leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

CUTLASS 2.3 initial commit (#134)

Browse Source 
CUTLASS 2.3 adds GEMMs targeting Sparse Tensor Cores on the NVIDIA Ampere Architecture, fast SGEMM, and small matrix classes, bug fixes, and performance enhancements.
This commit is contained in:
Andrew Kerr
2020-09-23 14:00:58 -07:00
committed by GitHub
parent 4dac7490e6
commit c53f3339bb
209 changed files with 46922 additions and 1677 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
CUDA.cmake
View File

@@ -213,7 +213,14 @@ function(cutlass_correct_source_file_language_property)
endif()
endfunction()
set(CUTLASS_UNITY_BUILD_ENABLED OFF CACHE BOOL "Enable combined source compilation")
# If building with all kernels, set UNITY build on by default.
if (CUTLASS_LIBRARY_KERNELS MATCHES "all")
set(CUTLASS_UNITY_BUILD_ENABLED_INIT ON)
else()
set(CUTLASS_UNITY_BUILD_ENABLED_INIT OFF)
endif()
set(CUTLASS_UNITY_BUILD_ENABLED ${CUTLASS_UNITY_BUILD_ENABLED_INIT} CACHE BOOL "Enable combined source compilation")
set(CUTLASS_UNITY_BUILD_BATCH_SIZE 16 CACHE STRING "Batch size for unified source files")
function(cutlass_unify_source_files TARGET_ARGS_VAR)