mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 14:29:05 +00:00
fa4473fde6
CK: Extract shared boilerplate from 47 gemm_quant test files (#6323) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Depends on #6303 ## Summary Extract shared test boilerplate (includes, type aliases, test fixture macros) from 47 `test_gemm_quant_*` files into a single `test_gemm_quant_common.hpp` header. Each test file is reduced from ~50 lines of boilerplate to ~5 lines. | Metric | Value | |--------|-------| | Files changed | 48 | | Insertions | +413 | | Deletions | −1,106 | | **Net lines removed** | **−693** | ### What changed | Before | After | |--------|-------| | 47 test files, each with ~50 lines of identical includes, type aliases, and fixture macros | 1 shared header (`test_gemm_quant_common.hpp`) + 47 thin files (~5 lines each: include + params) | ### Readability assessment A code realist review confirmed this change **improves readability**: the 47 test files had identical boilerplate obscuring the only meaningful content — the `GemmConfig` type alias and test dimensions. After the refactoring, each file's unique configuration is immediately visible, and adding a new test variant requires specifying only the varying parameters instead of copying 50 lines. ### Cumulative cleanup series stats | PR | Description | Net lines | |----|-------------|-----------| | #6300 | Remove 61 dead `#if 0` blocks | −2,648 | | #6302 | Remove 41 commented-out dead code blocks | −2,861 | | #6303 | Remove 4 orphaned files | −3,886 | | This PR | Extract gemm_quant test boilerplate | −693 | | **Total** | | **−10,088** |
33 lines
1.1 KiB
C++
33 lines
1.1 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
|
|
#include "common_instances.hpp"
|
|
|
|
using ADataType = BF16;
|
|
using BDataType = BF16;
|
|
using AccDataType = F32;
|
|
using CShuffleDataType = BF16;
|
|
using DDataType = BF16;
|
|
using DsDataType = ck::Tuple<DDataType>;
|
|
using EDataType = BF16;
|
|
using ComputeDataType = BF16;
|
|
|
|
static constexpr ck::index_t NumDimM = 2;
|
|
static constexpr ck::index_t NumDimN = 2;
|
|
static constexpr ck::index_t NumDimK = 2;
|
|
|
|
using AElementOp = ck::tensor_operation::element_wise::PassThrough;
|
|
using BElementOp = ck::tensor_operation::element_wise::PassThrough;
|
|
using CDEElementOp = ck::tensor_operation::element_wise::Bilinear;
|
|
|
|
// Instantiate DeviceOpInstance for all four layout variants (KK, KN, MK, MN).
|
|
// See common_instances.hpp for macro definition and available BASE/SUFFIX options.
|
|
CK_CONTRACTION_DEVICE_OP_INSTANCES(Generic, NN);
|
|
|
|
#include "run_contraction_bilinear_example.inc"
|
|
|
|
int main(int argc, char* argv[]) { return run_contraction_bilinear_example(argc, argv); }
|