Loop Id: 1047 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.28% |
---|
Loop Id: 1047 | Module: exec | Source: forall.hpp:59-59 [...] | Coverage: 0.28% |
---|
0x454840 VMULPD (%R8,%RCX,8),%YMM1,%YMM3 [2] |
0x454846 VFMADD231PD (%R10,%RCX,8),%YMM3,%YMM2 [1] |
0x45484c ADD $0x4,%RCX |
0x454850 CMP %R9,%RCX |
0x454853 JLE 454840 |
/scratch_na/users/xoserete/qaas_runs/171-416-9860/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/171-416-9860/intel/Kripke/build/Kripke/src/Kripke/Kernel/Population.cpp: 58 - 58 |
-------------------------------------------------------------------------------- |
58: part_red += w(d) * psi(d,g,z) * volume(z); |
/scratch_na/users/xoserete/qaas_runs/171-416-9860/intel/Kripke/build/Kripke/tpl/raja/include/RAJA/util/Operators.hpp: 307 - 307 |
-------------------------------------------------------------------------------- |
307: return Ret{lhs} + rhs; |
Coverage (%) | Name | Source Location | Module |
---|---|---|---|
►100.00+ | __kmp_invoke_microtask | libiomp5.so | |
○ | __kmp_invoke_task_func | libiomp5.so |
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 | 4.00 |
Bottlenecks | |
Function | void PopulationSdom::operator() |
Source | forall.hpp:59-59,Population.cpp:58-58,Operators.hpp:307-307 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 2.40 |
CQA cycles if fully vectorized | 2.00 |
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 | 0.00 |
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 | 4 |
FE+BE cycles (UFS) | 4.14 |
Stall cycles (UFS) | 2.29 |
Nb insns | 5.00 |
Nb uops | 4.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 3.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 4.00 |
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 | 16.00 |
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 | 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 | 1.67 |
CQA speedup if fully vectorized | 2.00 |
CQA speedup if no inter-iteration dependency | NA |
CQA speedup if next bottleneck killed | 4.00 |
Bottlenecks | |
Function | void PopulationSdom::operator() |
Source | forall.hpp:59-59,Population.cpp:58-58,Operators.hpp:307-307 |
Source loop unroll info | unrolled by 4 |
Source loop unroll confidence level | max |
Unroll/vectorization loop type | main |
Unroll factor | 4 |
CQA cycles | 4.00 |
CQA cycles if no scalar integer | 4.00 |
CQA cycles if FP arith vectorized | 2.40 |
CQA cycles if fully vectorized | 2.00 |
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 | 0.00 |
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 | 4 |
FE+BE cycles (UFS) | 4.14 |
Stall cycles (UFS) | 2.29 |
Nb insns | 5.00 |
Nb uops | 4.00 |
Nb loads | 2.00 |
Nb stores | 0.00 |
Nb stack references | 0.00 |
FLOP/cycle | 3.00 |
Nb FLOP add-sub | 0.00 |
Nb FLOP mul | 4.00 |
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 | 16.00 |
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 | 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 / |
nb instructions | 5 |
nb uops | 4 |
loop length | 21 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 3 |
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 | 1.00 | 0.67 | 0.67 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
cycles | 1.00 | 1.00 | 0.67 | 0.67 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00 |
FE+BE cycles | 4.14 |
Stall cycles | 2.29 |
ROB full (events) | 2.30 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 4.00 |
Overall L1 | 4.00 |
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,%RCX,8),%YMM1,%YMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R10,%RCX,8),%YMM3,%YMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
ADD $0x4,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R9,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 454840 <_ZNK14PopulationSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_RNS8_5FieldIdJNS1_9DirectionENS1_5GroupENS1_4ZoneEEEERNSC_IdJSD_EEERNSC_IdJSF_EEEPd.extracted+0x1d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |
nb instructions | 5 |
nb uops | 4 |
loop length | 21 |
used x86 registers | 4 |
used mmx registers | 0 |
used xmm registers | 0 |
used ymm registers | 3 |
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 | 1.00 | 0.67 | 0.67 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
cycles | 1.00 | 1.00 | 0.67 | 0.67 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.67 |
Cycles executing div or sqrt instructions | NA |
Longest recurrence chain latency (RecMII) | 4.00 |
FE+BE cycles | 4.14 |
Stall cycles | 2.29 |
ROB full (events) | 2.30 |
Front-end | 1.00 |
Dispatch | 1.00 |
Data deps. | 4.00 |
Overall L1 | 4.00 |
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,%RCX,8),%YMM1,%YMM3 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
VFMADD231PD (%R10,%RCX,8),%YMM3,%YMM2 | 1 | 0.50 | 0.50 | 0.33 | 0.33 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0.33 | 4 | 0.50 |
ADD $0x4,%RCX | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0.17 |
CMP %R9,%RCX | 1 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0.20 | 0 | 0 | 0 | 0.20 | 0 | 1 | 0.20 |
JLE 454840 <_ZNK14PopulationSdomclIN6Kripke11ArchLayoutTINS1_12ArchT_OpenMPENS1_11LayoutT_DGZEEEEEvT_NS1_6SdomIdERKNS1_4Core3SetESB_SB_RNS8_5FieldIdJNS1_9DirectionENS1_5GroupENS1_4ZoneEEEERNSC_IdJSD_EEERNSC_IdJSF_EEEPd.extracted+0x1d0> | 1 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0.50 | 0 | 0 | 0 | 0 | 0 | 0 | 0.50 |