Skip to content

Commit

Permalink
removed dummy loop to Field mul
Browse files Browse the repository at this point in the history
  • Loading branch information
ChristianVonMach committed May 8, 2022
1 parent 283bfd4 commit 05b0b6f
Show file tree
Hide file tree
Showing 2 changed files with 2 additions and 5 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/benchmark.yml
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ on:

jobs:
master-benchmark:
name: Benchmark
name: Benchmark Master
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
Expand Down
5 changes: 1 addition & 4 deletions src/field/Field.h
Original file line number Diff line number Diff line change
Expand Up @@ -128,10 +128,7 @@ class Field {
auto rhs_data = rhs.data;
#pragma acc parallel loop independent present(this->data[:m_size], rhs_data[:m_size]) async
for (size_t i = 0; i < m_size; ++i) {
this->data[i] *= rhs_data[i] * rhs_data[i];
}
for (size_t i = 0; i < m_size; ++i) {
this->data[i] /= rhs_data[i];
this->data[i] *= rhs_data[i];
}
#pragma acc wait
return *this;
Expand Down

2 comments on commit 05b0b6f

@github-actions
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Benchmark

Benchmark suite Current: 05b0b6f Previous: bbc468c Ratio
BM_AddScalar/8 1152.4034229243555 ns/iter 1424.3414406977233 ns/iter 0.81
BM_AddScalar/64 1183.3066285989566 ns/iter 1484.871451507898 ns/iter 0.80
BM_AddScalar/512 1401.3856085012546 ns/iter 1807.348702780047 ns/iter 0.78
BM_AddScalar/4096 3178.3814819867334 ns/iter 3996.1303871012374 ns/iter 0.80
BM_AddScalar/32768 15515.076725208635 ns/iter 25132.48286639052 ns/iter 0.62
BM_AddScalar/262144 171163.0885797779 ns/iter 268083.01108139707 ns/iter 0.64
BM_AddScalar/2097152 1487812.1004273014 ns/iter 2152721.851973788 ns/iter 0.69
BM_AddScalar/8388608 24338827.206896707 ns/iter 34278482.71428502 ns/iter 0.71
BM_AddFields/8 2308.40346025335 ns/iter 2968.1625001574416 ns/iter 0.78
BM_AddFields/64 2347.47607033554 ns/iter 3109.621952527783 ns/iter 0.75
BM_AddFields/512 2695.3879669490398 ns/iter 3401.3803537872186 ns/iter 0.79
BM_AddFields/4096 5706.125428110122 ns/iter 7610.886199992094 ns/iter 0.75
BM_AddFields/32768 28242.248557009356 ns/iter 62602.1290545821 ns/iter 0.45
BM_AddFields/262144 350561.86980475136 ns/iter 471873.5216009903 ns/iter 0.74
BM_AddFields/2097152 10467027.257575547 ns/iter 12456521.67742059 ns/iter 0.84
BM_AddFields/8388608 78104784.22221775 ns/iter 79615194.37499475 ns/iter 0.98
BM_MulScalar/8 1158.5564135201155 ns/iter 1426.461770168548 ns/iter 0.81
BM_MulScalar/64 1185.1378523759124 ns/iter 1476.6194696095884 ns/iter 0.80
BM_MulScalar/512 1398.99150332153 ns/iter 1791.2982181679424 ns/iter 0.78
BM_MulScalar/4096 3179.4790233336107 ns/iter 3971.3985250669352 ns/iter 0.80
BM_MulScalar/32768 15556.14820915721 ns/iter 26202.423130963714 ns/iter 0.59
BM_MulScalar/262144 179513.56325378397 ns/iter 262294.952218429 ns/iter 0.68
BM_MulScalar/2097152 1451584.9672131825 ns/iter 2152114.05345892 ns/iter 0.67
BM_MulScalar/8388608 41675050.76470527 ns/iter 52675574.61538148 ns/iter 0.79
BM_MulFields/8 2308.4812104416083 ns/iter 2845.6245131414967 ns/iter 0.81
BM_MulFields/64 2349.8332306721986 ns/iter 2898.889855818488 ns/iter 0.81
BM_MulFields/512 4462.580189443933 ns/iter 3305.1082506661573 ns/iter 1.35
BM_MulFields/4096 5707.7105889837 ns/iter 7494.890696498564 ns/iter 0.76
BM_MulFields/32768 28115.610300908615 ns/iter 58409.365716749366 ns/iter 0.48
BM_MulFields/262144 344340.7570093357 ns/iter 470131.5294118053 ns/iter 0.73
BM_MulFields/2097152 13759137.8039231 ns/iter 15383919.431818845 ns/iter 0.89
BM_MulFields/8388608 82199237.22222373 ns/iter 103083971.28570893 ns/iter 0.80

This comment was automatically generated by workflow using github-action-benchmark.

