Loop Id: 952 | Module: libkripke.so | Source: forall.hpp:59-59 [...] | Coverage: 0.26% |
---|
Loop Id: 952 | Module: libkripke.so | Source: forall.hpp:59-59 [...] | Coverage: 0.26% |
---|
0x55200 VMULPD (%R8,%R13,8),%YMM18,%YMM27 [2] |
0x55207 VFMADD231PD (%R10,%R13,8),%YMM19,%YMM27 [8] |
0x5520e VMOVUPD (%RCX,%R13,8),%YMM28 [1] |
0x55215 VFMADD231PD (%R14,%R13,8),%YMM20,%YMM27 [3] |
0x5521c VFMADD231PD (%R12,%R13,8),%YMM21,%YMM27 [9] |
0x55223 VFMADD213PD %YMM26,%YMM28,%YMM27 |
0x55229 VMULPD (%RBX,%R13,8),%YMM22,%YMM26 [6] |
0x55230 VFMADD231PD (%R11,%R13,8),%YMM23,%YMM26 [5] |
0x55237 VFMADD231PD (%RDI,%R13,8),%YMM24,%YMM26 [7] |
0x5523e VFMADD231PD (%R15,%R13,8),%YMM25,%YMM26 [4] |
0x55245 VFMADD213PD %YMM27,%YMM28,%YMM26 |
0x5524b ADD $0x4,%R13 |
0x5524f CMP %RSI,%R13 |
0x55252 JLE 55200 |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/policy/loop/forall.hpp: 59 - 59 |
-------------------------------------------------------------------------------- |
59: for (decltype(distance_it) i = 0; i < distance_it; ++i) { |
/scratch_na/users/xoserete/qaas_runs/171-291-2973/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp: 58 - 58 |
-------------------------------------------------------------------------------- |
58: part_red += w(d) * psi(d,g,z) * volume(z); |
Path / |
Metric | Value |
---|---|
CQA speedup if no scalar integer | 1.00 |
CQA speedup if FP arith vectorized | 1.47 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.60 |
Bottlenecks | |
Function | void PopulationSdom::operator() |
Source | Operators.hpp:307-307,forall.hpp:59-59,Population.cpp:58-58 |
Source loop unroll info | unrolled by 18 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | main |
Unroll factor | 18 |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 5.43 |
CQA cycles if fully vectorized | 4.00 |
Front-end cycles | 3.50 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.00 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 0.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 8 |
FE+BE cycles (UFS) | 8.26 |
Stall cycles (UFS) | 4.02 |
Nb insns | 14.00 |
Nb uops | 13.00 |
Nb loads | 9.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 9.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 8.00 |
Nb FLOP fma | 32.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 36.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 288.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 9.00 |
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 | 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 | 50.00 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | NA |
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 | 1.47 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 1.60 |
Bottlenecks | |
Function | void PopulationSdom::operator() |
Source | Operators.hpp:307-307,forall.hpp:59-59,Population.cpp:58-58 |
Source loop unroll info | unrolled by 18 |
Source loop unroll confidence level | low |
Unroll/vectorization loop type | main |
Unroll factor | 18 |
CQA cycles | 8.00 |
CQA cycles if no scalar integer | 8.00 |
CQA cycles if FP arith vectorized | 5.43 |
CQA cycles if fully vectorized | 4.00 |
Front-end cycles | 3.50 |
DIV/SQRT cycles | 5.00 |
P0 cycles | 5.00 |
P1 cycles | 3.00 |
P2 cycles | 3.00 |
P3 cycles | 0.00 |
P4 cycles | 0.00 |
P5 cycles | 1.00 |
P6 cycles | 0.00 |
P7 cycles | 0.00 |
P8 cycles | 0.00 |
P9 cycles | 0.00 |
P10 cycles | 3.00 |
P11 cycles | 0.00 |
Inter-iter dependencies cycles | 8 |
FE+BE cycles (UFS) | 8.26 |
Stall cycles (UFS) | 4.02 |
Nb insns | 14.00 |
Nb uops | 13.00 |
Nb loads | 9.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 9.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 8.00 |
Nb FLOP fma | 32.00 |
Nb FLOP div | 0.00 |
Nb FLOP rcp | 0.00 |
Nb FLOP sqrt | 0.00 |
Nb FLOP rsqrt | 0.00 |
Bytes/cycle | 36.00 |
Bytes prefetched | 0.00 |
Bytes loaded | 288.00 |
Bytes stored | 0.00 |
Stride 0 | 0.00 |
Stride 1 | 9.00 |
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 | 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 | 50.00 |
Vector-efficiency ratio load | 50.00 |
Vector-efficiency ratio store | NA |
Vector-efficiency ratio mul | 50.00 |
Vector-efficiency ratio add_sub | NA |
Vector-efficiency ratio fma | 50.00 |
Vector-efficiency ratio div_sqrt | NA |
Vector-efficiency ratio other | NA |
Path / |
