SAN JOSE, Calif., May 18, 2017 /PRNewswire/ -- Xilinx, Inc. (XLNX) today announced that it has invested in DeePhi Tech, a recognized leader in machine learning specializing in deep compression, compiling toolchain, and system-level optimization. Leveraging the architectural advantages of Xilinx® devices for machine learning, DeePhi provides inference platforms from edge to cloud for the coming wave of AI products and services in the industry.
DeePhi Tech was founded by researchers from Tsinghua University and Stanford University known for their pioneering research in machine learning and numerous papers published at top AI conferences around the world. Members of the DeePhi Tech team recently received the Best Paper Award at FPGA2017 for breakthrough results with a highly efficient FPGA-accelerated speech recognition engine achieving 43x the performance and 40x the performance per watt compared to a CPU; 3x the performance and 11x the performance per watt compared to a GPU.
"Xilinx FPGAs and MPSoCs provide the ideal combination of low latency and reconfigurability required for our inference solutions," said Yao Song, CEO at DeePhi Tech. "Xilinx's powerful platforms are already being used by DeePhi in commercial products from edge to cloud in smart surveillance and data center applications."
"Empowered by Xilinx technology and expertise, DeePhi solutions provide breakthroughs in efficiency through techniques like network pruning, compression and use of reduced precision data types," said Nazeem Noordeen, CVP of Acceleration and IP Solutions at Xilinx. "Our investment in DeePhi is further evidence of our commitment to provide our customers with industry-leading accelerated computing products."
Xilinx investments for accelerated computing target solutions for applications such as machine learning, image and video processing, and storage and network acceleration. To learn more about DeePhi Tech, visit www.deephi.com.
Xilinx is the leading provider of All Programmable semiconductor products, including FPGAs, SoCs, MPSoCs, RFSoCs, and 3D ICs. Xilinx uniquely enables applications that are both software defined and hardware optimized – powering industry advancements in Cloud Computing, 5G Wireless, Embedded Vision, and Industrial IoT. For more information, visit www.xilinx.com.
© Copyright 2017 Xilinx, Inc. Xilinx, the Xilinx logo, Artix, ISE, Kintex, Spartan, Virtex, Vivado, Zynq, and other designated brands included herein are trademarks of Xilinx in the United States and other countries. All other trademarks are the property of their respective owners.
Silvia E. Gianelli
SOURCE Xilinx, Inc.