Skip to content

Use the default zeros and ones for the POCL back-end - #795

Merged
vchuravy merged 1 commit into
mainfrom
tb/pocl-zeros-union
Sep 25, 2026
Merged

vchuravy merged 1 commit into
mainfrom
tb/pocl-zeros-union

Conversation

@maleadt

@maleadt maleadt commented Sep 25, 2026

Copy link
Copy Markdown
Member

Fixes #791.

The POCL back-end filled new arrays with init_kernel(arr, f, ::Type{T}). On Julia 1.13 and earlier, GPUCompiler's check_invocation cannot handle a Type{T} argument when T has no unique representation, which includes bits unions such as Union{Missing, Bool}. It calls fieldcount on it, which throws, so zeros and ones of those types failed. Julia master is not affected, because GPUCompiler turns Type{T} into a Core.TypeEgal{T} ghost argument there.

POCL arrays are plain host Arrays, so KernelInterface's generic allocate + fill! fallback works for them and handles bits unions. This PR removes the POCL overrides and the init_kernel they used. It also adds a POCL-only regression test. The test is kept out of the shared testsuite, because not every back-end supports bits-union arrays (OpenCL.jl's CLArray rejects them).

release-0.9 is not affected. It has no POCL back-end, and its native CPU() back-end runs init_kernel without GPUCompiler.

Once this is merged, JuliaGPU/AcceleratedKernels.jl#133's skip of the bits-union tests on this back-end can be removed.

The POCL back-end filled new arrays with a kernel that took the element type as an
argument. GPUCompiler cannot compile a kernel with a `Type{T}` argument when `T` is a
bits union such as `Union{Missing, Bool}`, so `zeros` and `ones` of such types threw.
POCL arrays are host `Array`s, so the generic `allocate` + `fill!` fallbacks in
KernelInterface work for them and handle bits unions.

