## 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.
## Motivation
<!-- Explain the purpose of this PR and the goals it aims to achieve.
-->
Add pooling in ck tile engine
## Technical Details
<!-- Explain the changes along with any relevant GitHub links. -->
## Test Plan
<!-- Explain any relevant testing done to verify this PR. -->
## Test Result
<!-- Briefly summarize test outcomes. -->
## Submission Checklist
- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
---------
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
* chore(copyright): update copyright header for test directory
* chore(copyright): update copyright header for test directory
[ROCm/composable_kernel commit: 7dfc46d73d]
* initial commit for testing datatypes, layouts and traits
* correct warp tile size for small datatype config to make a validate instance for fp16, bf16, fp8
* add tile size coverage test
* Cover more tests, parallel instance generation, documentation
* update cmakelist to run more tests
* initial codes to support add test params in json file
* add congurable problem sizes for different tests
* modify README.md
* clean test_gemm_simple code
* correct padding coverage test
* Add comprehensive and quick tile size config files
* remove fp64 from datatypes
* update documents. manage selecting tile_size config (quick or Comprehensive)
* correct padding test problem sizes
* update comprehensive test and correct documents
* Skip GEMM tests with unsupported arguments instead of failing
* change gen_single instead of gen_indivisual because of an issue. add splitk tests to tile_size_quick_config
* clean CMakeList, remod py file
* Refactor test configs: Rename tile_size to coverage, remove separate traits config, clean cmakefile, readme
* update fp32, fp8 to test all layouts, clean documents and comments
* limit fp32 test layouts to rcr because of compilation error on some gpus
* remove fp32 because of the removing from gemm_instance_builder, make quick test smaller, updating comments
* Fix fp8/bf8 test failures on gfx950 by adding OCP FP8 format support
* Reduce quick_coverage test count from ~250 to ~144 for faster CI
[ROCm/composable_kernel commit: d405641f06]
* Reading gpuname from target for gemm in ck tile engine
* Reading gpuname from target for gemm preshuffle in ck tile engine
* Reading gpuname from target for gemm preshuffle in ck tile engine
* Get GPU changes for GEMM Muti D in TILE ENGINE
* Addressing errors for gpu name in cktileengine
[ROCm/composable_kernel commit: 9f77061094]
* first try to understand how tile engine works
* 1st implemented unit tests
* manage different types for unit tests
* manage using different config files to have different unit tests
* manage different layouts
* making instances and running them by unit test
* Add reference calculation
* manage different input dimension combination
* add splitk to unit tests. clean code.
* remove unused files
* clean and test with a simple json file
[ROCm/composable_kernel commit: 96efe2f485]
