Skip to content

Check that malformed allocations throw and don't stackoverflow #576

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 26, 2025

Conversation

vchuravy
Copy link
Member

No description provided.

Copy link
Contributor

Benchmark Results

main 1312204... main/1312204356ac99...
saxpy/default/Float16/1024 0.0544 ± 0.026 ms 0.732 ± 0.0071 μs 74.4
saxpy/default/Float16/1048576 0.893 ± 0.026 ms 0.174 ± 0.0091 ms 5.14
saxpy/default/Float16/16384 0.0662 ± 0.028 ms 3.33 ± 0.031 μs 19.9
saxpy/default/Float16/2048 0.0585 ± 0.023 ms 0.912 ± 0.015 μs 64.2
saxpy/default/Float16/256 0.0614 ± 0.026 ms 0.588 ± 0.005 μs 104
saxpy/default/Float16/262144 0.271 ± 0.025 ms 0.0439 ± 0.0004 ms 6.19
saxpy/default/Float16/32768 0.078 ± 0.028 ms 6.01 ± 0.06 μs 13
saxpy/default/Float16/4096 0.0666 ± 0.026 ms 1.3 ± 0.028 μs 51.3
saxpy/default/Float16/512 0.0606 ± 0.026 ms 0.649 ± 0.0057 μs 93.4
saxpy/default/Float16/64 0.0621 ± 0.027 ms 0.558 ± 0.0042 μs 111
saxpy/default/Float16/65536 0.109 ± 0.028 ms 11.6 ± 0.11 μs 9.4
saxpy/default/Float32/1024 0.0598 ± 0.026 ms 0.648 ± 0.008 μs 92.2
saxpy/default/Float32/1048576 0.477 ± 0.031 ms 0.211 ± 0.037 ms 2.26
saxpy/default/Float32/16384 0.0564 ± 0.026 ms 2.82 ± 0.2 μs 20
saxpy/default/Float32/2048 0.051 ± 0.023 ms 0.761 ± 0.066 μs 67
saxpy/default/Float32/256 0.0609 ± 0.027 ms 0.573 ± 0.0068 μs 106
saxpy/default/Float32/262144 0.166 ± 0.034 ms 0.0451 ± 0.0047 ms 3.68
saxpy/default/Float32/32768 0.0622 ± 0.027 ms 5.46 ± 0.7 μs 11.4
saxpy/default/Float32/4096 0.0593 ± 0.025 ms 1.13 ± 0.077 μs 52.7
saxpy/default/Float32/512 0.0608 ± 0.026 ms 0.61 ± 0.0095 μs 99.8
saxpy/default/Float32/64 0.0619 ± 0.027 ms 0.56 ± 0.0054 μs 111
saxpy/default/Float32/65536 0.0806 ± 0.029 ms 12.1 ± 1.6 μs 6.68
saxpy/default/Float64/1024 0.0573 ± 0.025 ms 0.77 ± 0.078 μs 74.5
saxpy/default/Float64/1048576 0.509 ± 0.042 ms 0.48 ± 0.051 ms 1.06
saxpy/default/Float64/16384 0.0595 ± 0.026 ms 5.45 ± 0.55 μs 10.9
saxpy/default/Float64/2048 0.056 ± 0.023 ms 1.18 ± 0.14 μs 47.3
saxpy/default/Float64/256 0.0615 ± 0.026 ms 0.581 ± 0.0066 μs 106
saxpy/default/Float64/262144 0.176 ± 0.028 ms 0.0936 ± 0.013 ms 1.88
saxpy/default/Float64/32768 0.0656 ± 0.026 ms 12.1 ± 1 μs 5.43
saxpy/default/Float64/4096 0.0629 ± 0.024 ms 1.7 ± 0.11 μs 37
saxpy/default/Float64/512 0.0603 ± 0.026 ms 0.634 ± 0.011 μs 95.1
saxpy/default/Float64/64 0.0611 ± 0.026 ms 0.559 ± 0.0051 μs 109
saxpy/default/Float64/65536 0.0911 ± 0.027 ms 24 ± 3.6 μs 3.79
saxpy/static workgroup=(1024,)/Float16/1024 0.0521 ± 0.025 ms 2.22 ± 0.027 μs 23.5
saxpy/static workgroup=(1024,)/Float16/1048576 0.9 ± 0.027 ms 0.17 ± 0.023 ms 5.29
saxpy/static workgroup=(1024,)/Float16/16384 0.0622 ± 0.026 ms 4.47 ± 0.093 μs 13.9
saxpy/static workgroup=(1024,)/Float16/2048 0.0574 ± 0.024 ms 2.38 ± 0.029 μs 24.1
