Profiling-based L1 data cache bypassing to improve GPU performance and energy efficiency

While caches have been studied extensively in the context of CPUs, it remains largely unknown how to exploit caches efficiently to benefit GPGPU programs due to the distinct characteristics of CPU and GPU architectures. In this work, we analyze the memory access patterns of GPGPU applications and propose a cost-effective profiling-based method to identify the data accesses that should bypass the L1 data cache to improve performance and energy efficiency. The experimental results show that the proposed method can improve the performance by 13.8% and reduce the energy consumption by about 6% on average.