Strange behavior of `mapreduce`
CUDAnative support for Float16
How to time CUDA Event
cuArrays vs CUDANative
Freeing memory in the GPU with CUDAdrv / CUDAnative / CuArrays
How to set the diagonal part of a GPU Array
Performance of view with cuArrays
Is is possible to merge multiple kernels in CUDAnative to minimize launch overhead and execution overhead?
Shared library errors when using optirun
Is there any plan for GPU linear algebra?
Maintaining OpenCL packages
Support for Complex-valued CuArray
Can not use CuArray on Julia 0.7
Support for Sparse Matrices on GPU (CUSPARSE)
Optimizing the use of Blocks, Threads vs. Array Indexing
Package use, CUDA stream support, etc
Flux four errors in Julia v0.7 none in v0.6.4
Computing eigenvalues/eigenvectors using GPU?
CUDAnative question: "recursion not currently supported error" when running reduce.jl example
CuArray and Optim
GPUArrays, 64-32bit conversions, and Cassete.jl
LLVM crash when running Flux and CuArray examples in julia 0.7
Flux: GPU slower than CPU?
CLBlast, a tuned OpenCL BLAS library
CUDAdrv cannot find __host__ __device__ functions
What is the recommended type <: Integer to use when doing index arithmetics?
Packing structs for OpenCL
Sequence of warp and how to avoid divergence when folding shared memory in a reduction kernel
Generic Kernels for CLArrays
← previous page
next page →