Faster synchronization Fence primitive (#1773)

* try faster synchronization

move event

fixes

update bench

fix

fix

* non-functioning kernel

* try alternative fence

* cleanup barrier

* get rid of event_fence

* update benchmarks

* doc string in metal fence
This commit is contained in:
Awni Hannun
2025-01-17 18:42:19 -08:00
committed by GitHub
parent 0c259961ac
commit a4667da1eb
11 changed files with 362 additions and 31 deletions

View File

@@ -89,6 +89,7 @@ target_sources(
${CMAKE_CURRENT_SOURCE_DIR}/distributed.cpp
${CMAKE_CURRENT_SOURCE_DIR}/device.cpp
${CMAKE_CURRENT_SOURCE_DIR}/event.cpp
${CMAKE_CURRENT_SOURCE_DIR}/fence.cpp
${CMAKE_CURRENT_SOURCE_DIR}/fft.cpp
${CMAKE_CURRENT_SOURCE_DIR}/hadamard.cpp
${CMAKE_CURRENT_SOURCE_DIR}/indexing.cpp