Loop Id: 599 | Module: libqmcwfs.so | Source: inner_product.hpp:155-155 [...] | Coverage: 0.44% |
---|
Loop Id: 599 | Module: libqmcwfs.so | Source: inner_product.hpp:155-155 [...] | Coverage: 0.44% |
---|
0x5226b VMOVSD (%RDX),%XMM8 [4] |
0x5226f VMOVSD 0x8(%RDX),%XMM0 [4] |
0x52274 ADD $0x20,%RDX |
0x52278 ADD $0x60,%R8 |
0x5227c VMOVSD -0x10(%RDX),%XMM10 [2] |
0x52281 VMOVDDUP %XMM8,%XMM9 |
0x52286 VFMADD132PD -0x60(%R8),%XMM13,%XMM9 [3] |
0x5228c VMOVDDUP %XMM0,%XMM1 |
0x52290 VFMADD132SD -0x50(%R8),%XMM12,%XMM8 [3] |
0x52296 VFMADD132PD -0x48(%R8),%XMM9,%XMM1 [3] |
0x5229c VMOVDDUP %XMM10,%XMM11 |
0x522a1 VMOVSD -0x8(%RDX),%XMM12 [2] |
0x522a6 VFMADD132PD -0x30(%R8),%XMM1,%XMM11 [3] |
0x522ac VFMADD231SD -0x38(%R8),%XMM0,%XMM8 [3] |
0x522b2 VMOVDDUP %XMM12,%XMM13 |
0x522b7 VFMADD132PD -0x18(%R8),%XMM11,%XMM13 [3] |
0x522bd VFMADD231SD -0x20(%R8),%XMM10,%XMM8 [3] |
0x522c3 VFMADD132SD -0x8(%R8),%XMM8,%XMM12 [3] |
0x522c9 VMOVUPD %XMM13,(%R13) [1] |
0x522cf CMP %RDX,%R10 |
0x522d2 JNE 5226b |
/home/eoseret/qaas_runs_CPU_9468/171-145-9236/intel/miniqmc/build/miniqmc/src/Platforms/CPU/SIMD/inner_product.hpp: 155 - 155 |
-------------------------------------------------------------------------------- |
155: for (int i = 0; i < n; i++) |
/home/eoseret/qaas_runs_CPU_9468/171-145-9236/intel/miniqmc/build/miniqmc/src/Numerics/PETE/OperatorTags.h: 63 - 94 |
-------------------------------------------------------------------------------- |
63: return (a * b); |
[...] |
94: (const_cast<T1&>(a) += b); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.95 |
CQA speedup if fully vectorized | 6.46 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 4.00 |
Bottlenecks | |
Function | _ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi |
Source | inner_product.hpp:155-155,OperatorTags.h:63-63,OperatorTags.h:94-94 |
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 | 16.00 |
CQA cycles if no scalar integer | 16.00 |
CQA cycles if FP arith vectorized | 8.19 |
CQA cycles if fully vectorized | 2.48 |
Front-end cycles | 3.33 |
DIV/SQRT cycles | 4.00 |
P0 cycles | 4.00 |
P1 cycles | 4.00 |
P2 cycles | 4.00 |
P3 cycles | 0.50 |
P4 cycles | 4.00 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.00 |
P10 cycles | 4.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 16 |
FE+BE cycles (UFS) | 16.14 |
Stall cycles (UFS) | 12.27 |
Nb insns | 21.00 |
Nb uops | 20.00 |
Nb loads | 12.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.50 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 12.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 29.41 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | 100.00 |
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 | 16.18 |
Vector-efficiency ratio load | 16.67 |
Vector-efficiency ratio store | 25.00 |
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 | 1.00 |
CQA speedup if FP arith vectorized | 1.95 |
CQA speedup if fully vectorized | 6.46 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 4.00 |
Bottlenecks | |
Function | _ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi |
Source | inner_product.hpp:155-155,OperatorTags.h:63-63,OperatorTags.h:94-94 |
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 | 16.00 |
CQA cycles if no scalar integer | 16.00 |
CQA cycles if FP arith vectorized | 8.19 |
CQA cycles if fully vectorized | 2.48 |
Front-end cycles | 3.33 |
DIV/SQRT cycles | 4.00 |
P0 cycles | 4.00 |
P1 cycles | 4.00 |
P2 cycles | 4.00 |
P3 cycles | 0.50 |
P4 cycles | 4.00 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.00 |
P10 cycles | 4.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 16 |
FE+BE cycles (UFS) | 16.14 |
Stall cycles (UFS) | 12.27 |
Nb insns | 21.00 |
Nb uops | 20.00 |
Nb loads | 12.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 1.50 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 0.00 |
Nb FLOP fma | 12.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 9.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 128.00 |
Bytes stored | 16.00 |
Stride 0 | 1.00 |
Stride 1 | 1.00 |
Stride n | 1.00 |
Stride unknown | 0.00 |
Stride indirect | 0.00 |
Vectorization ratio all | 29.41 |
Vectorization ratio load | 33.33 |
Vectorization ratio store | 100.00 |
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 | 16.18 |
Vector-efficiency ratio load | 16.67 |
Vector-efficiency ratio store | 25.00 |
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 | _ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi |
Source file and lines | inner_product.hpp:155-155 |
Module | libqmcwfs.so |
nb instructions | 21 |
nb uops | 20 |
loop length | 105 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 8 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.33 cycles |
front end | 3.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.00 | 4.00 | 4.00 | 4.00 | 0.50 | 4.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 4.00 |
