Live Webcast 15th Annual Charm++ Workshop

We optimize a visual object detection application (that uses Vision Video Library kernels) and show that OpenCL is a unified programming paradigm that can provide high performance when running on the Ivy Bridge heterogeneous on-chip architecture. We evaluate different mapping techniques and show that running each kernel where it fits the best and using software pipelining can provide 1.91 times higher performance, and 42% better energy efficiency. We also show how to trade accuracy for energy at runtime. Overall, our application can perform accurate object detection at 40 frames per second (fps) rate, in an energy efficient manner.