Of the nearly twenty companies presenting at the event, three have made
significant announcements in the AI hardware field in the past three
Logix, an established FPGA company that are targeting
inference workloads in edge environments, announced their new inference
coprocessor: the InferX X1. The chip is based on patented interconnect
technology from its eFPGA chip designs. It combines the eFPGA tech with
inference-optimized nnMAX clusters in the new combination chip. InferX
X1 will be available as chips for edge devices and on half-height,
half-length PCIe cards for edge servers and gateways. Co-Founder & SVP
of Architecture & Engineering, Cheng Wang, will represent Flex Logix at
Earlier this month, US start up SambaNova
Systems announced a $150 million Series B round led by
Intel Capital & GV, in a bid to expand its work on a software-defined
processing architecture for server-based AI workloads. The company draws
on expertise from a variety of institutions including Oracle, Sun
Microsystems, Stanford University and Dell EMC. Co-Founder & Chief
Technologist, Kunle Olukotun, will be presenting at the summit.
In February, Horizon
Robotics closed a $600 million Series B funding round led by SK
China, taking the company’s valuation to $3 billion. The company has
secured government contracts and business with SK’s telecoms unit, which
is using Horizon’s technology to develop smart retail solutions.
Co-Founder & CEO, Yu Kai, will represent Horizon Robotics at the summit.
Dr. Yu was the founder and head of Baidu’s Institute of Deep Learning,
and sits on the Chinese government’s special advisory board for
“Two overarching efforts are indispensable in this AI chip
development frenzy: objectively evaluating and comparing different chips
(benchmarking), and reliably projecting the growth paths of AI chips
(road mapping).” White Paper on AI Chip Technologies: Tsing Hua
University & Beijing Innovation Center for Future Chips, December 2018.
Hardware Asia Summit aims to introduce the US and Chinese
markets to help build a roadmap of the global AI chip industry and
assess emerging technologies for processing machine learning in the data
center and at the Edge.