Closed proprietary software models dominate the world of AI and high-performance computing (HPC). To get high performance, systems need accelerators that have high levels of parallelism but use closed-programming models like CUDA. How do we open this up? How do we make these models safe enough to drive a car? How do we get an industry to work together with industry standards? 

Codeplay* has been working on these challenges for years. This talk shows the huge progress made through SYCL*, SPIR-V*, and oneAPI and where we're going next.