OpenCL-CLHPP VS kompute

Khronos has today released the OpenCL 3.0.14 maintenance update that introduces a new cl_khr_command_buffer_multi_device provisional extension that enables execution of a heterogeneous command-buffers across multiple devices. This release also includes significant improvements to the OpenCL C++ Bindings, a new code generation framework for the OpenCL extension headers, and the usual clarifications and bug fixes. The new specifications can be downloaded from the OpenCL Registry.

Please note that OpenCL consists of two parts: host API and a separate language which is used to write kernels (code which is going to be offloaded to devices). OpenCL specification describes host APIs as C-style APIs and that is what implementors has to provide. However, there are number of various libraries which provides bindings for other languages: - C++ - Python - Go - Rust

opencl.hpp from https://github.com/KhronosGroup/OpenCL-CLHPP evolved from the C++ wrapper API that Ben Gaster started at AMD and I continued evolving. That work has continued since. It is a wrapper for the OpenCL runtime API, but the kernel side code is provided as kernel strings or SPIRV blobs through that API.

I was actually writing my own application in C++. I got the OpenCL CLHPP library downloaded. Wish me luck.

The two I know of are IREE and Kompute[1]. I'm not sure how much momentum the latter has, I don't see it referenced much. There's also a growing body of work that uses Vulkan indirectly through WebGPU. This is currently lagging in performance due to lack of subgroups and cooperative matrix mult, but I see that gap closing. There I think wonnx[2] has the most momentum, but I am aware of other efforts.

[1]: https://kompute.cc/

[2]: https://github.com/webonnx/wonnx

Great to see the positive momentum of this framework! Best wishes and upvotes from the Vulkan Kompute team :)

To a first approximation, Kompute[1] is that. It doesn't seem to be catching on, I'm seeing more buzz around WebGPU solutions, including wonnx[2] and more hand-rolled approaches, and IREE[3], the latter of which has a Vulkan back-end.

[1]: https://kompute.cc/

[2]: https://github.com/webonnx/wonnx

[3]: https://github.com/openxla/iree

I look in an example and see similar instructions, stating that the build should be quite simple. But again, it doesn't work. It generates a bunch of folders with Visual Studio stuff, but no executables, no libraries, or anything like that.

I can't figure out how, and there are no tutorials. According to https://kompute.cc/overview/build-system.html I should simply run "cmake -Bbuild". But this doesn't output what I need, and when I look in the Makefile I get the sense that this is more an example Makefile... but then that contradicts the above tutorial.

Kompute is in my opinion good example to take inspiration for abstractions.

Currently, there's a few Vulkan compute frameworks floating around (like Kompute). I would work with those. Kompute simplifies a lot of the biolerplate and seems like you could benefit from using it.

Try Kompute, a project from the Linux foundation. It is quite simple to use, and does not require deep knowledge of graphics API. It’s a bit painful to setup, but it kinda works well (and I have a project going on on it)

This so much.

This makes alot of sense considering the Linux Foundation is also in charge of Kompute which is likely to be the basis of vendor agnostic GPGPU, and thus the basis of vendor agnostic GPU-based machine learning.