leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 24 Packages Projects Releases Wiki Activity

CUTLASS 2.6 (#298)

Browse Source 
CUTLASS 2.6
This commit is contained in:
Manish Gupta
2021-07-23 00:40:53 -04:00
committed by GitHub
parent 6c29fe20ba
commit e5d51840e8
308 changed files with 32408 additions and 4722 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/unit/conv/device/CMakeLists.txt
+8 -2
View File
@@ -141,6 +141,9 @@ cutlass_test_unit_add_executable(
conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm75.cu
conv2d_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm75.cu
conv2d_wgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm75.cu
conv2d_fprop_with_broadcast_sm75.cu
conv2d_fprop_with_reduction_sm75.cu
)
if (CUTLASS_NVCC_MAX_ARCH GREATER_EQUAL 80)
@@ -158,15 +161,18 @@ if (CUTLASS_NVCC_MAX_ARCH GREATER_EQUAL 80)
cutlass_test_unit_add_executable(
cutlass_test_unit_conv_device_tensorop_f32_sm80
conv2d_fprop_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
conv2d_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
conv2d_wgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
conv3d_wgrad_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm75.cu
conv3d_wgrad_implicit_gemm_f16ndhwc_f16ndhwc_f32ndhwc_tensor_op_f32_sm80.cu
# Strided Dgrad
conv2d_strided_dgrad_implicit_gemm_f16nhwc_f16nhwc_f32nhwc_tensor_op_f32_sm80.cu
)
# Conv2d - TF32 input, F32 output, F32 accumulation
cutlass_test_unit_add_executable(