HyperLink   An Adaptive Performance Modeling Tool for GPU Architectures
Paper of IMPACT - Cited Greater Than 250 Times
Publication Year:
  Sara Sadeghi Baghsorkhi, Matthieu Delahaye, Sanjay J. Patel, William D. Gropp, Wen-mei Hwu
  Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP), Jan. 2010

This paper presents an analytical model to predict the performance of general-purpose applications on a GPU architecture. The model is designed to provide performance information to an auto-tuning compiler and assist it in narrowing down the search to the more promising implementations. It can also be incorporated into a tool to help programmers better assess the performance bottlenecks in their code. We analyze each GPU kernel and identify how the kernel exercises major GPU microarchitecture features. To identify the performance bottlenecks accurately, we introduce an abstract
interpretation of a GPU kernel, work flow graph, based on which we estimate the execution time of a GPU kernel. We validated our performance model on the NVIDIA GPUs using CUDA (Compute Unified Device Architecture). For this purpose, we used data parallel benchmarks that stress different GPU microarchitecture events such as uncoalesced memory accesses, scratch-pad memory bank conflicts, and control flow divergence, which must be accurately modeled but represent challenges to the analytical performance models. The proposed model captures full system complexity and shows high accuracy in predicting the performance trends of different optimized kernel implementations. We also describe our approach to extracting the performance model automatically from a kernel code.