Run sycl ampere example on cuda

codeplaysoftware · May 20, 2024 · 00db8f6 · 00db8f6
1 parent 7180fae
commit 00db8f6
Show file tree

Hide file tree

Showing 5 changed files with 4 additions and 3 deletions.
diff --git a/examples/CMakeLists.txt b/examples/CMakeLists.txt
@@ -164,6 +164,7 @@ else()
     57_hopper_grouped_gemm
     58_ada_fp8_gemm
     59_ampere_gather_scatter_conv
+    sycl
   )
 
     add_subdirectory(${EXAMPLE})

diff --git a/examples/sycl/CMakeLists.txt b/examples/sycl/CMakeLists.txt
@@ -29,6 +29,6 @@
 
 if(SYCL_INTEL_TARGET)
   add_subdirectory(pvc)
-else(SYCL_NVIDIA_TARGET)
+else()
   add_subdirectory(ampere)
 endif()
diff --git a/examples/sycl/ampere/CMakeLists.txt b/examples/sycl/ampere/CMakeLists.txt
@@ -29,10 +29,10 @@
 
 cutlass_example_add_executable(
   ampere_gemm_fp16_fp16_fp32_tensor_op_fp32
-  ampere_gemm_fp16_fp16_fp32_tensor_op_fp32.cpp
+  ampere_gemm_fp16_fp16_fp32_tensor_op_fp32.cu
 )
 
 cutlass_example_add_executable(
   ampere_gemm_bf16_bf16_fp32_tensor_op_fp32
-  ampere_gemm_bf16_bf16_fp32_tensor_op_fp32.cpp
+  ampere_gemm_bf16_bf16_fp32_tensor_op_fp32.cu
 )
diff --git a/...re_gemm_bf16_bf16_fp32_tensor_op_fp32.cpp → ...ere_gemm_bf16_bf16_fp32_tensor_op_fp32.cu b/...re_gemm_bf16_bf16_fp32_tensor_op_fp32.cpp → ...ere_gemm_bf16_bf16_fp32_tensor_op_fp32.cu
diff --git a/...re_gemm_fp16_fp16_fp32_tensor_op_fp32.cpp → ...ere_gemm_fp16_fp16_fp32_tensor_op_fp32.cu b/...re_gemm_fp16_fp16_fp32_tensor_op_fp32.cpp → ...ere_gemm_fp16_fp16_fp32_tensor_op_fp32.cu