mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-20 14:59:17 +00:00
Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)
* Fix example * fix build error * update pk_i4 & moe test case * fix all instance build (examples) * fix batched_gemm_gemm (example) * disable example_gemm_bias_softmax_gemm_permute on gfx11 * remove unnecessary disable gfx11 * update tests * update tests2
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
||||
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "convnd_fwd_convscale_common.hpp"
|
||||
|
||||
@@ -58,10 +58,10 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
32, // KPerBlock
|
||||
8, // AK1
|
||||
8, // BK1
|
||||
32, // MPerXdl
|
||||
32, // NPerXdl
|
||||
2, // MXdlPerWave
|
||||
4, // NXdlPerWave
|
||||
16, // MPerXdl
|
||||
16, // NPerXdl
|
||||
4, // MXdlPerWave
|
||||
8, // NXdlPerWave
|
||||
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_AK0_M_AK1
|
||||
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
||||
@@ -79,7 +79,7 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
1,
|
||||
1,
|
||||
S<1, 32, 1, 8>,
|
||||
8,
|
||||
4,
|
||||
AComputeDataType,
|
||||
BComputeDataType>;
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
||||
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "convnd_fwd_convscale_common.hpp"
|
||||
|
||||
@@ -58,10 +58,10 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
32, // KPerBlock
|
||||
8, // AK1
|
||||
8, // BK1
|
||||
32, // MPerXdl
|
||||
32, // NPerXdl
|
||||
2, // MXdlPerWave
|
||||
4, // NXdlPerWave
|
||||
16, // MPerXdl
|
||||
16, // NPerXdl
|
||||
4, // MXdlPerWave
|
||||
8, // NXdlPerWave
|
||||
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_AK0_M_AK1
|
||||
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
||||
@@ -79,7 +79,7 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
1,
|
||||
1,
|
||||
S<1, 32, 1, 8>,
|
||||
8,
|
||||
4,
|
||||
AComputeDataType,
|
||||
BComputeDataType>;
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
||||
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "convnd_fwd_convscale_common.hpp"
|
||||
|
||||
@@ -58,10 +58,10 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
32, // KPerBlock
|
||||
8, // AK1
|
||||
8, // BK1
|
||||
32, // MPerXdl
|
||||
32, // NPerXdl
|
||||
2, // MXdlPerWave
|
||||
4, // NXdlPerWave
|
||||
16, // MPerXdl
|
||||
16, // NPerXdl
|
||||
4, // MXdlPerWave
|
||||
8, // NXdlPerWave
|
||||
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_AK0_M_AK1
|
||||
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
||||
@@ -79,7 +79,7 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
1,
|
||||
1,
|
||||
S<1, 32, 1, 8>,
|
||||
8,
|
||||
4,
|
||||
AComputeDataType,
|
||||
BComputeDataType>;
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
|
||||
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
|
||||
#include "convnd_fwd_convscale_common.hpp"
|
||||
|
||||
@@ -58,10 +58,10 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
32, // KPerBlock
|
||||
8, // AK1
|
||||
8, // BK1
|
||||
32, // MPerXdl
|
||||
32, // NPerXdl
|
||||
2, // MXdlPerWave
|
||||
4, // NXdlPerWave
|
||||
16, // MPerXdl
|
||||
16, // NPerXdl
|
||||
4, // MXdlPerWave
|
||||
8, // NXdlPerWave
|
||||
S<4, 64, 1>, // ABlockTransferThreadClusterLengths_AK0_M_AK1
|
||||
S<1, 0, 2>, // ABlockTransferThreadClusterArrangeOrder
|
||||
S<1, 0, 2>, // ABlockTransferSrcAccessOrder
|
||||
@@ -79,7 +79,7 @@ using DeviceGroupedConvNDFwdInstance =
|
||||
1,
|
||||
1,
|
||||
S<1, 32, 1, 8>,
|
||||
8,
|
||||
4,
|
||||
AComputeDataType,
|
||||
BComputeDataType>;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user