Optimizing FPGA-based Accelerator Design for Deep ...
Optimizing FPGA-based Accelerator Design for DeepConvolutional Neural NetworksChen Cong2,3,1, for Energy-Efficient Computing and Applications, Peking University, China2Computer Science Department, University of California, Los Angeles, USA3PKU/UCLA Joint Research Institute in Science and EngineeringABSTRACTConvolutional neural network (CNN) has been widely em-ployed for image recognition because it can achieve high ac-curacy by emulating behavior of optic nerves in living crea-tures. Recently, rapid growth of modern applications basedon deep learning algorithms has further improved researchand implementations.
Unfortunately, both advances of FPGA technology and deep learning algorithm aggravate this problem at the same time. On one hand, the increasing logic resources and mem-ory bandwidth provided by state-of-art FPGA platforms en-large the design space. In addition, when various FPGA optimization techniques, such as loop tiling and transforma-
Download Optimizing FPGA-based Accelerator Design for Deep ...
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
Related search queries
FPGA Logic Cells Comparison, Introduction FPGA, Field Programmable Gate Array, FPGA, Design, Introduction, Design: A Unified Hardware/Software, Intel, FPGA Software Installation and Licensing, Intel FPGA, High Bandwidth Memory (HBM2) Interface Intel, Tutorialspoint, Introduction to FPGA Design with Vivado High-Level, Introduction to FPGA Design with