Raghuveer Devulapalli

> I'm sure this project never made the claim, I just recall Phoronix touting something like a 10x gain when numpy used it in place of std::sort I believe that...

32-bit indices weren't supported until recently: https://github.com/intel/x86-simd-sort/pull/108. Did you try it after this was merged?

your argsort implementation looks incorrect. You want to sort `idxs` based on the values in `vals`: therefore `vals` is the key and `idxs` is the value. ``` std::vector argSort32(int32_t *vals,...

`idxs` should have `numVals` unique values (basically `[0,1,2, ..., numVals-1]` in a jumbled up order, else there is something seriously wrong with the code.

thanks for your PR, allow me some time to review it. will get back to you as soon as I can :)

Your benchmark also reports unto a 14% improvement on `avx512_qselect ` which is a bit surprising since there should be no changes to the way quick select runs with this...

> benchmarks it looks ~1.8x faster, so maybe it might have been beating IPP's index radix sort Yeah, that is unfortunate. Hopefully future hardware won't need these mitigations and we...

@KungFuJesus PR #120 improves 32-bit key value sorting by a fair bit. Do you mind timing your benchmarks with this patch to see if it improves anything at your end?

No worries. You can keep it open if you wish, I don't mind either way.

outdated. Closing.