Robert Williams (crispysilicon.delete@this.gmail.com) on April 9, 2021 12:46 pm wrote:
> Linus Torvalds (torvalds.delete@this.linux-foundation.org) on April 9, 2021 9:25 am wrote:
> > Honestly, I'm done with Intel's market fragmentation crap with Xeon
> > CPU's having features that the normal consumer CPU's don't.
> >
> > So I won't even bother to try TSX until it's in a CPU in a machine that
> > is worth getting, and not some stratospherically priced Xeon thing.
>
> My takeaway from all of this so far is that TSX has it's use cases, but not for most consumer
> software anyway? Add onto that it's going to take a fairly complex implementation to be
> performance competitive and I just don't see it tricking down full flavor?
>
> I hate the fragmentation like poison, but I dont think it sounds
> like the it's worth the transistors in desktop/mobile.

My employer runs a lot of hand optimized numeric code. We started with AltiVec on PowerPC, then moved to SSE on x86 and are now using AVX2 on x86.

One reason we HAVE NOT moved to Avx-512 is that the developers like being able to run code on their desktop/laptop machines. Until recently, Avx-512 was pretty much only available on server parts.

Making it difficult (or impossible) to run code on developer machines discourages adoption of new capabilities.

Note that a SLOW Avx-512 implementation on the laptop/desktop chips would have been okay. The developers (other than the performance optimization) team don't need the code to run QUICKLY on their machines -- they just need it to run.