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

Nvidia to Acquire Arm for $40B

nvidianews.nvidia.com

Post reply on HN
Print view View original

211–220 of 784 posts

Re: Nvidia to Acquire Arm for $40B

#211

Post by dylan604 »

jacques_chester wrote: post #82
therealmarv wrote: post #55

Earlier quoted context omitted.

Have you read the press release at all? It's too early to judge this now. ARM will stay in Cambridge and Nvidia wants to invest in this place.

My experience of acquisitions is that sweet songs are sung to calm the horses. Then the next financial quarter comes around and the truck from the glue factory arrives. If you take at face value anything from a press release, earnings call or investor relations website, then I would like to take a moment to share with you the prospectus of Brooklyn Bridge LLC.

My money is currently tied up in ocean front property in Arizona.

Re: Nvidia to Acquire Arm for $40B

#212

Post by shaklee3 »

sillysaurusx wrote: post #196
shaklee3 wrote: post #166

Earlier quoted context omitted.

Please show me the API where I can write a generic function on a TPU. I'm talking about writing something like a custom reduction or a peak search, not offloading a tensor flow model. I'll make it easier for you, directly from Google's website: TPUs Cloud TPUs are optimized for specific workloads. In some situations, you might want to use GPUs or CPUs on Compute Engine instances to run your machine learning workloads…

Sure, here you go: https://www.tensorflow.org/api_docs/python/tf/raw_ops In my experience, well over 80% of these operations are implemented on TPU CPUs, and at least 60% are implemented on TPU cores. Again, if you give a specific example, I can simply write a program demonstrating that it works. What kind of custom reduction do you want? What's a peak search? As for workloads that GPUs can't do, we regularly train G…

Well, there you go. For one TensorFlow is not a generic framework like cuda is, so you lose a whole bunch of the configurability you have with cuda. So, for example, even though there is an FFT raw function, there doesn't appear to be a way to do more complicated FFTs, such as an overlap-save. This is trivial to do on a GPU, and is built into the library. The raw functions it provides is not direct access to the hardware and memory subsystem. It's a set of raw functions that is a small subset of the total problem space. And certainly if you are saying that running something on a TPU's CPU cores are in any way going to compete with a gpu, then I don't know what to tell you.

You did not give an example of something GPUs can't do. all you said was that TPUs are faster for a specific function in your case.

Re: Nvidia to Acquire Arm for $40B

#213

Post by diesal11 »

nolaspring wrote: post #173
QuixoticQuibit wrote: post #129

Earlier quoted context omitted.

Look at their AI/CUDA documentation and associated githubs. Many of their tools and libraries are open source. Tell me, what other AI platform works with x86 and PowerPC and ARM? Currently NVIDIA’s GPUs do.

I spent most of this afternoon tying to get cuda in docker to work on my Mac for a machine learning use case. It doesn’t. Because nvidia

"Because NVIDIA" is blatantly false.

CUDA support for docker containers is provided through the open source Nvidia-Docker project maintained by Nvidia[1]. If anything this is a great argument for NVIDIAs usage of open source.

Searching that project's issues shows that Nvidia-Docker support on MacOS is blocked by the VM used by Docker for Mac(xhyve) not supporting PCI passthrough, which is required for any containers to use host GPU resources.[2]

xhyve has an issue for PCI passthrough, updated a few months ago, which notes that the APIs provided by Apple through DriverKit are insufficient for this use case[3]

So your comment should really say "Because Apple"

[1] https://github.com/NVIDIA/nvidia-docker

[2] https://github.com/NVIDIA/nvidia-docker/issues/101#issuecomm...

[3] https://github.com/machyve/xhyve/issues/108#issuecomment-616...

Re: Nvidia to Acquire Arm for $40B

#214

Post by exikyut »

dragontamer wrote: post #105
ChuckMcM wrote: post #77

Earlier quoted context omitted.

I would love OpenPOWER to succeed. I just don't see the 48 pin QFP version that costs I don't see OpenPOWER going there, but I can easily see RISC-V going there. So, for the moment, that is the horse I'm betting on.

Not quite 48-pin QFP chips, but 257-pin embedded is still smaller than Rasp. Pi. (Just searched what NXP's newest Power-chip is, and its a S32R274: 2MB 257-pin BGA. Definitely "embedded" size, but not as small as Cortex-M0) To be honest, I don't think that NVidia/ARM will screw over their Cortex-M0 or Cortex-M0+ customers over. I'm more worried about the higher-end, whether or not NVidia will "play nice" with its big…

The FS32R274VCK2VMM appears to be the cheapest in this series; Digi-Key have it for $30, NXP has it for "$13 @ 10K". This is for a 200MHz part.

https://www.nxp.com/part/FS32R274VCK2VMM

https://www.digikey.com/product-detail/en/nxp-usa-inc/FS32R2...

The two related devkits list for $529 and $4,123: https://www.digikey.com/products/en/development-boards-kits-...

--

Those processors make quite a few reference to an "e200", which I think is the CPU architecture. I discovered that Digi-Key lists quite a few variants of this under Core Processor; and checking the datasheets of some random results suggests that they are indeed Power architecture parts.

https://www.digikey.com/products/en/integrated-circuits-ics/...

The cheapest option appears to be the $2.67@1000, up-to-48MHz SPC560D40L1B3E0X with 256KB ECC RAM.

Selecting everything >100MHz finds the $7.10@1000 SPC560D40L1B3E0X, an up-to-120MHz part that adds 1MB flash (128KB ECC RAM).

Restricting to >=200MHz finds the $13.32@500 SPC5742PK1AMLQ9R has which has dual cores at 200MHz, 384KB ECC RAM and 2.5MB flash, and notes core lock-step.

--

After discovering the purpose of the "view prices at" field, the landscape changes somewhat.

https://www.digikey.com/products/en/integrated-circuits-ics/...

The SPC574S64E3CEFAR (https://www.st.com/resource/en/datasheet/spc574s64e3.pdf) is 140MHz, has 1.5MB code + 64KB data flash and 96KB+32KB data RAM, and is available for $14.61 per 1ea.

The SPC5744PFK1AMLQ9 (https://www.nxp.com/docs/en/data-sheet/MPC5744P.pdf) is $20.55@1, 200MHz, 2.5MB ECC flash, 384KB ECC RAM, and has two cores that support lockstep.

The MPC5125YVN400 (https://www.nxp.com/docs/en/product-brief/MPC5125PB.pdf) is $29.72@1, 400MHz, supports DDR2@200MHz (only has 32KB onboard (S)RAM), and supports external flash. (I wonder if you could boot Linux on this thing?)

Re: Nvidia to Acquire Arm for $40B

#215

Post by sorenbouma »

sillysaurusx wrote: post #164
shaklee3 wrote: post #152

Earlier quoted context omitted.

A TPU is a chip you cannot program. It's purpose built and can't run the fraction of the type of workloads that a GPU can.

I don't know where all of this misinformation is coming from or why, but, as someone who has spent the last year programming TPUs to do all kinds of things that a GPU can't do, this isn't true. Are we going to simply say "Nu uh" at each other, or do you want to throw down some specific examples so I can show you how mistaken they are?

I'm a TPU user and I'd be interested to see a specific example of something that can be done on TPU but not GPU.

Perhaps I'm just not experienced enough with the programming model, but I've found them to be strictly less flexible/more tricky than GPUs, especially for things like conditional execution, multiple graphs, variable size inputs and custom ops.

Re: Nvidia to Acquire Arm for $40B

#216

Post by saiojd »

01100011 wrote: post #153

Can we,for once, hear the opinions of people in the chip industry and not the same tired posts from software folks? NVIDIA Bad! Ok, we get it. Do you have anything more insightful than that? I'm starting to feel like social media based on upvotes is a utter waste of time. Echo chambers and groupthink. People commenting on things they barely know anything about and getting validation from others who don't know anythin…

Agreed, upvotes are a failed experiment, especially for comments.

Re: Nvidia to Acquire Arm for $40B

#217

Post by dylan604 »

stupendousyappi wrote: post #74
realbarack wrote: post #66

Earlier quoted context omitted.

Because it has an offensive slur in it

People should be fighting to join their favorite Silicon Valley FANMAG. Some would prefer the Bill Gates FANMAG, others Jeff Bezos...

Sounds more like a F-MANGA. Gates goes Super Saiyan while Bezos builds a mechwarrior army.

Re: Nvidia to Acquire Arm for $40B

#218

Post by barbecue_sauce »

dheera wrote: post #202
QuixoticQuibit wrote: post #124

Earlier quoted context omitted.

NVIDIA’s hardware works on x86, PowerPC, and ARM platforms. Many of their AI libraries/tools are in fact open source. They stand to be a force that could propel ARM’s strength in data center and desktop computing. For some reason you’re okay with the current x86 duopoly held by AMD and Intel, both who have their own destiny over CPUs and GPUs. The HN crowd is incredibly biased against certain companies. Why not look…

> The HN crowd is incredibly biased against certain companies. No kidding, regarding the HN crowd. -- every time I post a comment criticizing Apple's monopoly and policies I get downvoted to oblivion, and I'd say that some of the things they do e.g. on the Apple store and proprietary hardware/software combinations are far more egregious than anything Nvidia has ever done. The HN algorithm basically encourages an echo…

What's the point of pretending that people don't know you will get downvoted for holding an unpopular opinion? It's tautological.

Re: Nvidia to Acquire Arm for $40B

#219

Post by Shared404 »

dheera wrote: post #202
QuixoticQuibit wrote: post #124

Earlier quoted context omitted.

NVIDIA’s hardware works on x86, PowerPC, and ARM platforms. Many of their AI libraries/tools are in fact open source. They stand to be a force that could propel ARM’s strength in data center and desktop computing. For some reason you’re okay with the current x86 duopoly held by AMD and Intel, both who have their own destiny over CPUs and GPUs. The HN crowd is incredibly biased against certain companies. Why not look…

> The HN crowd is incredibly biased against certain companies. No kidding, regarding the HN crowd. -- every time I post a comment criticizing Apple's monopoly and policies I get downvoted to oblivion, and I'd say that some of the things they do e.g. on the Apple store and proprietary hardware/software combinations are far more egregious than anything Nvidia has ever done. The HN algorithm basically encourages an echo…

Haven't looked at the rest of your posts, but if this gets flagged, it's probably from this:

[Edit: I disagree with my past self of having put this comment here. This is something that if one feels that they notice, they should probably comment on. Leaving it here for clarity's sake]

> The HN algorithm basically encourages an echo chamber of people who gang up and downvote/flag others who don't agree with the gang opinion.

or this:

> (Psst ... If you see this comment disappear after a while, it's probably because the same Apple fanboys found this comment and decided to hammer it down again.)

than this:

> criticizing Apple's monopoly and policies

Source: Have criticized Apple without having been downvoted and flagged.

Post reply on HN