mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
5d2fce819d
[CK_TILE] Restructure Tile Engine's benchmarking and profiling (#4769) ## Motivation This PR introduces a restructure for the benchmarking and profiling aspects of CK Tile's Tile Engine, expanding on the groundwork from this previous https://github.com/ROCm/composable_kernel/pull/3434 and outlined in this [design document](https://amdcloud-my.sharepoint.com/:w:/r/personal/astharai_amd_com/Documents/Restructuring%20Tile%20Engine.docx?d=w14ea28a30718416988ed5ebb759bd3b2&csf=1&web=1&e=l3VBuX). In PR 3434, to reduce repeated code we implemented: - Base class that centralizes common functionality and provides a default implementation (Universal GEMM) - Child classes for GEMM variants override virtual functions to handle variant-specific behavior This refactoring in this PR follows the same process and should greatly reduce the duplicated code present in Tile Engine and make it simpler to add in new operations, increasing scalability. ## Technical Details The files have been refactored around new base structs for benchmarks, profiling and problem descriptions. The new base structs are: - GemmProblem - GemmBenchmark - GemmProfiler Universal GEMM, Preshuffle GEMM, and Multi-D GEMM all have child classes that will inherit from these base structs overriding only what differs per variant. All common functions across the benchmarking and profiling files have been moved into newly added common utility files under the commons/ directory. The new utility files are: - utils.hpp: common functions for the benchmarking and profiling process - benchmark_utils.py: common utility functions for the benchmark generation ## Test Plan I tested using the existing tests for Tile Engine. ## Test Result All tests passed. ## Submission Checklist - [x] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
55 lines
2.5 KiB
C++
55 lines
2.5 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#pragma once
|
|
|
|
#include <iostream>
|
|
#include <string>
|
|
|
|
#include "ck_tile/core.hpp"
|
|
|
|
namespace ck_tile {
|
|
|
|
// clang-format off
|
|
template <typename T> struct DataTypeTraits;
|
|
template <> struct DataTypeTraits<float> { static constexpr const char * name = "fp32"; };
|
|
template <> struct DataTypeTraits<double> { static constexpr const char * name = "fp64"; };
|
|
template <> struct DataTypeTraits<int32_t> { static constexpr const char * name = "int32"; };
|
|
template <> struct DataTypeTraits<fp16_t> { static constexpr const char * name = "fp16"; };
|
|
template <> struct DataTypeTraits<bf16_t> { static constexpr const char * name = "bf16"; };
|
|
template <> struct DataTypeTraits<fp8_t> { static constexpr const char * name = "fp8"; };
|
|
template <> struct DataTypeTraits<bf8_t> { static constexpr const char * name = "bf8"; };
|
|
template <> struct DataTypeTraits<int8_t> { static constexpr const char * name = "int8"; };
|
|
template <> struct DataTypeTraits<pk_int4_t> { static constexpr const char * name = "pk_int4"; };
|
|
template <> struct DataTypeTraits<pk_fp4_t> { static constexpr const char * name = "pk_fp4"; };
|
|
template <> struct DataTypeTraits<pk_fp6x16_t> { static constexpr const char * name = "pk_fp6x16"; };
|
|
template <> struct DataTypeTraits<pk_fp4_raw_t> { static constexpr const char * name = "pk_fp4_raw"; };
|
|
template <> struct DataTypeTraits<e8m0_t> { static constexpr const char * name = "e8m0"; };
|
|
template <> struct DataTypeTraits<ck_tile::tf32_t>{ static constexpr const char* name = "tf32"; };
|
|
|
|
template <memory_operation_enum MemOp> struct memOpToStr;
|
|
template <> struct memOpToStr<memory_operation_enum::set> { static constexpr const char * name = "set"; };
|
|
template <> struct memOpToStr<memory_operation_enum::atomic_add> { static constexpr const char * name = "atomic_add"; };
|
|
template <> struct memOpToStr<memory_operation_enum::atomic_max> { static constexpr const char * name = "atomic_max"; };
|
|
template <> struct memOpToStr<memory_operation_enum::add> { static constexpr const char * name = "add"; };
|
|
// clang-format on
|
|
|
|
template <typename ADataType_, typename BDataType_>
|
|
std::string gemm_prec_str()
|
|
{
|
|
std::string base_str = std::string(DataTypeTraits<ADataType_>::name);
|
|
if(!std::is_same_v<ADataType_, BDataType_>)
|
|
{
|
|
base_str += "_" + std::string(DataTypeTraits<BDataType_>::name);
|
|
}
|
|
return base_str;
|
|
}
|
|
|
|
template <memory_operation_enum MemOp_>
|
|
std::string mem_op_string()
|
|
{
|
|
return std::string(memOpToStr<MemOp_>::name);
|
|
}
|
|
|
|
} // namespace ck_tile
|