2 cycles | 5.00 |
P3 cycles | 1.00 |
P4 cycles | 4.83 |
P5 cycles | 2.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 2.00 |
P10 cycles | 5.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 6.91 - 7.11 |
Stall cycles (UFS) | 0.29 - 0.44 |
Nb insns | 33.00 |
Nb uops | 33.00 |
Nb loads | 15.00 |
Nb stores | 2.00 |
Nb stack references | 1.00 |
FLOP/cycle | 1.46 |
Nb FLOP add-sub | 3.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 3.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 25.30 |
Bytes prefetched | 0.00 |
Bytes loaded | 132.00 |
Bytes stored | 24.00 |
Stride 0 | 5.00 |
Stride 1 | 0.00 |
Stride n | 2.00 |
Stride unknown | 1.00 |
Stride indirect | 3.00 |
Vectorization ratio all | 38.89 |
Vectorization ratio load | 25.00 |
Vectorization ratio store | 50.00 |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 75.00 |
Vectorization ratio fma | 50.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | 33.33 |
Vector-efficiency ratio all | 17.36 |
Vector-efficiency ratio load | 15.63 |
Vector-efficiency ratio store | 18.75 |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 21.88 |
Vector-efficiency ratio fma | 18.75 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | 16.67 |
Path / |
Function | _ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE |
Source file and lines | NonLocalPP.hpp:131-132 |
Module | exec |
nb instructions | 33 |
nb uops | 33 |
loop length | 162 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 6.17 cycles |
front end | 6.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.17 | 5.00 | 5.00 | 1.00 | 4.83 | 2.00 | 1.00 | 1.00 | 1.00 | 2.00 | 5.00 |
cycles | 5.00 | 5.17 | 5.00 | 5.00 | 1.00 | 4.83 | 2.00 | 1.00 | 1.00 | 1.00 | 2.00 | 5.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 6.91-7.11 |
Stall cycles | 0.29-0.44 |
LM full (events) | 0.74-1.15 |
Front-end | 6.17 |
Dispatch | 5.17 |
Data deps. | 1.00 |
Overall L1 | 6.17 |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 30% |
load | 25% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 38% |
load | 25% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
all | 18% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
all | 16% |
load | 15% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 17% |
load | 15% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 21% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R15),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVDDUP (%RSI,%R14,8),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RBX),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD -0x10(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R9,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%R14,%RDI,2),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VFMADD213SD (%RSI,%R8,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VPBROADCASTQ %RSI,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVQ %RDI,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPSLLDQ $0x8,%XMM4,%XMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPADDQ %XMM4,%XMM0,%XMM4 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPSLLQ $0x3,%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 0.50 |
VPADDQ %XMM4,%XMM3,%XMM3 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM3,%RSI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VMOVSD (%RSI),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VPEXTRQ $0x1,%XMM3,%RSI | 2 | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VMOVHPD (%RSI),%XMM4,%XMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4-12 | 1 |
MOV 0x40(%R10),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VADDSD 0x10(%RSI,%RCX,8),%XMM2,%XMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VFMADD231PD -0x10(%R9,%RAX,1),%XMM1,%XMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VADDPD (%RSI,%RCX,8),%XMM3,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
MOV -0x60(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVUPD %XMM1,-0x10(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVSD %XMM2,(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x13f0(%R12),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SUB 0x13e8(%R12),%RSI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SHR $0x3,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
IMUL $-0x55555555,%ESI,%ESI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVSXD %ESI,%RSI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD $0x18,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 40d940 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x700> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | _ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE |
Source file and lines | NonLocalPP.hpp:131-132 |
Module | exec |
nb instructions | 33 |
nb uops | 33 |
loop length | 162 |
used x86 registers | 13 |
used mmx registers | 0 |
used xmm registers | 5 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 1 |
micro-operation queue | 6.17 cycles |
front end | 6.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.17 | 5.00 | 5.00 | 1.00 | 4.83 | 2.00 | 1.00 | 1.00 | 1.00 | 2.00 | 5.00 |
cycles | 5.00 | 5.17 | 5.00 | 5.00 | 1.00 | 4.83 | 2.00 | 1.00 | 1.00 | 1.00 | 2.00 | 5.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 6.91-7.11 |
Stall cycles | 0.29-0.44 |
LM full (events) | 0.74-1.15 |
Front-end | 6.17 |
Dispatch | 5.17 |
Data deps. | 1.00 |
Overall L1 | 6.17 |
all | 50% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 33% |
all | 30% |
load | 25% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 50% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 38% |
load | 25% |
store | 50% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 75% |
fma | 50% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 33% |
all | 18% |
load | NA (no load vectorizable/vectorized instructions) |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 25% |
fma | NA (no fma vectorizable/vectorized instructions) |
other | 16% |
all | 16% |
load | 15% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 18% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 17% |
load | 15% |
store | 18% |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 21% |
fma | 18% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | 16% |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
MOV (%R15),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVDDUP (%RSI,%R14,8),%XMM1 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOV (%RBX),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
MOVSXD -0x10(%RBX),%RDI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD (%R9,%RAX,1),%XMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
LEA (%R14,%RDI,2),%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.17 |
VFMADD213SD (%RSI,%R8,8),%XMM1,%XMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VPBROADCASTQ %RSI,%XMM3 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
VMOVQ %RDI,%XMM4 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VPSLLDQ $0x8,%XMM4,%XMM4 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.50 |
VPADDQ %XMM4,%XMM0,%XMM4 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VPSLLQ $0x3,%XMM4,%XMM4 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2-4 | 0.50 |
VPADDQ %XMM4,%XMM3,%XMM3 | 1 | 0.33 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.33 |
VMOVQ %XMM3,%RSI | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VMOVSD (%RSI),%XMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VPEXTRQ $0x1,%XMM3,%RSI | 2 | 1 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 1 |
VMOVHPD (%RSI),%XMM4,%XMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4-12 | 1 |
MOV 0x40(%R10),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VADDSD 0x10(%RSI,%RCX,8),%XMM2,%XMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VFMADD231PD -0x10(%R9,%RAX,1),%XMM1,%XMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VADDPD (%RSI,%RCX,8),%XMM3,%XMM1 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
MOV -0x60(%RBP),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVUPD %XMM1,-0x10(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VMOVSD %XMM2,(%RSI,%RAX,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 1 | 0.50 |
MOV 0x13f0(%R12),%RSI | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
SUB 0x13e8(%R12),%RSI | 1 | 0.20 | 0.20 | 0.33 | 0.33 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.33 | 1 | 0.33 |
INC %RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
SHR $0x3,%RSI | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0-2 | 0.50 |
IMUL $-0x55555555,%ESI,%ESI | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 1 |
MOVSXD %ESI,%RSI | 1 | 0 | 0.33 | 0 | 0 | 0 | 0.33 | 0 | 0 | 0 | 0 | 0.33 | 0 | 1 | 0.33 |
ADD $0x18,%RAX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%RDX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JL 40d940 <_ZN11qmcplusplus10NonLocalPPIdE8evaluateERKNS_11ParticleSetERNS_12WaveFunctionE+0x700> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |