Refactor the builder factory code into multiple files and subdirectories and a ck_tile::builder::factory namespace.
The factory implements compile-time dispatch from high-level signature and algorithm descriptors to our existing specialized convolution kernel implementations.
Major changes in this PR:
Dispatch logic is explicit in the function make_conv_instance instead of implicit in template specialization selection.
Helper code is moved to a subdirectory builder/factory/helpers.
Helpers now have unit tests.
Factories are moved to their own files.
Code moved to namespaces ck_tile::builder::factory and ck_tile::builder::factory::internal.
This does not yet fix the problem of bad error messages, but the make_conv_instance function makes the poor error messages clear. The choice of algorithm must be much more robust (perhaps with explicit enumeration in the algorithm descriptor), so that the dispatch doesn't fail.
Quality changes:
Making dispatch explicit rather than implicit will improve robustness, readability, maintainability, testability, and extensibility.
Separating code into separate files and subdirectories helps readability and extensibility.
Adding unit tests for helpers documents behavior and will enable more complex logic and functionality.
Separating files (especially unit tests) helps clarify includes and dependencies and makes code easier to refactor.
[ROCm/composable_kernel commit: 280bc42191]
The ConvDescription::detailed command wasn't using TreeFormatter::writeLast correctly, which led to extra lines being drawn in the tree view. It's a simple fix, just a cosmetic improvment out reflection output (ASCII art).
[ROCm/composable_kernel commit: d17994f3df]
Remove obsolete feature for extracting a description from a builder, since this should apply directly to the instance type. Also add some documentation, including a README.md for reflection.
[ROCm/composable_kernel commit: abd6a4b3fc]
There were four errors to fix:
1. The checks for defaulted direction were not implemented in the predicate concept.
2. Had to delete an obsolete and undefined operation enum.
3. A factory was passing a boolean in place of an integer.
4. Some of the factory tests are not compiling correctly when linking in the full source (with CK_EXPERIMENTAL_BUILDER=ON), so I commented them out.
[ROCm/composable_kernel commit: ea6e4fcbbc]
Our copyright were were mostly correct, but we inconsistently used (C) instead of (c) like the rest of the CK code. This PR fixes that (using lowercase c) and adds a missing copyright header to one file.
[ROCm/composable_kernel commit: f38c3de9f9]
Grouping transfer operations per tensor makes it easier to
constrain on and operate with the transfer operations. As an
example, we can now deduplicate the logic for translating
the transfer operations from the ck-builder interface to the old
ck interface for the A and B tensors.
[ROCm/composable_kernel commit: 245c6011cf]
Fixed issues encountered during merge of #3192
* fixed accidental drop of get_elementwise_operation during merge and added call to get_elementwise_op to 4 other builders
* run clang-format
---------
Co-authored-by: Kevin Abraham <kevin.abraham@streamhpc.com>
[ROCm/composable_kernel commit: 964f8e1f60]
Removed direction and elementwise operation from default values required for convolution signature concept. Added constexpr helpers to set default values. Add compile-time tests.
[ROCm/composable_kernel commit: 92498464f6]
Proposed changes
Improve the forward convolution builder implementation and addressed leftover feedback left from PR #3138. Main changes
Refactored tests such that they reflect better the builder pattern. The templates and types for the convolution algorithm concepts are created via factory that facilitates programmatic creation of the device op instances.
Moved tests into anonymous namespace.
The convolution factory had lot of if-else constructs when CK Builder types were converted into CK library types. I had initially trouble in using static_assert in the default branch of switch as the static_assert was evaluated at compile time even for valid types. However, if we change the static_assert to throw "<error message>", it will result in a compile-time error only if the default branch is actually hit. This assumes that the function is consteval. Hence, changed all conversions in the convolution factory to use switch, which is more intuitive.
Removed the explicit device op definition from convolution signature and the corresponding predicate file. The device ops are defined by the corresponding concepts. This allowed to remove lot of boilerplate code from the convolution factory.
Adde inheritance and convolution algorithm specialization to handle device ops that are specialization of a more generic ones. The large tensor support is more naturally expressed by this pattern.
Added support for the FP8 data type.
* WIP: Builder for expected test results.
* Improve ckb fwd conv instance tests.
* clang-format
* Change if-else statements into switch in conv factory.
* Fix clang-formatting.
* Removed unnecessary includes.
* Added missing copyright.
* Remove explicit device op flag from from convolution signature.
* Add missing concept.
* Fix build.
* clang-format
* Add test for building conv fwd FP8 instances.
* Add missing header to instance traits.
* Clean-up recently added instances.
* Introduce inheritance and specialization.
* Use builder to build conv algorithm templates and types.
* clang-format
* Fix conv description tests.
---------
Co-authored-by: John Shumway <john.shumwayjr@gmail.com>
[ROCm/composable_kernel commit: 7d57bc169f]