Function | void PopulationSdom::operator() |
Source file and lines | forall.hpp:59-59 |
Module | libkripke.so |
nb instructions | 14 |
nb uops | 13 |
loop length | 84 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 11 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.50 cycles |
front end | 3.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.00 | 3.00 | 3.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
cycles | 5.00 | 5.00 | 3.00 | 3.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 8.00 |
FE+BE cycles | 8.26 |
Stall cycles | 4.02 |
LB full (events) | 5.36 |
Front-end | 3.50 |
Dispatch | 5.00 |
Data deps. | 8.00 |
Overall L1 | 8.00 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 50% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMULPD (%R8,%R13,8),%YMM18,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R10,%R13,8),%YMM19,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD (%RCX,%R13,8),%YMM28 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD231PD (%R14,%R13,8),%YMM20,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R12,%R13,8),%YMM21,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD213PD %YMM26,%YMM28,%YMM27 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD (%RBX,%R13,8),%YMM22,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R11,%R13,8),%YMM23,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%RDI,%R13,8),%YMM24,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R15,%R13,8),%YMM25,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD213PD %YMM27,%YMM28,%YMM26 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 55200 <_ZNK14PopulationSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_RNS8_5FieldIdJNS1_9DirectionENS1_5GroupENS1_4ZoneEEEERNSC_IdJSD_EEERNSC_IdJSF_EEEPd.extracted+0x960> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
Function | void PopulationSdom::operator() |
Source file and lines | forall.hpp:59-59 |
Module | libkripke.so |
nb instructions | 14 |
nb uops | 13 |
loop length | 84 |
used x86 registers | 11 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 11 |
used zmm registers | 0 |
nb stack references | 0 |
micro-operation queue | 3.50 cycles |
front end | 3.50 cycles |
P0 | P1 | P2 | P3 | P4 | P5 | P6 | P7 | P8 | P9 | P10 | P11 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
uops | 5.00 | 5.00 | 3.00 | 3.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
cycles | 5.00 | 5.00 | 3.00 | 3.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 3.00 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 8.00 |
FE+BE cycles | 8.26 |
Stall cycles | 4.02 |
LB full (events) | 5.36 |
Front-end | 3.50 |
Dispatch | 5.00 |
Data deps. | 8.00 |
Overall L1 | 8.00 |
all | 100% |
load | 100% |
store | NA (no store vectorizable/vectorized instructions) |
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 | 50% |
load | 50% |
store | NA (no store vectorizable/vectorized instructions) |
mul | 50% |
add-sub | NA (no add-sub vectorizable/vectorized instructions) |
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
VMULPD (%R8,%R13,8),%YMM18,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R10,%R13,8),%YMM19,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VMOVUPD (%RCX,%R13,8),%YMM28 | 1 | 0 | 0 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 0-1 | 0.33 |
VFMADD231PD (%R14,%R13,8),%YMM20,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R12,%R13,8),%YMM21,%YMM27 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD213PD %YMM26,%YMM28,%YMM27 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
VMULPD (%RBX,%R13,8),%YMM22,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R11,%R13,8),%YMM23,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%RDI,%R13,8),%YMM24,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R15,%R13,8),%YMM25,%YMM26 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD213PD %YMM27,%YMM28,%YMM26 | 1 | 0.50 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 4 | 0.50 |
ADD $0x4,%R13 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %RSI,%R13 | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 55200 <_ZNK14PopulationSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_RNS8_5FieldIdJNS1_9DirectionENS1_5GroupENS1_4ZoneEEEERNSC_IdJSD_EEERNSC_IdJSF_EEEPd.extracted+0x960> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |