Updates for 3.1 (#932)

This commit is contained in:
ANIKET SHIVAM
2023-04-29 09:34:27 -04:00
committed by GitHub
parent 6f8596ce3f
commit 7c04f95415
51 changed files with 1796 additions and 328 deletions
+11
View File
@@ -41,6 +41,7 @@ add_custom_target(
cutlass_test_unit_gemm_device_tensorop_planar_complex
cutlass_test_unit_gemm_device_sparse_tensorop_sm80
cutlass_test_unit_gemv_device
cutlass_test_unit_gemv_device_strided_batched
cutlass_test_unit_gemm_device_tensorop_sm90
cutlass_test_unit_gemm_device_tensorop_cluster_multicast_sm90
)
@@ -60,6 +61,7 @@ add_custom_target(
test_unit_gemm_device_tensorop_planar_complex
test_unit_gemm_device_sparse_tensorop_sm80
test_unit_gemv_device
test_unit_gemv_device_strided_batched
test_unit_gemm_device_tensorop_sm90
)
@@ -498,6 +500,15 @@ cutlass_test_unit_add_executable(
gemv.cu
)
cutlass_test_unit_add_executable(
cutlass_test_unit_gemv_device_strided_batched
BATCH_SOURCES ON
BATCH_SIZE 4
gemv_strided_batched.cu
)
if (NOT CUDA_COMPILER MATCHES "[Cc]lang")
add_dependencies(