add N for hardware indices

[vchuravy]

No description provided.

[github-actions]

Benchmark Results

	main	2afdea1...	main/2afdea1881607f...
saxpy/default/Float16/1024	0.534 ± 0.0077 μs	0.588 ± 0.0056 μs	0.909
saxpy/default/Float16/1048576	0.174 ± 0.0075 ms	0.172 ± 0.0046 ms	1.01
saxpy/default/Float16/16384	3.12 ± 0.031 μs	3.16 ± 0.044 μs	0.989
saxpy/default/Float16/2048	0.71 ± 0.0094 μs	0.742 ± 0.0094 μs	0.957
saxpy/default/Float16/256	0.404 ± 0.0079 μs	0.445 ± 0.0083 μs	0.909
saxpy/default/Float16/262144	0.0441 ± 0.00043 ms	0.0436 ± 0.00038 ms	1.01
saxpy/default/Float16/32768	5.79 ± 0.05 μs	5.83 ± 0.073 μs	0.994
saxpy/default/Float16/4096	1.09 ± 0.018 μs	1.13 ± 0.018 μs	0.966
saxpy/default/Float16/512	0.452 ± 0.0077 μs	0.485 ± 0.005 μs	0.933
saxpy/default/Float16/64	0.378 ± 0.0068 μs	0.412 ± 0.0046 μs	0.915
saxpy/default/Float16/65536	11.4 ± 0.12 μs	11.4 ± 0.091 μs	1
saxpy/default/Float32/1024	0.429 ± 0.0068 μs	0.435 ± 0.0091 μs	0.986
saxpy/default/Float32/1048576	0.198 ± 0.034 ms	0.202 ± 0.031 ms	0.981
saxpy/default/Float32/16384	2.53 ± 0.14 μs	2.56 ± 0.19 μs	0.986
saxpy/default/Float32/2048	0.526 ± 0.017 μs	0.539 ± 0.054 μs	0.975
saxpy/default/Float32/256	0.371 ± 0.0063 μs	0.38 ± 0.0066 μs	0.976
saxpy/default/Float32/262144	0.0451 ± 0.0045 ms	0.0445 ± 0.0051 ms	1.01
saxpy/default/Float32/32768	4.99 ± 0.28 μs	5.05 ± 0.47 μs	0.989
saxpy/default/Float32/4096	0.907 ± 0.069 μs	0.916 ± 0.073 μs	0.991
saxpy/default/Float32/512	0.393 ± 0.0069 μs	0.393 ± 0.0069 μs	0.999
saxpy/default/Float32/64	0.366 ± 0.0055 μs	0.36 ± 0.0063 μs	1.02
saxpy/default/Float32/65536	11.8 ± 1.1 μs	11.7 ± 1.5 μs	1.01
saxpy/default/Float64/1024	0.531 ± 0.02 μs	0.521 ± 0.049 μs	1.02
saxpy/default/Float64/1048576	0.482 ± 0.054 ms	0.486 ± 0.051 ms	0.991
saxpy/default/Float64/16384	4.98 ± 0.43 μs	5.21 ± 1.5 μs	0.956
saxpy/default/Float64/2048	0.918 ± 0.095 μs	0.901 ± 0.084 μs	1.02
saxpy/default/Float64/256	0.398 ± 0.0075 μs	0.381 ± 0.0067 μs	1.05
saxpy/default/Float64/262144	0.0915 ± 0.01 ms	0.0884 ± 0.013 ms	1.03
saxpy/default/Float64/32768	11.9 ± 1.1 μs	12.1 ± 1.5 μs	0.983
saxpy/default/Float64/4096	1.47 ± 0.16 μs	1.48 ± 0.22 μs	0.99
saxpy/default/Float64/512	0.423 ± 0.011 μs	0.423 ± 0.0096 μs	0.999
saxpy/default/Float64/64	0.373 ± 0.0065 μs	0.357 ± 0.0049 μs	1.04
saxpy/default/Float64/65536	23.8 ± 3.7 μs	23.8 ± 3.6 μs	0.998
saxpy/static workgroup=(1024,)/Float16/1024	1.92 ± 0.024 μs	2.12 ± 0.035 μs	0.905
saxpy/static workgroup=(1024,)/Float16/1048576	0.159 ± 0.0093 ms	0.16 ± 0.0093 ms	0.992
saxpy/static workgroup=(1024,)/Float16/16384	4.18 ± 0.13 μs	4.41 ± 0.13 μs	0.947
