Researchers Design New Neuromorphic Chip for AI on the Edge

August 19, 2022

Aug. 19, 2022 — An international team of researchers has designed and built a chip that runs computations directly in memory and can run a wide variety of AI applications–all at a fraction of the energy consumed by computing platforms for general-purpose AI computing.

The NeuRRAM neuromorphic chip was developed by an international team of researchers co-led by UC San Diego engineers.
Credit: David Baillot/UC San Diego Jacobs School of Engineering

The NeuRRAM neuromorphic chip brings AI a step closer to running on a broad range of edge devices, disconnected from the cloud, where they can perform sophisticated cognitive tasks anywhere and anytime without relying on a network connection to a centralized server.  Applications abound in every corner of the world and every facet of our lives, and range from smart watches, to VR headsets, smart earbuds, smart sensors in factories and rovers for space exploration.

The NeuRRAM chip is not only twice as energy efficient as the state-of-the-art “compute-in-memory” chips, an innovative class of hybrid chips that runs computations in memory, it also delivers results that are just as accurate as conventional digital chips. Conventional AI platforms are a lot bulkier and typically are constrained to using large data servers operating in the cloud.

In addition, the NeuRRAM chip is highly versatile and supports many different neural network models and architectures. As a result, the chip can be used for many different applications, including image recognition and reconstruction as well as voice recognition.

“The conventional wisdom is that the higher efficiency of compute-in-memory is at the cost of versatility, but our NeuRRAM chip obtains efficiency while not sacrificing versatility,” said Weier Wan, the paper’s first corresponding author and a recent Ph.D. graduate of Stanford University who worked on the chip while at UC San Diego, where he was co-advised by Gert Cauwenberghs in the Department of Bioengineering.

The research team, co-led by bioengineers at the University of California San Diego, presents their results in the Aug. 17 issue of Nature.

Currently, AI computing is both power hungry and computationally expensive. Most AI applications on edge devices involve moving data from the devices to the cloud, where the AI processes and analyzes it. Then the results are moved back to the device. That’s because most edge devices are battery-powered and as a result only have a limited amount of power that can be dedicated to computing.

By reducing power consumption needed for AI inference at the edge, this NeuRRAM chip could lead to more robust, smarter and accessible edge devices and smarter manufacturing. It could also lead to better data privacy as the transfer of data from devices to the cloud comes with increased security risks.

On AI chips, moving data from memory to computing units is one major bottleneck.

“It’s the equivalent of doing an eight-hour commute for a two-hour work day,” Wan said.

To solve this data transfer issue, researchers used what is known as resistive random-access memory, a type of non-volatile memory that allows for computation directly within memory rather than in separate computing units. RRAM and other emerging memory technologies used as synapse arrays for neuromorphic computing were pioneered in the lab of Philip Wong, Wan’s advisor at Stanford and a main contributor to this work. Computation with RRAM chips is not necessarily new, but generally it leads to a decrease in the accuracy of the computations performed on the chip and a lack of flexibility in the chip’s architecture.

“Compute-in-memory has been common practice in neuromorphic engineering since it was introduced more than 30 years ago,” Cauwenberghs said.  “What is new with NeuRRAM is that the extreme efficiency now goes together with great flexibility for diverse AI applications with almost no loss in accuracy over standard digital general-purpose compute platforms.”

A carefully crafted methodology was key to the work with multiple levels of “co-optimization” across the abstraction layers of hardware and software, from the design of the chip to its configuration to run various AI tasks. In addition, the team made sure to account for various constraints that span from memory device physics to circuits and network architecture.

“This chip now provides us with a platform to address these problems across the stack from devices and circuits to algorithms,” said Siddharth Joshi, an assistant professor of computer science and engineering at the University of Notre Dame , who started working on the project as a Ph.D. student and postdoctoral researcher in Cauwenberghs lab at UC San Diego.

Chip performance

Researchers measured the chip’s energy efficiency by a measure known as energy-delay product, or EDP. EDP combines both the amount of energy consumed for every operation and the amount of times it takes to complete the operation. By this measure, the NeuRRAM chip achieves 1.6 to 2.3 times lower EDP (lower is better) and 7 to 13 times higher computational density than state-of-the-art chips.

Researchers ran various AI tasks on the chip. It achieved 99% accuracy on a handwritten digit recognition task; 85.7% on an image classification task; and 84.7% on a Google speech command recognition task. In addition, the chip also achieved a 70% reduction in image-reconstruction error on an image-recovery task. These results are comparable to existing digital chips that perform computation under the same bit-precision, but with drastic savings in energy.

Researchers point out that one key contribution of the paper is that all the results featured are obtained directly on the hardware. In many previous works of compute-in-memory chips, AI benchmark results were often obtained partially by software simulation.

