Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Arm is canceling Qualcomm's chip design license

bloomberg.com

Post reply on HN
Print view View original

161–170 of 480 posts

Re: Arm is canceling Qualcomm's chip design license

#161

Post by hnaccount_rng »

MBCook wrote: post #138
hajile wrote: post #129

Earlier quoted context omitted.

I don't believe any major company has done it. Even Intel failed numerous times to move away from x86 with iAPX432, i960, i860, and Itanium all failing to gain traction.

For Apple it was do or die the first few times. Until x86, if they didn’t move they’d just be left in the dust and their market would disappear. The ARM transition wasn’t strictly necessary like the last ones. It had huge benefits for them, so it makes sense, but they also knew what they were doing by then. In your examples (which are great) Intel wasn’t going to die. They had backups, and many of those seem guided m…

In a way that's also true for the x86->ARM transition, isn't it? I had an MacbookAir 2018. And.. "it was crap" is putting it very, very mildly. Yes it was still better than any Windows laptop I got since and much less of a hassle than any Linux laptop that I'm aware of in my circle. But the gap was really, really small and it cost twice as much.

But the most important part for the working of the transition is probably that, in any of theses cases, the typical final user didn't even notice. Yes a lot of Hackernews-like people noticed as they had to recompile some of their programs. But most people :tm: didn't. They either use AppStore apps, which were fixed ~immediately or Rosetta made everything runnable, even if performance suffered.

But that's pretty much the requirement you have: You need to be handle to transition ~all users to the new platform with ~no user work and even without most vendors doing anything. Intel never could provide that, not even aim for it. So they basically have to either a) rip their market in pieces or b) support the "deprecated" ISA forever.

Re: Arm is canceling Qualcomm's chip design license

#162

Post by wmf »

msh wrote: post #149
monocasa wrote: post #123

Earlier quoted context omitted.

RISC-V is very competitive with ARM when comparing similar PPA niches.

High performance and low power laptop and phone SoC’s, no way. There exists no competitive risc-v chip.

We're all assuming that Oryon-V is already being developed.

Re: Arm is canceling Qualcomm's chip design license

#163

Post by dagmx »

snvzz wrote: post #141
dagmx wrote: post #130

Earlier quoted context omitted.

Fair, though I don’t think translation is a good long term strategy. You need native apps otherwise you’re always dealing with a ~20-30% disadvantage. The competition isn’t sitting still either and QC already hit this with Intel stealing their thunder with Lunar Lake. They’re efficient enough that the difference in efficiency is far overshadowed by their compatibility story. Ecosystem support will always go to the in…

>You need native apps For native apps, you need users. For users, you need emulation. It cannot be overstated how important successful x86 emulation is for the migration to anything else to be feasible.

I think you just ignored the rest of my comment though which specifically addresses why I don’t think just relying on translation is an effective strategy. Users aren’t going to switch to a platform that has lower compatibility when the incumbent has almost as good efficiency and performance.

Re: Arm is canceling Qualcomm's chip design license

#164

Post by snvzz »

saagarjha wrote: post #153
snvzz wrote: post #152

Earlier quoted context omitted.

>It’s easy to claim a lot of things. It certainly is easy to casually spread fear and doubt. But it is really far-fetched to think that the people at Tenstorrent, who have successfully delivered very high performance microarchitectures in other companies before, are lying about Ascalon, and that LG is helping them do that. It would even be more far fetched to claim that Ventana Veyron V2, SiFive P870, Akeana 5000-ser…

[flagged]

[flagged]

Re: Arm is canceling Qualcomm's chip design license

#165

Post by sarlalian »

coder543 wrote: post #156
IshKebab wrote: post #148

Earlier quoted context omitted.

1. That doesn't mean you can just slap a RISC-V decoder on an ARM chip and it will magically work though. The semantics of the instructions and all the CSRs are different. It's going to be way more work than you're implying. But Qualcomm have already been working on RISC-V for ages so I wouldn't be too surprised if they already have high performance designs in progress.

