/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/docs-6.4.3/include/ck/tensor_operation/gpu/device/device_grouped_gemm_tile_loop.hpp Source File

• docs-6.4.3
• include
• ck
• tensor_operation
• gpu
• device

device_grouped_gemm_tile_loop.hpp

Go to the documentation of this file.

1 // SPDX-License-Identifier: MIT

2 // Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.

3 

4 #pragma once

5 

6 #include "device_grouped_gemm.hpp"

7 

8 namespace ck {

9 namespace tensor_operation {

10 namespace device {

11 

20 

21 template <typename ALayout,

22  typename BLayout,

23  typename DsLayout,

24  typename ELayout,

25  typename ADataType,

26  typename BDataType,

27  typename DsDataType,

28  typename EDataType,

29  typename AElementwiseOperation,

30  typename BElementwiseOperation,

31  typename CDEElementwiseOperation>

32 struct DeviceGroupedGemmTileLoop : public DeviceGroupedGemm<ALayout,

33  BLayout,

34  DsLayout,

35  ELayout,

36  ADataType,

37  BDataType,

38  DsDataType,

39  EDataType,

40  AElementwiseOperation,

41  BElementwiseOperation,

42  CDEElementwiseOperation>

43 {

44 };

45 

46 } // namespace device

47 } // namespace tensor_operation

48 } // namespace ck

device_grouped_gemm.hpp

ck

Definition: ck.hpp:264

ck::tensor_operation::device::DeviceGroupedGemm

Definition: device_grouped_gemm.hpp:105

ck::tensor_operation::device::DeviceGroupedGemmTileLoop

Grouped GEMM kernel using output Tile Looping algorithm.

Definition: device_grouped_gemm_tile_loop.hpp:43