Next steps include improving architectures and circuits and scaling the design to more advanced technology nodes. Researchers also plan to tackle other applications, such as spiking neural networks.

“We can do better at the device level, improve circuit design to implement additional features and address diverse applications with our dynamic NeuRRAM platform,” said Rajkumar Kubendran, an assistant professor for the University of Pittsburgh, who started work on the project while a Ph.D. student in Cauwenberghs’ research group at UC San Diego.

In addition, Wan is a founding member of a startup that works on productizing the compute-in-memory technology. “As a researcher and  an engineer, my ambition is to bring research innovations from labs into practical use,” Wan said.

New architecture 

The key to NeuRRAM’s energy efficiency is an innovative method to sense output in memory. Conventional approaches use voltage as input and measure current as the result. But this leads to the need for more complex and more power hungry circuits. In NeuRRAM, the team engineered a neuron circuit that senses voltage and performs analog-to-digital conversion in an energy efficient manner. This voltage-mode sensing can activate all the rows and all the columns of an RRAM array in a single computing cycle, allowing higher parallelism.

In the NeuRRAM architecture, CMOS neuron circuits are physically interleaved with RRAM weights. It differs from conventional designs where CMOS circuits are typically on the peripheral of RRAM weights.The neuron’s connections with the RRAM array can be configured to serve as either input or output of the neuron. This allows neural network inference in various data flow directions without incurring overheads in area or power consumption. This in turn makes the architecture easier to reconfigure.

To make sure that accuracy of the AI computations can be preserved across various neural network architectures, researchers developed a set of hardware algorithm co-optimization techniques. The techniques were verified on various neural networks including convolutional neural networks, long short-term memory, and restricted Boltzmann machines.

As a neuromorphic AI chip, NeuroRRAM performs parallel distributed processing across 48 neurosynaptic cores. To simultaneously achieve high versatility and high efficiency, NeuRRAM supports data-parallelism by mapping a layer in the neural network model onto multiple cores for parallel inference on multiple data. Also, NeuRRAM offers model-parallelism by mapping different layers of a model onto different cores and performing inference in a pipelined fashion.

An international research team

The work is the result of an international team of researchers.

The UC San Diego team designed the CMOS circuits that implement the neural functions interfacing with the RRAM arrays to support the synaptic functions in the chip’s architecture, for high efficiency and versatility. Wan, working closely with the entire team, implemented the design; characterized the chip; trained the AI models; and executed the experiments. Wan also developed a software toolchain that maps AI applications onto the chip.

The RRAM synapse array and its operating conditions were extensively characterized and optimized at Stanford University.

The RRAM array was fabricated and integrated onto CMOS at Tsinghua University.

The Team at Notre Dame contributed to both the design and architecture of the chip and the subsequent machine learning model design and training.

The research started as part of the National Science Foundation funded Expeditions in Computing project on Visual Cortex on Silicon at Penn State University, with continued funding support from the Office of Naval Research Science of AI program, the Semiconductor Research Corporation and DARPA JUMP program, and Western Digital Corporation.

A compute-in-memory chip based on resistive random-access memory

Published open-access in Nature, August 17, 2022, https://www.nature.com/articles/s41586-022-04992-8.

Authors

Weier Wan, Rajkumar Kubendran, Stephen Deiss, Siddharth Joshi, Gert Cauwenberghs, University of California San Diego

Weier Wan, S. Burc Eryilmaz, Priyanka Raina, H-S Philip Wong, Stanford University

Clemens Schaefer, Siddharth Joshi, University of Notre Dame

Rajkumar Kubendran, University of Pittsburgh

Wenqiang Zhang, Dabin Wu, He Qian, Bin Gao, Huaqiang Wu, Tsinghua University

Corresponding authors: Wan, Gao, Joshi, Wu, Wong and Cauwenberghs


Source: Ioana Patringenaru, UC San Diego

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Supercomputing Helps Explain the Milky Way’s Shape

September 30, 2022

If you look at the Milky Way from “above,” it almost looks like a cat’s eye: a circle of spiral arms with an oval “iris” in the middle. That iris — a starry bar that connects the spiral arms — has two stran Read more…

Top Supercomputers to Shake Up Earthquake Modeling

September 29, 2022

Two DOE-funded projects — and a bunch of top supercomputers — are converging to improve our understanding of earthquakes and enable the construction of more earthquake-resilient buildings and infrastructure. The firs Read more…

How Intel Plans to Rebuild Its Manufacturing Supply Chain

September 29, 2022

Intel's engineering roots saw a revival at this week's Innovation, with attendees recalling the show’s resemblance to Intel Developer Forum, the company's annual developer gala last held in 2016. The chipmaker cut t Read more…

