pitrou commented on PR #47515: URL: https://github.com/apache/arrow/pull/47515#issuecomment-3298723494
The benchmarks above are interesting @AntoinePrv . On all 4 machines, the scalar version is faster than the SIMD version for bit_width=20. Perhaps more insights could be gained by looking at the generated SIMD code. From a quick look at the AVX2 unpack32 functions, I see a lot of scalar shifts (`shld`) and single-element inserts (`vpinsrd`). Ideally, we would expect the compiler to generate shuffle instructions and vector shifts? -- 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]
