zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-06-24 01:17:26 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add profiler annotations in common primitives for CUDA backend (#2244)

Browse Source
This commit is contained in:
Cheng 2025-06-05 11:55:12 +09:00 committed by GitHub
parent aede70e81d
commit 52dc8c8cd5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mlx/backend/cuda/CMakeLists.txt
View File

@ -17,6 +17,8 @@ target_sources(
${CMAKE_CURRENT_SOURCE_DIR}/utils.cpp
${CMAKE_CURRENT_SOURCE_DIR}/worker.cpp)
target_compile_definitions(mlx PRIVATE MLX_USE_CUDA)
# Enable defining device lambda functions.
target_compile_options(mlx
PRIVATE "$<$<COMPILE_LANGUAGE:CUDA>:--extended-lambda>")

8
mlx/backend/gpu/primitives.cpp
View File

@ -5,9 +5,17 @@
#include "mlx/backend/gpu/copy.h"
#include "mlx/backend/gpu/slicing.h"
#if defined(MLX_USE_CUDA)
#include <nvtx3/nvtx3.hpp>
#endif
#include <cassert>
#if defined(MLX_USE_CUDA)
#define MLX_PROFILER_RANGE(message) nvtx3::scoped_range r(message)
#else
#define MLX_PROFILER_RANGE(message)
#endif
namespace mlx::core {