Loop Id: 370 | Module: exec | Source: TwoBodyJastrowRef.h:324-331 | Coverage: 0.27% |
---|
Loop Id: 370 | Module: exec | Source: TwoBodyJastrowRef.h:324-331 | Coverage: 0.27% |
---|
0x41fc90 VMOVUPD (%R8,%R15,8),%YMM2 [2] |
0x41fc96 VSUBPD (%R9,%R15,8),%YMM2,%YMM2 [1] |
0x41fc9c VMOVUPD (%RCX,%R15,8),%YMM3 [7] |
0x41fca2 VFMADD213PD (%R10,%R15,8),%YMM1,%YMM3 [6] |
0x41fca8 VMOVUPD (%R11,%R15,8),%YMM4 [8] |
0x41fcae VADDPD (%RSI,%R15,8),%YMM2,%YMM2 [4] |
0x41fcb4 VMOVUPD (%R14,%R15,8),%YMM5 [3] |
0x41fcba VMOVUPD %YMM2,(%RSI,%R15,8) [4] |
0x41fcc0 VSUBPD %YMM3,%YMM4,%YMM2 |
0x41fcc4 VFMADD213PD (%RDX,%R15,8),%YMM1,%YMM5 [5] |
0x41fcca VADDPD %YMM2,%YMM5,%YMM2 |
0x41fcce VMOVUPD %YMM2,(%RDX,%R15,8) [5] |
0x41fcd4 VSUBPD %YMM3,%YMM0,%YMM0 |
0x41fcd8 ADD $0x4,%R15 |
0x41fcdc CMP %RDI,%R15 |
0x41fcdf JBE 41fc90 |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/QMCWaveFunctions/Jastrow/TwoBodyJastrowRef.h: 324 - 331 |
-------------------------------------------------------------------------------- |
324: for (int jat = 0; jat < N; jat++) |
325: { |
326: const valT du = cur_u[jat] - old_u[jat]; |
327: const valT newl = cur_d2u[jat] + lapfac * cur_du[jat]; |
328: const valT dl = old_d2u[jat] + lapfac * old_du[jat] - newl; |
329: Uat[jat] += du; |
330: d2Uat[jat] += dl; |
331: cur_d2Uat -= newl; |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.31 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | P1, |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi |
Source | TwoBodyJastrowRef.h:324-331 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 3.50 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 1.75 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 3.50 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 1.00 |
P4 cycles | 2.50 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 3.37 |
Stall cycles (UFS) | 0.00 |
Nb insns | 16.00 |
Nb uops | 15.00 |
Nb loads | 8.00 |
Nb stores | 2.00 |
Nb stack references | 0.00 |
FLOP/cycle | 10.29 |
Nb FLOP add-sub | 20.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 91.43 |
Bytes prefetched | 0.00 |
Bytes loaded | 256.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 8.00 |
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 | 100.00 |
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 | 50.00 |
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 | 1.31 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.11 |
Bottlenecks | P1, |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi |
Source | TwoBodyJastrowRef.h:324-331 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 3.50 |
CQA cycles if no scalar integer | 3.50 |
CQA cycles if FP arith vectorized | 2.67 |
CQA cycles if fully vectorized | 1.75 |
Front-end cycles | 3.17 |
DIV/SQRT cycles | 2.00 |
P0 cycles | 3.50 |
P1 cycles | 2.67 |
P2 cycles | 2.67 |
P3 cycles | 1.00 |
P4 cycles | 2.50 |
P5 cycles | 1.00 |
P6 cycles | 1.00 |
P7 cycles | 1.00 |
P8 cycles | 1.00 |
P9 cycles | 0.00 |
P10 cycles | 2.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 3 |
FE+BE cycles (UFS) | 3.37 |
Stall cycles (UFS) | 0.00 |
Nb insns | 16.00 |
Nb uops | 15.00 |
Nb loads | 8.00 |
Nb stores | 2.00 |
Nb stack references | 0.00 |
FLOP/cycle | 10.29 |
Nb FLOP add-sub | 20.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 8.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 91.43 |
Bytes prefetched | 0.00 |
Bytes loaded | 256.00 |
Bytes stored | 64.00 |
Stride 0 | 0.00 |
Stride 1 | 8.00 |
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 | 100.00 |
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 | 50.00 |
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 | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi |
Source file and lines | TwoBodyJastrowRef.h:324-331 |
Module | exec |
nb instructions | 16 |
nb uops | 15 |
loop length | 81 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 6 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.50 | 2.67 | 2.67 | 1.00 | 2.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 2.67 |
