OpenCL Introducing Cooperative Matrix Extensions For Machine Learning
Back in 2023 the Vulkan API introduced its initial Cooperative Matrix extension and necessary SPIR-V integration for helping with machine learning / AI inferencing use. Since then the cooperative matrix support has continued to be built upon for helping Vulkan in AI/ML areas. Now the OpenCL API is also introducing similar cooperative matrix extensions.
The OpenCL Working Group has published their initial cooperative matrix extensions work. Their first extension is cl_khr_cooperative_matrix and is now available in working draft form for enabling OpenCL implementations to accept SPIR-V modules using SPV_KHR_cooperative_matrix.
Those interested in this OpenCL Cooperative Matrix work can find out all of the details via today's announcement on Khronos.org. The cl_khr_cooperative_matrix initial extension is under review via the OpenCL-Docs on GitHub.
The OpenCL Working Group has published their initial cooperative matrix extensions work. Their first extension is cl_khr_cooperative_matrix and is now available in working draft form for enabling OpenCL implementations to accept SPIR-V modules using SPV_KHR_cooperative_matrix.
👁 cl_khr_cooperative_matrix extension spec
Those interested in this OpenCL Cooperative Matrix work can find out all of the details via today's announcement on Khronos.org. The cl_khr_cooperative_matrix initial extension is under review via the OpenCL-Docs on GitHub.