Automatic CPU-GPU communication management and optimization
Citations Over TimeTop 1% of 2011 papers
Abstract
The performance benefits of GPU parallelism can be enormous, but unlocking this performance potential is challenging. The applicability and performance of GPU parallelizations is limited by the complexities of CPU-GPU communication. To address these communications problems, this paper presents the first fully automatic system for managing and optimizing CPU-GPU communcation. This system, called the CPU-GPU Communication Manager (CGCM), consists of a run-time library and a set of compiler transformations that work together to manage and optimize CPU-GPU communication without depending on the strength of static compile-time analyses or on programmer-supplied annotations. CGCM eases manual GPU parallelizations and improves the applicability and performance of automatic GPU parallelizations. For 24 programs, CGCM-enabled automatic GPU parallelization yields a whole program geomean speedup of 5.36x over the best sequential CPU-only execution.
Related Papers
- → Parallel simulation of equation-based models on CUDA-enabled GPUs(2010)11 cited
- → Autotuning GPU Compiler Parameters Using OpenTuner(2015)5 cited
- → Comparative Cross-Platform Performance Results from a Parallelizing SML Compiler(2002)6 cited
- → Streaming-Oriented Parallelization of Domain-Independent Irregular Kernels(2011)
- Comparative Cross-Platform Performance Results from a Parallelizing SML Compiler(2001)