cycles | 2.00 | 3.50 | 2.67 | 2.67 | 1.00 | 2.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 3.37 |
Stall cycles | 0.00 |
Front-end | 3.17 |
Dispatch | 3.50 |
Data deps. | 3.00 |
Overall L1 | 3.50 |
all | 100% |
load | 100% |
store | 100% |
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 | 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) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%R8,%R15,8),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VSUBPD (%R9,%R15,8),%YMM2,%YMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD (%RCX,%R15,8),%YMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD213PD (%R10,%R15,8),%YMM1,%YMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD (%R11,%R15,8),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VADDPD (%RSI,%R15,8),%YMM2,%YMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD (%R14,%R15,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD %YMM2,(%RSI,%R15,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VSUBPD %YMM3,%YMM4,%YMM2 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VFMADD213PD (%RDX,%R15,8),%YMM1,%YMM5 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VADDPD %YMM2,%YMM5,%YMM2 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVUPD %YMM2,(%RDX,%R15,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VSUBPD %YMM3,%YMM0,%YMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD $0x4,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDI,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 41fc90 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x4d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | _ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi |
Source file and lines | TwoBodyJastrowRef.h:324-331 |
Module | exec |
nb instructions | 16 |
nb uops | 15 |
loop length | 81 |
used x86 registers | 10 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 6 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.17 cycles |
front end | 3.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.00 | 2.50 | 2.67 | 2.67 | 1.00 | 2.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 2.67 |
cycles | 2.00 | 3.50 | 2.67 | 2.67 | 1.00 | 2.50 | 1.00 | 1.00 | 1.00 | 1.00 | 0.00 | 2.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 3.00 |
FE+BE cycles | 3.37 |
Stall cycles | 0.00 |
Front-end | 3.17 |
Dispatch | 3.50 |
Data deps. | 3.00 |
Overall L1 | 3.50 |
all | 100% |
load | 100% |
store | 100% |
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 | 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) |
Instruction | Nb FU | P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVUPD (%R8,%R15,8),%YMM2 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VSUBPD (%R9,%R15,8),%YMM2,%YMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD (%RCX,%R15,8),%YMM3 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD213PD (%R10,%R15,8),%YMM1,%YMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD (%R11,%R15,8),%YMM4 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VADDPD (%RSI,%R15,8),%YMM2,%YMM2 | 1 | 0 | 0.50 | 0.33 | 0.33 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.33 | 3 | 0.50 |
VMOVUPD (%R14,%R15,8),%YMM5 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VMOVUPD %YMM2,(%RSI,%R15,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VSUBPD %YMM3,%YMM4,%YMM2 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VFMADD213PD (%RDX,%R15,8),%YMM1,%YMM5 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VADDPD %YMM2,%YMM5,%YMM2 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
VMOVUPD %YMM2,(%RDX,%R15,8) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
VSUBPD %YMM3,%YMM0,%YMM0 | 1 | 0 | 0.50 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 3 | 0.50 |
ADD $0x4,%R15 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RDI,%R15 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JBE 41fc90 <_ZN16miniqmcreference17TwoBodyJastrowRefIN11qmcplusplus14BsplineFunctorIdEEE10acceptMoveERNS1_11ParticleSetEi+0x4d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |