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

181–190 of 380 posts

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

#181

Post by alexey-salmin »

brindlejim wrote: post #158
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…

Intel spent more than a decade under Otellini, Krzanich and Swan. Bean counters. Gelsinger was appointed out of desperation, but the problem runs much deeper. I doubt that culture is gone. It has already cost Intel many opportunities.

Otellini wasn't an engineer but still he made the historical x86-mac deal, pushed like crazy for x86-android and owned the top500 with xeon phi.

The downfall began with Krzanich who had no goal besides raising the stock price and no strategy other than cutting long-term projects and other costs that got in the way. What a shame.

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

#182

Post by aseipp »

Figs wrote: post #105
bartwr wrote: post #16

If they create a better tool chain, ecosystem, and programming experience than CUDA and compatible with all computational platforms at their peak performance - awesome! Everyone wins! Until then, it's a bit funny claim, especially considering what a failure OpenCL was (programmer's experience and fading support). Or trying to do GPGPU with compute shaders in DX/GL/Vulkan. Are they really "motivated"? Because they had…

I wish AMD or Intel would just ship a giant honking CPU with 1000s of cores that doesn't need any special purpose programming languages to utilize. Screw co-processors. Screw trying to make yet another fucked up special purpose language -- whether that's C/C++-with-quirks or a half-assed Python clone or whatever. Nuts to that. Just ship more cores and let me use real threads in regular programming languages.

It doesn't work if you're going against GPUs. All the nice goodies we are accustomed to on large desktop x86 machines with gigantic caches and huge branch predictor area and OOO execution engines -- the features that yield the performance profile we expect -- simply do not translate or scale up to thousands of cores per die. To scale that up, you need to redesign the microarchitecture in a fundamental way to allow more compute-per-mm^2 of area, but at that point none of the original software will work in any meaningful capacity because the pipeline is so radically different, it might as well be a different architecture entirely. That means you might as well just write an entirely different software stack, too, and if you're rewriting the software, well, a different ISA is actually the easy part. And no, shoving sockets on the mobo does not change this; it doesn't matter if it's a single die or multi socket. The same dynamics apply.

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

#183

Post by cavisne »

My hunch is that there is some fundamental misunderstanding of what CUDA is and why it works. Its been like 6 years now of well funded attempts to displace CUDA, and there has been very little progress. In fact I'd argue its gone backwards as things like FlashAttention have further locked in the benefits of CUDA & Nvidia chips.

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

#184

Post by CuriousCosmic »

jorvi wrote: post #162
pgeorgi wrote: post #88

Earlier quoted context omitted.

> for 2 years already ... All that has happened is they launched a very mid GPU Hardware development cycles are closer to 5 years. So while he might have gotten some adjustments done on the designs so far, if he turned the ship around it'll take a while longer to materialize. The software side is more agile, so any tea leave reading to discern what Gelsinger's strategy looks like is best done over there.

Not only that, for a “first” (not sure how much of Larrabee was salvaged) discrete GPU attempt, Intel Arc is fantastic. Look at the first GPUs Nvidia and ATI launched. It’s only when you put them up against Nvidia and AMDs comes-with-decades-of-experience offerings that Intel’s GPUs seem less than stellar.

Yeah Arc is incredible in how much it accomplished as a first attempt and as long as they keep at it without chopping it up into a bunch of artificially limited market segments then it'll probably be incredibly competitive in a few generations.

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

#185

Post by slavik81 »

shihab wrote: post #83
lacker wrote: post #66

Earlier quoted context omitted.

The funny thing to me is that so much of the "AI software ecosystem" is just PyTorch. You don't need to develop some new framework and make it popular. You don't need to support a zillion end libraries. Just literally support PyTorch. If PyTorch worked fine on Intel GPUs, a lot of people would be happy to switch.

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.

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

#186

Post by zozbot234 »

raphlinus wrote: post #178
zozbot234 wrote: post #176

Earlier quoted context omitted.

How feasible would it be to target Vulkan 1.3 or such from standard SYCL (as first seen in Sylkan, for earlier Vulkan Compute)? Is it still lacking the numerical properties for some math functions that OpenCL and SYCL seem to expect?

That's a really good question. I don't know enough about SYCL to be able to tell you the answer, but I've heard rumblings that it may be the thing to watch. I think there may be some other limitations, for example SYCL 2020 depends on unified shared memory, and that is definitely not something you can depend on in compute shader land (in some cases you can get some of it, for example with resizable BAR, but it depend…

https://enccs.github.io/sycl-workshop/unified-shared-memory/ seems to suggest that USM is still a hardware-specific feature in SYCL 2020, so compatibility with hardware that requires a buffer copying approach is still maintained. Is this incorrect?

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

#187

Post by ac29 »

brindlejim wrote: post #15

Fun fact: More than half of all engineers at NVIDIA are software engineers. Jensen has deliberately and strategically built a powerful software stack on top of his GPUs, and he's spent decades doing it. Until Intel finds a CEO who is as technical and strategic, as opposed to the bean-counters, I doubt that they will manage to organize a successful counterattack on CUDA.

