Back then you wanted maximum compression like XZ, because the slowest part of the process was the download. Now especially with XZ awful decompress rate, the slowest part is extract. In many cases it's better to have 9% larger size, for 500% increase in extract, like you get with ZST.
Sure, you can say the problem is JSON, protobuf, whatever. But in a huge organization with hundreds or thousands of types of documents, it's a needless friction to require custom optimized formats for each one.
So a faster decompressor is often a no-brainer of a win and can have substantial dollar values attached.
There might be no latency benefits to that, but there's always a throughput gain from using fewer cpu cycles over all - the cpu cycles you would have spent decompressing can be used for other things.
For that reason single-core performance would still be nice to have and always great to have open source code which is performance centric so that we all get to find out "How the hell did they do it?" (it is very readable assembly [1])
> I'd like to see compression speeds and performance on AVX if AVX-512 is not available.
The ARM is probably more interesting in the elastic compute world right now, the AVX world is unlikely to get cheaper.
And unlike before, I don't need to wait for a vendor to sell me an SoC, Gravitons are already here.
[1] - https://github.com/SnellerInc/sneller/blob/master/ion/zion/i...
Benchmarks are hard though.