JuliaGPU / JuliaGPU/AMDGPU.jl

AMDGPU.versioninfo() crashes when using Archlinux

Open
#767 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Julia
Stars
344
Forks
79
Avg merge
2d 23h
Merged PRs (30d)
27

Description

Both on Julia 1.10 and 1.11

julia> using AMDGPU

julia> AMDGPU.versioninfo()
[ Info: AMDGPU versioninfo
julia: /usr/src/debug/hip-runtime/hip-runtime-clr/hipamd/src/hip_code_object.cpp:1152: hip::FatBinaryInfo** hip::StatCO::addFatBinary(const void*, bool): Assertion `err == hipSuccess' failed.

[462812] signal 6 (-6): Aborted
in expression starting at REPL[6]:1
unknown function (ip: 0x7a58175a574c)
gsignal at /usr/lib/libc.so.6 (unknown line)
abort at /usr/lib/libc.so.6 (unknown line)
unknown function (ip: 0x7a58175334e2)
unknown function (ip: 0x7a578404bc6f)
unknown function (ip: 0x7a5664f7a608)
unknown function (ip: 0x7a58177452f6)
unknown function (ip: 0x7a58177453cc)
_dl_catch_exception at /lib64/ld-linux-x86-64.so.2 (unknown line)
unknown function (ip: 0x7a581774c0c8)
_dl_catch_exception at /lib64/ld-linux-x86-64.so.2 (unknown line)
unknown function (ip: 0x7a581774c4dd)
unknown function (ip: 0x7a581759fb33)
_dl_catch_exception at /lib64/ld-linux-x86-64.so.2 (unknown line)
unknown function (ip: 0x7a5817742568)
unknown function (ip: 0x7a581759f622)
dlopen at /usr/lib/libc.so.6 (unknown line)
ijl_load_dynamic_library at /cache/build/tester-amdci5-12/julialang/julia-release-1-dot-11/src/dlload.c:365
jl_get_library_ at /cache/build/tester-amdci5-12/julialang/julia-release-1-dot-11/src/runtime_ccall.cpp:45 [inlined]
jl_get_library_ at /cache/build/tester-amdci5-12/julialang/julia-release-1-dot-11/src/runtime_ccall.cpp:29
ijl_lazy_load_and_lookup at /cache/build/tester-amdci5-12/julialang/julia-release-1-dot-11/src/runtime_ccall.cpp:73
macro expansion at /home/vchuravy/src/AMDGPU/src/utils.jl:125 [inlined]
rocblas_get_version_string at /home/vchuravy/src/AMDGPU/src/blas/librocblas.jl:7631 [inlined]
rocblas_get_version_string at /home/vchuravy/src/AMDGPU/src/blas/rocBLAS.jl:24
version at /home/vchuravy/src/AMDGPU/src/blas/rocBLAS.jl:29
_ver at /home/vchuravy/src/AMDGPU/src/utils.jl:5 [inlined]
versioninfo at /home/vchuravy/src/AMDGPU/src/utils.jl:6
julia> AMDGPU.ROCmDiscovery.librocblas
"/opt/rocm/lib/librocblas.so"

julia> AMDGPU.ROCmDiscovery._hip_runtime_version()
v"6.3.42134"

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce AMDGPU.versioninfo() on Arch Linux with Julia 1.10 or 1.11, using the reported ROCm and rocBLAS paths. Trace the call through src/utils.jl, src/blas/librocblas.jl, and src/blas/rocBLAS.jl; done means versioninfo() reports the versions without aborting during rocBLAS loading.

Written by the indexing model from the issue text.

Assessment

Tech stack
arch-linux, julia
Domain
hpc
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.