CUDAnative.jl

CUDAnative.jl copied to clipboard

This PR contains an initial implementation of (my proposal for) an API to instantiate flexible matrix multiplication kernels. It is divided in two large parts: - A Tiling API that...

thomasfaingnaert

This pull request updates the manifest for Julia v1.3.1: ``` Project CUDAnative v3.1.0 Status `~/work/CUDAnative.jl/CUDAnative.jl/Project.toml` [79e6a3ab] Adapt v1.0.1 [b99e7846] ↑ BinaryProvider v0.5.9 ⇒ v0.5.10 [fa961155] CEnum v0.3.0 [3895d2a7] CUDAapi v4.0.0...

github-actions[bot]

WIP: Use contextual dispatch for replacing functions

57

On 1.1 Cassette should be performant enough for these kinds of transforms. Fixes https://github.com/JuliaGPU/CUDAnative.jl/issues/27 @maleadt did you have a branch similar to this around?

vchuravy

WIP: Support custom allocators, implement a bump allocator

10

This PR allows `@cuda` callers to pick a custom allocation function and implements a bump allocator, as per your request, @maleadt, in #419. I also threw in an example program...

jonathanvdc

EXPERIMENTAL: Implement a GC

3

Hi! Here's a PR that implements a garbage collector for CUDAnative. Major additions include: * The garbage collector itself (`gc.jl`). The GC is a non-moving, semi-conservative, stop-the-world GC that uses...

jonathanvdc

Deprecate atan2

3

To be consistent with Julia's `atan(x, y)` function, I renamed `atan2` to `atan`. Here's the help message for atan: ``` atan(y) atan(y, x) Compute the inverse tangent of y or...

benchislett