Heterogeneous architectures can improve the performance of applications with computationally intensive, data-parallel operations. Even when these architectures may reduce the execution time of applications, there are opportunities for additional performance improvement as the memory hierarchy of the central processor cores and the graphics processor cores are separate. Applications executing on heterogeneous architectures must allocate space in the GPU global memory, copy input data, invoke kernels, and copy results to the CPU memory. This scheme does not overlap inter-memory data transfers and GPU computations steps, thus increasing application execution time. This research presents a software architecture with a runtime pipeline for GPU input/output scheduling that acts as a bidirectional interface between the GPU computing application and the physical device. The main aim of this system is to reduce the impact of the processor-memory performance gap by exploiting device I/O and computation overlap. Evaluation using application benchmarks shows processing improvements with speedups above 2x with respect to baseline, non-streamed GPU execution.
