关键词：对象识别；光学流；能源效率；有界性分析
摘 要：In this report, we analyze the computational and performance aspects of current stateof the-art object recognition and optical flow algorithms. First, we identify important algorithms for object recognition and optical flow, then we perform a pattern decomposition to identify key computations. We include pro les of the runtime and energy eciency (GFLOPS/W) for our implementation of these applications on a commercial architecture.Finally, we include an analysis of memory-bandwidth boundedness for optical flow to identify opportunities for communication-avoiding algorithms.