A small OpenCL benchmark program to measure peak GPU/CPU performance.
active 2024-12-20 → 2026-05-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 517 days from 2024-12-20 to 2026-05-20. Pushes: 21 total, peak 2 in a day. Pull requests: 5 total, peak 2 in a day. Issues: 8 total, peak 2 in a day. Comments: 22 total, peak 5 in a day. Stars: 61 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| ProjectPhysX | 40 | 21 | 3 | 12 |
| pioto1225 | 3 | 0 | 0 | 3 |
| Mixaill | 2 | 0 | 0 | 1 |
| donberke | 2 | 0 | 1 | 1 |
| kouchy | 1 | 0 | 0 | 0 |
| Snektron | 1 | 0 | 0 | 1 |
| chucko58 | 1 | 0 | 0 | 1 |
| junka | 1 | 0 | 1 | 0 |
| Artoria2e5 | 1 | 0 | 0 | 1 |
| ZalgoSoft | 1 | 0 | 0 | 1 |
| LouisBenGu | 1 | 0 | 0 | 0 |
| xiaoran007 | 1 | 0 | 0 | 1 |
| gfkdliucheng | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#39ProjectPhysX2026-03-25 18:28INT16 Dot Product
- Issue comment#37Mixaill2025-11-20 08:39Invalid CU and cores count on AMD + RustiCL
- Issue#37Mixaill2025-11-19 23:27Invalid CU and cores count on AMD + RustiCL
- Issue#28ProjectPhysX2025-10-07 16:08Jetson Nano with Tegra X1 and PoCL 3.0 works neither with CPU nor GPU
- Issue comment#35ZalgoSoft2025-10-01 17:03Warning: stringInput.cl:55:1: error: implicit declaration of function 'arm_dot_acc' is invalid in OpenCL
- Issue#33LouisBenGu2025-09-14 14:21Can additional GPU computing power test modes be added?
- Issue#20ProjectPhysX2025-09-12 13:24Coalesced read is slower than misaligned read
- Issue#15ProjectPhysX2025-09-12 13:14Apple M3 Max no FP64 problem
- Issue comment#14Artoria2e52025-09-02 09:53Question: How to get good AMD CPU results?
- Issue#32kouchy2025-08-31 08:38Kernel launch latency
- Issue#31gfkdliucheng2025-08-27 02:41could you develop a arm version for mali gpu
- Issue comment#15chucko582025-08-03 02:58Apple M3 Max no FP64 problem
- Issue comment#27ProjectPhysX2025-05-17 07:437950x results: with Intel OCL runtime with dot product ext supp. way slower than without it..
- Issue comment#27ProjectPhysX2025-04-27 06:007950x results: with Intel OCL runtime with dot product ext supp. way slower than without it..
- Issue comment#26ProjectPhysX2025-03-09 18:29use dp4a for arm mali gpu for int8
- Pull request#26ProjectPhysX2025-03-09 18:29
- Pull request#25junka2025-03-05 06:34
- ReleaseProjectPhysX2025-03-01 08:19OpenCL-Benchmark v1.8
- Issue comment#23ProjectPhysX2025-02-22 19:36Proposal for Adding Low-Bit Computing Power Tests, Custom Device Selection, and CPU Computing Power Evaluation
- ReleaseProjectPhysX2025-02-22 10:56
- Issue comment#24ProjectPhysX2025-02-22 10:48Build error on macOS (arm64)
- Issue#24ProjectPhysX2025-02-22 10:48Build error on macOS (arm64)
- Issue comment#24xiaoran0072025-02-22 08:51Build error on macOS (arm64)
- Issue comment#24ProjectPhysX2025-02-22 08:16Build error on macOS (arm64)
- ReleaseProjectPhysX2025-02-18 06:27OpenCL-Benchmark v1.7
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 61 stars here means stars gained during the window, not the repo's star count.