Skip to content

[FEATURE] Fused NEON WaveNet engine for AArch64 (Apple Silicon) #308

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

Open
rikkus wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[FEATURE] Fused NEON WaveNet engine for AArch64 (Apple Silicon) #308

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
5 changes: 5 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,3 +37,8 @@ docs/_build/
*.DS_Store

example_audio/output.wav

# Local build and benchmark artifacts
build/
build_nofused/
benchmark_reports/tmp_models/
10 changes: 10 additions & 0 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,16 @@ if(NAM_ENABLE_A2_FAST)
add_compile_definitions(NAM_ENABLE_A2_FAST)
endif()

# Build the fused NEON WaveNet engine. When ON, standard-shape WaveNet models
# (e.g. the A1 standard/lite/feather family and A2 standard) are routed to a
# fused, register-tiled NEON implementation on AArch64 (Apple Silicon etc.).
# On other architectures the flag is harmless: the shape detector returns
# false and all models use the generic path.
option(NAM_ENABLE_FUSED "Build the fused NEON WaveNet engine" ON)
if(NAM_ENABLE_FUSED)
add_compile_definitions(NAM_ENABLE_FUSED)
endif()

add_subdirectory(tools)

#file(MAKE_DIRECTORY build/tools)
Expand Down
Loading