News for hackers. Stuff that matters.
Re:Nvidia dethrones Apple as the most valuable company by jiggawatts on Saturday October 26, 2024 @07:09AM (#41954041)
Sure, but most of the money is being sunk into the execution of the a small number of distinct codes, scaled out.

AMD doesn't need to duplicate everything NVIDIA provides, they just need to duplicate the parts relevant to most of the $3T spend the market seems to be expecting.

Just make llama.cpp work robustly on AMD accelerators, and that might unlock a $500B slice of the pie by itself.

Re:Nvidia dethrones Apple as the most valuable company by pjmlp on Saturday October 26, 2024 @10:13AM (#41954832)
And this is why NVidia keeps winning.
Re:Nvidia dethrones Apple as the most valuable company by talldayo on Saturday October 26, 2024 @01:44PM (#41956371)
cough Apple could be winning if they weren't a pussy about OpenCL. cough

Sorry, got something in my throat.

Re:Nvidia dethrones Apple as the most valuable company by pjmlp on Sunday October 27, 2024 @03:41AM (#41960548)
Why? Intel, AMD and Google never made anything useful with OpenCL.

That is OpenCL 3.0 is OpenCL 1.0 without the OpenCL 2.x stuff that no one ever adopted.

Re:Nvidia dethrones Apple as the most valuable company by talldayo on Saturday October 26, 2024 @01:56PM (#41956457)
> AMD doesn't need to duplicate everything NVIDIA provides, they just need to duplicate the parts relevant to most of the $3T spend the market seems to be expecting.

In effect, they already have. Both AMD, Apple and a number of smaller OEMs all wrote GPU compute shaders to do "the AI inference stuff" and shipped it upstream. That's about as much as they can do without redesigning their hardware, and they've already done it.

Nvidia wins not because they have everything sorted out in software. They win because CUDA is baked into the design of every Nvidia GPU made in the past decade. The software helps, but it's so bloated at this point that only a small subset of it's functionality is ever used in production at any one point. What makes Nvidia fast and flexible is integration of compute in hardware at the SM-level. This is an architecture AMD and Apple both had the opportunity to reprise, even working together if they wanted, but chose not to. Now we're here.

I tend to steelman the idea that it was AMD and especially Apple's mistake for eschewing this vision and abandoning OpenCL. But apparently a lot of people tend to think that AMD and Apple were right despite being less efficient at both raster and compute operations.

Re:Nvidia dethrones Apple as the most valuable company by pjmlp on Sunday October 27, 2024 @03:51AM (#41960592)
With CUDA a researcher can use C++20 (minus modules), Fortran, Julia, Python, Haskell, Java, C#, and a couple of other stuff that compiles to PTX, have nice graphical debuggers for the GPU, IDE integration, a large ecosystem of libraries.

With OpenCL, C99, some C++ support, printf debugging, and that is about it.

For good C++ experience, one needs to reach out to Intel's Data Parallel C++, which has Intel's special sauce on top of SYCL efforts, which only became a reality since a British company specialised in compilers for game consoles decided to pivot their target market and produce ComputeCpp, followed by being acquired by Intel.