@github-actions
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Benchmark

Benchmark suite Current: 05b0b6f Previous: bbc468c Ratio
BM_AddScalar/8 1037.4187536456582 ns/iter 1424.3414406977233 ns/iter 0.73
BM_AddScalar/64 1057.223844688072 ns/iter 1484.871451507898 ns/iter 0.71
BM_AddScalar/512 1272.978089928739 ns/iter 1807.348702780047 ns/iter 0.70
BM_AddScalar/4096 3304.4045180860944 ns/iter 3996.1303871012374 ns/iter 0.83
BM_AddScalar/32768 22714.373299533967 ns/iter 25132.48286639052 ns/iter 0.90
BM_AddScalar/262144 201821.09606307844 ns/iter 268083.01108139707 ns/iter 0.75
BM_AddScalar/2097152 3651357.1919381157 ns/iter 2152721.851973788 ns/iter 1.70
BM_AddScalar/8388608 38293926.10997376 ns/iter 34278482.71428502 ns/iter 1.12
BM_AddFields/8 2098.2859219487 ns/iter 2968.1625001574416 ns/iter 0.71
BM_AddFields/64 2129.4074993532677 ns/iter 3109.621952527783 ns/iter 0.68
BM_AddFields/512 2713.011501224947 ns/iter 3401.3803537872186 ns/iter 0.80
BM_AddFields/4096 7549.002270658465 ns/iter 7610.886199992094 ns/iter 0.99
BM_AddFields/32768 50916.41694791202 ns/iter 62602.1290545821 ns/iter 0.81
BM_AddFields/262144 384870.79693106725 ns/iter 471873.5216009903 ns/iter 0.82
BM_AddFields/2097152 18382105.630160753 ns/iter 12456521.67742059 ns/iter 1.48
BM_AddFields/8388608 75378480.00518149 ns/iter 79615194.37499475 ns/iter 0.95
BM_MulScalar/8 1027.8843583857958 ns/iter 1426.461770168548 ns/iter 0.72
BM_MulScalar/64 1053.5483615881315 ns/iter 1476.6194696095884 ns/iter 0.71
BM_MulScalar/512 1262.4267595086544 ns/iter 1791.2982181679424 ns/iter 0.70
BM_MulScalar/4096 2971.4158479954335 ns/iter 3971.3985250669352 ns/iter 0.75
BM_MulScalar/32768 22482.038300813667 ns/iter 26202.423130963714 ns/iter 0.86
BM_MulScalar/262144 201127.0525271285 ns/iter 262294.952218429 ns/iter 0.77
BM_MulScalar/2097152 3411971.208937828 ns/iter 2152114.05345892 ns/iter 1.59
BM_MulScalar/8388608 38280329.052617565 ns/iter 52675574.61538148 ns/iter 0.73
BM_MulFields/8 2088.773511619757 ns/iter 2845.6245131414967 ns/iter 0.73
BM_MulFields/64 2130.244981687677 ns/iter 2898.889855818488 ns/iter 0.73
BM_MulFields/512 2715.4537280508293 ns/iter 3305.1082506661573 ns/iter 0.82
BM_MulFields/4096 7551.499704673715 ns/iter 7494.890696498564 ns/iter 1.01
BM_MulFields/32768 50956.393917653826 ns/iter 58409.365716749366 ns/iter 0.87
BM_MulFields/262144 384531.64506591036 ns/iter 470131.5294118053 ns/iter 0.82
BM_MulFields/2097152 18301212.605652645 ns/iter 15383919.431818845 ns/iter 1.19
BM_MulFields/8388608 75113384.99736868 ns/iter 103083971.28570893 ns/iter 0.73

This comment was automatically generated by workflow using github-action-benchmark.

Please sign in to comment.