mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 05:31:24 +00:00
Adding Instances and Examples for FP8-based Scaled Convolution and AMAX Reduction. (#1473)
* Enable CMakePresets build * Verify Convolution, Scaling and ReLU algorithms. * Add tensor element-wise scale and type cast operation. * Reduction implemented but does not work. * Exploration of Reduction functionality. * Completed example for Convolution scaled with ReLu activation and AMAX reduction. * WIP: Add required instances for convolution. * WIP: Create client example. Implement convolution stage. * Add elementwise instances. * Add elementwise scale + convert example. * Add reduction instances. * WIP: Client example for AMAX reduction. * WIP: Add instances for multistage reduction. * WIP: Implementation of multistage reduction. * Refactoring. * Clean up. * Add CMakePresets.json * Guard off FP8 instances when the data type is not available. * Add example for Scaled FP8 Convolution with AMAX reduction. * Refactor CombConvScaleRelu instances. * Add CombConvScale instances. * Add client example for Scaled FP8 Convolution with AMAX reduction. * Cleanup.
This commit is contained in:
committed by
GitHub
parent
e20f20efbf
commit
c3515f277c
@@ -3,7 +3,6 @@
|
||||
|
||||
#pragma once
|
||||
|
||||
#include "ck/utility/data_type.hpp"
|
||||
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
||||
|
||||
namespace ck {
|
||||
@@ -107,6 +106,9 @@ struct TrinaryWithUnaryCombinedOp
|
||||
UnaryOp2 unary_op2_{};
|
||||
};
|
||||
|
||||
using ScaleScalePass = UnaryCombinedOp<Scale, Scale, PassThrough>;
|
||||
using ScaleScaleRelu = UnaryCombinedOp<Scale, Scale, Relu>;
|
||||
|
||||
} // namespace element_wise
|
||||
} // namespace tensor_operation
|
||||
} // namespace ck
|
||||
|
||||
Reference in New Issue
Block a user