Mark Roulo (nothanks.delete@this.xxx.com) on March 31, 2021 12:15 pm wrote:
> Linus Torvalds (torvalds.delete@this.linux-foundation.org) on March 31, 2021 12:00 pm wrote:
> > Linus Torvalds (torvalds.delete@this.linux-foundation.org) on March 31, 2021 11:54 am wrote:
> > >
> > > In reality, TSX is disabled pretty much everywhere either due
> > > to outright CPU bugs, or due to all the side channel leaks.
> >
> > Btw, I would like to say that I was really hopeful about transactional memory.
> > I'd have absolutely loved for it to be useful. So my negative comments about
> > it are about how disappointed I've been with the reality of it.
>
> Any idea what is up with IBM's zSeries mainframes and transactional memory? They
> started shipping it in 2012 and continue to provide it with the newer CPUs.
>
> I can imagine that the concept works fine, that IBM got it right, and Intel is just struggling.
>
> I can also imagine that it is so niche that none of this really matters at all.
>
> IBM added transactional memory to POWER (with POWER8, I think), so it seems unlikely to just "not work" ...

Here is an interesting piece on expanding Hardware Transactional Memory on IBM systems:

https://arxiv.org/pdf/2003.03317.pdf