ankitsultana commented on code in PR #16617:
URL: https://github.com/apache/pinot/pull/16617#discussion_r2284060490
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/io/util/FixedByteValueReaderWriter.java:
##########
@@ -92,6 +92,13 @@ public String getPaddedString(int index, int
numBytesPerValue, byte[] buffer) {
return new String(buffer, 0, numBytesPerValue, UTF_8);
}
+ public void getCustomPaddedString(int offset, int numBytesPerValue,
ByteBuffer buffer) {
+ long l1 = _dataBuffer.getLong(offset);
Review Comment:
Diving into Java instruction set, getLong seems to always resolve into
`invokevirtual`, which means there's no chance of auto vectorization here
(except for offset computation). Kinda surprising to me how sub-optimal all of
this is
--
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]
