Chinese Acad Sci, Inst Software, Lab Parallel Software & Comp Sci, Beijing 100190, Peoples R China. Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China. China Assoc Sci & Technol, Informat Ctr, Beijing 100863, Peoples R China.
Abstract:
Computation reuse is known as an effective optimization technique. However, due to the complexity of modern GPU architectures, there is yet not enough understanding regarding the intriguing implications of the interplay of computation reuse and hardware specifics on application performance. In this paper, we propose an automatic code generator for a class of stencil codes with inherent computation reuse on GPUs. For such applications, the proper reuse of intermediate results, combined with careful register and on-chip local memory usage, has profound implications on performance. Current state of the art does not address this problem in depth, partially due to the lack of a good program representation that can expose all potential computation reuse. In this paper, we leverage the computation overlap graph (COG), a simple representation of data dependence and data reuse with "element view", to expose potential reuse opportunities. Using COG, we propose a portable code generation and tuning framework for GPUs. Compared with current state-of-the-art code generators, our experimental results show up to 56.7% performance improvement on modern GPUs such as NVIDIA C2050.
English Abstract:
Computation reuse is known as an effective optimization technique. However, due to the complexity of modern GPU architectures, there is yet not enough understanding regarding the intriguing implications of the interplay of computation reuse and hardware specifics on application performance. In this paper, we propose an automatic code generator for a class of stencil codes with inherent computation reuse on GPUs. For such applications, the proper reuse of intermediate results, combined with careful register and on-chip local memory usage, has profound implications on performance. Current state of the art does not address this problem in depth, partially due to the lack of a good program representation that can expose all potential computation reuse. In this paper, we leverage the computation overlap graph (COG), a simple representation of data dependence and data reuse with "element view", to expose potential reuse opportunities. Using COG, we propose a portable code generation and tuning framework for GPUs. Compared with current state-of-the-art code generators, our experimental results show up to 56.7% performance improvement on modern GPUs such as NVIDIA C2050.
Ma, WJ,Gao, K,Long, GP. Highly Optimized Code Generation for Stencil Codes with Computation Reuse for GPUs[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2016-01-01,31(6):1262-1274.
