Flex Logix's Cheng Wang Speaking at Linley Fall Processor Conference on Accelerating Neural Inferencing Performance Using Low DRAM Bandwidth

MOUNTAIN VIEW, Calif., Oct. 29, 2018 — (PRNewswire) —   Flex Logix® Technologies, Inc. today announced that its co-founder and Senior VP of Engineering Cheng Wang will be speaking about neural inferencing at next week's Linley Fall Processor Conference at the Hyatt Regency in Santa Clara, CA.  The presentation is titled "A High-Performance Reconfigurable Neural Accelerator with Low DRAM Bandwidth," and will be part of the Session 1 Tract titled "AI SoC Design."

Flex Logix Corporate Logo

Date of Panel: Wednesday, October 31, 2018

Time: 10:10 am - 12:15 pm

About Cheng's presentation:  This presentation will introduce NMAX™, a reconfigurable, scalable, high-performance neural-network accelerator with low DRAM bandwidth. NMAX utilizes eFPGA for fast control-logic reconfiguration for each stage, as well as a novel, high-bandwidth memory architecture, including use of XFLX interconnect, that keeps the MAC arrays highly utilized. For edge computing, NMAX is competitive on performance, power, and die area while using much less DRAM bandwidth than conventional solutions.

About the AI SoC Design Tract Session 1:  AI processors employ complex heterogeneous architectures with high data parallelism. To meet performance and power requirements, designers must distribute the workload to the most efficient processor core, optimize the data flow between those cores, and ensure that the interface to external memory meets the high-bandwidth demands of deep neural-networks. This session, moderated by The Linley Group senior analyst Mike Demler, will discuss how using heterogeneous architectures, low-latency DNN accelerators, and AI-optimized interconnect can improve AI processor performance.

About Flex Logix 
Flex Logix, founded in March 2014, provides solutions for reconfigurable RTL in chip and system designs using embedded FPGA IP cores and software. The company's technology platform delivers significant customer benefits by dramatically reducing design and manufacturing risks, accelerating technology roadmaps, and bringing greater flexibility to customers' hardware by enabling customization; real-time updating of protocols and algorithms; and reconfigurable acceleration 30-100x faster than processors. Flex Logix has raised more than $13 million of venture capital. Its EFLX® eFPGA has now been ported to process nodes from 180nm to FinFet across multiple fabs and is in use by multiple customers in a wide range of applications.  The company is headquartered in Mountain View, California and has sales rep offices in China, Europe, Israel, Japan, Taiwan and Texas. More information can be obtained at http://www.flex-logix.com or follow on Twitter at @efpga.

PRESS CONTACT:
Kelly Karr
Tanis Communications, Inc.
Email Contact
+408-718-9350

Copyright 2018. All rights reserved. Flex Logix and EFLX are registered trademarks and NMAX is a trademark of Flex Logix, Inc.

 

 

Cision View original content to download multimedia: http://www.prnewswire.com/news-releases/flex-logixs-cheng-wang-speaking-at-linley-fall-processor-conference-on-accelerating-neural-inferencing-performance-using-low-dram-bandwidth-300739208.html

SOURCE Flex Logix Technologies, Inc.

Contact:
Company Name: Flex Logix Technologies, Inc.
Web: http://www.flex-logix.com/





© 2024 Internet Business Systems, Inc.
670 Aberdeen Way, Milpitas, CA 95035
+1 (408) 882-6554 — Contact Us
ShareCG™ is a trademark of Internet Business Systems, Inc.

Report a Bug Report Abuse Make a Suggestion About Privacy Policy Contact Us User Agreement Advertise