During the past decade or so, software developers have been bound to CUDA* to write highly parallel software for GPUs. The challenge with this approach is that CUDA is a proprietary programming interface and can only be used with NVIDIA* GPUs. Intel and other vendors are changing the landscape for processors, and new specialized processors (such as those harnessing the RISC-V ISA) bring increasing choices.

This session shows how to migrate your code from CUDA and port it to SYCL*, enabling your organization to be free to make a vendor-neutral choice while still supporting your existing GPU hardware. Practical examples explain the steps to semiautomatically port your code from CUDA to SYCL and provide tips to achieve the best performance on your target processor.

Speaker

Rod Burns has been helping developers to build complex software for well over a decade. Working at Codeplay* Software, Rod is involved in providing support and building educational materials for developers using our SYCL product. Rod has been involved in writing a range of training courses. Most recently, he helped to create SYCL Academy, a set of materials for teaching SYCL that have been adopted by some of the top universities in the world.