Fixes #791
@github-actions

Copy link
Copy Markdown
Contributor

Benchmark Results

Show table
main e5e5c17... main / e5e5c17...
const/@Const/Float32/262144 0.343 ± 0.034 ms 0.345 ± 0.028 ms 0.995 ± 0.13
const/@Const/Float32/65536 0.134 ± 0.027 ms 0.125 ± 0.028 ms 1.07 ± 0.32
const/@Const/Float64/262144 0.441 ± 0.071 ms 0.434 ± 0.03 ms 1.01 ± 0.18
const/@Const/Float64/65536 0.168 ± 0.014 ms 0.17 ± 0.014 ms 0.988 ± 0.11
const/unmarked/Float32/262144 1.16 ± 0.038 ms 1.16 ± 0.041 ms 1 ± 0.048
const/unmarked/Float32/65536 0.327 ± 0.033 ms 0.324 ± 0.031 ms 1.01 ± 0.14
const/unmarked/Float64/262144 1.35 ± 0.047 ms 1.36 ± 0.039 ms 0.987 ± 0.044
const/unmarked/Float64/65536 0.382 ± 0.041 ms 0.397 ± 0.035 ms 0.961 ± 0.13
launch/3D static workgroup, dynamic ndrange 0.0728 ± 0.032 ms 0.0747 ± 0.0082 ms 0.974 ± 0.44
launch/3D static workgroup, static ndrange 0.0731 ± 0.031 ms 0.0741 ± 0.012 ms 0.987 ± 0.45
launch/dynamic workgroup, dynamic ndrange 0.0752 ± 0.03 ms 0.0746 ± 0.027 ms 1.01 ± 0.54
launch/dynamic workgroup, dynamic ndrange, workgroupsize given 0.0687 ± 0.033 ms 0.067 ± 0.035 ms 1.03 ± 0.72
launch/static workgroup, dynamic ndrange 0.0696 ± 0.033 ms 0.0732 ± 0.026 ms 0.951 ± 0.55
launch/static workgroup, static ndrange 0.0717 ± 0.032 ms 0.0737 ± 0.02 ms 0.973 ± 0.51
partition/dynamic workgroup, dynamic ndrange 0.06 ± 0.0013 μs 0.0592 ± 0.0015 μs 1.01 ± 0.034
partition/static workgroup, dynamic ndrange 0.0689 ± 0.012 μs 0.0647 ± 0.012 μs 1.06 ± 0.28
partition/static workgroup, static ndrange 1.55 ± 0.009 ns 1.55 ± 0.01 ns 1 ± 0.0087
saxpy/default/Float16/1024 0.0788 ± 0.02 ms 0.0771 ± 0.022 ms 1.02 ± 0.4
saxpy/default/Float16/1048576 0.776 ± 0.031 ms 0.803 ± 0.037 ms 0.966 ± 0.059
saxpy/default/Float16/16384 0.0654 ± 0.033 ms 0.0678 ± 0.034 ms 0.965 ± 0.69
saxpy/default/Float16/2048 0.081 ± 0.022 ms 0.0787 ± 0.027 ms 1.03 ± 0.45
saxpy/default/Float16/256 0.0784 ± 0.016 ms 0.0774 ± 0.016 ms 1.01 ± 0.29
saxpy/default/Float16/262144 0.239 ± 0.031 ms 0.254 ± 0.035 ms 0.941 ± 0.18
saxpy/default/Float16/32768 0.0748 ± 0.031 ms 0.0777 ± 0.033 ms 0.964 ± 0.57
saxpy/default/Float16/4096 0.0825 ± 0.032 ms 0.0779 ± 0.032 ms 1.06 ± 0.59
saxpy/default/Float16/512 0.0786 ± 0.018 ms 0.0772 ± 0.017 ms 1.02 ± 0.32
saxpy/default/Float16/64 0.0778 ± 0.024 ms 0.0774 ± 0.016 ms 1 ± 0.38
saxpy/default/Float16/65536 0.0967 ± 0.026 ms 0.0977 ± 0.031 ms 0.989 ± 0.41
saxpy/default/Float32/1024 0.0784 ± 0.017 ms 0.0762 ± 0.02 ms 1.03 ± 0.36
saxpy/default/Float32/1048576 0.495 ± 0.027 ms 0.511 ± 0.046 ms 0.968 ± 0.1
saxpy/default/Float32/16384 0.0588 ± 0.032 ms 0.0607 ± 0.032 ms 0.969 ± 0.73
saxpy/default/Float32/2048 0.0772 ± 0.03 ms 0.075 ± 0.03 ms 1.03 ± 0.57
saxpy/default/Float32/256 0.079 ± 0.017 ms 0.0775 ± 0.017 ms 1.02 ± 0.31
saxpy/default/Float32/262144 0.166 ± 0.03 ms 0.182 ± 0.031 ms 0.914 ± 0.23
saxpy/default/Float32/32768 0.0651 ± 0.029 ms 0.0642 ± 0.03 ms 1.01 ± 0.66
saxpy/default/Float32/4096 0.0771 ± 0.032 ms 0.0723 ± 0.029 ms 1.07 ± 0.61
saxpy/default/Float32/512 0.0784 ± 0.014 ms 0.0759 ± 0.019 ms 1.03 ± 0.32
saxpy/default/Float32/64 0.0788 ± 0.018 ms 0.077 ± 0.021 ms 1.02 ± 0.36
saxpy/default/Float32/65536 0.0792 ± 0.029 ms 0.0824 ± 0.033 ms 0.961 ± 0.52
saxpy/default/Float64/1024 0.0778 ± 0.011 ms 0.0765 ± 0.0093 ms 1.02 ± 0.19
saxpy/default/Float64/1048576 0.587 ± 0.088 ms 0.605 ± 0.062 ms 0.97 ± 0.18
saxpy/default/Float64/16384 0.0591 ± 0.028 ms 0.0584 ± 0.03 ms 1.01 ± 0.71
