Anton Smirnov

Yes, Julia 1.10

ROCm does not support integrated APU I think, but since it is visible it tries to run multi-gpu tests. If you hide it with `HIP_VISIBLE_DEVICES` and some tests still fail,...

These MIOpen errors are most likely during algorithm search and are not fatal. It mostly means there's no suitable algorithm for the current backend (OpenCL) so it moves to other...

`MIOpen Error: /usr/src/debug/miopen-hip/MIOpen-rocm-6.0.2/src/ocl/convolutionocl.cpp:129: Invalid filter channel number` Actually this was a bug in fwd conv workspace calculation. Fixed by #678

@vchuravy if that's OK, I'd also like to tag a new release after this PR is merged.

Still the same error: ```julia ERROR: LoadError: AssertionError: Enzyme : mismatch between innerTy LLVM.PointerType([1 x { { i64, {} addrspace(10)*, {} addrspace(10)* } }] addrspace(11)*) and tape type LLVM.PointerType({} addrspace(10)*)...

Now segfaulting: ``` [13222] signal (11.1): Segmentation fault in expression starting at /home/pxlth/.julia/dev/AMDGPU/t.jl:24 typekeyvalue_hash at /cache/build/builder-amdci4-2/julialang/julia-release-1-dot-10/src/jltypes.c:1622 [inlined] lookup_typevalue at /cache/build/builder-amdci4-2/julialang/julia-release-1-dot-10/src/jltypes.c:1059 jl_inst_arg_tuple_type at /cache/build/builder-amdci4-2/julialang/julia-release-1-dot-10/src/jltypes.c:2162 jl_f_tuple at /cache/build/builder-amdci4-2/julialang/julia-release-1-dot-10/src/builtins.c:868 [inlined] jl_f_tuple at /cache/build/builder-amdci4-2/julialang/julia-release-1-dot-10/src/builtins.c:863...

Test failures are unrelated.

> Coming from [#1555 (comment)](https://github.com/FluxML/Zygote.jl/pull/1555#issuecomment-2611733494), I think we need at least one test that shows we aren't introducing new type instabilities when multiple paths try to accumulate different (un)thunked types....

@ToucheSir do you have such a test in mind?