Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 2 additions & 22 deletions Project.toml
Original file line number Diff line number Diff line change
@@ -1,42 +1,22 @@
name = "DaggerGPU"
uuid = "68e73e28-2238-4d5a-bf97-e5d4aa3c4be2"
authors = ["Julian P Samaroo <[email protected]>"]
version = "0.2.0"
version = "0.2.1"

[deps]
AMDGPU = "21141c5a-9bdb-4563-92ae-f87d6854732e"
Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
Dagger = "d58978e5-989f-55fb-8d15-ea34adc7bf54"
Distributed = "8ba89e20-285c-5b6f-9357-94700520ee1b"
KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
MemPool = "f9f48841-c794-520a-933b-121f7ba6ed94"
Metal = "dde4c033-4e86-420c-a63e-0dd931031962"
oneAPI = "8f75cd03-7ff8-4ecb-9b8f-daf728133b1b"
Requires = "ae029012-a4dd-5104-9daa-d747884805df"
UUIDs = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"

[weakdeps]
AMDGPU = "21141c5a-9bdb-4563-92ae-f87d6854732e"
CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
Metal = "dde4c033-4e86-420c-a63e-0dd931031962"
oneAPI = "8f75cd03-7ff8-4ecb-9b8f-daf728133b1b"

[extensions]
CUDAExt = "CUDA"
IntelExt = "oneAPI"
MetalExt = "Metal"
ROCExt = "AMDGPU"

[compat]
AMDGPU = "0.9.4"
Adapt = "1, 2, 3, 4"
CUDA = "3, 4, 5"
Dagger = "0.18.12"
Dagger = "0.18.17"
KernelAbstractions = "0.9"
MemPool = "0.3, 0.4"
Metal = "1.1"
oneAPI = "1"
Requires = "1"
julia = "1.7"
6 changes: 6 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,12 @@

**GPU integrations for Dagger.jl**

## Deprecation Notice

DaggerGPU's logic and extensions have been merged upstream into Dagger.jl, making DaggerGPU no longer necessary. You can now load CUDA logic with `using Dagger, CUDA`, and similarly for all other backends. Please report all issues to the [Dagger issue tracker](https://github.com/JuliaParallel/Dagger.jl/issues).

## Original README

DaggerGPU.jl makes use of the `Dagger.Processor` infrastructure to dispatch Dagger kernels to NVIDIA, AMD, and Apple GPUs, via CUDA.jl, AMDGPU.jl, and Metal.jl respectively. Usage is simple: `add` or `dev` DaggerGPU.jl and CUDA.jl/AMDGPU.jl/Metal.jl appropriately, load it with `using DaggerGPU`, and add `DaggerGPU.CuArrayDeviceProc`/`DaggerGPU.ROCArrayProc`/`DaggerGPU.MtlArrayDeviceProc` to your scheduler or thunk options (see Dagger.jl documentation for details on how to do this).

DaggerGPU.jl is still experimental, but we welcome GPU-owning users to try it out and report back on any issues or sharp edges that they encounter. When filing an issue about DaggerGPU.jl, please provide:
Expand Down
Loading