Michel Schanen

Travis bitches because they removed encrypted environment variables so I cannot pull the third-party libraries. I'll look into that.

I'm here to confirm this issue, too. The source code points to the C compiler call. The C compiler seems to not return. I tried different C compilers via `JULIA_CC`,...

@wsmoses Forward mode doesn't work anymore, which used to work when I started on this. I'm on latest `Enzyme#main` [out_fwd.log](https://github.com/JuliaGPU/KernelAbstractions.jl/files/14054650/out_fwd.log). ```julia (KernelAbstractions) pkg> st Project KernelAbstractions v0.9.15 Status `~/.julia/dev/KernelAbstractions/Project.toml` [79e6a3ab]...

I added the following allocate call: ```julia subtape = allocate(CUDABackend(), TapeType, size(blocks(iterspace))) ``` Now with `[email protected]` and the artifact I get: ``` ╰─$ julia --project=. reverse_gpu.jl kernels: Error During Test...

The reverse kernel uses `autodiff_deferred_thunk` as opposed to the forward mode using `autodiff_deferred`. Indeed, there is no test for `autodiff_deferred_thunk` on CUDA in `Enzyme.jl`. Trying my luck, but not sure...

@vchuravy Cleaned up. Are we waiting for https://github.com/EnzymeAD/Enzyme.jl/pull/1104 and https://github.com/JuliaGPU/CUDA.jl/pull/2260 ?

@wsmoses @vchuravy Cleanup with working tests (if CUDA is working). Last unresolved issue is active arguments to a kernel. The compiler cannot figure out the type here for the actives,...

@vchuravy Bump. Is there a blocker here?

I can't because I need to apply forward over the reverse pass. Or at least I got an error indicating that. Do you know whether there is a way to...

Ok. I think I see. I have to move the tuples out. Thanks.