[XLA:GPU] Explicit algorithm support for dot instructions #63429
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Outdated suggestions cannot be applied.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.
[XLA:GPU] Explicit algorithm support for dot instructions
Now we can set PrecisionConfig::algorithm instead of PrecisionConfig::operand_precision.
The old PrecisionConfig::operand_precision is also still supported.
It would be a big change to remove it or even convert it to algorithm internally (because we support many type combinations and many tests would need to be updated).
PrecisionConfig::algorithm is not yet added to StableHLO, so we can only use it if we feed an HLO to XLA directly.
Future plans:
FUTURE_COPYBARA_INTEGRATE_REVIEW=openxla/xla#10011 from ROCm:ci_cusolver_fix_240227 d965fd3a817838c4b7440868afb6884ea011b078