SUGGESTION: Run the OpenCL tests under Oclgrind in CI to catch data races and invalid memory accesses in kernels
维护者通常 1 天内回复
@SteveBronder 已经在做这个了。
开始于 2026年10月5日。
评估
调研方向
Start by reading how runTests.py prefixes MPI tests, then inspect the CI setup for where a CPU-only OpenCL test stage belongs. Build test/unit/math/opencl with STAN_OPENCL=true and run its test binaries through Oclgrind with race logging. Done means the stage fails on non-empty logs and can later be made required once the reported races are fixed.
由索引模型根据 Issue 内容生成。
描述
Description
Motivation. CI runs the OpenCL tests on one GPU. A kernel bug that this device happens to tolerate stays invisible. Example: https://github.com/stan-dev/math/issues/3429, where the cholesky_decompose kernel returns a wrong factor on an AMD GPU because its barriers fence local memory only.
Oclgrind is an OpenCL device simulator. It needs no GPU and checks what real devices do not:
- data races between work items, including a barrier with the wrong fence flag (
--data-races), - reads and writes outside a buffer (always on),
- use of uninitialized values (
--uninitialized).
It runs our test binaries unchanged:
oclgrind --data-races --log races.log ./test/unit/math/opencl/cholesky_decompose_test
On develop this reports read-write races in cholesky_decompose, already for the 3×3 case, and nothing once the barriers are fixed. A first local pass also reports races in tridiagonalization_householder.
Suggested steps.
- Add
oclgrindto the CI image. - Add a CPU-only stage that builds
test/unit/math/openclwithSTAN_OPENCL=trueand runs each test binary throughoclgrind --data-races --log <file>.runTests.pyalready prefixes MPI tests withmpirun; the same mechanism can prefixoclgrind. - Fail the stage when a log is not empty.
- Start it as non-blocking and make it required once the existing reports are fixed.
- 主要语言
- C++
- 星标
- 845
- 派生
- 225
- 平均合并
- 3 天 9 小时
- 30 天内合并 PR
- 12
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
stan-dev/math 的其他 Issue
-
难度 3/5 1-2 天 新手友好度 54/100
维护者通常 1 天内回复
-
难度 4/5 3-5 天 新手友好度 54/100
维护者通常 1 天内回复
-
难度 5/5 一周以上 新手友好度 35/100
维护者通常 1 天内回复
-
numerics performance
难度 5/5 一周以上 新手友好度 35/100
stan-dev/math#3481 · 1 个 reaction ·
维护者通常 1 天内回复
-
`eigendecompose_sym`, `eigenvalues_sym` and `eigenvectors_sym` do not compile for complex matrices of `fvar<var>` or `fvar<fvar<double>>`可能重新可做 关联的 PR 已关闭且未合并。 未关闭bug
难度 3/5 1-2 天 新手友好度 55/100
维护者通常 1 天内回复
相似的 Issue
-
难度 1/5 1 小时以内 新手友好度 72/100
rhalbersma/xstd-ints#395 ·
维护者通常 1 天内回复
-
[Bug] Root filesystem scope (/) incorrectly rejects all descendant paths可能已有人在做 @mugenkyou 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 72/100
neutralinojs/neutralino.js#304 · 1 条评论 ·
-
CLI: enforce absolute ADB device paths in file and directory commands可能已有人在做 关联的 PR 仍在进行中或已合并。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
维护者通常 1 天内回复
-
FuSa
难度 2/5 1-3 小时 新手友好度 76/100
tenstorrent/tt-umd#3851 ·
维护者通常 3 天内回复
-
bug
难度 2/5 1-3 小时 新手友好度 73/100
mattgodbolt/zindex#67 ·
维护者通常 1 天内回复