mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-24 06:44:36 +00:00
Improve normalization (#580)
* Sync the order of type string with template parameter
* Add more instances
* Check the vector size and remove redundant var
* Extract var to static, prepare to separate sweep once kernel
* Separate sweeponce flow and optimize the flow
* 1. Rename AccDatatype in normalization to computeData
2. Rename AccElementwiseOperation to YElementwiseOperation in normalization
* Remove useless code
* Update naive variance kernel
* Refine string
* Fix typo
* Support naive variance for device_normalization
* Check the blocksize
* Share the VGPR of x and y
* Share the VGPR of gamma and beta
* Add more instances
* Support fp16 sqrt for experiment
* Add CHANGELOG
* Fix typo
* clang-format
[ROCm/composable_kernel commit: 6a6163a3d1]
This commit is contained in:
@@ -12,12 +12,12 @@
|
||||
|
||||
#include "ck/library/tensor_operation_instance/gpu/normalization.hpp"
|
||||
|
||||
using XDataType = ck::half_t;
|
||||
using GammaDataType = ck::half_t;
|
||||
using BetaDataType = ck::half_t;
|
||||
using YDataType = ck::half_t;
|
||||
using AccDataType = float;
|
||||
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
||||
using XDataType = ck::half_t;
|
||||
using GammaDataType = ck::half_t;
|
||||
using BetaDataType = ck::half_t;
|
||||
using YDataType = ck::half_t;
|
||||
using ComputeDataType = float;
|
||||
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
||||
|
||||
constexpr int Rank = 2;
|
||||
constexpr int NumReduceDim = 1;
|
||||
@@ -54,7 +54,7 @@ int main(int argc, char* argv[])
|
||||
using DeviceOp = ck::tensor_operation::device::DeviceNormalization<XDataType,
|
||||
GammaDataType,
|
||||
BetaDataType,
|
||||
AccDataType,
|
||||
ComputeDataType,
|
||||
YDataType,
|
||||
PassThrough,
|
||||
Rank,
|
||||
|
||||
Reference in New Issue
Block a user