ukernels: sub-8-bit support, types s16 * u4 -> s32
and s16 * s16 -> s32
#15343
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
s16 * u4 -> s32
is the main goal in #15158, ands16 * s16 -> s32
is seen as a less-optimized but generically useful path to run generic "some non-8-bit quantized matmuls that we don't have super specialized code for" on.