Hacker News Reader

Comment by joe_the_user | Hacker News Reader

Nvidia, moreover, increasingly views its software for programming its chips, called CUDA, as a kind of vast operating system that would span all of the machine learning in the world, an operating system akin to what Microsoft (MSFT) was in the old days of PCs.

Yeah, nVidia throwing it's weight around in terms of requiring that data centers pay more to use cheap consumer gaming chips may turn out to backfire and certainly has an abusive-monopoly flavor to it.

As I've researched the field, Cuda really seems provides considerable value to the individual programmer. But making maneuvers of this sort may show the limits of that sort of advantage.

https://www.theregister.co.uk/2018/01/03/nvidia_server_gpus/

View on HN

It probably won't. For every oppressive move NVDA has made so far, there has been a swarm of low-information technophobe MBA sorts who eat their computational agitprop right up, some of them even fashion themselves as data scientists. More likely, NVDA continues becoming the Oracle of AI that everyone needs and everyone hates.

So is OpenCL dead? Because that's how everyone is talking. The tools you choose, and their licensing, matters!

Almost as dead as its original creator, Steve Jobs, who only summoned it into existence because Jensen Huang leaked a deal between AAPL and NVDA ahead of him.

OpenCL could have been killer on mobile, and it could have delivered low-power machine learning and computation there all the way back in 2012, but both AAPL and GOOG went out of their way to cripple its use despite many of the mobile GPUs having hardware support for it. We all lost there IMO.

When I looked at OpenCl, my impression was it was simply a kind of bundle of functionality that happened to be shared by different GPUs (thin-layer of syntax on top of each manufacturers chip) whereas Cuda is a library that actually shields the programmer from the complexity of programming a GPU. I think AMD is working on an open-source system somewhat equivalent to Cuda which might be nice to see develop. But it seems like the OpenCl consortium is the kind of organization that could never care about the individual developer or meet their needs. I'd love if someone could prove me wrong.

OpenCL isn't dead, if you write your code from scratch you can use it just fine and match CUDA performance. In my experience, OpenCL has two basic issues.

The first is the ecosystem. Nvidia went to great lengths to provide well optimized libraries built on top of CUDA that supply things people care about - deep learning stuff, dense as well as sparse linear algebra, etc. There's nothing meaningfully competitive on the OpenCL side of things.

The second is user friendliness of the API and the implementations. OpenCL is basically analogous to OpenGL in terms of design, it's a verbose annoying C API with huge amounts of trivial boilerplate. By contrast, CUDA supports most of the C++ convenience features relevant in this problem space, has decent tools, IDE and debugger integration, etc.

Neither of these issues is necessary a dealbreaker if you're willing to invest the effort, but choosing OpenCL over CUDA requires prioritizing portability over user friendliness, available libraries and tooling. As a consequence, not many people choose OpenCL and the dominance of CUDA continues to grow. Unfortunately, I don't see that changing in the near future.

It seems like people are placing their hopes into HIP more than OpenCL now when it comes to using chips from AMD and others.

This is complete nonsense, and since you’ve said it twice in this thread I’ll respond.

The reason NVidia is used in deep learning is because the frameworks give the best performance on it.

The reason they give good performance on it is because CUDA an CuDNN (which is even more important but I don’t see mention of) work really well and give better performance than anything else.

There are no MBA, just lots of grad students trying anything to get better speed.

NVidia have had similar dodgy tactics in the past, including blocking their GPUs from being used in a VM using IOMMU. For my use case (where I had Windows in a VM on a Linux host) this was a massive PITA.

Reply on news.ycombinator.com