saxpy/default/Float64/2048 0.0766 ± 0.031 ms 0.0729 ± 0.031 ms 1.05 ± 0.62
saxpy/default/Float64/256 0.0786 ± 0.0054 ms 0.0767 ± 0.012 ms 1.02 ± 0.18
saxpy/default/Float64/262144 0.182 ± 0.038 ms 0.21 ± 0.038 ms 0.869 ± 0.24
saxpy/default/Float64/32768 0.0676 ± 0.028 ms 0.0722 ± 0.032 ms 0.936 ± 0.56
saxpy/default/Float64/4096 0.0673 ± 0.031 ms 0.0704 ± 0.027 ms 0.957 ± 0.57
saxpy/default/Float64/512 0.0778 ± 0.014 ms 0.0751 ± 0.026 ms 1.03 ± 0.4
saxpy/default/Float64/64 0.0767 ± 0.031 ms 0.0768 ± 0.015 ms 0.999 ± 0.45
saxpy/default/Float64/65536 0.0847 ± 0.027 ms 0.0951 ± 0.033 ms 0.891 ± 0.42
saxpy/static workgroup=(1024,)/Float16/1024 0.0764 ± 0.023 ms 0.0741 ± 0.026 ms 1.03 ± 0.47
saxpy/static workgroup=(1024,)/Float16/1048576 0.778 ± 0.031 ms 0.799 ± 0.039 ms 0.973 ± 0.061
saxpy/static workgroup=(1024,)/Float16/16384 0.0612 ± 0.031 ms 0.0636 ± 0.033 ms 0.963 ± 0.7
saxpy/static workgroup=(1024,)/Float16/2048 0.0786 ± 0.023 ms 0.0753 ± 0.027 ms 1.04 ± 0.49
saxpy/static workgroup=(1024,)/Float16/256 0.0754 ± 0.027 ms 0.0743 ± 0.023 ms 1.01 ± 0.48
saxpy/static workgroup=(1024,)/Float16/262144 0.234 ± 0.03 ms 0.248 ± 0.035 ms 0.941 ± 0.18
saxpy/static workgroup=(1024,)/Float16/32768 0.0719 ± 0.029 ms 0.0746 ± 0.032 ms 0.965 ± 0.57
saxpy/static workgroup=(1024,)/Float16/4096 0.0782 ± 0.034 ms 0.0724 ± 0.033 ms 1.08 ± 0.68
saxpy/static workgroup=(1024,)/Float16/512 0.0763 ± 0.021 ms 0.0743 ± 0.023 ms 1.03 ± 0.43
saxpy/static workgroup=(1024,)/Float16/64 0.0735 ± 0.031 ms 0.074 ± 0.022 ms 0.994 ± 0.51
saxpy/static workgroup=(1024,)/Float16/65536 0.0934 ± 0.024 ms 0.0956 ± 0.03 ms 0.977 ± 0.4
saxpy/static workgroup=(1024,)/Float32/1024 0.0756 ± 0.022 ms 0.0733 ± 0.023 ms 1.03 ± 0.44
saxpy/static workgroup=(1024,)/Float32/1048576 0.492 ± 0.026 ms 0.505 ± 0.043 ms 0.975 ± 0.098
saxpy/static workgroup=(1024,)/Float32/16384 0.0559 ± 0.029 ms 0.0602 ± 0.031 ms 0.929 ± 0.67
saxpy/static workgroup=(1024,)/Float32/2048 0.0741 ± 0.03 ms 0.0717 ± 0.03 ms 1.03 ± 0.6
saxpy/static workgroup=(1024,)/Float32/256 0.0755 ± 0.026 ms 0.0745 ± 0.023 ms 1.01 ± 0.47
saxpy/static workgroup=(1024,)/Float32/262144 0.161 ± 0.028 ms 0.179 ± 0.031 ms 0.902 ± 0.22
saxpy/static workgroup=(1024,)/Float32/32768 0.0621 ± 0.027 ms 0.0661 ± 0.029 ms 0.939 ± 0.58
saxpy/static workgroup=(1024,)/Float32/4096 0.0744 ± 0.033 ms 0.0642 ± 0.03 ms 1.16 ± 0.74
saxpy/static workgroup=(1024,)/Float32/512 0.0757 ± 0.022 ms 0.0735 ± 0.018 ms 1.03 ± 0.4
saxpy/static workgroup=(1024,)/Float32/64 0.0748 ± 0.03 ms 0.0735 ± 0.027 ms 1.02 ± 0.55
saxpy/static workgroup=(1024,)/Float32/65536 0.077 ± 0.028 ms 0.082 ± 0.03 ms 0.939 ± 0.48
saxpy/static workgroup=(1024,)/Float64/1024 0.0758 ± 0.026 ms 0.0736 ± 0.013 ms 1.03 ± 0.39
saxpy/static workgroup=(1024,)/Float64/1048576 0.584 ± 0.083 ms 0.608 ± 0.063 ms 0.961 ± 0.17
saxpy/static workgroup=(1024,)/Float64/16384 0.0574 ± 0.026 ms 0.0639 ± 0.029 ms 0.899 ± 0.58
saxpy/static workgroup=(1024,)/Float64/2048 0.0739 ± 0.031 ms 0.0649 ± 0.031 ms 1.14 ± 0.72
saxpy/static workgroup=(1024,)/Float64/256 0.0759 ± 0.027 ms 0.0741 ± 0.011 ms 1.02 ± 0.4
saxpy/static workgroup=(1024,)/Float64/262144 0.183 ± 0.036 ms 0.206 ± 0.034 ms 0.888 ± 0.23
saxpy/static workgroup=(1024,)/Float64/32768 0.0657 ± 0.026 ms 0.0737 ± 0.029 ms 0.891 ± 0.5
saxpy/static workgroup=(1024,)/Float64/4096 0.0615 ± 0.032 ms 0.0643 ± 0.027 ms 0.956 ± 0.63
saxpy/static workgroup=(1024,)/Float64/512 0.0756 ± 0.021 ms 0.0732 ± 0.02 ms 1.03 ± 0.41
