Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU • Hacker News Board

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#41

Post by ElFitz » Thu, May 14, 2020, 2:15 PM UTC

pjmlp wrote: post #28

wegs wrote: post #23

Earlier quoted context omitted.

Yeah. That's been my general problem with adopting NVidia for anything. They make good hardware, but there's a lot of lock-in, and not a lot of transparency. That introduces business risk. I'm not in a position where I need GPGPU, but if there wasn't that risk, and generally there were mature, open standards, I'd definitely use it. The major breakpoint would be when libraries like Numpy do it natively, and better yet…

Given that I hardly saw any clone vendors other than AMD, I really doubt that they had any influence on Intel's market share. What worked out was IBM not being able to prevent PC clones, but given the wide adoption of laptops, tablets and phones that hardly matters nowadays.

I think the parent only means that if Intel somehow shut down, decided to radically pivot or to close everything, because it is somewhat open, you still had alternatives and neither your code, your product, or your company would face insurmontable hardship or die because of it.

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#42

Post by Keyframe » Thu, May 14, 2020, 2:15 PM UTC

5 petaflops in DGX? That alone would put one of those babies into TOP500 top 50, and a superPOD would make no. 1, no? Well, if it could do that performance on Linpack/Rmax.

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#43

Post by sailingparrot » Thu, May 14, 2020, 2:20 PM UTC

aloer wrote: post #21

For those in the industry: When a new generation like this is released, will a typical AI company replace the current GPUs? Is there a chance to acquire the older versions for private use or is it too early for that?

> will a typical AI company replace the current GPUs?

(Not speaking for everyone of course)

No we keep the current GPUs as well, the one we throw away are several generations old (like K80s), so not very interesting.

For private use, those GPUs are really not worth it. Once their used price reaches an acceptable level, you can be sure that the new general public GPUs will outperform them.

For example a Titan RTX is probably still twice as cheap as V100, while only being ~20% slower.

Edit: Actually a Titan RTX is about the same price as a P100 now, while being much better.

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#44

Post by hank_z » Thu, May 14, 2020, 2:20 PM UTC

Hmm, I was expecting 3080 ti.

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#45

Post by lightcatcher » Thu, May 14, 2020, 2:20 PM UTC

wegs wrote: post #23

xvilka wrote: post #16

Probably even more closed than ever. They tend to become more and more restrictive with every new hardware generation. I wonder where their promised open source announcement they preannounced before.

Yeah. That's been my general problem with adopting NVidia for anything. They make good hardware, but there's a lot of lock-in, and not a lot of transparency. That introduces business risk. I'm not in a position where I need GPGPU, but if there wasn't that risk, and generally there were mature, open standards, I'd definitely use it. The major breakpoint would be when libraries like Numpy do it natively, and better yet…

> Intel keeps getting it right with numerical libraries. They're open. They work well. They work on AMD.

What Intel numerical libraries are you thinking of? When I think of Intel numerical libraries, the first that comes to mind is MKL. MKL is neither open-source nor does it work well on AMD without some fragile hacks [0].

[0] https://www.pugetsystems.com/labs/hpc/How-To-Use-MKL-with-AM...

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#46

Post by liminal » Thu, May 14, 2020, 2:22 PM UTC

How does RAPIDS relate to GOAI and Arrow? It seems like the same technology keeps getting a name change...?

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#47

Post by ethbro » Thu, May 14, 2020, 2:24 PM UTC

wegs wrote: post #31

pjmlp wrote: post #25

Earlier quoted context omitted.

The large majority of researchers and business getting into NVidia products doesn't seem to find it that relevant, rather what tools, GPU programming languages and hardware they are able to put their hands on.

It's irrelevant to researchers. Research operates on rapid cycles: prototype, publish, move on. It does impact businesses. It doesn't prevent adoption for e.g. deep learning, but I haven't seen e.g. GPU-based databases reach broad adoption, or many other places where MIMD/SIMD would reduce costs or improve performance. Using classical hardware is clearly cheaper than the business risk and engineering time of relying…

Hypothetically, from an ISA perspective, why couldn't Intel and AMD extend x86-64 more fully with SIMD / MIMD instructions? (as in, way more fully than MMX / SSE / AVX)

Naive question, because I literally don't know the link between CPU instruction stream and GPGPU instruction stream.

But it seems like there would be an opportunity to seize the higher (open) ground at the ISA level, and then force Nvidia to implement its own support for that standard.

With the point of being able to run identical code across CPU / CPU-with-embedded-GPU / CPU + GPU.

Understand we're talking about mind-boggling levels of complexity here, but it feels like the CPU shops ceded the role of graphical ISA to Nvidia & Microsoft (DirectX).

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#48

Post by jamesblonde » Thu, May 14, 2020, 2:25 PM UTC

lowdose wrote: post #38

> DGX-A100 - The First HPC System With 140 Peta-OPs Compute Shipping Now For $199,000 Crazy pricing for a chip that basically started as a game solution. Anybody actually seen these Nvidia DGX systems in the wild?

We are working with 20 of them at a customer....

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#49

Post by sailingparrot » Thu, May 14, 2020, 2:26 PM UTC

lowdose wrote: post #38

> DGX-A100 - The First HPC System With 140 Peta-OPs Compute Shipping Now For $199,000 Crazy pricing for a chip that basically started as a game solution. Anybody actually seen these Nvidia DGX systems in the wild?

Yes, we use them (with V100 not A100 of course). Mind you that the full box is more than just the 16 GPUs.

Re: Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU

#50

Post by notact » Thu, May 14, 2020, 2:27 PM UTC

reedwolf wrote: post #26

Stealing Epic Games/Unreal Engine's thunder. If Nvidia was a human, they'd be the type to propose at someone else's wedding.

So wait, the GTC keynote which was scheduled weeks/months ago, happens to follow news that Epic dropped with absolutely no warning, and apparently that counts as stealing thunder. Is that really what you are saying?