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.
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.
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.
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.
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>
Removed direction and elementwise operation from default values required for convolution signature concept. Added constexpr helpers to set default values. Add compile-time tests.
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>