saxpy/static workgroup=(1024,)/Float64/64 0.0749 ± 0.029 ms 0.0747 ± 0.015 ms 1 ± 0.44
saxpy/static workgroup=(1024,)/Float64/65536 0.0821 ± 0.027 ms 0.0966 ± 0.032 ms 0.85 ± 0.4
time_to_load 0.788 ± 0.0099 s 0.781 ± 0.0059 s 1.01 ± 0.015
main e5e5c17... main / e5e5c17...
const/@Const/Float32/262144 1 allocs: 16 B 1 allocs: 16 B 1
const/@Const/Float32/65536 1 allocs: 16 B 1 allocs: 16 B 1
const/@Const/Float64/262144 1 allocs: 16 B 1 allocs: 16 B 1
const/@Const/Float64/65536 1 allocs: 16 B 1 allocs: 16 B 1
const/unmarked/Float32/262144 1 allocs: 16 B 1 allocs: 16 B 1
const/unmarked/Float32/65536 1 allocs: 16 B 1 allocs: 16 B 1
const/unmarked/Float64/262144 1 allocs: 16 B 1 allocs: 16 B 1
const/unmarked/Float64/65536 1 allocs: 16 B 1 allocs: 16 B 1
launch/3D static workgroup, dynamic ndrange 5 allocs: 0.141 kB 5 allocs: 0.141 kB 1
launch/3D static workgroup, static ndrange 6 allocs: 0.172 kB 6 allocs: 0.172 kB 1
launch/dynamic workgroup, dynamic ndrange 15 allocs: 0.312 kB 15 allocs: 0.312 kB 1
launch/dynamic workgroup, dynamic ndrange, workgroupsize given 1 allocs: 16 B 1 allocs: 16 B 1
launch/static workgroup, dynamic ndrange 1 allocs: 16 B 1 allocs: 16 B 1
launch/static workgroup, static ndrange 2 allocs: 0.0469 kB 2 allocs: 0.0469 kB 1
partition/dynamic workgroup, dynamic ndrange 2 allocs: 0.0625 kB 2 allocs: 0.0625 kB 1
partition/static workgroup, dynamic ndrange 2 allocs: 32 B 2 allocs: 32 B 1
partition/static workgroup, static ndrange 0 allocs: 0 B 0 allocs: 0 B
saxpy/default/Float16/1024 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/1048576 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/16384 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/2048 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/256 16 allocs: 0.328 kB 16 allocs: 0.328 kB 1
saxpy/default/Float16/262144 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/32768 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/4096 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/512 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float16/64 16 allocs: 0.328 kB 16 allocs: 0.328 kB 1
saxpy/default/Float16/65536 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/1024 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/1048576 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/16384 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/2048 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/256 16 allocs: 0.328 kB 16 allocs: 0.328 kB 1
saxpy/default/Float32/262144 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/32768 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/4096 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/512 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float32/64 16 allocs: 0.328 kB 16 allocs: 0.328 kB 1
saxpy/default/Float32/65536 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/1024 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/1048576 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/16384 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/2048 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/256 16 allocs: 0.328 kB 16 allocs: 0.328 kB 1
saxpy/default/Float64/262144 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/32768 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/4096 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/512 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/default/Float64/64 16 allocs: 0.328 kB 16 allocs: 0.328 kB 1
