kaivalnp commented on PR #15742: URL: https://github.com/apache/lucene/pull/15742#issuecomment-3957258135
> VectorUtilBenchmark.binaryHalfByteSquareVector is quite a bit slower This worried me, so I attempted to change it back to operating on shorts (but still avoiding `convert` using reinterpret casting + bit manipulation). JMH benchmarks on AWS Graviton3 somehow improved further: ``` Benchmark (size) Mode Cnt Score Error Units VectorUtilBenchmark.binaryHalfByteDotProductBothPackedVector 1024 thrpt 15 19.555 ± 0.032 ops/us VectorUtilBenchmark.binaryHalfByteDotProductSinglePackedVector 1024 thrpt 15 20.531 ± 0.079 ops/us VectorUtilBenchmark.binaryHalfByteDotProductVector 1024 thrpt 15 26.234 ± 0.118 ops/us VectorUtilBenchmark.binaryHalfByteSquareBothPackedVector 1024 thrpt 15 16.225 ± 0.040 ops/us VectorUtilBenchmark.binaryHalfByteSquareSinglePackedVector 1024 thrpt 15 17.840 ± 0.040 ops/us VectorUtilBenchmark.binaryHalfByteSquareVector 1024 thrpt 15 20.381 ± 0.083 ops/us ``` -- 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]