Intel Labs Launches Neuromorphic ‘Kapoho Point’ Board

September 28, 2022

Over the past five years, Intel has been iterating on its neuromorphic chips and systems, aiming to create devices (and software for those devices) that closely mimic the behavior of the human brain through the use of co Read more…

DOE Announces $42M ‘COOLERCHIPS’ Datacenter Cooling Program

September 28, 2022

With massive machines like Frontier guzzling tens of megawatts of power to operate, datacenters’ energy use is of increasing concern for supercomputer operations – and particularly for the U.S. Department of Energy ( Read more…

AWS Solution Channel

Shutterstock 1818499862

Rearchitecting AWS Batch managed services to leverage AWS Fargate

AWS service teams continuously improve the underlying infrastructure and operations of managed services, and AWS Batch is no exception. The AWS Batch team recently moved most of their job scheduler fleet to a serverless infrastructure model leveraging AWS Fargate. Read more…

Microsoft/NVIDIA Solution Channel

Shutterstock 1166887495

Improving Insurance Fraud Detection using AI Running on Cloud-based GPU-Accelerated Systems

Insurance is a highly regulated industry that is evolving as the industry faces changing customer expectations, massive amounts of data, and increased regulations. A major issue facing the industry is tracking insurance fraud. Read more…

Do You Believe in Science? Take the HPC Covid Safety Pledge

September 28, 2022

ISC 2022 was back in person, and the celebration was on. Frontier had been named the first exascale supercomputer on the Top500 list, and workshops, poster sessions, paper presentations, receptions, and booth meetings we Read more…

How Intel Plans to Rebuild Its Manufacturing Supply Chain

September 29, 2022

Intel's engineering roots saw a revival at this week's Innovation, with attendees recalling the show’s resemblance to Intel Developer Forum, the company's ann Read more…

Intel Labs Launches Neuromorphic ‘Kapoho Point’ Board

September 28, 2022

Over the past five years, Intel has been iterating on its neuromorphic chips and systems, aiming to create devices (and software for those devices) that closely Read more…

HPE to Build 100+ Petaflops Shaheen III Supercomputer

September 27, 2022

The King Abdullah University of Science and Technology (KAUST) in Saudi Arabia has announced that HPE has won the bid to build the Shaheen III supercomputer. Sh Read more…

Intel’s New Programmable Chips Next Year to Replace Aging Products

September 27, 2022

Intel shared its latest roadmap of programmable chips, and doesn't want to dig itself into a hole by following AMD's strategy in the area.  "We're thankfully not matching their strategy," said Shannon Poulin, corporate vice president for the datacenter and AI group at Intel, in response to a question posed by HPCwire during a press briefing. The updated roadmap pieces together Intel's strategy for FPGAs... Read more…

Intel Ships Sapphire Rapids – to Its Cloud

September 27, 2022

Intel has had trouble getting its chips in the hands of customers on time, but is providing the next best thing – to try out those chips in the cloud. Delayed chips such as Sapphire Rapids server processors and Habana Gaudi 2 AI chip will be available on a platform called the Intel Developer Cloud, which was announced at the Intel Innovation event being held in San Jose, California. Read more…

More Details on ‘Half-Exaflop’ Horizon System, LCCF Emerge

September 26, 2022

Since 2017, plans for the Leadership-Class Computing Facility (LCCF) have been underway. Slated for full operation somewhere around 2026, the LCCF’s scope ext Read more…

Nvidia Shuts Out RISC-V Software Support for GPUs 

September 23, 2022

Nvidia is not interested in bringing software support to its GPUs for the RISC-V architecture despite being an early adopter of the open-source technology in its GPU controllers. Nvidia has no plans to add RISC-V support for CUDA, which is the proprietary GPU software platform, a company representative... Read more…

Nvidia Introduces New Ada Lovelace GPU Architecture, OVX Systems, Omniverse Cloud

September 20, 2022

In his GTC keynote today, Nvidia CEO Jensen Huang launched another new Nvidia GPU architecture: Ada Lovelace, named for the legendary mathematician regarded as Read more…

Nvidia Shuts Out RISC-V Software Support for GPUs 

September 23, 2022

Nvidia is not interested in bringing software support to its GPUs for the RISC-V architecture despite being an early adopter of the open-source technology in its GPU controllers. Nvidia has no plans to add RISC-V support for CUDA, which is the proprietary GPU software platform, a company representative... Read more…

AWS Takes the Short and Long View of Quantum Computing

August 30, 2022

It is perhaps not surprising that the big cloud providers – a poor term really – have jumped into quantum computing. Amazon, Microsoft Azure, Google, and th Read more…

