Collecting a context together with its memory segfaults
维护者通常 1 天内回复
已经有一个关联 PR 被合并了。
- #716 来自 @maleadt —— 已合并
评估
调研方向
Start with the ZeContext finalizer and the memory allocation and release paths in oneAPI.jl; the issue does not name their files or tests. Trace how context ownership interacts with allocations that become unreachable in the same collection, then check the proposed lifecycle against the CUDA.jl comparison and Level Zero constraints. Done means collecting a context and its allocations no longer segfaults; an open pull request already addresses this issue.
由索引模型根据 Issue 内容生成。
描述
Every Level Zero object is destroyed by its own finalizer, and Julia runs the finalizers of objects that become unreachable in the same collection in no particular order. A ZeContext can thus be destroyed before memory allocated in it, and freeing that memory afterwards crashes in NEO:
using oneAPI, oneAPI.oneL0
function work()
ctx = ZeContext(oneAPI.driver())
for _ in 1:3; GC.gc(true); end # the context is old by the time the array is allocated
old = context()
context!(ctx)
a = oneArray{Float32}(undef, 1_000_000)
context!(old)
return
end
work()
GC.gc(true)
[19895] signal 11 (1): Segmentation fault
_ZN2L07Context7freeMemEPKvb at libze_intel_gpu.so.1
zeMemFree at ...
This fails every time on an Iris Xe with NEO 26.35. Without the collections before the allocation the finalizers happen to run in a working order. A context in which a kernel was launched, or small (pooled) arrays were allocated, stays reachable from oneAPI.jl's caches and is never collected, which is probably why this hasn't come up.
Forcing other parent-before-child orders (a queue before its fences, an event pool before its events, a module before its kernels, a command list while it is executing) does not crash on NEO, though the Level Zero spec doesn't allow them either. The context is the one that matters: destroying it frees the allocations made in it.
CUDA.jl avoids this by not destroying contexts from a finalizer at all (CuContext has no finalizer, see also JuliaGPU/CUDA.jl#3404 for releases after an explicit destroy).
- 主要语言
- Julia
- 星标
- 218
- 派生
- 36
- 平均合并
- 1 天 5 小时
- 30 天内合并 PR
- 55
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南，环境需要你自己搭建：先看它的 README，通用步骤见我们的新手贡献指南。
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。
JuliaGPU/oneAPI.jl 的其他 Issue
-
performance
难度 4/5 3-5 天 新手友好度 48/100
维护者通常 1 天内回复
-
libraries upstream
难度 4/5 1-2 天 新手友好度 22/100
JuliaGPU/oneAPI.jl#703 · 2 条评论 ·
维护者通常 1 天内回复
-
ci
难度 5/5 一周以上 新手友好度 35/100
JuliaGPU/oneAPI.jl#663 · 1 个 reaction ·
维护者通常 1 天内回复
-
runtime upstream
难度 4/5 3-5 天 新手友好度 48/100
维护者通常 1 天内回复
-
ci kernels upstream
难度 4/5 3-5 天 新手友好度 35/100
JuliaGPU/oneAPI.jl#538 · 2 条评论 ·
维护者通常 1 天内回复
查看 JuliaGPU/oneAPI.jl 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 72/100
JuliaGPU/GPUArrays.jl#837 ·
维护者通常 2 天内回复
-
难度 1/5 1 小时以内 新手友好度 88/100
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 68/100
-
难度 2/5 1-3 小时 新手友好度 72/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 78/100
bmad-sim/BeamTracking.jl#382 ·
维护者通常 1 天内回复