mccullocht commented on code in PR #15736:
URL: https://github.com/apache/lucene/pull/15736#discussion_r2835076660
##########
lucene/core/src/java25/org/apache/lucene/internal/vectorization/PanamaVectorUtilSupport.java:
##########
@@ -610,11 +610,10 @@ private static int int4DotProductSinglePackedBody(
prod8a.convertShape(ZERO_EXTEND_B2S, Int4Constants.SHORT_SPECIES,
0);
acc1 = acc1.add(prod16a);
}
- Vector<Integer> intAcc0 = acc0.convert(S2I, 0);
- Vector<Integer> intAcc1 = acc0.convert(S2I, 1);
- Vector<Integer> intAcc2 = acc1.convert(S2I, 0);
- Vector<Integer> intAcc3 = acc1.convert(S2I, 1);
- sum +=
intAcc0.add(intAcc1).add(intAcc2).add(intAcc3).reinterpretAsInts().reduceLanes(ADD);
+ ShortVector accShort = acc0.add(acc1);
+ Vector<Integer> intAcc0 = accShort.convert(ZERO_EXTEND_S2I, 0);
+ Vector<Integer> intAcc1 = accShort.convert(ZERO_EXTEND_S2I, 1);
+ sum += intAcc0.add(intAcc1).reinterpretAsInts().reduceLanes(ADD);
}
Review Comment:
If it improves the byte -> short conversion that one is a 64-bit -> 128-bit
register conversion and really should be fast in all cases. There might be more
throughput lurking here because if this widening operation is really that slow
you may want to also load 128 bits at a time with the reinterpret cast summing
workaround.
--
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]
