Switch Format.yml to CUDA.jl style

[vchuravy]

No description provided.

[vchuravy]

• Switch Format.yml to CUDA.jl style #568 👈 (View in Graphite)
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[github-actions]

Benchmark Results

	main	0c3bc1c...	main/0c3bc1cc6b22bf...
saxpy/default/Float16/1024	0.738 ± 0.007 μs	0.738 ± 0.0093 μs	1
saxpy/default/Float16/1048576	0.176 ± 0.0084 ms	0.174 ± 0.008 ms	1.02
saxpy/default/Float16/16384	3.35 ± 0.053 μs	3.34 ± 0.025 μs	1
saxpy/default/Float16/2048	0.914 ± 0.011 μs	0.914 ± 0.011 μs	1
saxpy/default/Float16/256	0.596 ± 0.0053 μs	0.592 ± 0.0077 μs	1.01
saxpy/default/Float16/262144	0.0444 ± 0.00091 ms	0.0442 ± 0.00043 ms	1
saxpy/default/Float16/32768	6.04 ± 0.097 μs	6.01 ± 0.052 μs	1
saxpy/default/Float16/4096	1.32 ± 0.026 μs	1.32 ± 0.025 μs	1
saxpy/default/Float16/512	0.654 ± 0.0068 μs	0.649 ± 0.0091 μs	1.01
saxpy/default/Float16/64	0.565 ± 0.005 μs	0.559 ± 0.0062 μs	1.01
saxpy/default/Float16/65536	11.7 ± 0.18 μs	11.7 ± 0.12 μs	1
saxpy/default/Float32/1024	0.638 ± 0.011 μs	0.646 ± 0.012 μs	0.988
saxpy/default/Float32/1048576	0.209 ± 0.038 ms	0.238 ± 0.019 ms	0.875
saxpy/default/Float32/16384	2.84 ± 0.36 μs	2.78 ± 0.19 μs	1.02
saxpy/default/Float32/2048	0.761 ± 0.027 μs	0.76 ± 0.055 μs	1
saxpy/default/Float32/256	0.566 ± 0.0057 μs	0.577 ± 0.0077 μs	0.982
saxpy/default/Float32/262144	0.0448 ± 0.0041 ms	0.0577 ± 0.0034 ms	0.777
saxpy/default/Float32/32768	5.5 ± 0.81 μs	5.28 ± 0.29 μs	1.04
saxpy/default/Float32/4096	1.13 ± 0.064 μs	1.15 ± 0.11 μs	0.982
saxpy/default/Float32/512	0.602 ± 0.0082 μs	0.609 ± 0.011 μs	0.988
saxpy/default/Float32/64	0.558 ± 0.0051 μs	0.564 ± 0.0056 μs	0.989
saxpy/default/Float32/65536	12.2 ± 1.2 μs	12.4 ± 0.77 μs	0.983
saxpy/default/Float64/1024	0.742 ± 0.026 μs	0.753 ± 0.072 μs	0.986
saxpy/default/Float64/1048576	0.488 ± 0.054 ms	0.523 ± 0.037 ms	0.934
saxpy/default/Float64/16384	5.4 ± 0.73 μs	5.29 ± 0.34 μs	1.02
saxpy/default/Float64/2048	1.13 ± 0.081 μs	1.15 ± 0.1 μs	0.976
saxpy/default/Float64/256	0.571 ± 0.0078 μs	0.575 ± 0.0066 μs	0.993
saxpy/default/Float64/262144	0.0915 ± 0.01 ms	0.0907 ± 0.012 ms	1.01
saxpy/default/Float64/32768	12.3 ± 1.1 μs	12.4 ± 0.73 μs	0.985
saxpy/default/Float64/4096	1.73 ± 0.23 μs	1.69 ± 0.15 μs	1.02
saxpy/default/Float64/512	0.624 ± 0.01 μs	0.626 ± 0.01 μs	0.997
saxpy/default/Float64/64	0.549 ± 0.0065 μs	0.556 ± 0.0065 μs	0.988
saxpy/default/Float64/65536	23.7 ± 2.5 μs	28.6 ± 1.5 μs	0.829
saxpy/static workgroup=(1024,)/Float16/1024	2.17 ± 0.027 μs	2.19 ± 0.028 μs	0.994
saxpy/static workgroup=(1024,)/Float16/1048576	0.158 ± 0.0088 ms	0.158 ± 0.0088 ms	0.998
saxpy/static workgroup=(1024,)/Float16/16384	4.44 ± 0.13 μs	4.43 ± 0.072 μs	1
