Skip to content

ci[gpu]: run cuda micro-benchmarks with codspeed #7696

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.

Sign up for GitHub

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
0ax1 merged 4 commits into from
Apr 29, 2026

try

1fdbfb8
Select commit
Loading
Failed to load commit list.
Merged

ci[gpu]: run cuda micro-benchmarks with codspeed #7696

try
1fdbfb8
Select commit
Loading
Failed to load commit list.
CodSpeed HQ / CodSpeed Performance Analysis succeeded Apr 29, 2026 in 0s

Performance Gate Passed

⚠️ Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data.

For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

✅ 1130 untouched benchmarks
🆕 68 new benchmarks
⏩ 33 skipped benchmarks1

Performance Changes

Mode Benchmark BASE HEAD Efficiency
🆕 WallTime alp_decode[10%] N/A 4.5 ms N/A
🆕 WallTime for[10M_u64] N/A 349 µs N/A
🆕 WallTime alp_decode[0%] N/A 3.3 ms N/A
🆕 WallTime dict[10M_u64_values_u8_codes] N/A 218.1 µs N/A
🆕 WallTime runend[100M_i32_runlen_100000] N/A 829.4 µs N/A
🆕 WallTime alp_decode[0%] N/A 2.5 ms N/A
🆕 WallTime dict[10M_u32_values_u16_codes] N/A 150.3 µs N/A
🆕 WallTime for[10M_u64] N/A 202 µs N/A
🆕 WallTime alp_decode[10%] N/A 6.9 ms N/A
🆕 WallTime for[10M_u16] N/A 94.8 µs N/A
🆕 WallTime for[10M_u8] N/A 73.1 µs N/A
🆕 WallTime mix[0%_in/100%_out] N/A 226.3 µs N/A
🆕 WallTime runend[100M_i32_runlen_10] N/A 1.4 ms N/A
🆕 WallTime alp_decode[1%] N/A 6.6 ms N/A
🆕 WallTime mix[100%_in/0%_out] N/A 449.5 µs N/A
🆕 WallTime for[10M_u16] N/A 72.1 µs N/A
🆕 WallTime for[10M_u32] N/A 114.2 µs N/A
🆕 WallTime runend[10M_i32_runlen_10] N/A 160.6 µs N/A
🆕 WallTime dict[10M_u32_values_u8_codes] N/A 129.5 µs N/A
🆕 WallTime runend[10M_i32_runlen_100000] N/A 90.1 µs N/A
... ... ... ... ... ...

ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.

Comparing ad/gpu-codspeed (1fdbfb8) with develop (d2d79f0)

Open in CodSpeed

Footnotes

  1. 33 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

View more details on CodSpeed HQ