ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 05:31:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] FMHA BWD Optimization For GFX950 (#2628)

Browse Source 
* simplify fmha_bwd_kernel MakeKargs & dq_dram_window

* simply duplicate

* trload pipeline

* Try two-stage

* add prefetch

* optimize & iglp
This commit is contained in:
Yi DING
2025-08-12 11:11:55 +08:00
committed by GitHub
parent a7badc6ec5
commit 4fde1646e5
16 changed files with 2216 additions and 586 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
include/ck_tile/core/numeric/integral_constant.hpp
View File

@@ -1,5 +1,5 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
#pragma once
@@ -83,4 +83,14 @@ CK_TILE_BINARY_OP(<=)
#undef CK_TILE_LEFT_UNARY_OP
#undef CK_TILE_BINARY_OP
template <typename T>
struct is_constant : std::false_type
{
};
template <auto v>
struct is_constant<constant<v>> : std::true_type
{
};
template <typename T>
inline constexpr bool is_constant_v = is_constant<T>::value;
} // namespace ck_tile