The OpenCL Working Group today published a draft extension, cl_khr_cooperative_matrix, which introduces cooperative matrix operations to OpenCL. Developed in collaboration with Arm, Intel, and Qualcomm, this extension brings "a key technology for accelerating ML inference" directly to the OpenCL ecosystem. This move aims to enhance OpenCL's capabilities for machine learning workloads on various hardware. A companion extension to expose these new operations directly within the OpenCL C language is also in progress. The OpenCL Working Group has invited the community to review both draft specifications and provide feedback before their finalization.