Following your suggestion, I went ahead and modified the scrambling formula. The crux of the problem is that the secret is allowed to be absolutely anything (it's user provided). As a consequence, it's a bad idea to…
Well, if you believe a better scrambling operation is possible, you are certainly welcomed to suggest one. Considering feedbacks on the algorithm is one of the objectives of the test phase. If the issue is about the…
According to the UMAC paper, the 32x32=>64 multiplication only contains 32-bit of entropy, even though it uses 64-bit space. That's understandable : most of the entropy will be in the middle of the register. That's…
wyhash is a close relative to mumhashv2, and feature approximately the same performance strength and weaknesses.
zstd availability is becoming more and more common nowadays. See for example this tracker : https://repology.org/metapackage/zstd/versions
There is now a pzstd implementation, if you wish to compare it to pigz
zstd goes at > 1 GB/s on uncompressible data. It has some fast heuristics for such cases too.
MetroHash source code is impressively close to xxHash one, to the point that it seems to be a tweaked version of it. Yet, the author never mentions a single word about it in its source.
In all tests I know, xxh64 should be about 2x faster than xxh32 on x86_64 systems. Surprisingly, it doesn't match with the readme table.
Following your suggestion, I went ahead and modified the scrambling formula. The crux of the problem is that the secret is allowed to be absolutely anything (it's user provided). As a consequence, it's a bad idea to…
Well, if you believe a better scrambling operation is possible, you are certainly welcomed to suggest one. Considering feedbacks on the algorithm is one of the objectives of the test phase. If the issue is about the…
According to the UMAC paper, the 32x32=>64 multiplication only contains 32-bit of entropy, even though it uses 64-bit space. That's understandable : most of the entropy will be in the middle of the register. That's…
wyhash is a close relative to mumhashv2, and feature approximately the same performance strength and weaknesses.
zstd availability is becoming more and more common nowadays. See for example this tracker : https://repology.org/metapackage/zstd/versions
There is now a pzstd implementation, if you wish to compare it to pigz
zstd goes at > 1 GB/s on uncompressible data. It has some fast heuristics for such cases too.
MetroHash source code is impressively close to xxHash one, to the point that it seems to be a tweaked version of it. Yet, the author never mentions a single word about it in its source.
In all tests I know, xxh64 should be about 2x faster than xxh32 on x86_64 systems. Surprisingly, it doesn't match with the readme table.