That is a good comment, and I agree things like CSR differences could be annoying, but compared to the engineering challenges of designing the Oryon cores from scratch… I still think the scope of work would be relatively small. I just don’t think Qualcomm seriously wants to invest in RISC-V unless ARM forces them to.

The bigger question is how much of their existing cores utilize Arm IP… and how sure are they that they would find all of it?

Re: Arm is canceling Qualcomm's chip design license

#166

Post by snvzz »

MBCook wrote: post #151
snvzz wrote: post #146

Earlier quoted context omitted.

>And if your emulator is too good, what stops ISVs from saying “you did it for us, we don’t have to care”? So once again they don’t have to do it at all and you have no native software. x86 emulation enables adoption. Adoption means having an user base. Having an user base means developers will consider making the platform a target. >Saying “Ha ha, just kidding, it’s RISC-V now” would be a disaster. Would it now? If…

> If anything, offering RISC-V support as well would further reinforce the idea that Windows is ISA-independent, and not tied to x86 anymore. Anymore? It’s been independent since the 90s. It’s only ISVs that have been an issue. And a rug pull is a fantastic way to scare all the ISVs far far away.

Whose's rug would even be pulled?

Re: Arm is canceling Qualcomm's chip design license

#167

Post by wmf »

fargle wrote: post #102

> If Arm follows through with the license termination, Qualcomm would be prevented from doing its own designs using Arm’s instruction set i'm not sure this is true. certainly "chip" IP has been a real legal quagmire since, forever. but it was my understanding that you could neither patent nor copyright simply an "instruction set". presumably what you get from ARM with an architecture license would be patent licenses…

You can patent something like "any possible hardware circuit that implements [the functionality of some weird yet mandatory ARM instruction]". The patent doesn't cover emulators because they're not hardware.

Way back in the day there were some MIPS patents that only covered a few instructions so people would build not-quite-MIPS clone CPUs without paying any royalties.

Re: Arm is canceling Qualcomm's chip design license

#168

Post by chasil »

lizknope wrote: post #69
chasil wrote: post #50

Earlier quoted context omitted.

The phones haven't been custom ARM chips since 32-bit Krait, IIRC. This is about Nuvia. https://en.m.wikipedia.org/wiki/Krait_(processor)

Snapdragon 805 had a 32-bit Krait designed by Qualcomm https://www.qualcomm.com/products/mobile/snapdragon/smartpho... 810 had a 64-bit core designed by ARM https://www.qualcomm.com/products/mobile/snapdragon/smartpho... 820/821 had a 64-bit Kryo custom core designed by Qualcomm https://www.qualcomm.com/products/mobile/snapdragon/smartpho... After that it was all cores from ARM. The custom CPU team worked on their se…

I need to have a closer look. Thanks.

Re: Arm is canceling Qualcomm's chip design license

#170

Post by wmf »

IshKebab wrote: post #154
bhouston wrote: post #20

Earlier quoted context omitted.

Most people do not realize how slow RISC-V is right now. Yes, it will definitely get better, but it will take some time given how far behind it is. Like 30x slower than a top of the line Apple Mx series CPU. Maybe there is a high performing RISC-V chip out there but I haven't yet run into one. RISC-V benchmarks: https://browser.geekbench.com/search?q=RISC-V . Compare to an Apple M4 benchmark: https://browser.geekbenc…

You're confusing the ISA with the chip. Current RISC-V chips are slower than high performance ARM ones, but that's because you don't start by designing high performance chips! You start with small embedded cores and work your way up. Exactly the same thing happened with ARM. It started in embedded, then phones, and finally laptops and servers. ARM was never slow, they just hadn't worked up to highly complex high perf…

you don't start by designing high performance chips! You start with small embedded cores and work your way up.

I disagree. For example, the first PowerPC was pretty fast and went into flagship products immediately. Itanium also went directly for the high end market (it failed for unrelated reasons). RISC-V would be much better off if some beastly chips like Rivos were released early on.

Post reply on HN