Loop Id: 275 | Module: exec | Source: OneBodyJastrowRef.h:186-187 | Coverage: 0.03% |
---|
Loop Id: 275 | Module: exec | Source: OneBodyJastrowRef.h:186-187 | Coverage: 0.03% |
---|
0x41a610 VADDPD (%RBX,%RSI,8),%YMM0,%YMM0 [1] |
0x41a615 VFMADD231PD (%R13,%RSI,8),%YMM1,%YMM0 [2] |
0x41a61c ADD $0x4,%RSI |
0x41a620 CMP %RDX,%RSI |
0x41a623 JB 41a610 |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/OneBodyJastrowRef.h: 186 - 187 |
-------------------------------------------------------------------------------- |
186: for (int jat = 0; jat < Nions; ++jat) |
187: lap += d2u[jat] + lapfac * du[jat]; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.67 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 7.00 |
Bottlenecks | |
Function | _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE |
Source | OneBodyJastrowRef.h:186-187 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 7.00 |
CQA cycles if no scalar integer | 7.00 |
CQA cycles if FP arith vectorized | 4.20 |
CQA cycles if fully vectorized | 3.50 |
Front-end cycles | 1.00 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.00 |
P4 cycles | 0.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 7 |
FE+BE cycles (UFS) | 7.10 |
Stall cycles (UFS) | 5.25 |
Nb insns | 5.00 |
Nb uops | 4.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.71 |
Nb FLOP add-sub | 4.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 4.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.14 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
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 | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 50.00 |
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 | 1.67 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 7.00 |
Bottlenecks | |
Function | _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE |
Source | OneBodyJastrowRef.h:186-187 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 7.00 |
CQA cycles if no scalar integer | 7.00 |
CQA cycles if FP arith vectorized | 4.20 |
CQA cycles if fully vectorized | 3.50 |
Front-end cycles | 1.00 |
DIV/SQRT cycles | 1.00 |
P0 cycles | 1.00 |
P1 cycles | 0.67 |
P2 cycles | 0.67 |
P3 cycles | 0.00 |
P4 cycles | 0.50 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 0.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 7 |
FE+BE cycles (UFS) | 7.10 |
Stall cycles (UFS) | 5.25 |
Nb insns | 5.00 |
Nb uops | 4.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.71 |
Nb FLOP add-sub | 4.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 4.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.14 |
Bytes prefetched | 0.00 |
Bytes loaded | 64.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 2.00 |
Stride n | 0.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 100.00 |
Vectorization ratio load | 100.00 |
Vectorization ratio store | NA |
Vectorization ratio mul | NA |
Vectorization ratio add_sub | 100.00 |
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 | NA |
Vector-efficiency ratio mul | NA |
Vector-efficiency ratio add_sub | 50.00 |
Vector-efficiency ratio fma | 50.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE |
Source file and lines | OneBodyJastrowRef.h:186-187 |
Module | exec |
nb instructions | 5 |
nb uops | 4 |
loop length | 21 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.00 cycles |
front end | 1.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.50 | 0.67 | 0.67 | 0.00 | 0.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
cycles | 1.00 | 1.00 | 0.67 | 0.67 | 0.00 | 0.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 7.00 |
FE+BE cycles | 7.10 |
Stall cycles | 5.25 |
ROB full (events) | 6.13 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 7.00 |
Overall L1 | 7.00 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 50% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
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) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VADDPD (%RBX,%RSI,8),%YMM0,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VFMADD231PD (%R13,%RSI,8),%YMM1,%YMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
ADD $0x4,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JB 41a610 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | _ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE |
Source file and lines | OneBodyJastrowRef.h:186-187 |
Module | exec |
nb instructions | 5 |
nb uops | 4 |
loop length | 21 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 2 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 1.00 cycles |
front end | 1.00 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 1.00 | 0.50 | 0.67 | 0.67 | 0.00 | 0.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
cycles | 1.00 | 1.00 | 0.67 | 0.67 | 0.00 | 0.50 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 7.00 |
FE+BE cycles | 7.10 |
Stall cycles | 5.25 |
ROB full (events) | 6.13 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 7.00 |
Overall L1 | 7.00 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
mul | NA (no mul vectorizable/vectorized instructions) |
add-sub | 100% |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 50% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
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) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VADDPD (%RBX,%RSI,8),%YMM0,%YMM0 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VFMADD231PD (%R13,%RSI,8),%YMM1,%YMM0 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
ADD $0x4,%RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDX,%RSI | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JB 41a610 <_ZN16miniqmcreference17OneBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE9ratioGradERNS1_11ParticleSetEiRNS1_10TinyVectorIdLj3EEE+0x90> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |