News for hackers. Stuff that matters.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by lwb on Thursday March 05, 2020 @04:52PM (#22498743)
Anyone here use OpenCL for their day job? Practically speaking, what are the use cases for it in a corporate environment?
Re:Vortex: OpenCL Compatible RISC-V GPGPU by bubblethink on Thursday March 05, 2020 @06:49PM (#22499711)
It's like CUDA, but not owned by NVIDIA. AMD's entire ROCM stack is based on OpenCL. That means that if you run tenserflow on amd gpus, you are using OpenCL. By corporate environment, if you mean day to day IT, probably none. It's useful for high performance and parallel code.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by rrss on Friday March 06, 2020 @01:47AM (#22501471)
Pretty sure the rocm backend for tensorflow uses hip, not OpenCL, and hip is basically just AMD's implementation of cuda.

I don't think it's accurate to say that the "entire ROCM stack is based on OpenCL." The rocm stack supports OpenCL, but it also supports hip, which is what AMD chose to use to implement many of the new libraries in the rocm platform (rocBLAS, rocFFT, rccl; replacing cuBLAS, cuFFT, nccl)

FWIW, rocm also doesn't support OpenCL 2.0.

Re:Vortex: OpenCL Compatible RISC-V GPGPU by pjmlp on Friday March 06, 2020 @01:32AM (#22501411)
You got it wrong, it is like CUDA but only supports C, has lousier debugging tools, and buggy drivers.

Yes it does support C++ and finally has its own bytecode format for heterogeneous programming, but unless the card is OpenCL 2.2, it is back to my first paragraph.

Re:Vortex: OpenCL Compatible RISC-V GPGPU by nl on Friday March 06, 2020 @02:20AM (#22501615)
ROCM isn't OpenCL based.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by lmeyerov on Thursday March 05, 2020 @06:19PM (#22499454)
We abandoned it due to lack of ecosystem support. We originally picked it for general ETL / analytics / preprocessing data viz when opencl vs. nvidia for commodity data parallel hardware ( = GPU ) was unclear, and as a long option in case FGPAs would ultimately make sense. But the CUDA software stack's community + Nvidia investments eventually converted us.

Interestingly, we now exclusively use high-level data parallel abstractions like RAPIDS dataframes, so if there was say a Modin->risc-v path, wouldn't be too heavy a lift to port most of our stack. (Though, as is, little reason to.)

Re:Vortex: OpenCL Compatible RISC-V GPGPU by zozbot234 on Thursday March 05, 2020 @07:57PM (#22500130)
The ecosystem seems to be moving to Vulkan-based compute these days. That's more aligned to the hardware than plain old OpenCL, so performance should be improved.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by lmeyerov on Thursday March 05, 2020 @08:06PM (#22500176)
Not sure what hw support adds here. While I prefer stacks that a megacorp doesn't own at the bottom, my point is it's the software. Current langs + frameworks are relegated to a tiny fragment of the coding population. So more about making it as easy to reach for GPU / data parallel stuff as folks do for say Spark or Pandas.

We tried working with AMD & Intel early on here but they didn't really get it (architects, investors, and a few other decision-maker-types). It's easy to put $10-20M into the ecosystem and just build it -- a16z finally has several years after we pitched it to them, and so did Nvidia with rapids.ai after we pushed them for a couple years ("what's a dataframe?"). Nothing stopping AMD/Intel and other opencl ecosystem players. But they still aren't.

Re:Vortex: OpenCL Compatible RISC-V GPGPU by Athas on Friday March 06, 2020 @03:11AM (#22501814)
I don't think this is true, or at least as simple a story as "Vulkan is faster". OpenCL is already a pretty good and modern API, and computation in Vulkan doesn't seem like it's the main point. It's my impression that Vulkan is mostly fast compared to OpenGL, and particularly by removing driver overheads, but that has never really been a big problem with OpenCL.

Last year, I had a student add a Vulkan backend to a GPU-targeting compiler[0]. Compared to the OpenCL backend, many programs ran substantially slower, and very few ran faster. It's certainly possible that this backend is imperfect, but it's more of a data point that I have seen elsewhere.

[0]: https://futhark-lang.org/student-projects/steffen-msc-projec...

Re:Vortex: OpenCL Compatible RISC-V GPGPU by fulafel on Friday March 06, 2020 @02:26AM (#22501637)
Blender and Darktable use it at least. Also commercial Mac apps like Photoshop, Premiere etc.

It's emitted by a bunch of compiler backends (eg Futhark).

ML and computer vision toolkits support it (eg PyTorch, OpenCL etc).

Not sure what you mean by corporate environments but the suits probably mostly use Excel and calc.exe :)

Re:Vortex: OpenCL Compatible RISC-V GPGPU by kitd on Friday March 06, 2020 @03:00AM (#22501776)
Tbf, Excel making use of OpenCL kind of makes sense :)
Re:Vortex: OpenCL Compatible RISC-V GPGPU by Ono-Sendai on Thursday March 05, 2020 @09:39PM (#22500575)
Yes, we use it for Indigo Renderer (https://www.indigorenderer.com/) and Chaotica Fractals (https://www.chaoticafractals.com/). It allows cross-platform (Windows, Mac, Linux) execution on GPUs.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by boulos on Friday March 06, 2020 @01:07AM (#22501335)
Vlado mentioned at SIGGRAPH, that they basically gave up and has gone from OpenCL => CUDA => "let OptiX handle it" => "OptiX7 w/ RTX". Do you have a CUDA and/or RTX comparison?

P.S. It's awesome you're still working on Indigo!

Re:Vortex: OpenCL Compatible RISC-V GPGPU by Ono-Sendai on Friday March 06, 2020 @10:23AM (#22504238)
OpenCL seemed to have comparable performance to CUDA when we stopped using CUDA. I don't have comparisons with RTX on hand. The main problem with OpenCL now is not performance but vendor/driver support. For example the Apple OpenCL drivers are pretty buggy.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by sjmulder on Thursday March 05, 2020 @05:53PM (#22499223)
I’ve been exploring it for use for financial calculations that are ‘embarrassingly parallel’. It’s much faster alright but people here aren’t trained in data oriented programming. Might end up writing some generic accelerated building blocks for use from VBA.
Re:Vortex: OpenCL Compatible RISC-V GPGPU by wyldfire on Thursday March 05, 2020 @11:08PM (#22500919)
If you have an HPC workload it can make sense. Lots and lots of software work is I/O bound and doesn't do a whole heckuva lot of computation.

I used to use OpenCL at work a lot.

Re:Vortex: OpenCL Compatible RISC-V GPGPU by pjmlp on Friday March 06, 2020 @01:29AM (#22501404)
Currently none.

Android uses its own dialect, RenderScript.

iOS had OpenCL, but since Metal got introduced, Metal Shaders are much better.

On Windows I used C++AMP for a while, now I just make use of Java/.NET libraries that plug into CUDA.

OpenCL biggest mistake was focusing on C only instead of opening the programming model to other languages.

SPIR and SYS-CL came too late into the game.

Re:Vortex: OpenCL Compatible RISC-V GPGPU by Awtem on Friday March 06, 2020 @12:46AM (#22501259)
Sadly, OpenCL (alongside OpenGL) are already deprecated on Mac...