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

Use KernelAbstractions.jl for upsample kernels #486

Merged
merged 11 commits into from
Apr 10, 2023
Merged

Use KernelAbstractions.jl for upsample kernels #486

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
d0b2e11
Use KernelAbstractions.jl for upsample kernels
pxl-th Apr 5, 2023
5e6cd97
Remove upsample from NNlibCUDA.jl
pxl-th Apr 5, 2023
4c5f827
Remove allocation in '∇upsample_linear'
pxl-th Apr 6, 2023
efedbc1
Change indexing order
pxl-th Apr 6, 2023
e496616
Specialize kernels for CPU & GPU
pxl-th Apr 6, 2023
97fb365
Remove @atomic for CPU
pxl-th Apr 6, 2023
7cc9524
Fixes
pxl-th Apr 6, 2023
f30fb37
Add compatibility layers back
pxl-th Apr 6, 2023
a39d91b
Refactor to use 'cpu' & 'device' functions
pxl-th Apr 10, 2023
5fbf12f
Refactor
pxl-th Apr 10, 2023
bf4d6cf
Optimize CPU kernels
pxl-th Apr 10, 2023
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 @@ -5,6 +5,7 @@ version = "0.8.19"
[deps]
Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
KernelAbstractions = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
Pkg = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
Expand All @@ -21,6 +22,7 @@ NNlibAMDGPUExt = "AMDGPU"
AMDGPU = "0.4.8"
Adapt = "2, 3.2"
ChainRulesCore = "1.13"
KernelAbstractions = "0.9"
Requires = "0.5, 1.0"
julia = "1.6"

Expand Down
1 change: 0 additions & 1 deletion ext/NNlibCUDA/src/NNlibCUDA.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@ using Random, Statistics

const IntOrIntTuple = Union{Integer, NTuple{N,<:Integer} where N}

include("upsample.jl")
include("sampling.jl")
include("activations.jl")
include("batchedadjtrans.jl")
Expand Down
361 changes: 0 additions & 361 deletions ext/NNlibCUDA/src/upsample.jl
View file
Open in desktop

This file was deleted.

1 change: 0 additions & 1 deletion ext/NNlibCUDA/test/runtests.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,6 @@ include("activations.jl")
include("dropout.jl")
include("batchedadjtrans.jl")
include("batchedmul.jl")
include("upsample.jl")
include("conv.jl")
include("ctc.jl")
include("fold.jl")
Expand Down
Loading