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

Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

tomshardware.com

Post reply on HN
Print view View original

361–370 of 380 posts

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#361

Post by shihab »

slavik81 wrote: post #185
shihab wrote: post #83

Earlier quoted context omitted.

But you can't support Pytorch without a proper foundation in place. They don't need to support zillion _end_ libraries, sure, but they do need to have at least a very good set of standard libraries, equivalent of Cublas, Curand etc. And they don't. My work recently had me working with rocRAND (Rocm's answer to Curand). It was frankly pretty bad- the design, performance (50% slower in places that don't make any sense…

If you haven't already, please consider filing issues on the rocrand GitHub repo for the problems you encountered. The rocrand library is being actively developed and your feedback would be valuable for guiding improvements.

Appreciate it, will do.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#362

Post by frognumber »

krapp wrote: post #235
code_biologist wrote: post #230

Earlier quoted context omitted.

Long ago, under a different account, I emailed dang about removing some comment content that became too identifying only years after the comments in question. He did so and was very gracious about it. dang, you're cool af and you make HN a great place!

You're being very obsequious about having to personally get approval from a moderator to do on your behalf something every other forum lets you do on your own by default.

Plus, dang does a good job.

Not a perfect job -- everyone screws up once in a while -- but this forum works better than most.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#363

Post by latchkey »

PeterisP wrote: post #360
latchkey wrote: post #339

Earlier quoted context omitted.

> The way I see it, the whole point of ROCm support is being able to service the many users who have pre-existing AMD cards and nothing else available. ROCm is a stack of a whole lot of stuff. I don't see a stack of software being "the whole point". > the thing I need from AMD is to ensure that the ROCm support I make will work without hassle for these end-users with random old AMD gaming cards (because these are the…

I'm talking about what would be the point for someone to add ROCm support to various pieces of software which currently require CUDA, as IMHO this is the core context not only of this thread but of the whole discussion of this article - about ROCm becoming a widely used replacement or alternative for CUDA. > "ROCm is primarily targeted at discrete professional GPUs" That's kind of true, and that is a big part of the…

> what would be the point for someone to add ROCm support to various pieces of software which currently require CUDA

It isn't just old cards though, CUDA is a point of centralization on a single provider during a time when access to that providers higher end cards isn't even available and that is causing people to look elsewhere.

ROCm supports CUDA through the included HIP projects...

https://github.com/ROCm/HIP

https://github.com/ROCm/HIPCC

https://github.com/ROCm/HIPIFY

The later will regex replace your CUDA methods with HIP methods. If it is as easy as running hipify on your codebase (or just coding to HIP apis), it certainly makes sense to do so.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#364

Post by dang »

_7il4 wrote: post #261
latchkey wrote: post #188

Earlier quoted context omitted.

Normally, I wouldn't do that, but this time I felt like both comments were intentionally inflammatory and then the context for my response was lost. "literally nothing" is also wrong given that they just had a large press announcement on Dec 6th (yt as part of my response below), where they spent 2 hours saying (and showing) they are serious. The second comment was made and then immediately deleted, in a way that was…

I deleted it because I was in an extremely bad mood and later realized it was simply wrong of me to post it and vent my unrelated frustration in those comments. I think it's in extremely bad taste to repost what I wrote when I made the clear choice to delete it.

(Posting here because I don't have an email address for you.)

I reassigned your comments in this thread to a random user ID, so it's as if you had used a throwaway account to post them and there's no link to your main account. I also updated the reference to your username in another comment. Does that work for you?

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#365

Post by janwas »

vkazanov wrote: post #311
jauntywundrkind wrote: post #204

Earlier quoted context omitted.

I don't disagree anywhere but I don't think any of these statements actually condemn Xeon Phi outright. It didn't work at the time, and doing it with so little software support to tile out workloads well was a big & possibly bad gambit, but I'm so unsure we can condemn the architecture. There seems to be so few folks who made good attempts and succeeded or failed & wrote about it. I tend to think there was tons of un…

I don't thing anybody seriously considered Phi's for generic compute or something. Most experimenters saw it as a way to have something GPU-like in terms of raw power but with no limitations charateristic of SIMT's. Like, slightly different code paths for threads doing number crunching or something. But it turns out that it's easier to force everything into a matrix. Or a very big matrix. Or a very-very-very big matr…

Why are we not also talking about memory bandwidth? Personal opinion: this is the key. The latest Phi had about 100 GB/s in 2017. The contemporary Nvidia GTX 1080: 320 GB/s.

When CPUs actually come with bandwidth and a decent vector unit, such as the A64FX, lo and behold, they lead the Top500 supercomputer list, also beating out GPUs of the day.

Why have we not been getting bandwidth in CPUs? Is it because SPECint benchmarks do not use much? Or because there is too much branch-heavy code, so we think hundreds of cores are helpful?

Existing machines are ridiculously imbalanced, hundreds of times more compute vs bandwidth than the 1:1 still seen in the 90s. Hence matmul as a way of using/wasting the extra compute.

The AMD MI300a looks like a very interesting development: >5 TB/s shared by 24 cores plus GPUs.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#366

Post by pjmlp »

AnthonyMouse wrote: post #355
pjmlp wrote: post #275

Earlier quoted context omitted.

Nah, POSIX on servers is only relevant enough for language runtimes and compilers, which then use their own package managers and cloud APIs for everything else. Alongside a cloud shell, which yeah, we now have a VT100 running on a browser window. There is a reason why there are USENIX papers on the loss of POSIX relevance.

> Nah, POSIX on servers is only relevant enough for language runtimes and compilers, which then use their own package managers and cloud APIs for everything else. Those things are a different level of abstraction. The cloud API is making POSIX system calls under the hood, which would allow the implementation of the cloud API to be ported to different POSIX-compatible systems (if anybody cared to). > There is a reason…

Hardly as many recent TCP/IP features aren't fully exposed by POSIX socket API, rather OS specific APIs.

Security and asynchronous servers are also hardly implemented with raw POSIX APIs.

POSIX also doesn't have anything to say about hypervisors, containers, kubernetes infrastructure, or unikernels.

Nor it says anything about infrastructure written in Go, Java, .NET, Rust, C++.

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#367

Post by rbanffy »

ladberg wrote: post #39
rbanffy wrote: post #12

Earlier quoted context omitted.

Wouldn't a 100% Cuda-compatible toolchain suffice? Then you could write your software for Cuda and the software environment would run it on whatever is on your computer.

CUDA the language itself isn't necessarily the biggest obstacle for porting code, it's the usage of low level hardware features. You'd have to make a chip that's pretty dang close to Nvidia's before most hand-written CUDA code could run on it performantly.

What is CUDA not abstracting away? Is it geometry of the SIMD pipelines or the functionalities they have that would be absent (and couldn’t be emulated) by other implementations?

In many ways it feels like the same situation we had in the 70’s and 80’s personal computers, with many different software bases divided by different hardware implementations. In that regard, Unix was a boon in that it allowed one to write software that’d be compiled out of a single source into multiple architectures (rather than the PC-clone way, where non-identical implementations were driven to extinction).

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#368

Post by rbanffy »

quickthrower2 wrote: post #237
rbanffy wrote: post #4

Earlier quoted context omitted.

While we are at it, why not both? Also, can we move away from Windows and Office as well? And SharePoint, please? And add good search capabilities to Confluence.

Office and x86 are both things I like because 3rd parties can create compatible ware.

We can create compatible things against any open API using any ISA (and just about any ISA is nicer than x86 right now).

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#369

Post by tester756 »

jbm wrote: post #207
tester756 wrote: post #161

Earlier quoted context omitted.

>Intel spent more than a decade under Otellini, Krzanich and Swan. Bean counters. It still doesn't change mistake in your original message. >Gelsinger was appointed out of desperation, but the problem runs much deeper. How much "much deeper"? VPs? middle level managers? engineers? The example goes from the top, so if he can change the culture at the top, it will eventually get deeper.

> as technical and strategic It seems that this is an AND not an OR.

Point is valid regardless of "AND" or "OR"

He is both - technical and has a vision

Re: Intel CEO: 'The entire industry is motivated to eliminate the CUDA market'

#370

Post by tester756 »

natbennett wrote: post #201
tester756 wrote: post #125

Earlier quoted context omitted.

>finds a CEO who is as technical and strategic, as opposed to the bean-counters Did you just call Gelsinger a "non-technical"? wow, how out of touch with reality >Gelsinger first joined Intel at 18 years old in 1979 just after earning an associate degree from Lincoln Tech.[9] He spent much of his career with the company in Oregon,[12] where he maintains a home.[13] In 1987, he co-authored his first book about program…

If you read carefully you’ll see the comment is “as technical and strategic.” That’s very different from “non-technical.” He was clearly capable of leading a team to develop a new processor but that’s not the issue here.

What makes you think that he is not strategic?

I believe his vision/strategy is really sound

Post reply on HN