clspv

From the "Learn More" link (https://lights0123.com/blog/2025/01/07/hip-script/): "By chaining chipStar¹ (a HIP and NVIDIA® CUDA® to OpenCL compiler), Clspv² (an OpenCL to Vulkan compiler), and Tint³ (among others, a Vulkan shader to WebGPU shader compiler), you can run CUDA code in the browser!" ¹ https://github.com/CHIP-SPV/chipStar/ ² https://github.com/google/clspv/ ³ https://dawn.googlesource.com/dawn/+/refs/heads/main/src/tin...

See https://github.com/google/clspv for an OpenCL implementation on Vulkan Compute. There are plenty of quirks involved because the two standards use different varieties of SPIR-V ("kernels" vs. "shaders") and provide different guarantees (Vulkan Compute doesn't care much about numerical accuracy). The Mesa folks are also looking into this as part of their RustiCL (a modern OpenCL implementation) and Zink (implementing OpenGL and perhaps OpenCL itself on Vulkan) projects.

Vulkan Compute backends for numerical compute (as typified by both OpenCL and SYCL) are challenging, you can look at clspv https://github.com/google/clspv project for the nitty gritty details. The lowest-effort path so far is most likely via some combination of Rocm/HIP (for hardware that AMD bothers to support themselves) and the Mesa project's RustiCL backend (for everything else).

D3D12 has more compute features than Vulkan has. It works out for DXVK because games often don’t use those, but it’ll cause much more issues with CLon12. By the way, if you are ready to have a _limited_ implementation without a full feature set because of Vulkan API limitations, clvk is a thing. The list of limitations of that approach is at https://github.com/google/clspv/blob/master/docs/OpenCLCOnVu... tldr: Vulkan and OpenCL SPIR-V dialects are different, and the former has significant limitations affecting this use case

For OpenCL on DX12, the test suite doesn't pass yet. Every Khronos OpenCL 1.2 CTS test passes on at least one hardware driver, but there's none that pass them all. That is why CLon12 isn't submitted to Khronos's compliant products list yet. The pointer semantics that Vulkan has aren't very amenable to implementing a compliant OpenCL implementation on top of. There are also some other limitatons: https://github.com/google/clspv/blob/master/docs/OpenCLCOnVu....

These are not proper pointers, see: https://github.com/google/clspv/blob/master/docs/OpenCLCOnVu... > Pointers are an abstract type - they have no known compile-time size. Using a pointer type as the argument to the sizeof() operator will result in an undefined value. > Pointer-to-integer casts must not be used. > Integer-to-pointer casts must not be used. > Pointers must not be compared for equality or inequality The first one in that list is a quite big limitation, affecting a significant number of scenarios… (And yes, you cannot actually make a compliant OpenCL 1.2 implementation on top of Vulkan, Vulkan has too few features for that purpose)

Some people are working on being able to run OpenCL kernels on Vulkan: https://github.com/google/clspv

We run OpenCL on top of Vulkan in a production application on Android, thanks to a project from Google / Codeplay and other contributors https://github.com/google/clspv. SPIR-V can't represent all of OpenCL, but maybe enough for most people's use cases.

One issue is that the Vulkan API is absurdly low-level and verbose. There are good reasons for this if you're writing a game engine, but if you just want to run simple compute kernel you're looking at ~500 LoC, probably an order of magnitude more than with OpenCL. So the barrier to entry is really high. It also seems the Vulkan supports a different variant of SPIR-V than OpenCL, with the result that some OpenCL C code can't be compiled to work with Vulkan. [1] But it does seem like a combination of lifting Vulkan compute restrictions and building compute-oriented APIs on top of it could be a better path forward. Especially since this new version basically seems to be giving up an getting vendors to support the features that would make OpenCL competitive with CUDA. [1] https://github.com/google/clspv/blob/master/docs/OpenCLCOnVu...

Some googlers are working on OpenCL source to Vulkan-profile-SPIR-V though: https://github.com/google/clspv