Intel has over 15,000 software engineers, per their website. I couldn't find a number for NVIDIA, but it looks like they have a bit above 26k total employees.

So, its very likely Intel has more software engineers than NVIDIA. Intel has far more products than NVIDIA though, so NVIDIA almost certainly has more software engineers working on GPU.

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

#188

Post by latchkey »

frognumber wrote: post #166
latchkey wrote: post #130

Earlier quoted context omitted.

What _7il4 removed were these two comments: "AMD is not serious, and neither is Intel for that matter. Their software are piles of proprietary garbage fires. They may say they are serious but literally nothing indicates they are." "Yes, and ROCm also doesn't work on anything non-AMD. In fact it doesn't even work on all recent AMD gpus. T"

It's not too polite to repost what people removed. Errors on the internet shouldn't haunt people forever. However, my experience is that the comments about AMD are spot-on, with the exception of the word "proprietary." Intel hasn't gotten serious yet, and has a good track record in other domains (compilers, numerical libraries, etc.). They've been flailing for a while, but I'm curious if they'll come up with somethin…

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 to send me a message directly. It is what irked me enough to post their comments back.

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

#189

Post by aseipp »

jauntywundrkind wrote: post #160
vkazanov wrote: post #131

Earlier quoted context omitted.

I used to play with these toys 7-8 years ago. We tried everything, and it was bad at it all. Traditional compute? The cores were too weak. Number crunching? Okay-ish but gpus were better. Useless stuff.

They seemed exceedingly hard to use well but interestingly capable & full of promise. And they were made in a much more primitive software age. I'd love to hear about what didn't work. OpenMP support seemed ok maybe but OpenMP is just a platform, figuring out software architectures that's mechanistically sympathetic to the system is hard. It would be so interesting to see what Xeon Phi might have been if we had Calci…

Some observations:

- Very bad performance at existing x86 workloads, so a major selling point was basically not there in practice, because extracting any meaningful performance required a software rewrite anyway. This was an important adoption criteria; if they outright said "All your existing workloads are compatible, but will perform like complete dogshit", why would anyone bother? Compatibility was a big selling point that ended up meaning little in practice, unfortunately.

- Not actually what x86 users wanted. This was at the height of "Intel stagnation" and while I think they were experimenting with lots of stuff, well, in this case, they were serving a market that didn't really want what they had (or at least wasn't convinced they wanted it).

- GPU creators weren't sitting idle and twiddling their thumbs. Nvidia was continuously improving performance and programmability of their GPUs across all segments (gaming, HPC, datacenters, scientific workloads) while this was all happening. They improved their compilers, programming models, and microarchitecture. They did not sit by on any of these fronts.

Ironically the main living legacy of Phi is AVX-512, which people did and still do want. But that kind of gives it all away, doesn't it? People didn't want a new massively multicore microarchitecture. They wanted new vector instructions that were flexible and easier to program than what they had -- and AVX-512 is really much better. They wanted the things they were already doing to get better, not things that were like, effectively a different market.

Anyway, the most important point is probably the last one, honestly. Like we could talk a lot about compiler optimizations or autovectorization. But really, the market that Phi was trying to occupy just wasn't actually that big, and in the end, GPUs got better at things they were bad at, quicker than Phi got better at things it was bad at. It's not dissimilar to Optane. Technically interesting, and I mourn its death, but the competition simply improved faster than the adoption rate of the new thing, and so flash is what we have.

Once you factor in that you have to rewrite software to get meaningful performance uplift, the rest sort of falls into place. Keep in mind that if you have a $10,000 chip and you can only extract 50% of the performance, you more or less have just $5,000 on fire for nothing in return. You might as well go all the way and use a GPU because at least then you're getting more ops/mm^2 of silicon.

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

#190

Post by ac29 »

aseipp wrote: post #182
Figs wrote: post #105

Earlier quoted context omitted.

I wish AMD or Intel would just ship a giant honking CPU with 1000s of cores that doesn't need any special purpose programming languages to utilize. Screw co-processors. Screw trying to make yet another fucked up special purpose language -- whether that's C/C++-with-quirks or a half-assed Python clone or whatever. Nuts to that. Just ship more cores and let me use real threads in regular programming languages.

It doesn't work if you're going against GPUs. All the nice goodies we are accustomed to on large desktop x86 machines with gigantic caches and huge branch predictor area and OOO execution engines -- the features that yield the performance profile we expect -- simply do not translate or scale up to thousands of cores per die. To scale that up, you need to redesign the microarchitecture in a fundamental way to allow mo…

While the first >1000 core x86 processor is probably a little ways out, Intel is releasing a 288-core x86 processor in the first half of 2024 (Sierra Forest). I assume AMD will have something similarly high core in 2024-25 as well.
Post reply on HN