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

[ROCm/composable_kernel commit: 321627aec5]
This commit is contained in:
linqunAMD
2025-09-12 23:17:07 +08:00
committed by GitHub
parent adc66b9b0e
commit 07def6b13d
123 changed files with 848 additions and 574 deletions

View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2023-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2023-2025, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -71,10 +71,10 @@ 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
@@ -92,7 +92,7 @@ using DeviceGroupedConvNDFwdInstance =
1,
1,
S<1, 32, 1, 8>,
8>;
4>;
template <ck::index_t NDimSpatial,
typename InDataType,