NeuReality collaborates with Xilinx to deliver first AI-centric server

NeuReality, an Israeli AI startup developing high performance AI compute platforms for cloud data centers and edge nodes, is collaborating with Xilinx, Inc. to deliver new AI-centric platforms that empower, optimize, and tune real-world AI applications. The collaboration is based on NeuReality’s novel AI-centric inference platform NR1-P, which includes a new type of AI Server-on-Chip (SoC) developed by NeuReality and delivers all components necessary to deploy a complete inference solution. The platform targets high volume AI applications in various fields such as public safety, e-commerce, healthcare, retail, and many other computer-vision use cases.

NeuReality has worked closely with Xilinx to deliver the world’s first fully functional AI-centric server to the market. This breakthrough prototype platform will reduce the two key barriers that inhibit customers’ AI deployment today, cost and complexity. As part of the collaboration, the NR1-P platform, based on the Xilinx Versal ACAP architecture, can be purchased directly from NeuReality, and will be fulfilled through Colfax International.

NR1-P is NeuReality’s first implementation of the company’s new AI-centric architecture, with other implementations to follow. The new prototype platform is accessible for testing and evaluation via remote access. NeuReality’s NR1-P was built upon the Xilinx Versal VCK5000 development card and can deliver up to 3X greater performance/Dollar/Watt compared to the latest Nvidia A100 or T4 based systems, according to NeuReality. The complete prototype solution includes a 4xRU server chassis, 16 AI-centric modules based on the Xilinx development cards, an embedded Linux software stack with Kubernetes support, orchestration functionality and a model database.

Moshe Tanach, CEO and co-founder of NeuReality, noted: “Working closely with Xilinx, the market leader of FPGAs for AI, has taken us one step closer to a new reality of AI-centric Server-on-Chip silicon devices that deliver best in class TCO, linear scalability, reduced latency and a simple user interface and experience. These can enable use cases such as healthcare, public safety and other applications that depend on higher efficiency and much lower cost solutions compared to the existing CPU-centric offerings from companies such as Nvidia.”

NeuReality Ltd. is an AI technology innovation company creating purpose-built AI-platforms for ultra-scalability of real-life AI applications. NeuReality is a pioneer in the deep learning and AI solutions market.

NeuReality was founded in 2019 and is led by a seasoned management team with extensive experience in data centers architecture, system, and software. The co-founders are CEO Moshe Tanach, VP Operations Tzvika Shmueli and VP VLSI Yossi Kasus. Prior to founding NeuReality, Tanach served in several executive roles as Director of Engineering at Marvell and Intel and AVP R&D at DesignArt-Networks (later acquired by Qualcomm). Tzvika Shmueli served as VP of Backend at Mellanox Technologies and VP of Engineering at Habana Labs. Yossi Kasus served as Senior Director of Engineering at Mellanox and the head of VLSI at EZChip.

Analog Devices Files IP Lawsuit Against Xilinx

Photo above: Xilinx’s High End Zynq UltraScale+ RFSoC chip

Analog Devices (ADI) announced that it has filed a patent infringement lawsuit against Xilinx, for unauthorized use by Xilinx of several ADI patents relating to converter technology in two of Xilinx’s High End Zynq UltraScale+ RFSoC products. Filed in the United States District Court for the District of Delaware, the lawsuit seeks damages and an injunction that prevents Xilinx from selling any products that infringe ADI’s patents.

Zynq UltraScale+ Radio Frequency (RF) System-on-Chip (SoC) portfolio is a flagship product of Xilinx. It combines computing, field-programmable gate array (FPGA) and RF circuits in a single chip. It can cover the entire sub-6 gigahertz (GHz) spectrum needed for next-generation 5G deployment, supports direct RF sampling of up to 5 giga-samples per-second (GS/S) 14-bit analog-to-digital converters (ADCs) and 10 GS/S 14-bit digital-to-analog converters (DACs), both up to 6 GHz of analog bandwidth.

“ADI is a market leader in analog, mixed-signal and power integrated circuit technologies,” said Larry Weiss, Senior Vice President and General Counsel, Analog Devices. “Our continued investment in research and development totaled over $1 billion in the last fiscal year. We are committed to defending and protecting our intellectual property.”

Xilinx: “Analog Devices has chosen to litigate rather than compete”

In response, Xilinx announced it intend to “vigorously defend against this lawsuit. We created what many thought could not be done with the introduction of the Zynq UltraScale+ RFSoC – the industry’s only single-chip adaptable radio platform.  Through its patent lawsuit, Analog Devices has chosen to litigate rather than compete in the market.”

ADI said the complaint is focused on eight important ADI patents relating to ADCs. Those patents covers issues such as circuit and technique for enhancing linearity in analog-to-digital converters by injecting dither to sampled signals, calibrating an offset mismatch in ADCs using chopping techniques, ADC pipelined architecture, and more.

ADI claims that it has worked closely with Xilinx for many years to develop solutions tailored to Xilinx’s FPGA products, including Xilinx’s Kintex 7 and Kintex UltraScale products, its Virtex 7 and UltraScale products, Zynq 7 and initial Zynq UltraScale products. “Over the course of the parties’ collaboration, ADI has shared with Xilinx, under a non-disclosure agreement, extensive and detailed technical information concerning its many innovations in ADC technology.

But, “At the same time that Xilinx purportedly was working with ADI as an alleged partner to combine ADI’s proprietary ADC technology with Xilinx’s programmable system-ona-chip (SoC), it was also separately working to incorporate ADI’s patented technology directly into its new Integrated Direct-RF Subsystem.”

Moshe Gavrielov Joins the Board of Foretellix

The former President and CEO of Xilinx, Moshe Gavrielov, joins the Board of Directors of the Tel aviv based Foretellix. During his 10 years tenure ended in 2018 as the leader of Xilinx, Moshe redefined its strategy and drove the company through a broad transformation process bringing it to record annual revenues of $2.54 billion in 2018 and market cap valuation of approximately $20B. Today he also serves as an Executive Chairman of Wind River Systems and Member of the TSMC BOD Compensation Committee.

Foretellix has developed a verification framework for Autonomous Cars, based on approaches brought from the field of VLSI chip design. its Coverage Driven Verification Platform is based on a proprietary Scenario Description Language (SDL), planned to be an open language capable to generate billions of scenarios in order to verify the compliance of Autonomous Vehicles to regulatory and operational demands.

Foretellix is founded by a team of experienced VLSI verification experts. The Founder and CTO, Yoav Hollander, founded Verisity where he invented the “e” verification language. Verisity that was acquired by Cadence Design Systems for $315 million. The CEO Ziv Binyamini also sterted in Verisity, and later served as Corporate VP for simulation and verification business at Cadence and led the development of Verification IP. They all know each other very well: Gavrielov was the CEO of Verisity and closed the deal with Cadence.

Foretellix Founders Yoav Hollander (left) and Ziv Binyamini
Foretellix Founders Yoav Hollander (left) and Ziv Binyamini

“I am honored to welcome Moshe to the board of directors,” said Ziv Binyamini, CEO of Foretellix. “Moshe has not only led a multi-billion dollar company, but has previously worked with many of the Foretellix leaders to build a successful start-up focused on measurable verification.” Gavrielov said that Foretellix will help shape the future of mobility. “I strongly believe in the ability of this leadership team to enable measurable safety, removing the largest barrier to the broad deployment of autonomous vehicles.”