61–70 of 135 posts
Earlier quoted context omitted.
They were pretty clear at Hot Chips that it's native
.... I -so- miss RealWorldTech write-ups, I'd love to see what David Kanter would have to say about this thing...
Earlier quoted context omitted.
There are already microcontrollers that have both arm + riscv support. This isn't something insane.
RP2350 has separate cores for that. This is one core that speaks both.
I was reading HN comments yesterday shitting on modern IBM for being a non tech consulting company that has not innovated since the mid nineties.
well that's nonsense. IBM does incredibly cool stuff. https://research.ibm.com/blog
Earlier quoted context omitted.
RP2350 has separate cores for that. This is one core that speaks both.
To my understanding, the RP2350 has two ARM cores and two RISC-V cores, the two pairs are separate, and only one architecture can be used at a time on the chip.
Earlier quoted context omitted.
ARM has better software support for AI applications and half of their presentation was about their inference accelerators that can go in the mainframes (and POWER machines). IBM mainframes are almost designed by their users. The previous generation skipped a lot of speed boost on the CPU side because their users didn’t want the machine to blow over their power delivery limits. Now, with their architecture behind it,…
At least back in the day, there was talk about Nvidia + ppc64le. Wasn't there even a supercomputer with that setup? But I guess that has fallen by the wayside.
Earlier quoted context omitted.
well that's nonsense. IBM does incredibly cool stuff. https://research.ibm.com/blog
What does IBM actually do? I just can never understand their business and operating model. It seems like they just do a bunch of random stuff and sell to the most enterprisey of enterprises.
Earlier quoted context omitted.
Yeah, their cache work is undeniably really cool. That being said I think it's a natural consequence of the difference between a mainframe and commodity servers. A mainframe is going to be running pretty disparate workloads simultaneously, so it makes sense to steal from your neighbor if they aren't using their cache. Whereas it's more likely that a commodity server is just running the same server on each core, and i…
Even though their CPUs are insanely fast, the real power of mainframes is in their IO. The amount of data you can push through those machines is absolutely mind blowing.
Huh. ARM instead of ppc64le?
ARM has better software support for AI applications and half of their presentation was about their inference accelerators that can go in the mainframes (and POWER machines). IBM mainframes are almost designed by their users. The previous generation skipped a lot of speed boost on the CPU side because their users didn’t want the machine to blow over their power delivery limits. Now, with their architecture behind it,…
I was reading HN comments yesterday shitting on modern IBM for being a non tech consulting company that has not innovated since the mid nineties.
The z mainframe team does good technical work but then the high price cancels out all the value of that work. I'm not sure if that counts as innovation or not.
Earlier quoted context omitted.
But those ARM and s390x decoders have a “Telum III” architecture behind them with a cache that’s pretty innovative. IBM has never stopped innovating. It’s just that most people can’t afford their machines.
Yeah, their cache work is undeniably really cool. That being said I think it's a natural consequence of the difference between a mainframe and commodity servers. A mainframe is going to be running pretty disparate workloads simultaneously, so it makes sense to steal from your neighbor if they aren't using their cache. Whereas it's more likely that a commodity server is just running the same server on each core, and i…