high performance computing on graphics processing units: hgpu.org

GPU’s are massively multicore architectures managing several thousands of concurrent threads. This concurrence, maintained through several schedulers, is necessary to keep high performance but negatively impact predictability. In this work, we first propose measures of predictability as well as CUDA tests to estimate this measure regarding warp and block scheduler for architectures from G80 to GK104. Finally, we evaluate the impact of hardware reset, underclocking and heavy synchronization to increase predictability on those architectures.