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

Jump to bottom

Fixing transpose function, a missing "end" and some argument orders. #487

Merged
merged 2 commits into from
Jul 1, 2024
Merged

Fixing transpose function, a missing "end" and some argument orders. #487

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
db8b8e7
Fixing transpose function, a missing "end" and some argument orders.
Sixzero Jun 26, 2024
a11e226
Update performance.jl
Sixzero Jun 27, 2024
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
9 changes: 5 additions & 4 deletions examples/performance.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ end

@kernel function simple_transpose_kernel!(output, @Const(input))
I, J = @index(Global, NTuple)
@inbounds output[I, J] = input[I, J]
@inbounds output[J, I] = input[I, J]
end

# Local memory variants
Expand Down Expand Up @@ -143,7 +143,8 @@ for block_dims in ((TILE_DIM, TILE_DIM), (TILE_DIM*TILE_DIM, 1), (1, TILE_DIM*TI
# compile kernel
kernel(input, output, ndrange=size(output))
for rep in 1:nreps
KernelAbstractions.synchronize(backend)
KernelAbstractions.synchronize(backend)
vchuravy marked this conversation as resolved.
Show resolved Hide resolved
end
end
end
end
Expand All @@ -161,7 +162,7 @@ for (name, kernel) in (
# compile kernel
kernel(input, output, Val(Int(bank)), ndrange=size(output))
for rep in 1:nreps
kernel(input, output, Val(Int(bank)), ndrange=size(output))
kernel(output, input, Val(Int(bank)), ndrange=size(output))
vchuravy marked this conversation as resolved.
Show resolved Hide resolved
end
KernelAbstractions.synchronize(backend)
end
Expand All @@ -187,7 +188,7 @@ for (name, kernel) in (
# compile kernel
kernel(input, output, Val(Int(bank)), ndrange=ndrange)
for rep in 1:nreps
kernel(input, output, Val(Int(bank)), ndrange=ndrange)
kernel(output, input, Val(Int(bank)), ndrange=ndrange)
end
KernelAbstractions.synchronize(backend)
end
Expand Down