In this episode, we will look at how to overlap communication of data with computation on the coprocessor and CPU at the same time in the explicit offload model. For that, we will use functionality called an asynchronous offload.
Videos Within This Chapter:
Part 1: Overview of Programming Options
Part 2: Native Coprocessor Applications
Part 3: Native MPI Applications
Part 4: Explicit Offload Programming Model
Part 5: Additional Offload Controls
Part 6: Shared Virtual Memory
Part 7: Asynchronous Offload
Part 8: Heterogeneous Programming with Coprocessors using MPI
Part 9: File I/O in MPI Applications on Coprocessors
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.