mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-19 20:40:07 +00:00
Transpose profiler fix (#1114)
* added working example for 5D input using 1D kernel
* example with 5D input tensor and 2d kernel - not working: issues with arguments
* added updated version of 3d device op - changed descriptors/dims
* added example file to check kernel
* fixed descriptor and isSupportedArgument stride problem
* added and modified kernel for 3d - updated tids/loop
* adding some more 5d example files
* fixed some issues
* changes made for testing
* working version: fixed error in stride for A, still a bit inefficient
* cleaned up formatting/comments
* updating formatting
* more formatting fixes
* fixing cmake, adding back gpu targets in cmake script
* adding client example
* added instances for client example
* fixed errors in client example
* implemented client ex with device_elementwise.hpp and device_elementwise_3d_impl.hpp
* removed extra files
* minor formatting and naming fixes
* adding test files and profiler
* fixing minor error
* minor fix
* removed unneccesary comments, renamed files
* updated instance list for client example, added different layout example
* removing instances
* fixed error in instance generation
* remove comments
* update profiler and client example tensor layouts
* fixed errors in test/profiler
* updated vector dim access to enable vector load
* updated test/profiler files
* updated example with 1d kernel
* updating profiler
* renamed files
* disabled device op for MI300
* skip elementwise_permute_2d on gfx94x
* Update CMakeLists.txt
* fixing CMake - disabling some GPU targets
* added transpose profiler to CMake
* fixed transpose profiler errors
* fixed instances for tests/profiler
* cleaned up code in transpose profiler source code
* added some comments, updated copyright
* made function arguments const where possible
---------
Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: Jing Zhang <jizhan@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
[ROCm/composable_kernel commit: aa3e2d7967]
This commit is contained in:
@@ -14,8 +14,8 @@
|
||||
using F16 = ck::half_t;
|
||||
using F32 = float;
|
||||
|
||||
using ADataType = F16;
|
||||
using BDataType = F16;
|
||||
using ADataType = F32;
|
||||
using BDataType = F32;
|
||||
|
||||
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
||||
using DeviceElementwisePermuteInstance =
|
||||
@@ -25,10 +25,10 @@ using DeviceElementwisePermuteInstance =
|
||||
2, // NumDim_m, {N, C}
|
||||
2, // NumDim_n, {H, W}
|
||||
1, // NumDim_k, {D}
|
||||
8, // MPerThread
|
||||
8, // NPerThread
|
||||
8, // KPerThread
|
||||
ck::Sequence<8>, // InScalarPerVectorSeq
|
||||
4, // MPerThread
|
||||
4, // NPerThread
|
||||
4, // KPerThread
|
||||
ck::Sequence<4>, // InScalarPerVectorSeq
|
||||
ck::Sequence<4>>; // OutScalarPerVectorSeq
|
||||
|
||||
template <typename HostTensorA, typename HostTensorB, typename Functor>
|
||||
|
||||
Reference in New Issue
Block a user