By: Michael S (already5chosen.delete@this.yahoo.com), November 4, 2019 9:58 am
Room: Moderated Discussions
Gabriele Svelto (gabriele.svelto.delete@this.gmail.com) on November 4, 2019 6:13 am wrote:
> anon (spam.delete.delete@this.this.spam.com) on November 4, 2019 6:03 am wrote:
> > You're missing the point.
> > Just because making something a mandatory part of the ISA would be a problem for low end implementations
> > is no excuse to ignore it completely and claim that fusion will fix everything.
> > That's the whole point of extensions.
> > They've given up on the "single cycle execution" rule because no one would take them seriously without
> > mul/div, yet they insist on 2R/1W with only wild handwaving about fusion removing all the downsides.
>
> Who is they? There's a lot of companies and people involved in designing the RISC-V ISA nowadays.
But is not Krste Asanović a BDFL?
> anon (spam.delete.delete@this.this.spam.com) on November 4, 2019 6:03 am wrote:
> > You're missing the point.
> > Just because making something a mandatory part of the ISA would be a problem for low end implementations
> > is no excuse to ignore it completely and claim that fusion will fix everything.
> > That's the whole point of extensions.
> > They've given up on the "single cycle execution" rule because no one would take them seriously without
> > mul/div, yet they insist on 2R/1W with only wild handwaving about fusion removing all the downsides.
>
> Who is they? There's a lot of companies and people involved in designing the RISC-V ISA nowadays.
But is not Krste Asanović a BDFL?