Pulkitg64 commented on issue #12403: URL: https://github.com/apache/lucene/issues/12403#issuecomment-3542675720
I think JDK now support [Float16 objects](https://docs.oracle.com/en/java/javase/25/docs/api/jdk.incubator.vector/jdk/incubator/vector/Float16.html). The HotSpot C2 compiler can auto-vectorize addition, subtraction, division, multiplication, square root, and fused multiply/add on supporting CPUs (From the [JEP-529](https://openjdk.org/jeps/529)). But VectorAPI still doesn't support Float16 vectors operations in the main. From the doc: ` We may broaden the auto-vectorization of Float16 operations, eventually covering all relevant operations on supporting hardware. We may also enhance the Vector API and implementation to cover vectors of Float16 values; for exploratory work, see the [vectorIntrinsics+fp16 branch](https://github.com/openjdk/panama-vector/tree/vectorIntrinsics+fp16) of Project Panama's development repository. We will migrate Float16 to become a value class when [Project Valhalla](https://openjdk.org/projects/valhalla/) becomes available. ` Does this mean, we should wait for Project Valhalla before pursuing this idea of supporting fp16 vectors or should we just add support using Float16 arrays and implementing vector score implementation in DefaultVectorUtilSupport class? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
