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

221–230 of 480 posts

Re: Arm is canceling Qualcomm's chip design license

#221

Post by snvzz »

dagmx wrote: post #163
snvzz wrote: post #141

Earlier quoted context omitted.

>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.

>when the incumbent has almost as good efficiency and performance.

The incumbent is the only two companies -Intel and AMD- that can make x86 hardware.

The alternative is the rest of the industry.

Thus having a migration path should be plenty on its own.

Intel and AMD can both join by making RISC-V or ARM hardware themselves. My take is that they will too, eventually, come around. Or they'll just disappear from relevance.

Re: Arm is canceling Qualcomm's chip design license

#223

Post by saagarjha »

darksaints wrote: post #197
saagarjha wrote: post #139

Earlier quoted context omitted.

NDK exists.

The companies with large relevant apps running on the NDK are well staffed and funded enough to recompile.

It's not about whether they can, it's whether they will. History has proven that well-resourced teams don't like doing this very much and will drag their feet if given the chance.

Re: Arm is canceling Qualcomm's chip design license

#225

Post by objclxt »

m463 wrote: post #198
hajile wrote: post #52

Earlier quoted context omitted.

Qualcomm doesn't have nearly as much to lose as ARM does and they know it. Qualcomm is almost certainly ARM's biggest customer. If ARM loses, Qualcomm doesn't have to pay out. If ARM wins, Qualcomm moves to RISC-V and ARM loses even harder in the long-term. The most likely outcome is that Qualcomm agrees to pay a slight bit more than they are currently paying, but nowhere near what ARM is demanding and in the meantim…

> Qualcomm doesn't have nearly as much to lose as ARM does and they know it. question: isn't arm somewhat apple? ...Advanced RISC Machines Limited and structured as a joint venture between Acorn Computers, Apple, and VLSI Technology. https://en.wikipedia.org/wiki/Arm_Holdings#Founding

> question: isn't arm somewhat apple?

Not for decades. Apple sold its stake in ARM when Steve Jobs came back, they needed the money to keep the company going.

Re: Arm is canceling Qualcomm's chip design license

#226

Post by adrian_b »

haerwu wrote: post #192
lizknope wrote: post #69

Earlier quoted context omitted.

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…

When you look at https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.ht... table then you can see that in Snapdragon 8xx series the first "ARM cores out of shelf" was 888 in 2020. 865 (2019) has Cortex-A77 + Kryo 4xx Silver 888 (2002) uses Cortex-X1 + Cortex-A78 + Cortex-A55 cores

Most of the cores branded "Kryo" have negligible differences from the original Arm cores. There might be some differences in the cache memories and in the interfaces between the cores and the rest of the Qualcomm SoC, but there are no differences in the inner CPU cores.

Snapdragon 865 has standard Arm cores. The same is true for the older Snapdragon 855, Snapdragon 845 and Snapdragon 835, which I am using or I have used in my phones.

The claim of Qualcomm that those cores have been "semi-custom", is mostly BS, because the changes made by Qualcomm to the cores licensed from Arm have been minimal.

Re: Arm is canceling Qualcomm's chip design license

#227

Post by nasretdinov »

biosboiii wrote: post #203
hajile wrote: post #52

Earlier quoted context omitted.

Qualcomm doesn't have nearly as much to lose as ARM does and they know it. Qualcomm is almost certainly ARM's biggest customer. If ARM loses, Qualcomm doesn't have to pay out. If ARM wins, Qualcomm moves to RISC-V and ARM loses even harder in the long-term. The most likely outcome is that Qualcomm agrees to pay a slight bit more than they are currently paying, but nowhere near what ARM is demanding and in the meantim…

Thing is businesses don't work like side-projects do. Qualcomm is more or less a research company, the main cost of their business is paying engineers to build their modems/SoCs/processors/whatever. They have been working with ARM for the last, I dont know, 20 years? Even if they manage to switch to RISC-V, and each employee has negative performance impact of like 15% for 2-3 years this ends up in billions of dollars…

> If corporate would force me to work with idk Golang instead of TypeScript

I think the most evil thing to do would be to switch places: TS for backend, Go for frontend. It can certainly work though!

Re: Arm is canceling Qualcomm's chip design license

#228

Post by mazurnification »

coder543 wrote: post #75
nemothekid wrote: post #62

Earlier quoted context omitted.

> Qualcomm moves to RISC-V and ARM loses even harder in the long-term. I think long term is doing a lot of heavy lifting here. How long until: 1. Qualcomm develops a chip that competitive in performance to ARM 2. The entire software world is ready to recompile everything for RISC-V Unless you are Apple I see such a transition taking a decade easily.

> 1. Qualcomm develops a chip that competitive in performance to ARM Virtually all high performance processors these days operate on their own internal “instructions”. The instruction decoder at the very front of the pipeline that actually sees ARM or RISC-V or whatever is a relatively small piece of logic. If Qualcomm were motivated, I believe they could swap ISAs relatively easily on their flagship processors, and…

I am fan of the Jeff Geerling Youtube series in which he is trying to make GPU (AMD/Nvidia) run on Raspbery Pi. It is not easy - and they have linux kernel source code available to modify. Now imagine all Qualcomm clients have to do similar stuff with their third party hardware, possibly with no access to source code of drivers. Then debug and fix for 3y all the bugs that pop up in the wild. What a nightmare.

Apple at least have full control on hardware stack (Qualcomm do not as they only sells chips to others).

Re: Arm is canceling Qualcomm's chip design license

#229

Post by Joel_Mckay »

mrweasel wrote: post #211
SG- wrote: post #68

Earlier quoted context omitted.

you think they can just flip a RISC-V switch and keep all the performance instantly? I can't really understand the logic from some people here.

People also seem to forget that everything needs to be ported. If you're an Android manufacturer, you're not going to stop shipping phones, waiting for the Android RISC-V to catch-up to ARM, or for RISC-V to get the speed and features of current ARM CPUs. You're going to buy ARM processors from another vendor. The Windows ARM port is going to take even longer, I doubt that Microsoft has that working at anything beyon…

In theory, the Raspberry Pi foundation could easily move 3 million 1.8GHz RVA23 in 1 quarter... with 64 cores + DSP ops it wouldn't necessarily need a GPU initially. =3

Re: Arm is canceling Qualcomm's chip design license

#230

Post by numpad0 »

dagmx wrote: post #23
talldayo wrote: post #2

Could be the best thing that's ever happened for RISC-V!

Maybe fine for Android but this will set their windows plans back another decade if it happens It has taken them that long to make arm be a thing on windows and that’s building on people porting stuff to arm for Mac to finally get momentum. RISC-V with windows will be an eternity to be feasible.

Just something I as a random person been thinking, how likely is next version of Windows _not_ going to be something Linux-based with WINE+Bochs preinstalled?

Windows branding is now forever tied with x86/x64 Win32 legacy compatibility, meanwhile WSL had captured back a lot of webdevs from Mac. Google continues to push Chrome, but Electron continues to grow side by side. Lots of stuff happening with AI on Linux too, with both Windows and Mac remaining to be consumer deployment targets. Phone CPUs are fast enough to run some games on WINE+Bochs.

At this point, would it not make sense for MS to make its own ChromeOS and bolt-on an "LSW"?

Post reply on HN