Skip to content

GitLab

Commit fa5a501f authored by Anthony Chang's avatar Anthony Chang
Browse files

format

parent 33beec37
Show whitespace changes
Inline Side-by-side
Showing with 19 additions and 18 deletions
include/ck/tensor_operation/gpu/device/device_gemm_reduce_xdl_cshuffle.hpp
View file @ fa5a501f
...@@ -15,7 +15,8 @@ namespace tensor_operation { ...@@ -15,7 +15,8 @@ namespace tensor_operation {
namespace device { namespace device {
// Note: inter-wave loop scheduler is rolled out to c-shuffle version first. Becuase non c-shuffle // Note: inter-wave loop scheduler is rolled out to c-shuffle version first. Becuase non c-shuffle
// version currently has compiler issues with register spill which further causes validation failures. // version currently has compiler issues with register spill which further causes validation
// failures.
template <typename ALayout, template <typename ALayout,
typename BLayout, typename BLayout,
typename CLayout, typename CLayout,
......
include/ck/tensor_operation/gpu/device/device_gemm_xdl_cshuffle.hpp
View file @ fa5a501f
...@@ -15,7 +15,8 @@ namespace tensor_operation { ...@@ -15,7 +15,8 @@ namespace tensor_operation {
namespace device { namespace device {
// Note: inter-wave loop scheduler is rolled out to c-shuffle version first. Becuase non c-shuffle // Note: inter-wave loop scheduler is rolled out to c-shuffle version first. Becuase non c-shuffle
// version currently has compiler issues with register spill which further causes validation failures. // version currently has compiler issues with register spill which further causes validation
// failures.
template <typename ALayout, template <typename ALayout,
typename BLayout, typename BLayout,
typename CLayout, typename CLayout,
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_pipeline_v1.hpp
View file @ fa5a501f
...@@ -276,8 +276,7 @@ struct GridwiseGemmPipelineInterwave_v1<1> ...@@ -276,8 +276,7 @@ struct GridwiseGemmPipelineInterwave_v1<1>
typename BBlockTransferStep, typename BBlockTransferStep,
typename BlockwiseGemm, typename BlockwiseGemm,
typename CThreadBuffer> typename CThreadBuffer>
static __device__ void static __device__ void Run(const AGridDesc& a_grid_desc,
Run(const AGridDesc& a_grid_desc,
const ABlockDesc& a_block_desc, const ABlockDesc& a_block_desc,
ABlockTransfer& a_blockwise_copy, ABlockTransfer& a_blockwise_copy,
const AGridBuffer& a_grid_buf, const AGridBuffer& a_grid_buf,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment