goankur commented on code in PR #13572:
URL: https://github.com/apache/lucene/pull/13572#discussion_r1819699896
##########
lucene/core/src/java21/org/apache/lucene/internal/vectorization/Lucene99MemorySegmentByteVectorScorer.java:
##########
@@ -103,6 +125,27 @@ public float score(int node) throws IOException {
}
}
+ static final class NativeDotProductScorer extends
Lucene99MemorySegmentByteVectorScorer {
+
+ NativeDotProductScorer(
+ MemorySegmentAccessInput input, KnnVectorValues values, byte[]
queryVector) {
+ super(input, values, queryVector);
+ if (offHeapQuery == null) {
Review Comment:
This whole `NativeDotProductScorer` is gone in the next iteration. For the
byteVector case, I am planning to generate offHeap MemorySegments in case
native dot product is enabled. Then in
`PanamaVectorUtilSupport.dotProduct(MemorySegment a, MemorySegment b)` we will
delegate the computation to native code if both segments are native.
--
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]
