KernelAbstractions.jl
KernelAbstractions.jl copied to clipboard
Add Enzyme as a normal test dependency
Benchmark Results
| main | 043270b6d5f1b4... | main/043270b6d5f1b4... | |
|---|---|---|---|
| saxpy/default/Float16/1024 | 0.06 ± 0.026 ms | 0.0448 ± 0.026 ms | 1.34 |
| saxpy/default/Float16/1048576 | 0.895 ± 0.031 ms | 0.891 ± 0.028 ms | 1 |
| saxpy/default/Float16/16384 | 0.0659 ± 0.028 ms | 0.061 ± 0.027 ms | 1.08 |
| saxpy/default/Float16/2048 | 0.0588 ± 0.023 ms | 0.0468 ± 0.02 ms | 1.26 |
| saxpy/default/Float16/256 | 0.0627 ± 0.026 ms | 0.0421 ± 0.027 ms | 1.49 |
| saxpy/default/Float16/262144 | 0.272 ± 0.025 ms | 0.27 ± 0.026 ms | 1.01 |
| saxpy/default/Float16/32768 | 0.0788 ± 0.027 ms | 0.074 ± 0.026 ms | 1.07 |
| saxpy/default/Float16/4096 | 0.0626 ± 0.025 ms | 0.053 ± 0.025 ms | 1.18 |
| saxpy/default/Float16/512 | 0.0611 ± 0.026 ms | 0.0444 ± 0.027 ms | 1.38 |
| saxpy/default/Float16/64 | 0.0647 ± 0.026 ms | 0.042 ± 0.03 ms | 1.54 |
| saxpy/default/Float16/65536 | 0.109 ± 0.027 ms | 0.101 ± 0.026 ms | 1.07 |
| saxpy/default/Float32/1024 | 0.0619 ± 0.026 ms | 0.0549 ± 0.027 ms | 1.13 |
| saxpy/default/Float32/1048576 | 0.481 ± 0.037 ms | 0.469 ± 0.054 ms | 1.03 |
| saxpy/default/Float32/16384 | 0.0565 ± 0.026 ms | 0.0543 ± 0.023 ms | 1.04 |
| saxpy/default/Float32/2048 | 0.054 ± 0.023 ms | 0.0468 ± 0.023 ms | 1.15 |
| saxpy/default/Float32/256 | 0.0601 ± 0.026 ms | 0.0448 ± 0.027 ms | 1.34 |
| saxpy/default/Float32/262144 | 0.165 ± 0.035 ms | 0.153 ± 0.035 ms | 1.08 |
| saxpy/default/Float32/32768 | 0.0619 ± 0.027 ms | 0.0598 ± 0.025 ms | 1.04 |
| saxpy/default/Float32/4096 | 0.0594 ± 0.025 ms | 0.0504 ± 0.025 ms | 1.18 |
| saxpy/default/Float32/512 | 0.0599 ± 0.026 ms | 0.044 ± 0.027 ms | 1.36 |
| saxpy/default/Float32/64 | 0.0609 ± 0.026 ms | 0.0597 ± 0.028 ms | 1.02 |
| saxpy/default/Float32/65536 | 0.0775 ± 0.029 ms | 0.0742 ± 0.028 ms | 1.04 |
| saxpy/default/Float64/1024 | 0.0602 ± 0.026 ms | 0.0472 ± 0.026 ms | 1.27 |
| saxpy/default/Float64/1048576 | 0.512 ± 0.04 ms | 0.505 ± 0.045 ms | 1.01 |
| saxpy/default/Float64/16384 | 0.0593 ± 0.026 ms | 0.0551 ± 0.025 ms | 1.08 |
| saxpy/default/Float64/2048 | 0.0528 ± 0.024 ms | 0.0447 ± 0.021 ms | 1.18 |
| saxpy/default/Float64/256 | 0.0605 ± 0.026 ms | 0.0447 ± 0.027 ms | 1.35 |
| saxpy/default/Float64/262144 | 0.175 ± 0.029 ms | 0.171 ± 0.031 ms | 1.02 |
| saxpy/default/Float64/32768 | 0.0655 ± 0.026 ms | 0.0637 ± 0.025 ms | 1.03 |
| saxpy/default/Float64/4096 | 0.061 ± 0.025 ms | 0.0517 ± 0.025 ms | 1.18 |
| saxpy/default/Float64/512 | 0.0597 ± 0.027 ms | 0.0454 ± 0.027 ms | 1.32 |
| saxpy/default/Float64/64 | 0.0612 ± 0.027 ms | 0.0436 ± 0.03 ms | 1.4 |
| saxpy/default/Float64/65536 | 0.0891 ± 0.027 ms | 0.0832 ± 0.027 ms | 1.07 |
| saxpy/static workgroup=(1024,)/Float16/1024 | 0.0553 ± 0.026 ms | 0.0433 ± 0.026 ms | 1.28 |
| saxpy/static workgroup=(1024,)/Float16/1048576 | 0.902 ± 0.032 ms | 0.902 ± 0.031 ms | 1 |
| saxpy/static workgroup=(1024,)/Float16/16384 | 0.0608 ± 0.026 ms | 0.0583 ± 0.025 ms | 1.04 |
| saxpy/static workgroup=(1024,)/Float16/2048 | 0.057 ± 0.023 ms | 0.0501 ± 0.022 ms | 1.14 |
| saxpy/static workgroup=(1024,)/Float16/256 | 0.0598 ± 0.026 ms | 0.0418 ± 0.026 ms | 1.43 |
| saxpy/static workgroup=(1024,)/Float16/262144 | 0.268 ± 0.027 ms | 0.266 ± 0.027 ms | 1.01 |
