Title | Parallelization, Customization and Automation |
Author | *Jason Cong (UCLA, U.S.A.) |
Page | pp. 297 - 299 |
Abstract | In order to meet ever-increasing computing needs and overcome power density limitations, the computing industry has halted simple processor frequency scaling and entered the era of parallelization, with tens to hundreds of computing cores integrated in a single processor, and hundreds to thousands of computing servers connected in a warehouse-scale data center. However, such highly parallel, general-purpose computing systems still face serious challenges in terms of performance, power, heat dissipation, space, and cost. We believe that we need to look beyond parallelization and focus on domain-specific customization to provide capability of adapting architecture to application in order to achieve significant power-performance efficiency improvement. This paradigm shift requires a great deal of innovation in architecture, compilation, and runtime system design, and offers many exciting and challenging research opportunities. I shall discuss the research progress in this direction and implication to the EDA industry. |
PDF file |