v0.2.1

AcceleratedKernels v0.2.1

Diff since v0.2.0

Merged pull requests:

• Add Buildkite CI for CUDA (#9) (@jpsamaroo)
• added foreach + tests. Started updating indices within kernels to use… local types without int64 promotions - about 25% faster in sort for example. Set default block_size to 256 (#11) (@anicusan)

Closed issues:

• Support for a :serial scheduler (#7)

v0.2.0

AcceleratedKernels v0.2.0

• N-dimensional reduce and mapreduce
• map
• docs + and tests for each of the above.
• In-place functions now also return the modified argument as in Base.

Diff since v0.1.0

Merged pull requests:

• Update deps (#8) (@pxl-th)

v0.1.0

AcceleratedKernels v0.1.0

Merged pull requests:

• Remove unnecessary Const (#3) (@pxl-th)
• Remove redundant Const and inbounds macros (#4) (@pxl-th)

Closed issues:

• Use GPUArraysCore? (#1)
• Invalid IR for sortperm! on AMDGPU (#2)

0.1.0

First release of AcceleratedKernels.jl, for archiving purposes supporting the "AcceleratedKernels.jl: Cross-Architecture Parallel Algorithms from a Unified, Transpiled Codebase" paper.