saxpy/default/Float64/65536 24 allocs: 0.453 kB 24 allocs: 0.453 kB 1
saxpy/static workgroup=(1024,)/Float16/1024 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/1048576 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/16384 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/2048 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/256 1 allocs: 16 B 1 allocs: 16 B 1
saxpy/static workgroup=(1024,)/Float16/262144 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/32768 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/4096 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/512 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float16/64 1 allocs: 16 B 1 allocs: 16 B 1
saxpy/static workgroup=(1024,)/Float16/65536 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/1024 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/1048576 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/16384 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/2048 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/256 1 allocs: 16 B 1 allocs: 16 B 1
saxpy/static workgroup=(1024,)/Float32/262144 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/32768 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/4096 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/512 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float32/64 1 allocs: 16 B 1 allocs: 16 B 1
saxpy/static workgroup=(1024,)/Float32/65536 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/1024 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/1048576 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/16384 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/2048 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/256 1 allocs: 16 B 1 allocs: 16 B 1
saxpy/static workgroup=(1024,)/Float64/262144 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/32768 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/4096 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/512 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
saxpy/static workgroup=(1024,)/Float64/64 1 allocs: 16 B 1 allocs: 16 B 1
saxpy/static workgroup=(1024,)/Float64/65536 4 allocs: 0.0625 kB 4 allocs: 0.0625 kB 1
time_to_load 0.201 k allocs: 11.8 kB 0.201 k allocs: 11.8 kB 1

Benchmark Plots

A plot of the benchmark results have been uploaded as an artifact to the workflow run for this PR.
Go to "Actions"->"Benchmark a pull request"->[the most recent run]->"Artifacts" (at the bottom).

@vchuravy
vchuravy merged commit 34e8b65 into main Sep 25, 2026
76 of 78 checks passed
@vchuravy
vchuravy deleted the tb/pocl-zeros-union branch September 25, 2026 13:48
@codecov

codecov Bot commented Sep 25, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 66.66%. Comparing base (c657ae2) to head (e5e5c17).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main     #795      +/-   ##
==========================================
- Coverage   66.88%   66.66%   -0.22%     
==========================================
  Files          24       24              
  Lines        2023     2010      -13     
==========================================
- Hits         1353     1340      -13     
  Misses        670      670              

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

POCL backend: KernelAbstractions.zeros of a bits-union element type throws

2 participants