Files
composable_kernel/experimental/builder
Adam Osewski 22de6a19d9 [rocm-libraries] ROCm/rocm-libraries#4750 (commit c065793)
[CK_BUILDER] ck builder conv transfer fix

## Motivation

This PR fixes how CK Builder is validating transfer vector size and adds
proper validation for LDS transfer vector size as well.

## Changes:

* [__source vector dim__] -- Before this PR the data transfer validation
logic didn't allow to set the source vectorized dimension to 1. However
there are CK instances that are doing this when the group merging is
used. This is used only for
`DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle` kernel.
* [__valid vector size__] -- Before this PR the validation logic
concerned only single instruction maximum vector size. However our
buffer loading logic has implemented support for loading more values
through multiple buffer instructions. This again was discovered to be
used in some of the convolution instances. Thus this behavior was
reflected in validation logic.
* [__valid LDS vector size__] -- Before this PR the LDS vector size
validation was done in the same way as VMEM. This PR adds proper LDS
vector size validation based on the available LDS instruction sizes.

## Test Plan

Run CK BUILDER conv fwd factories tests

## Test Result

All CK BUILDER conv fwd factories work (except DL one & ck tile since
they're not yet added now)

## Submission Checklist

- [ ] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
2026-02-27 13:48:58 +00:00
..

Builder

This directory contains the experimental builder feature for composable_kernel.

  • Status: In development (October 2025 - March 2026)

Overview

The builder provides a high-level, semantically-clear interface for constructing composable kernel operations, with an initial focus on convolution kernels for MIOpen. It leverages modern C++20 features (such as POD structs as non-type template parameters, concepts, and designated initializers) to simplify kernel instantiation and improve developer experience.

This project is a prototype for a more general builder pattern for all of composable_kernel (CK) and CK Tile, but is currently limited to formalizing the interface between MIOpen and CK.

Design descriptions

Directory Structure

  • include/ck_tile/builder/ Core builder headers and public API.
  • include/ck_tile/builder/reflect Reflection mechanism.
  • include/ck_tile/builder/factory Compile-time dispatch from builder descriptors to our exisitng specialized convolution kernel implementations.
  • test/ Unit tests and example usage of the builder pattern.
  • CMakeLists.txt CMake configuration for building the experimental builder and its tests.

CMake Configuration

To enable the experimental builder, configure your build with:

cmake                                                                                             \
  -D CMAKE_PREFIX_PATH=/opt/rocm                                                                  \
  -D CMAKE_CXX_COMPILER=/opt/rocm/bin/hipcc                                                       \
  -D CMAKE_BUILD_TYPE=Release                                                                     \
  -D GPU_TARGETS="gfx942"                                                                         \
  -D CK_EXPERIMENTAL_BUILDER=ON                                                                   \
  -D CMAKE_CXX_STANDARD=20                                                                        \
  -G Ninja                                                                                        \
  ..

Note: The tests for WMMA builders are only built when CK_USE_WMMA is enabled. Add e.g. gfx1121 or any of the other gfx11/gfx12 architectures to the GPU targets. Alternatively, one can add flag -D CK_USE_WMMA=ON to build the tests. For the end-to-end tests that use the instances from builder, one needs an actual Navi card.

Building and Testing

The builder test suite is organized into two main categories:

Smoke Tests (Fast Unit Tests)

Quick unit tests that verify the builder's internal logic without compiling GPU kernels. These complete in under 1 second total and are suitable for frequent execution during development.

ninja smoke-builder

Regression Tests (Integration Tests)

Integration tests that compile actual GPU kernels to verify that the builder generates valid, compilable code. These are more expensive than smoke tests (can take minutes to compile) but cover more fuctionality. )

ninja regression-builder

Running All Tests

To build and run the complete test suite:

ninja check-builder

Building Individual Tests

To build and run a specific test:

ninja test_ckb_conv_builder && bin/test_ckb_conv_builder

Test Organization

  • Smoke tests: Fast feedback during active development
  • Regression tests: Thorough validation before submitting changes
  • Factory tests: Expensive tests that build all MIOpen kernels (included in regression tests)

When adding new tests, please follow the convention where the CMake build target starts with a prefix test_ckb. This allows filtering of CK Builder tests from the full CK repository test suite.