Skip to content

GitLab

Commit 18ba135f authored by Po-Yen, Chen's avatar Po-Yen, Chen
Browse files

Add N/H/WPerBlock template parameter to 'DevicePermute'

parent b8abc3e3
Hide whitespace changes
Inline Side-by-side
Showing with 11 additions and 5 deletions
example/36_permute/permute_fp16.cpp
View file @ 18ba135f
...@@ -8,11 +8,11 @@ using BDataType = F16; ...@@ -8,11 +8,11 @@ using BDataType = F16;
// clang-format off // clang-format off
using DevicePermuteInstance = ck::tensor_operation::device::DevicePermute using DevicePermuteInstance = ck::tensor_operation::device::DevicePermute
// ######| InData| OutData| Elementwise| NumDim| MPerThread| InScalar| OutScalar| // ######| InData| OutData| Elementwise| NumDim| NPer| HPer| WPer|MPerThread| InScalar| OutScalar|
// ######| Type| Type| Operation| | | PerVector| PerVector| // ######| Type| Type| Operation| | Block| Block| Block| | PerVector| PerVector|
// ######| | | | | | | | // ######| | | | | | | | | | |
// ######| | | | | | | | // ######| | | | | | | | | | |
< ADataType, BDataType, PassThrough, 4, 8, 8, 1>; < ADataType, BDataType, PassThrough, 4, 128, 128, 128, 8, 8, 1>;
// clang-format on // clang-format on
#include "run_permute_example.inc" #include "run_permute_example.inc"
......
include/ck/tensor_operation/gpu/device/device_permute.hpp
View file @ 18ba135f
...@@ -77,6 +77,9 @@ template <typename InDataType, ...@@ -77,6 +77,9 @@ template <typename InDataType,
typename OutDataType, typename OutDataType,
typename ElementwiseOperation, typename ElementwiseOperation,
index_t NumDim, index_t NumDim,
index_t NPerBlock,
index_t HPerBlock,
index_t WPerBlock,
index_t MPerThread, index_t MPerThread,
index_t InScalarPerVector, index_t InScalarPerVector,
index_t OutScalarPerVector> index_t OutScalarPerVector>
...@@ -84,6 +87,9 @@ struct DevicePermute : detail::DevicePermuteBase<DevicePermute<InDataType, ...@@ -84,6 +87,9 @@ struct DevicePermute : detail::DevicePermuteBase<DevicePermute<InDataType,
OutDataType, OutDataType,
ElementwiseOperation, ElementwiseOperation,
NumDim, NumDim,
NPerBlock,
HPerBlock,
WPerBlock,
MPerThread, MPerThread,
InScalarPerVector, InScalarPerVector,
OutScalarPerVector>> OutScalarPerVector>>
......
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