mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-01 12:11:19 +00:00
1acd8e041c
* Fix a typo * Use std::variant to call run_gemm_example_with_layouts with the available layout variant combinations * Use a unified run_gemm_example_prec_type for basic gemm and universal gemm * Factor out run_gemm_example_prec_type * Refactor argument parsing in gemm_splitk_two_stage_reduce.cpp * Parse arguments outside of create_args * Move the gemm operators to separate structs to facilitate their reuse * Move the invokers to separate files to facilitate their reuse * Rename the invoker files for consistency with the examples that use them * Add fp32 support to the elementwise examples, and produce an error message for unsupported types * Get rid of four unused variables * Make two variables const * Add support for different input-output type combinations in elementwise examples * Test support for different input and output types in elementwise examples * Add support for different operations in the elementwise unary tests * Add support for UnaryConvert in the elementwise unary tests * Add support for bf16 in elementwise examples, excluding unsupported type combinations * Make some operator parameters const in ElementWiseKernel * Remove some unnecessary include statements * Implement a two-stage GEMM that does a type conversion in the second stage using the elementwise kernel * Clear workspace instead of output when flushing the cache in SplitKTwoStageInvoker::gemm * Fix formatting issues reported by clang * Add back CK_TILE_USE_WMMA related changes * Use the right prec type for bf16 in the universal GEMM and two stage split K examples * Add some brackets * Add some brackets * Separate the clearing of the GEMM output memory from the cache flushing in the universal GEMM example * Separate the clearing of the GEMM output memory from the cache flushing in the split K two stage example * Fix formatting * No need to call SetZero on ws_m_n_dev_buf here, as clear_gemm_output now does this as part of the kernel preprocessing * Add fp16 data type to splitk two stage example * Add preprocessing with optional cache flushing and clearing of output for k_batch > 1 to the basic GEMM example
103 lines
2.7 KiB
C++
103 lines
2.7 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/core.hpp"
|
|
|
|
namespace ck_tile {
|
|
namespace element_wise {
|
|
|
|
struct Add
|
|
{
|
|
template <typename Y, typename X0, typename X1>
|
|
__host__ __device__ constexpr void operator()(Y& y, const X0& x0, const X1& x1) const;
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<float>(float& y, const float& x0, const float& x1) const
|
|
{
|
|
y = x0 + x1;
|
|
};
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<double>(double& y, const double& x0, const double& x1) const
|
|
{
|
|
y = x0 + x1;
|
|
};
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<float>(float& y, const float& x0, const half_t& x1) const
|
|
{
|
|
y = x0 + type_convert<half_t>(x1);
|
|
};
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<half_t>(half_t& y, const float& x0, const float& x1) const
|
|
{
|
|
y = type_convert<half_t>(x0 + x1);
|
|
};
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<half_t>(half_t& y, const float& x0, const half_t& x1) const
|
|
{
|
|
y = type_convert<half_t>(x0) + x1;
|
|
};
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<half_t>(half_t& y, const half_t& x0, const half_t& x1) const
|
|
{
|
|
y = x0 + x1;
|
|
};
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<float>(float& y, const float& x0, const bf16_t& x1) const
|
|
{
|
|
const float x1_tmp = type_convert<float>(x1);
|
|
y = x0 + x1_tmp;
|
|
}
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<bf16_t>(bf16_t& y, const bf16_t& x0, const bf16_t& x1) const
|
|
{
|
|
const float x1_tmp = type_convert<float>(x0);
|
|
const float x2_tmp = type_convert<float>(x1);
|
|
const float y_tmp = x1_tmp + x2_tmp;
|
|
y = type_convert<bf16_t>(y_tmp);
|
|
}
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<bf16_t>(bf16_t& y, const float& x0, const bf16_t& x1) const
|
|
{
|
|
const float x2_tmp = type_convert<float>(x1);
|
|
const float y_tmp = x0 + x2_tmp;
|
|
y = type_convert<bf16_t>(y_tmp);
|
|
}
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<bf16_t>(bf16_t& y, const float& x0, const float& x1) const
|
|
{
|
|
const float y_tmp = x0 + x1;
|
|
y = type_convert<bf16_t>(y_tmp);
|
|
}
|
|
|
|
template <>
|
|
__host__ __device__ constexpr void
|
|
operator()<int8_t>(int8_t& y, const int8_t& x0, const int8_t& x1) const
|
|
{
|
|
y = x0 + x1;
|
|
};
|
|
};
|
|
|
|
} // namespace element_wise
|
|
} // namespace ck_tile
|