Domains GPU

Strange behavior of `mapreduce` (3)

CUDAnative support for Float16 (6)

How to time CUDA Event (4)

cuArrays vs CUDANative (4)

Freeing memory in the GPU with CUDAdrv / CUDAnative / CuArrays (9)

How to set the diagonal part of a GPU Array (7)

Performance of view with cuArrays (12)

Is is possible to merge multiple kernels in CUDAnative to minimize launch overhead and execution overhead? (13)

Shared library errors when using optirun (2)

Is there any plan for GPU linear algebra? (4)

Maintaining OpenCL packages (1)

Support for Complex-valued CuArray (3)

Can not use CuArray on Julia 0.7 (4)

Support for Sparse Matrices on GPU (CUSPARSE) (2)

Optimizing the use of Blocks, Threads vs. Array Indexing (16)

Package use, CUDA stream support, etc (6)

Flux four errors in Julia v0.7 none in v0.6.4 (2)

Computing eigenvalues/eigenvectors using GPU? (10)

CUDAnative question: "recursion not currently supported error" when running reduce.jl example (2)

CuArray and Optim (10)

GPUArrays, 64-32bit conversions, and Cassete.jl (9)

LLVM crash when running Flux and CuArray examples in julia 0.7 (14)

Flux: GPU slower than CPU? (8)

CLBlast, a tuned OpenCL BLAS library (7)

CUDAdrv cannot find __host__ __device__ functions (6)

What is the recommended type <: Integer to use when doing index arithmetics? (4)

Packing structs for OpenCL (2)

Sequence of warp and how to avoid divergence when folding shared memory in a reduction kernel (4)

Constant Memory? (12)

Generic Kernels for CLArrays (2)