SSE4.2 functions

[nemequ]

It would be good to support the SSE4.2 instruction set, which are mostly string functions.

This might be a good first issue; you don't need to implement all of the functions at once, and you if your machine supports SSE4.2 natively it's pretty easy to test.

You can find details about each one at https://software.intel.com/sites/landingpage/IntrinsicsGuide/#techs=SSE4_2

For progress, see https://github.com/simd-everywhere/implementation-status/blob/main/x86.md#sse42

[mr-c]

@nemequ Could you set up the build / test infrastructure for this? There is some interest @ FU Berlin in using SIMDe w/ SSE4.2

[nemequ]

It's all ready to go, though it was a bit difficult to understand how to use it without looking at another ISA extension. I just added _mm_cmpgt_epi64 (11b0c2e7e08afbddad99ebb26ed66b52568a8ab7) as an example, hopefully that helps clear things up.

[FaresSalem]

I might consider this issue to work on as part of GSoC, is anybody working on it already?

[nemequ]

Yes, @masterchef2209 is planning to work on this. Sorry.

[pthariensflame]

Any progress on this?

[sebpop]

I'm missing intrinsic _mm_cmpestri.

[jserv]

I'm missing intrinsic _mm_cmpestri.

Recently, SSE2NEON implements both _mm_cmpestri and _mm_cmpestrm.

[mr-c]

I'm missing intrinsic _mm_cmpestri.

Recently, SSE2NEON implements both _mm_cmpestri and _mm_cmpestrm.

Yes, they have all of the SSE4.2 functions we are missing; porting those to SIMDe style would be greatly appreciated!

https://github.com/DLTcollab/sse2neon/blob/39d854002840f12baa85cfdf01b120eabdfa76ed/sse2neon.h#L8093-L8097