Loop Id: 887 | Module: exec | Source: MultiBsplineRef.hpp:68-70 | Coverage: 27.34% |
---|
Loop Id: 887 | Module: exec | Source: MultiBsplineRef.hpp:68-70 | Coverage: 27.34% |
---|
0x43c3c0 VMULPD (%R12,%RDI,1),%XMM3,%XMM9 [4] |
0x43c3c6 VFMADD231PD (%R9,%RDI,1),%XMM2,%XMM9 [1] |
0x43c3cc VFMADD231PD (%R8,%RDI,1),%XMM4,%XMM9 [3] |
0x43c3d2 VFMADD231PD (%RCX,%RDI,1),%XMM5,%XMM9 [5] |
0x43c3d8 VFMADD213PD (%R13,%RDI,1),%XMM8,%XMM9 [2] |
0x43c3df VMOVUPD %XMM9,(%R13,%RDI,1) [2] |
0x43c3e6 ADD $0x10,%RDI |
0x43c3ea DEC %RSI |
0x43c3ed JNE 43c3c0 |
/home/eoseret/qaas_runs_CPU_9468/171-143-7755/intel/miniqmc/build/miniqmc/src/Numerics/Spline2/MultiBsplineRef.hpp: 68 - 70 |
-------------------------------------------------------------------------------- |
68: for (size_t n = 0; n < num_splines; n++) |
69: vals[n] += pre00 * |
70: (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] + |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.50 |
CQA speedup if fully vectorized | 4.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.15 |
Bottlenecks | P0, P1, |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source | MultiBsplineRef.hpp:68-70 |
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 | 2.50 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 1.67 |
CQA cycles if fully vectorized | 0.63 |
Front-end cycles | 2.17 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 0.50 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.00 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.80 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 5.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 7.20 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 2.00 |
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 | 38.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 16.00 |
Stride 0 | 0.00 |
Stride 1 | 5.00 |
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 | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 25.00 |
Vector-efficiency ratio load | 25.00 |
Vector-efficiency ratio store | 25.00 |
Vector-efficiency ratio mul | 25.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 25.00 |
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 | 1.50 |
CQA speedup if fully vectorized | 4.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.15 |
Bottlenecks | P0, P1, |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source | MultiBsplineRef.hpp:68-70 |
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 | 2.50 |
CQA cycles if no scalar integer | 2.50 |
CQA cycles if FP arith vectorized | 1.67 |
CQA cycles if fully vectorized | 0.63 |
Front-end cycles | 2.17 |
DIV/SQRT cycles | 2.50 |
P0 cycles | 2.50 |
P1 cycles | 1.67 |
P2 cycles | 1.67 |
P3 cycles | 0.50 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 0.50 |
P7 cycles | 0.50 |
P8 cycles | 0.50 |
P9 cycles | 0.00 |
P10 cycles | 1.67 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 1 |
FE+BE cycles (UFS) | 2.80 |
Stall cycles (UFS) | 0.00 |
Nb insns | 9.00 |
Nb uops | 8.00 |
Nb loads | 5.00 |
Nb stores | 1.00 |
Nb stack references | 0.00 |
FLOP/cycle | 7.20 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 2.00 |
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 | 38.40 |
Bytes prefetched | 0.00 |
Bytes loaded | 80.00 |
Bytes stored | 16.00 |
Stride 0 | 0.00 |
Stride 1 | 5.00 |
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 | 100.00 |
Vectorization ratio add_sub | NA |
Vectorization ratio fma | 100.00 |
Vectorization ratio div_sqrt | NA |
Vectorization ratio other | NA |
Vector-efficiency ratio all | 25.00 |
Vector-efficiency ratio load | 25.00 |
Vector-efficiency ratio store | 25.00 |
Vector-efficiency ratio mul | 25.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 25.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source file and lines | MultiBsplineRef.hpp:68-70 |
Module | exec |
nb instructions | 9 |
nb uops | 8 |
loop length | 47 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 6 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.17 cycles |
front end | 2.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.50 | 1.67 | 1.67 | 0.50 | 0.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 1.67 |
cycles | 2.50 | 2.50 | 1.67 | 1.67 | 0.50 | 0.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.80 |
Stall cycles | 0.00 |
Front-end | 2.17 |
Dispatch | 2.50 |
Data deps. | 1.00 |
Overall L1 | 2.50 |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 25% |
load | 25% |
store | 25% |
mul | 25% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 25% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMULPD (%R12,%RDI,1),%XMM3,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R9,%RDI,1),%XMM2,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R8,%RDI,1),%XMM4,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%RCX,%RDI,1),%XMM5,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD213PD (%R13,%RDI,1),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM9,(%R13,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
ADD $0x10,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 43c3c0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x650> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | _ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE |
Source file and lines | MultiBsplineRef.hpp:68-70 |
Module | exec |
nb instructions | 9 |
nb uops | 8 |
loop length | 47 |
used x86 registers | 7 |
used mmx registers | 0 |
used xmm registers | 6 |
used ymm registers | 0 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 2.17 cycles |
front end | 2.17 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 2.50 | 2.50 | 1.67 | 1.67 | 0.50 | 0.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 1.67 |
cycles | 2.50 | 2.50 | 1.67 | 1.67 | 0.50 | 0.00 | 1.00 | 0.50 | 0.50 | 0.50 | 0.00 | 1.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 1.00 |
FE+BE cycles | 2.80 |
Stall cycles | 0.00 |
Front-end | 2.17 |
Dispatch | 2.50 |
Data deps. | 1.00 |
Overall L1 | 2.50 |
all | 100% |
load | 100% |
store | 100% |
mul | 100% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 100% |
div/sqrt | NA (no div/sqrt vectorizable/vectorized instructions) |
other | NA (no other vectorizable/vectorized instructions) |
all | 25% |
load | 25% |
store | 25% |
mul | 25% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
fma | 25% |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMULPD (%R12,%RDI,1),%XMM3,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R9,%RDI,1),%XMM2,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R8,%RDI,1),%XMM4,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%RCX,%RDI,1),%XMM5,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD213PD (%R13,%RDI,1),%XMM8,%XMM9 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD %XMM9,(%R13,%RDI,1) | 1 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0.50 | 0.50 | 0.50 | 0 | 0 | 0-1 | 0.50 |
ADD $0x10,%RDI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
DEC %RSI | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
JNE 43c3c0 <_ZN16miniqmcreference17einspline_spo_refIdE8evaluateERKN11qmcplusplus11ParticleSetEiRNS2_6VectorIdSaIdEEE+0x650> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |