2017 Poster Sessions : Generating Heterogeneous Systems from Image Processing DSL

Student Name : Jing Pu
Advisor : Mark Horowitz
Research Areas: Computer Systems
Image processing continues to become increasingly important in areas like computer vision, computational photography, and augmented reality. And there is great demand to deploy these algorithms on mobile platforms. A heterogeneous system containing processors and custom accelerators makes a promising platform due to its high performance and energy efficiency. However, designing and programming such systems are hard.We extend the image processing language, Halide, to map applications to efficient heterogeneous system target. Based on these extensions, we build a system offering a high level interface for defining hardware and software implementations simultaneously, which great-ly raises the level of design automation and enables a large space for co-optimizing hardware and software as well. Experimental results show that Xilinx ZYNQ designs produced by our system achieve up to 5x performance speedup and 50x energy efficiency compared to an NVIDIA Tegra K1 CPU, and 2.5x performance speedup with 10x energy efficiency compared to a K1 GPU.

Jing Pu received a B.S. in microelectronics from Peking University and an M.S. in electrical engineering from Stanford University. He is currently pursuing a PhD at Stanford University. His research interests include VLSI design, computer architecture, graphics and imaging system. He is currently working on building energy efficient architecture for image processing applications. Previously, he has worked on the efficient FPU generator, FPGen, and the Software Actuated Genetic Engineering (SAGE) lab-on-a-chip (LoC) project.