US Senate Passes CHIPS Act Temperature Check, but Challenges Linger

July 19, 2022

The U.S. Senate on Tuesday passed a major hurdle that will open up close to $52 billion in grants for the semiconductor industry to boost manufacturing, supply chain and research and development. U.S. senators voted 64-34 in favor of advancing the CHIPS Act, which sets the stage for the final consideration... Read more…

Chinese Startup Biren Details BR100 GPU

August 22, 2022

Amid the high-performance GPU turf tussle between AMD and Nvidia (and soon, Intel), a new, China-based player is emerging: Biren Technology, founded in 2019 and headquartered in Shanghai. At Hot Chips 34, Biren co-founder and president Lingjie Xu and Biren CTO Mike Hong took the (virtual) stage to detail the company’s inaugural product: the Biren BR100 general-purpose GPU (GPGPU). “It is my honor to present... Read more…

Newly-Observed Higgs Mode Holds Promise in Quantum Computing

June 8, 2022

The first-ever appearance of a previously undetectable quantum excitation known as the axial Higgs mode – exciting in its own right – also holds promise for developing and manipulating higher temperature quantum materials... Read more…

AMD’s MI300 APUs to Power Exascale El Capitan Supercomputer

June 21, 2022

Additional details of the architecture of the exascale El Capitan supercomputer were disclosed today by Lawrence Livermore National Laboratory’s (LLNL) Terri Read more…

Tesla Bulks Up Its GPU-Powered AI Super – Is Dojo Next?

August 16, 2022

Tesla has revealed that its biggest in-house AI supercomputer – which we wrote about last year – now has a total of 7,360 A100 GPUs, a nearly 28 percent uplift from its previous total of 5,760 GPUs. That’s enough GPU oomph for a top seven spot on the Top500, although the tech company best known for its electric vehicles has not publicly benchmarked the system. If it had, it would... Read more…

Exclusive Inside Look at First US Exascale Supercomputer

July 1, 2022

HPCwire takes you inside the Frontier datacenter at DOE's Oak Ridge National Laboratory (ORNL) in Oak Ridge, Tenn., for an interview with Frontier Project Direc Read more…

Leading Solution Providers

Contributors

AMD Opens Up Chip Design to the Outside for Custom Future

June 15, 2022

AMD is getting personal with chips as it sets sail to make products more to the liking of its customers. The chipmaker detailed a modular chip future in which customers can mix and match non-AMD processors in a custom chip package. "We are focused on making it easier to implement chips with more flexibility," said Mark Papermaster, chief technology officer at AMD during the analyst day meeting late last week. Read more…

Nvidia, Intel to Power Atos-Built MareNostrum 5 Supercomputer

June 16, 2022

The long-troubled, hotly anticipated MareNostrum 5 supercomputer finally has a vendor: Atos, which will be supplying a system that includes both Nvidia and Inte Read more…

UCIe Consortium Incorporates, Nvidia and Alibaba Round Out Board

August 2, 2022

The Universal Chiplet Interconnect Express (UCIe) consortium is moving ahead with its effort to standardize a universal interconnect at the package level. The c Read more…

Using Exascale Supercomputers to Make Clean Fusion Energy Possible

September 2, 2022

Fusion, the nuclear reaction that powers the Sun and the stars, has incredible potential as a source of safe, carbon-free and essentially limitless energy. But Read more…

Is Time Running Out for Compromise on America COMPETES/USICA Act?

June 22, 2022

You may recall that efforts proposed in 2020 to remake the National Science Foundation (Endless Frontier Act) have since expanded and morphed into two gigantic bills, the America COMPETES Act in the U.S. House of Representatives and the U.S. Innovation and Competition Act in the U.S. Senate. So far, efforts to reconcile the two pieces of legislation have snagged and recent reports... Read more…

Nvidia, Qualcomm Shine in MLPerf Inference; Intel’s Sapphire Rapids Makes an Appearance.

September 8, 2022

The steady maturation of MLCommons/MLPerf as an AI benchmarking tool was apparent in today’s release of MLPerf v2.1 Inference results. Twenty-one organization Read more…

India Launches Petascale ‘PARAM Ganga’ Supercomputer

March 8, 2022

Just a couple of weeks ago, the Indian government promised that it had five HPC systems in the final stages of installation and would launch nine new supercomputers this year. Now, it appears to be making good on that promise: the country’s National Supercomputing Mission (NSM) has announced the deployment of “PARAM Ganga” petascale supercomputer at Indian Institute of Technology (IIT)... Read more…

Not Just Cash for Chips – The New Chips and Science Act Boosts NSF, DOE, NIST

August 3, 2022

After two-plus years of contentious debate, several different names, and final passage by the House (243-187) and Senate (64-33) last week, the Chips and Science Act will soon become law. Besides the $54.2 billion provided to boost US-based chip manufacturing, the act reshapes US science policy in meaningful ways. NSF’s proposed budget... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire