Skip to content

Define shared memory for oneAPI (Flash attention on Intel GPUs) #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Define shared memory for oneAPI (Flash attention on Intel GPUs) #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,12 @@ StaticArrays = "90137ffa-7385-5640-81b9-e52037218182"
[weakdeps]
AMDGPU = "21141c5a-9bdb-4563-92ae-f87d6854732e"
CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
oneAPI = "8f75cd03-7ff8-4ecb-9b8f-daf728133b1b"

[extensions]
NNopAMDGPUExt = "AMDGPU"
NNopCUDAExt = "CUDA"
NNoponeAPIExt = "oneAPI"

[compat]
AMDGPU = "1.2.5, 2"
Expand Down
11 changes: 11 additions & 0 deletions ext/NNoponeAPIExt.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
module NNoponeAPIExt

using oneAPI
using NNop

function NNop._shared_memory(::oneAPIBackend, device_id::Integer)
dev = oneAPI.devices()[device_id]
return UInt64(oneAPI.compute_properties(dev).maxSharedLocalMemory)
end

end
5 changes: 5 additions & 0 deletions test/runtests.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ import Pkg

#ENV["NNOP_TEST_AMDGPU"] = true
#ENV["NNOP_TEST_CUDA"] = true
#ENV["NNOP_TEST_ONEAPI"] = true

if get(ENV, "NNOP_TEST_AMDGPU", "false") == "true"
Pkg.add("AMDGPU")
Expand All @@ -18,6 +19,10 @@ elseif get(ENV, "NNOP_TEST_CUDA", "false") == "true"
Pkg.add("CUDA")
using CUDA
kab = CUDABackend()
elseif get(ENV, "NNOP_TEST_ONEAPI", "false") == "true"
Pkg.add("oneAPI")
using oneAPI
kab = oneAPIBackend()
else
error("No GPU backend is set.")
end
Expand Down