mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 13:41:24 +00:00
00247e3c29
Adds V3 GEMM pipeline for MX FP4 and MX FP8 Adds V3 GEMM pipeline for MX FP4 with preshuffling Adds MXFP4 GEMM tests (#2275) Adds MXFP4 GEMM examples Adds MXFP4 GEMMs to ckProfiler Co-authored-by: Andriy Roshchenko <107577548+andriy-ca@users.noreply.github.com> Co-authored-by: Andriy Roshchenko <andriy.roshchenko@amd.com> Co-authored-by: aska-0096 <haocwang@amd.com> Co-authored-by: lalala-sh <Jiaxing.Wen@amd.com> Co-authored-by: OscarXu <huaiguxu@amd.com> Co-authored-by: mtgu0705 <mtgu@amd.com> Co-authored-by: Ding, Yi <yi.ding@amd.com> Co-authored-by: feifei14119 <feiw@amd.com> Co-authored-by: Lin, Qun <qlin@amd.com> Co-authored-by: joye <joye@amd.com> Co-authored-by: Rostyslav Geyyer <46627076+geyyer@users.noreply.github.com>
65 lines
2.0 KiB
C++
65 lines
2.0 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
namespace ck {
|
|
|
|
template <auto v>
|
|
struct constant
|
|
{
|
|
using value_type = decltype(v);
|
|
using type = constant; // using injected-class-name
|
|
static constexpr value_type value = v;
|
|
__host__ __device__ constexpr operator value_type() const noexcept { return value; }
|
|
__host__ __device__ constexpr value_type operator()() const noexcept { return value; }
|
|
};
|
|
|
|
template <class T, T v>
|
|
struct integral_constant : constant<v>
|
|
{
|
|
static constexpr T value = v;
|
|
typedef T value_type;
|
|
typedef integral_constant type;
|
|
};
|
|
|
|
template <typename TX, TX X, typename TY, TY Y>
|
|
__host__ __device__ constexpr auto operator+(integral_constant<TX, X>, integral_constant<TY, Y>)
|
|
{
|
|
return integral_constant<decltype(X + Y), X + Y>{};
|
|
}
|
|
|
|
template <typename TX, TX X, typename TY, TY Y>
|
|
__host__ __device__ constexpr auto operator-(integral_constant<TX, X>, integral_constant<TY, Y>)
|
|
{
|
|
static_assert(Y <= X, "wrong!");
|
|
return integral_constant<decltype(X - Y), X - Y>{};
|
|
}
|
|
|
|
template <typename TX, TX X, typename TY, TY Y>
|
|
__host__ __device__ constexpr auto operator*(integral_constant<TX, X>, integral_constant<TY, Y>)
|
|
{
|
|
return integral_constant<decltype(X * Y), X * Y>{};
|
|
}
|
|
|
|
template <typename TX, TX X, typename TY, TY Y>
|
|
__host__ __device__ constexpr auto operator/(integral_constant<TX, X>, integral_constant<TY, Y>)
|
|
{
|
|
static_assert(Y > 0, "wrong!");
|
|
return integral_constant<decltype(X / Y), X / Y>{};
|
|
}
|
|
|
|
template <typename TX, TX X, typename TY, TY Y>
|
|
__host__ __device__ constexpr auto operator%(integral_constant<TX, X>, integral_constant<TY, Y>)
|
|
{
|
|
static_assert(Y > 0, "wrong!");
|
|
return integral_constant<decltype(X % Y), X % Y>{};
|
|
}
|
|
|
|
template <bool B>
|
|
using bool_constant = integral_constant<bool, B>;
|
|
|
|
using true_type = bool_constant<true>;
|
|
using false_type = bool_constant<false>;
|
|
} // namespace ck
|