CUTLASS 2.7 (#318)

CUTLASS 2.7

Mainloop fusion for GEMM: summation over A or B
Strided DGRAD (optimized iterators)
Half-precision GELU_taylor activation functions
Use these when accumulation and epilogue compute types are all cutlass::half_t
Tuning and bug fixes to fused GEMM + GEMM example
Support for smaller than 128b aligned Convolutions: see examples
Caching of results to accelerate Convolution unit tests
Can be enabled or disabled by running cmake .. -DCUTLASS_TEST_ENABLE_CACHED_RESULTS=OFF
Corrections and bug fixes reported by the CUTLASS community
Thank you for filing these issues!

authored-by: Haicheng Wu haichengw@nvidia.com, Manish Gupta manigupta@nvidia.com, Dustyn Blasig dblasig@nvidia.com, Andrew Kerr akerr@nvidia.com

test/unit/CMakeLists.txt

@@ -49,6 +49,8 @@ target_link_libraries(
   cutlass_test_unit_infra
   )
 
+set(CUTLASS_TEST_UNIT_RESULTS_CACHE_DIR ${CMAKE_CURRENT_LIST_DIR}/data/hashes)
+
 function(cutlass_test_unit_add_executable NAME)
 
   set(options)
@@ -58,6 +60,8 @@ function(cutlass_test_unit_add_executable NAME)
 
   cutlass_add_executable(${NAME} ${__UNPARSED_ARGUMENTS})
 
+  target_compile_definitions(${NAME} PUBLIC CUTLASS_TARGET_NAME="${NAME}")
+
   target_link_libraries(
     ${NAME}
     PRIVATE
@@ -67,11 +71,18 @@ function(cutlass_test_unit_add_executable NAME)
 
   string(REGEX REPLACE cutlass_ "" NAME_STEM ${NAME})
 
+  set(RESULT_CACHE_FILE "${CUTLASS_TEST_UNIT_RESULTS_CACHE_DIR}/cached_results_${NAME}.txt")
+
+  if (EXISTS ${RESULT_CACHE_FILE})
+    set(RESULT_CACHE_FILE_ARGS RESULT_CACHE_FILE ${RESULT_CACHE_FILE})
+  endif()
+
   set(CUTLASS_TEST_UNIT_TEST_COMMAND_OPTIONS --gtest_output=xml:${NAME_STEM}.gtest.xml)
 
   cutlass_add_executable_tests(
-    ${NAME_STEM} ${NAME} 
+    ${NAME_STEM} ${NAME}
     TEST_COMMAND_OPTIONS CUTLASS_TEST_UNIT_TEST_COMMAND_OPTIONS
+    ${RESULT_CACHE_FILE_ARGS}
     )
 
 endfunction()