cycles | 4.00 | 4.00 | 4.00 | 4.00 | 0.50 | 4.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 4.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 16.00 |
FE+BE cycles | 16.14 |
Stall cycles | 12.27 |
LB full (events) | 14.40 |
LM full (events) | 0.36 |
Front-end | 3.33 |
Dispatch | 4.00 |
Data deps. | 16.00 |
Overall L1 | 16.00 |
all | 29% |
load | 33% |
store | 100% |
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 | 16% |
load | 16% |
store | 25% |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%RDX),%XMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD 0x8(%RDX),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x20,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x60,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VMOVSD -0x10(%RDX),%XMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVDDUP %XMM8,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VFMADD132PD -0x60(%R8),%XMM13,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVDDUP %XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VFMADD132SD -0x50(%R8),%XMM12,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD132PD -0x48(%R8),%XMM9,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVDDUP %XMM10,%XMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VMOVSD -0x8(%RDX),%XMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD132PD -0x30(%R8),%XMM1,%XMM11 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231SD -0x38(%R8),%XMM0,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVDDUP %XMM12,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VFMADD132PD -0x18(%R8),%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231SD -0x20(%R8),%XMM10,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD132SD -0x8(%R8),%XMM8,%XMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM13,(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CMP %RDX,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 5226b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x12b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | _ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi |
Source file and lines | inner_product.hpp:155-155 |
Module | libqmcwfs.so |
nb instructions | 21 |
nb uops | 20 |
loop length | 105 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 8 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.33 cycles |
front end | 3.33 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 4.00 | 4.00 | 4.00 | 4.00 | 0.50 | 4.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 4.00 |
cycles | 4.00 | 4.00 | 4.00 | 4.00 | 0.50 | 4.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 4.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 16.00 |
FE+BE cycles | 16.14 |
Stall cycles | 12.27 |
LB full (events) | 14.40 |
LM full (events) | 0.36 |
Front-end | 3.33 |
Dispatch | 4.00 |
Data deps. | 16.00 |
Overall L1 | 16.00 |
all | 29% |
load | 33% |
store | 100% |
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 | 16% |
load | 16% |
store | 25% |
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 | P8 | P9 | P10 | P11 | Latency | Recip. throughput |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMOVSD (%RDX),%XMM8 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVSD 0x8(%RDX),%XMM0 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
ADD $0x20,%RDX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
ADD $0x60,%R8 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
VMOVSD -0x10(%RDX),%XMM10 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VMOVDDUP %XMM8,%XMM9 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VFMADD132PD -0x60(%R8),%XMM13,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVDDUP %XMM0,%XMM1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VFMADD132SD -0x50(%R8),%XMM12,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD132PD -0x48(%R8),%XMM9,%XMM1 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVDDUP %XMM10,%XMM11 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VMOVSD -0x8(%RDX),%XMM12 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 1 | 0.33 |
VFMADD132PD -0x30(%R8),%XMM1,%XMM11 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231SD -0x38(%R8),%XMM0,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVDDUP %XMM12,%XMM13 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 |
VFMADD132PD -0x18(%R8),%XMM11,%XMM13 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231SD -0x20(%R8),%XMM10,%XMM8 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD132SD -0x8(%R8),%XMM8,%XMM12 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM13,(%R13) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
CMP %RDX,%R10 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JNE 5226b <_ZN16miniqmcreference19DiracDeterminantRefIN11qmcplusplus13DelayedUpdateIddEEE8evalGradERNS1_11ParticleSetEi+0x12b> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |