Skip to content
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

Improve block and thread calculations and invoke only if in range #76

Merged
merged 1 commit into from
Apr 18, 2024
Merged

Improve block and thread calculations and invoke only if in range #76

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
18 changes: 12 additions & 6 deletions ext/JACCCUDA/JACCCUDA.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,10 +6,14 @@ using JACC, CUDA
include("array.jl")

function JACC.parallel_for(N::I, f::F, x...) where {I <: Integer, F <: Function}
maxPossibleThreads = attribute(device(), CUDA.DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X)
threads = min(N, maxPossibleThreads)
blocks = ceil(Int, N / threads)
CUDA.@sync @cuda threads = threads blocks = blocks _parallel_for_cuda(f, x...)
parallel_args = (N, f, x...)
parallel_kargs = cudaconvert.(parallel_args)
parallel_tt = Tuple{Core.Typeof.(parallel_kargs)...}
parallel_kernel = cufunction(_parallel_for_cuda, parallel_tt)
maxPossibleThreads = CUDA.maxthreads(parallel_kernel)
threads = min(N, maxPossibleThreads)
blocks = ceil(Int, N / threads)
parallel_kernel(parallel_kargs...; threads=threads, blocks=blocks)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this guarantee to be synchronized?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't know :)

end

function JACC.parallel_for((M, N)::Tuple{I, I}, f::F, x...) where {I <: Integer, F <: Function}
Expand Down Expand Up @@ -46,9 +50,11 @@ function JACC.parallel_reduce((M, N)::Tuple{I, I}, f::F, x...) where {I <: Integ
return rret
end

function _parallel_for_cuda(f, x...)
function _parallel_for_cuda(N, f, x...)
i = (blockIdx().x - 1) * blockDim().x + threadIdx().x
f(i, x...)
if i <= N
f(i, x...)
end
return nothing
end

Expand Down