saxpy/static workgroup=(1024,)/Float16/2048	2.11 ± 0.041 μs	2.31 ± 0.054 μs	0.912
saxpy/static workgroup=(1024,)/Float16/256	2.58 ± 0.026 μs	2.77 ± 0.032 μs	0.929
saxpy/static workgroup=(1024,)/Float16/262144	0.042 ± 0.0016 ms	0.0418 ± 0.0015 ms	1.01
saxpy/static workgroup=(1024,)/Float16/32768	6.62 ± 0.26 μs	6.83 ± 0.26 μs	0.969
saxpy/static workgroup=(1024,)/Float16/4096	2.4 ± 0.034 μs	2.64 ± 0.04 μs	0.909
saxpy/static workgroup=(1024,)/Float16/512	3.02 ± 0.026 μs	3.21 ± 0.057 μs	0.94
saxpy/static workgroup=(1024,)/Float16/64	2.29 ± 0.047 μs	2.46 ± 0.062 μs	0.932
saxpy/static workgroup=(1024,)/Float16/65536	12.4 ± 0.59 μs	12.5 ± 0.57 μs	0.995
saxpy/static workgroup=(1024,)/Float32/1024	1.96 ± 0.034 μs	2.11 ± 0.043 μs	0.931
saxpy/static workgroup=(1024,)/Float32/1048576	0.2 ± 0.034 ms	0.21 ± 0.037 ms	0.953
saxpy/static workgroup=(1024,)/Float32/16384	4.11 ± 0.31 μs	4.22 ± 0.32 μs	0.975
saxpy/static workgroup=(1024,)/Float32/2048	2.1 ± 0.037 μs	2.27 ± 0.07 μs	0.926
saxpy/static workgroup=(1024,)/Float32/256	2.46 ± 0.052 μs	2.56 ± 0.04 μs	0.962
saxpy/static workgroup=(1024,)/Float32/262144	0.0486 ± 0.0046 ms	0.0473 ± 0.0059 ms	1.03
saxpy/static workgroup=(1024,)/Float32/32768	7.23 ± 0.43 μs	7.18 ± 0.55 μs	1.01
saxpy/static workgroup=(1024,)/Float32/4096	2.4 ± 0.071 μs	2.53 ± 0.067 μs	0.946
saxpy/static workgroup=(1024,)/Float32/512	2.44 ± 0.043 μs	2.6 ± 0.065 μs	0.941
saxpy/static workgroup=(1024,)/Float32/64	2.86 ± 8.9 μs	2.62 ± 5.3 μs	1.09
saxpy/static workgroup=(1024,)/Float32/65536	14.2 ± 1.5 μs	14.2 ± 1.5 μs	0.998
saxpy/static workgroup=(1024,)/Float64/1024	2.05 ± 0.057 μs	2.22 ± 0.061 μs	0.92
saxpy/static workgroup=(1024,)/Float64/1048576	0.507 ± 0.047 ms	0.505 ± 0.046 ms	1
saxpy/static workgroup=(1024,)/Float64/16384	6.88 ± 0.33 μs	7.12 ± 0.54 μs	0.966
saxpy/static workgroup=(1024,)/Float64/2048	2.32 ± 0.06 μs	2.48 ± 0.063 μs	0.935
saxpy/static workgroup=(1024,)/Float64/256	2.43 ± 0.13 μs	2.65 ± 0.14 μs	0.917
saxpy/static workgroup=(1024,)/Float64/262144	0.0987 ± 0.015 ms	0.0971 ± 0.014 ms	1.02
saxpy/static workgroup=(1024,)/Float64/32768	14.3 ± 1.5 μs	14.4 ± 1.6 μs	0.998
saxpy/static workgroup=(1024,)/Float64/4096	2.87 ± 0.14 μs	3.07 ± 0.23 μs	0.936
saxpy/static workgroup=(1024,)/Float64/512	2.39 ± 0.05 μs	2.59 ± 0.11 μs	0.922
saxpy/static workgroup=(1024,)/Float64/64	2.39 ± 11 μs	20.5 ± 27 μs	0.117
saxpy/static workgroup=(1024,)/Float64/65536	26.3 ± 3.5 μs	26.3 ± 3.8 μs	0.999
time_to_load	0.324 ± 0.0016 s	0.321 ± 0.0038 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).