Programming and Optimizing Multi-GPU Applications with SYCL*
Subscribe Now
Stay in the know on all things CODE. Updates are delivered to your inbox.
Contend with the challenge of systems with multiple GPUs.
Explore expert techniques for programming with SYCL* to develop optimized multi-GPU applications. Get equipped with the latest Intel® technology, thanks to Intel® Tiber™ Developer Cloud running 4th generation Intel® Xeon® Scalable processors and Intel® Data Center GPU Max Series 1100. This workshop is for intermediate to advanced programmers who want to take maximum advantage of the GPU resources available in a system.
Topics covered include how to:
- Determine available GPUs for offloading compute tasks.
- Use SYCL to assign compute kernels to multiple GPUs.
- Use SYCL to split workloads across multiple GPUs.
- Write portable SYCL code that taps available GPUs resources.
- Optimize SYCL code to run kernels concurrently across the full range of GPUs.
Watch this workshop replay to advance your understanding of SYCL programming techniques and distributing GPU resources.
Examples and hands-on demonstrations of Intel Tiber Developer Cloud give a practical view of the techniques available to efficiently harness the GPUs in a system. An Intel Tiber Developer Cloud account is required to participate in hands-on activities.