Skip to content

Actually use the llvm backend and not the khronos backend - #706

Merged
vchuravy merged 1 commit into
mainfrom
vc/backend_llvm
Jun 9, 2026
Merged

Actually use the llvm backend and not the khronos backend#706
vchuravy merged 1 commit into
mainfrom
vc/backend_llvm

Conversation

@vchuravy

@vchuravy vchuravy commented Jun 9, 2026

Copy link
Copy Markdown
Member

As noticed by Simeon in #626 (comment)

@christiangnrd

Copy link
Copy Markdown
Member

This could explain why we weren't encountering this issue over in OpenCL with validation on

@github-actions

github-actions Bot commented Jun 9, 2026

Copy link
Copy Markdown
Contributor

Benchmark Results

main e08d61a... main / e08d61a...
saxpy/default/Float32/1024 0.0841 ± 0.012 ms 0.0861 ± 0.0086 ms 0.976 ± 0.17
saxpy/default/Float32/1048576 0.451 ± 0.027 ms 0.464 ± 0.024 ms 0.971 ± 0.076
saxpy/default/Float32/16384 0.0653 ± 0.033 ms 0.0675 ± 0.034 ms 0.968 ± 0.69
saxpy/default/Float32/2048 0.0813 ± 0.029 ms 0.0856 ± 0.024 ms 0.95 ± 0.43
saxpy/default/Float32/256 0.0836 ± 0.022 ms 0.0865 ± 0.013 ms 0.966 ± 0.29
saxpy/default/Float32/262144 0.165 ± 0.031 ms 0.167 ± 0.031 ms 0.988 ± 0.26
saxpy/default/Float32/32768 0.0692 ± 0.03 ms 0.0722 ± 0.031 ms 0.959 ± 0.59
saxpy/default/Float32/4096 0.0757 ± 0.03 ms 0.081 ± 0.03 ms 0.935 ± 0.51
saxpy/default/Float32/512 0.0833 ± 0.021 ms 0.0856 ± 0.0088 ms 0.973 ± 0.26
saxpy/default/Float32/64 0.0825 ± 0.027 ms 0.0864 ± 0.013 ms 0.955 ± 0.34
saxpy/default/Float32/65536 0.0834 ± 0.03 ms 0.086 ± 0.031 ms 0.969 ± 0.49
saxpy/default/Float64/1024 0.0839 ± 0.024 ms 0.085 ± 0.015 ms 0.987 ± 0.33
saxpy/default/Float64/1048576 0.58 ± 0.058 ms 0.576 ± 0.071 ms 1.01 ± 0.16
saxpy/default/Float64/16384 0.065 ± 0.029 ms 0.0706 ± 0.03 ms 0.921 ± 0.57
saxpy/default/Float64/2048 0.0805 ± 0.032 ms 0.0853 ± 0.026 ms 0.944 ± 0.48
saxpy/default/Float64/256 0.0842 ± 0.013 ms 0.0854 ± 0.01 ms 0.986 ± 0.19
saxpy/default/Float64/262144 0.198 ± 0.037 ms 0.199 ± 0.038 ms 0.994 ± 0.27
saxpy/default/Float64/32768 0.0751 ± 0.029 ms 0.0787 ± 0.029 ms 0.954 ± 0.51
saxpy/default/Float64/4096 0.0758 ± 0.03 ms 0.0781 ± 0.03 ms 0.971 ± 0.53
saxpy/default/Float64/512 0.0838 ± 0.026 ms 0.0855 ± 0.0079 ms 0.98 ± 0.32
saxpy/default/Float64/64 0.0843 ± 0.023 ms 0.086 ± 0.013 ms 0.98 ± 0.3
saxpy/default/Float64/65536 0.0921 ± 0.029 ms 0.096 ± 0.031 ms 0.959 ± 0.43
saxpy/static workgroup=(1024,)/Float32/1024 0.082 ± 0.012 ms 0.0832 ± 0.0073 ms 0.986 ± 0.17
saxpy/static workgroup=(1024,)/Float32/1048576 0.455 ± 0.022 ms 0.461 ± 0.023 ms 0.986 ± 0.068
saxpy/static workgroup=(1024,)/Float32/16384 0.0627 ± 0.031 ms 0.0638 ± 0.032 ms 0.982 ± 0.69
