CLArrays.jl icon indicating copy to clipboard operation
CLArrays.jl copied to clipboard

OpenCL-backed GPU Arrays

Results 18 CLArrays.jl issues
Sort by recently updated
recently updated
newest added

Seems like I lost my admin rights on this package, but we should archieve CLArrays!

``` julia> Pkg.add("CLArrays") Resolving package versions... ERROR: Unsatisfiable requirements detected for package Sugar [e18849f4]: Sugar [e18849f4] log: ├─possible versions are: [0.0.1-0.0.3, 0.1.0, 0.2.0, 0.3.0-0.3.1, 0.4.0-0.4.5] or uninstalled ├─restricted by julia...

You're receiving this pull request because the now-deprecated [Julia TagBot GitHub App](https://github.com/apps/julia-tagbot) is installed for this repository. This pull request installs [TagBot as a GitHub Action](https://github.com/marketplace/actions/julia-tagbot). If this PR does...

``` ayush99@ayush99:~/beignet/build$ sudo apt-get install cmake pkg-config python ocl-icd-dev libegl1-mesa- dev ocl-icd-opencl-dev libdrm-dev libxfixes-dev libxext-dev llvm-3.6-dev clang-3.6 libclang-3.6-dev libtinfo-dev libedit-dev zlib1g-devD ``` Gives me a number on unable to locate...

Not an issue, but just a question to inspire discussion. Instead of the transpiler approach, has anyone considered using https://github.com/hughperkins/coriander ? This has already been adapted to tensorflow (https://github.com/hughperkins/tf-coriander).

Originally posted as issue https://github.com/FluxML/Flux.jl/issues/325, but reposted here because it seems to be more of a CLArrays/Transpiler error than a Flux error. This issue seems to be similar to issue...

gpu_call does not seem to work for multidimensional grids when I run the simple following code `using CLArrays, GPUArrays` `n_b = 100` `n_h = 10` `n_m = 100` `grid =...

Trying to install OpenCL drivers for Linux gives me a `E: Unable to locate package zlib1g-devD` while installing dependencies. I'm on Ubuntu 16.04. Which package should I install for my...

It might be worth discussing to change the BLAS backend for `CLArray`s to [CLBlast.jl](https://github.com/JuliaGPU/CLBlast.jl) instead of [CLBLAS.jl](https://github.com/JuliaGPU/CLBLAS.jl). [CLBlast](https://github.com/CNugteren/CLBlast) is "a tuned OpenCL BLAS library". While it is not necessarily better...