saxpy/static workgroup=(1024,)/Float16/2048	2.35 ± 0.032 μs	2.36 ± 0.03 μs	0.996
saxpy/static workgroup=(1024,)/Float16/256	2.81 ± 0.033 μs	2.81 ± 0.031 μs	1
saxpy/static workgroup=(1024,)/Float16/262144	0.0426 ± 0.0028 ms	0.0427 ± 0.0015 ms	0.998
saxpy/static workgroup=(1024,)/Float16/32768	6.86 ± 0.22 μs	6.9 ± 0.2 μs	0.994
saxpy/static workgroup=(1024,)/Float16/4096	2.67 ± 0.046 μs	2.67 ± 0.041 μs	1
saxpy/static workgroup=(1024,)/Float16/512	3.25 ± 0.036 μs	3.26 ± 0.036 μs	0.999
saxpy/static workgroup=(1024,)/Float16/64	2.51 ± 0.21 μs	2.51 ± 0.21 μs	1
saxpy/static workgroup=(1024,)/Float16/65536	12.5 ± 0.31 μs	12.7 ± 0.37 μs	0.981
saxpy/static workgroup=(1024,)/Float32/1024	2.21 ± 0.035 μs	2.21 ± 0.03 μs	1
saxpy/static workgroup=(1024,)/Float32/1048576	0.204 ± 0.025 ms	0.245 ± 0.017 ms	0.836
saxpy/static workgroup=(1024,)/Float32/16384	4.55 ± 0.71 μs	4.39 ± 0.33 μs	1.04
saxpy/static workgroup=(1024,)/Float32/2048	2.36 ± 0.04 μs	2.37 ± 0.059 μs	0.997
saxpy/static workgroup=(1024,)/Float32/256	2.66 ± 0.058 μs	2.68 ± 0.046 μs	0.993
saxpy/static workgroup=(1024,)/Float32/262144	0.0493 ± 0.0048 ms	0.0613 ± 0.0029 ms	0.805
saxpy/static workgroup=(1024,)/Float32/32768	7.52 ± 0.71 μs	7.35 ± 0.61 μs	1.02
saxpy/static workgroup=(1024,)/Float32/4096	2.65 ± 0.062 μs	2.66 ± 0.096 μs	0.995
saxpy/static workgroup=(1024,)/Float32/512	2.67 ± 0.037 μs	2.69 ± 0.032 μs	0.992
saxpy/static workgroup=(1024,)/Float32/64	2.7 ± 5.7 μs	2.72 ± 5.3 μs	0.994
saxpy/static workgroup=(1024,)/Float32/65536	14.4 ± 1.3 μs	15.3 ± 0.97 μs	0.941
saxpy/static workgroup=(1024,)/Float64/1024	2.32 ± 0.062 μs	2.31 ± 0.074 μs	1
saxpy/static workgroup=(1024,)/Float64/1048576	0.537 ± 0.051 ms	0.516 ± 0.023 ms	1.04
saxpy/static workgroup=(1024,)/Float64/16384	7.23 ± 0.61 μs	7.28 ± 0.46 μs	0.994
saxpy/static workgroup=(1024,)/Float64/2048	2.59 ± 0.08 μs	2.61 ± 0.1 μs	0.994
saxpy/static workgroup=(1024,)/Float64/256	2.63 ± 0.053 μs	2.65 ± 0.063 μs	0.996
saxpy/static workgroup=(1024,)/Float64/262144	0.1 ± 0.014 ms	0.118 ± 0.007 ms	0.849
saxpy/static workgroup=(1024,)/Float64/32768	14.6 ± 1.5 μs	15.2 ± 0.98 μs	0.962
saxpy/static workgroup=(1024,)/Float64/4096	3.2 ± 0.24 μs	3.17 ± 0.24 μs	1.01
saxpy/static workgroup=(1024,)/Float64/512	2.65 ± 0.055 μs	2.65 ± 0.065 μs	1
saxpy/static workgroup=(1024,)/Float64/64	2.6 ± 0.065 μs	2.59 ± 0.066 μs	1
saxpy/static workgroup=(1024,)/Float64/65536	26.5 ± 2.5 μs	31.2 ± 1.4 μs	0.849
time_to_load	0.325 ± 0.0018 s	0.321 ± 0.0058 s	1.01

Benchmark Plots

A plot of the benchmark results have been uploaded as an artifact to the workflow run for this PR.
Go to "Actions"->"Benchmark a pull request"->[the most recent run]->"Artifacts" (at the bottom).