| saxpy/static workgroup=(1024,)/Float16/32768 | 0.0735 ± 0.025 ms | 0.0714 ± 0.025 ms | 1.03 |
| saxpy/static workgroup=(1024,)/Float16/4096 | 0.0497 ± 0.026 ms | 0.0491 ± 0.027 ms | 1.01 |
| saxpy/static workgroup=(1024,)/Float16/512 | 0.054 ± 0.026 ms | 0.0424 ± 0.026 ms | 1.28 |
| saxpy/static workgroup=(1024,)/Float16/64 | 0.0607 ± 0.026 ms | 0.0405 ± 0.026 ms | 1.5 |
| saxpy/static workgroup=(1024,)/Float16/65536 | 0.106 ± 0.026 ms | 0.099 ± 0.024 ms | 1.07 |
| saxpy/static workgroup=(1024,)/Float32/1024 | 0.0562 ± 0.026 ms | 0.0414 ± 0.026 ms | 1.36 |
| saxpy/static workgroup=(1024,)/Float32/1048576 | 0.467 ± 0.043 ms | 0.456 ± 0.051 ms | 1.02 |
| saxpy/static workgroup=(1024,)/Float32/16384 | 0.0527 ± 0.025 ms | 0.0516 ± 0.023 ms | 1.02 |
| saxpy/static workgroup=(1024,)/Float32/2048 | 0.049 ± 0.023 ms | 0.0437 ± 0.021 ms | 1.12 |
| saxpy/static workgroup=(1024,)/Float32/256 | 0.061 ± 0.026 ms | 0.041 ± 0.026 ms | 1.49 |
| saxpy/static workgroup=(1024,)/Float32/262144 | 0.16 ± 0.035 ms | 0.148 ± 0.034 ms | 1.09 |
| saxpy/static workgroup=(1024,)/Float32/32768 | 0.0584 ± 0.025 ms | 0.0569 ± 0.025 ms | 1.03 |
| saxpy/static workgroup=(1024,)/Float32/4096 | 0.0496 ± 0.026 ms | 0.0471 ± 0.026 ms | 1.05 |
| saxpy/static workgroup=(1024,)/Float32/512 | 0.0589 ± 0.026 ms | 0.043 ± 0.026 ms | 1.37 |
| saxpy/static workgroup=(1024,)/Float32/64 | 0.059 ± 0.025 ms | 0.0437 ± 0.026 ms | 1.35 |
| saxpy/static workgroup=(1024,)/Float32/65536 | 0.0736 ± 0.028 ms | 0.0702 ± 0.028 ms | 1.05 |
| saxpy/static workgroup=(1024,)/Float64/1024 | 0.0585 ± 0.026 ms | 0.0427 ± 0.027 ms | 1.37 |
| saxpy/static workgroup=(1024,)/Float64/1048576 | 0.502 ± 0.047 ms | 0.503 ± 0.043 ms | 0.998 |
| saxpy/static workgroup=(1024,)/Float64/16384 | 0.055 ± 0.025 ms | 0.0543 ± 0.024 ms | 1.01 |
| saxpy/static workgroup=(1024,)/Float64/2048 | 0.0513 ± 0.024 ms | 0.0442 ± 0.021 ms | 1.16 |
| saxpy/static workgroup=(1024,)/Float64/256 | 0.0607 ± 0.026 ms | 0.0419 ± 0.026 ms | 1.45 |
| saxpy/static workgroup=(1024,)/Float64/262144 | 0.172 ± 0.029 ms | 0.168 ± 0.031 ms | 1.02 |
| saxpy/static workgroup=(1024,)/Float64/32768 | 0.0631 ± 0.025 ms | 0.0619 ± 0.024 ms | 1.02 |
| saxpy/static workgroup=(1024,)/Float64/4096 | 0.0536 ± 0.026 ms | 0.0466 ± 0.026 ms | 1.15 |
| saxpy/static workgroup=(1024,)/Float64/512 | 0.0598 ± 0.026 ms | 0.0427 ± 0.026 ms | 1.4 |
| saxpy/static workgroup=(1024,)/Float64/64 | 0.0609 ± 0.026 ms | 0.0429 ± 0.027 ms | 1.42 |
| saxpy/static workgroup=(1024,)/Float64/65536 | 0.0857 ± 0.027 ms | 0.0799 ± 0.026 ms | 1.07 |
| time_to_load | 1.13 ± 0.0093 s | 1.16 ± 0.011 s | 0.977 |
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).
Codecov Report
Attention: Patch coverage is 0% with 17 lines in your changes missing coverage. Please review.
Project coverage is 0.00%. Comparing base (
365bf2c) to head (043270b).
| Files with missing lines | Patch % | Lines |
|---|---|---|
| ext/EnzymeCore07Ext.jl | 0.00% | 9 Missing :warning: |
| ext/EnzymeCore08Ext.jl | 0.00% | 8 Missing :warning: |
Additional details and impacted files
@@ Coverage Diff @@
## main #583 +/- ##
=====================================
Coverage 0.00% 0.00%
=====================================
Files 21 21
Lines 1571 1511 -60
=====================================
+ Misses 1571 1511 -60
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: 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.