saxpy/static workgroup=(1024,)/Float32/2048 0.0802 ± 0.03 ms 0.0821 ± 0.027 ms 0.977 ± 0.48
saxpy/static workgroup=(1024,)/Float32/256 0.0825 ± 0.019 ms 0.0839 ± 0.013 ms 0.984 ± 0.28
saxpy/static workgroup=(1024,)/Float32/262144 0.166 ± 0.029 ms 0.165 ± 0.028 ms 1.01 ± 0.25
saxpy/static workgroup=(1024,)/Float32/32768 0.0666 ± 0.027 ms 0.0697 ± 0.029 ms 0.956 ± 0.55
saxpy/static workgroup=(1024,)/Float32/4096 0.075 ± 0.03 ms 0.0831 ± 0.029 ms 0.902 ± 0.48
saxpy/static workgroup=(1024,)/Float32/512 0.0823 ± 0.013 ms 0.0832 ± 0.015 ms 0.989 ± 0.23
saxpy/static workgroup=(1024,)/Float32/64 0.0825 ± 0.021 ms 0.0839 ± 0.015 ms 0.984 ± 0.31
saxpy/static workgroup=(1024,)/Float32/65536 0.0808 ± 0.029 ms 0.0838 ± 0.031 ms 0.964 ± 0.49
saxpy/static workgroup=(1024,)/Float64/1024 0.0814 ± 0.023 ms 0.0826 ± 0.017 ms 0.985 ± 0.34
saxpy/static workgroup=(1024,)/Float64/1048576 0.57 ± 0.051 ms 0.574 ± 0.054 ms 0.994 ± 0.13
saxpy/static workgroup=(1024,)/Float64/16384 0.0626 ± 0.028 ms 0.0673 ± 0.029 ms 0.931 ± 0.57
saxpy/static workgroup=(1024,)/Float64/2048 0.078 ± 0.032 ms 0.0823 ± 0.029 ms 0.948 ± 0.52
saxpy/static workgroup=(1024,)/Float64/256 0.0824 ± 0.017 ms 0.0835 ± 0.014 ms 0.987 ± 0.26
saxpy/static workgroup=(1024,)/Float64/262144 0.194 ± 0.032 ms 0.192 ± 0.032 ms 1.01 ± 0.24
saxpy/static workgroup=(1024,)/Float64/32768 0.0713 ± 0.026 ms 0.0754 ± 0.027 ms 0.946 ± 0.48
saxpy/static workgroup=(1024,)/Float64/4096 0.0735 ± 0.03 ms 0.0767 ± 0.03 ms 0.958 ± 0.54
saxpy/static workgroup=(1024,)/Float64/512 0.0818 ± 0.011 ms 0.083 ± 0.0086 ms 0.985 ± 0.17
saxpy/static workgroup=(1024,)/Float64/64 0.0819 ± 0.027 ms 0.0836 ± 0.017 ms 0.979 ± 0.38
saxpy/static workgroup=(1024,)/Float64/65536 0.0901 ± 0.027 ms 0.0916 ± 0.028 ms 0.984 ± 0.42
time_to_load 0.975 ± 0.0061 s 0.968 ± 0.0085 s 1.01 ± 0.011

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 17bdaed into main Jun 9, 2026
51 of 54 checks passed
@vchuravy
vchuravy deleted the vc/backend_llvm branch June 9, 2026 15:05
@codecov

codecov Bot commented Jun 9, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 52.21%. Comparing base (0586ae6) to head (e08d61a).
⚠️ Report is 4 commits behind head on main.

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #706   +/-   ##
=======================================
  Coverage   52.21%   52.21%           
=======================================
  Files          22       22           
  Lines        1691     1691           
=======================================
  Hits          883      883           
  Misses        808      808           

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

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.

2 participants