saxpy/static workgroup=(1024,)/Float16/256 0.0595 ± 0.026 ms 2.82 ± 0.035 μs 21.2
saxpy/static workgroup=(1024,)/Float16/262144 0.27 ± 0.028 ms 0.0416 ± 0.0011 ms 6.49
saxpy/static workgroup=(1024,)/Float16/32768 0.0746 ± 0.026 ms 6.92 ± 0.17 μs 10.8
saxpy/static workgroup=(1024,)/Float16/4096 0.0581 ± 0.026 ms 2.7 ± 0.039 μs 21.5
saxpy/static workgroup=(1024,)/Float16/512 0.0579 ± 0.025 ms 3.27 ± 0.039 μs 17.7
saxpy/static workgroup=(1024,)/Float16/64 0.0596 ± 0.026 ms 2.53 ± 0.21 μs 23.6
saxpy/static workgroup=(1024,)/Float16/65536 0.108 ± 0.026 ms 12.6 ± 0.28 μs 8.56
saxpy/static workgroup=(1024,)/Float32/1024 0.0568 ± 0.025 ms 2.19 ± 0.028 μs 26
saxpy/static workgroup=(1024,)/Float32/1048576 0.466 ± 0.031 ms 0.205 ± 0.03 ms 2.27
saxpy/static workgroup=(1024,)/Float32/16384 0.0537 ± 0.025 ms 4.36 ± 0.26 μs 12.3
saxpy/static workgroup=(1024,)/Float32/2048 0.0533 ± 0.023 ms 2.35 ± 0.058 μs 22.7
saxpy/static workgroup=(1024,)/Float32/256 0.0611 ± 0.025 ms 2.64 ± 0.037 μs 23.1
saxpy/static workgroup=(1024,)/Float32/262144 0.163 ± 0.035 ms 0.048 ± 0.0041 ms 3.39
saxpy/static workgroup=(1024,)/Float32/32768 0.0585 ± 0.026 ms 7.51 ± 0.48 μs 7.79
saxpy/static workgroup=(1024,)/Float32/4096 0.0589 ± 0.026 ms 2.65 ± 0.097 μs 22.2
saxpy/static workgroup=(1024,)/Float32/512 0.0571 ± 0.025 ms 2.66 ± 0.032 μs 21.4
saxpy/static workgroup=(1024,)/Float32/64 0.0613 ± 0.025 ms 2.68 ± 4.7 μs 22.9
saxpy/static workgroup=(1024,)/Float32/65536 0.0754 ± 0.028 ms 14.7 ± 1.5 μs 5.13
saxpy/static workgroup=(1024,)/Float64/1024 0.0576 ± 0.026 ms 2.31 ± 0.069 μs 24.9
saxpy/static workgroup=(1024,)/Float64/1048576 0.499 ± 0.044 ms 0.495 ± 0.046 ms 1.01
saxpy/static workgroup=(1024,)/Float64/16384 0.0564 ± 0.026 ms 7.35 ± 0.42 μs 7.67
saxpy/static workgroup=(1024,)/Float64/2048 0.0529 ± 0.023 ms 2.62 ± 0.1 μs 20.2
saxpy/static workgroup=(1024,)/Float64/256 0.0606 ± 0.025 ms 2.61 ± 0.05 μs 23.2
saxpy/static workgroup=(1024,)/Float64/262144 0.172 ± 0.028 ms 0.102 ± 0.016 ms 1.69
saxpy/static workgroup=(1024,)/Float64/32768 0.0652 ± 0.026 ms 14.7 ± 1.4 μs 4.43
saxpy/static workgroup=(1024,)/Float64/4096 0.0611 ± 0.026 ms 3.15 ± 0.16 μs 19.4
saxpy/static workgroup=(1024,)/Float64/512 0.0587 ± 0.026 ms 2.62 ± 0.056 μs 22.4
saxpy/static workgroup=(1024,)/Float64/64 0.0612 ± 0.026 ms 2.57 ± 0.065 μs 23.8
saxpy/static workgroup=(1024,)/Float64/65536 0.0884 ± 0.027 ms 27.7 ± 4.3 μs 3.19
time_to_load 1.13 ± 0.022 s 0.302 ± 0.0011 s 3.74

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).

@vchuravy vchuravy merged commit ccb0211 into release-0.9 Feb 26, 2025
34 of 37 checks passed
@vchuravy vchuravy deleted the vc/throw_error_on_allocate branch February 26, 2025 13:19
vchuravy added a commit that referenced this pull request Feb 26, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant