Deep-AI Launches Industry-First Integrated AI Training and Inference Solution for the Edge

October 7, 2020

CAESAREA, Israel, Oct. 7, 2020 — Deep-AI Technologies is emerging from stealth and launching the industry’s first integrated training and inference solution for deep learning at the edge. With Deep-AI, every inference node at the edge also becomes a training node, enabling faster, cheaper, scalable, and more secure AI versus today’s cloud-centric AI approach.

Deep-AI’s solution runs on off-the-shelf FPGA cards, eliminating the need for GPUs, and provides a 10X gain in performance/power or performance/cost versus a GPU. The FPGA hardware is completely under-the-hood and transparent to the data scientists and the developers designing their AI applications. Standard deep learning frameworks are supported including Tensorflow, PyTorch and Keras.

Training deep learning models and servicing inference queries demand massive compute resources delivered by expensive, power-hungry GPUs, and consequently deep learning is performed in the cloud or in large on-premise data centers. Training new models takes days and weeks to complete, and inference queries suffer from long latencies of the round-trip delays to and from the cloud.

Deep-AI LogoYet, the data which feeds into the cloud systems, for updating the training models and the inference queries, is generated mostly at the edge – in stores, factories, terminals, office buildings, hospitals, city facilities, 5G cell sites, vehicles, farms, homes and hand-held mobile devices. Transporting the rapidly growing data to and from the cloud or data center leads to unsustainable network bandwidth, high cost and slow responsiveness, as well as compromises data privacy and security and reduces device autonomy and application reliability.

To overcome these limitations, Deep-AI has uniquely developed an integrated, holistic, and efficient training and inference deep learning solution for the edge. With Deep-AI, application developers can deploy an integrated training-inference solution with real-time retraining of their model in parallel to online inference on the same device.

At the core of Deep-AI’s technology is the ability to train at 8-bit fixed-point coupled with high sparsity ratios at training time, as opposed to 32-bit floating-point and no sparsity which is the norm today with GPUs. These two technological breakthroughs enable AI platforms that are superior in performance, power, and cost. When realized into an ASIC they can drive a 100X efficiency in silicon area and power over GPUs.

Innovative algorithms compensate for the lower precision of 8-bit fixed-point and the high sparsity and minimize any reduction in training accuracy. For edge applications, where the use cases typically call for the retraining of pre-trained models with incremental data updates, the training accuracy is fully maintained in most cases and with minimal reduction in other cases.

Furthermore, in most systems today training is done at 32-bit floating-point while there is a growing desire to run inference at 8bit fixed-point. In these cases, one needs to manually run challenging as well as time and resource consuming quantization processes to convert the 32-bit training output into an 8-bit inference input. Moreover, this conversion often results in loss of accuracy. Because Deep-AI’s training is done in 8-bit fixed-point it is inference-ready by design and feeds directly to inference. No manual intervention nor processing is needed to quantize the training output before inference and no loss of accuracy is experienced from moving from training to inference.

Deep-AI’s solution uses FPGAs, which are rapidly growing in adoption for a wide variety of acceleration workloads. Recent advancements in deep learning enable inference with 8-bit fixed-point number formats and enable very low-latency inference on FPGAs. Deep-AI’s breakthrough technology takes a huge step forward by also enabling training on FPGAs with 8-bit fixed-point number formats and running both training and inference on the same FPGA platform.

Deep-AI’s solution is available today for on-premise deployments on standard off-the-shelf FPGA cards from Xilinx and leading server vendors. The solution will also be available on Xilinx cloud-based FPGA-as-a-service instances in the first quarter of 2021.

Collaboration with Xilinx, Dell Technologies and One Convergence

Deep-AI’s solution runs on Xilinx Alveo accelerator cards, PCIe add-in cards certified and available on a variety of standard servers from leading server vendors. The same hardware is used for inference and retraining of the deep learning model, allowing an on-going iterative process that keeps the model updated to the new data that is continuously generated.

“Deep-AI has demonstrated impressive capability to address the challenges of fixed-point training for deep learning models” said Ramine Roane, Vice President of Software & AI Solutions Marketing at Xilinx. “Xilinx is excited to be working with Deep-AI to bring to market a training solution based on our adaptive platforms.”

Deep-AI working with Dell Technologies has validated the PowerEdge R740xd rack servers with pre-installed Xilinx Alveo cards and sample network models and data sets, in particularly for the retail and manufacturing markets.

In addition, Deep-AI has partnered with One Convergence, to offer customers the Deep-AI solution integrated with the One Convergence DKube complete end-to-end enterprise MLOps platform.

“We are happy to be partnering with Deep AI and offer cost effective, integrated training and inference acceleration solutions to our customers though our DKube platform” said Ajai Tyagi, Senior Director, Marketing and Sales. “ DKube ( is a modern Kubernetes-based platform based on open standards such as Kubeflow and MLFlow, and it addresses the critical needs of the AI communities for a common, integrated MLOps workflow, especially those that want to deploy on-prem and/or hybrid models.”

About Deep-AI Technologies

Deep-AI Technologies delivers accelerated and integrated deep-learning training and inference at the network edge for fast, secure, and efficient AI deployments. Our solutions feature breakthrough technology for training at 8-bit fixed-point coupled with high sparsity ratios, to enable deep-learning at a fraction of the cost and power of GPU systems. For more information and scheduling a demo visit

Source: Deep-AI Technologies

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!

IBM Research Scales to 11,400 Cores for EDA

August 5, 2021

For many HPC users, their needs are not evenly distributed throughout a year: some might need few – if any – resources for months, then they might need a very large system for a week. For those kinds of users, large Read more…

Careers in Cybersecurity Featured at PEARC21

August 5, 2021

The PEARC21 (Practice & Experience in Advanced Research Computing) Student Program featured a Cybersecurity Careers Panel. Five experts shared lessons learned from more than 100 years of combined experience. While it Read more…

HPC Career Notes: August 2021 Edition

August 4, 2021

In this monthly feature, we’ll keep you up-to-date on the latest career developments for individuals in the high-performance computing community. Whether it’s a promotion, new company hire, or even an accolade, we’ Read more…

The Promise (and Necessity) of Runtime Systems like Charm++ in Exascale Power Management

August 4, 2021

Big heterogeneous computer systems, especially forthcoming exascale computers, are power hungry and difficult to program effectively. This is, of course, not an unrecognized problem. In a recent blog, Charmworks’ CEO S Read more…

Digging into the Atos-Nimbix Deal: Big US HPC and Global Cloud Aspirations. Look out HPE?

August 2, 2021

Behind Atos’s deal announced last week to acquire HPC-cloud specialist Nimbix are ramped-up plans to penetrate the U.S. HPC market and global expansion of its HPC cloud capabilities. Nimbix will become “an Atos HPC c Read more…

AWS Solution Channel

Pushing pixels, not data with NICE DCV

NICE DCV, our high-performance, low-latency remote-display protocol, was originally created for scientists and engineers who ran large workloads on far-away supercomputers, but needed to visualize data without moving it. Read more…

Berkeley Lab Makes Strides in Autonomous Discovery to Tackle the Data Deluge

August 2, 2021

Data production is outpacing the human capacity to process said data. Whether a giant radio telescope, a new particle accelerator or lidar data from autonomous cars, the sheer scale of the data generated is increasingly Read more…

Careers in Cybersecurity Featured at PEARC21

August 5, 2021

The PEARC21 (Practice & Experience in Advanced Research Computing) Student Program featured a Cybersecurity Careers Panel. Five experts shared lessons learn Read more…

Digging into the Atos-Nimbix Deal: Big US HPC and Global Cloud Aspirations. Look out HPE?

August 2, 2021

Behind Atos’s deal announced last week to acquire HPC-cloud specialist Nimbix are ramped-up plans to penetrate the U.S. HPC market and global expansion of its Read more…

What’s After Exascale? The Internet of Workflows Says HPE’s Nicolas Dubé

July 29, 2021

With the race to exascale computing in its final leg, it’s natural to wonder what the Post Exascale Era will look like. Nicolas Dubé, VP and chief technologist for HPE’s HPC business unit, agrees and shared his vision at Supercomputing Frontiers Europe 2021 held last week. The next big thing, he told the virtual audience at SFE21, is something that will connect HPC and (broadly) all of IT – into what Dubé calls The Internet of Workflows. Read more…

How UK Scientists Developed Transformative, HPC-Powered Coronavirus Sequencing System

July 29, 2021

In November 2020, the COVID-19 Genomics UK Consortium (COG-UK) won the HPCwire Readers’ Choice Award for Best HPC Collaboration for its CLIMB-COVID sequencing project. Launched in March 2020, CLIMB-COVID has now resulted in the sequencing of over 675,000 coronavirus genomes – an increasingly critical task as variants like Delta threaten the tenuous prospect of a return to normalcy in much of the world. Read more…

IBM and University of Tokyo Roll Out Quantum System One in Japan

July 27, 2021

IBM and the University of Tokyo today unveiled an IBM Quantum System One as part of the IBM-Japan quantum program announced in 2019. The system is the second IB Read more…

Intel Unveils New Node Names; Sapphire Rapids Is Now an ‘Intel 7’ CPU

July 27, 2021

What's a preeminent chip company to do when its process node technology lags the competition by (roughly) one generation, but outmoded naming conventions make it seem like it's two nodes behind? For Intel, the response was to change how it refers to its nodes with the aim of better reflecting its positioning within the leadership semiconductor manufacturing space. Intel revealed its new node nomenclature, and... Read more…

Will Approximation Drive Post-Moore’s Law HPC Gains?

July 26, 2021

“Hardware-based improvements are going to get more and more difficult,” said Neil Thompson, an innovation scholar at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL). “I think that’s something that this crowd will probably, actually, be already familiar with.” Thompson, speaking... Read more…

With New Owner and New Roadmap, an Independent Omni-Path Is Staging a Comeback

July 23, 2021

Put on a shelf by Intel in 2019, Omni-Path faced a uncertain future, but under new custodian Cornelis Networks, OmniPath is looking to make a comeback as an independent high-performance interconnect solution. A "significant refresh" – called Omni-Path Express – is coming later this year according to the company. Cornelis Networks formed last September as a spinout of Intel's Omni-Path division. Read more…

AMD Chipmaker TSMC to Use AMD Chips for Chipmaking

May 8, 2021

TSMC has tapped AMD to support its major manufacturing and R&D workloads. AMD will provide its Epyc Rome 7702P CPUs – with 64 cores operating at a base cl Read more…

Berkeley Lab Debuts Perlmutter, World’s Fastest AI Supercomputer

May 27, 2021

A ribbon-cutting ceremony held virtually at Berkeley Lab's National Energy Research Scientific Computing Center (NERSC) today marked the official launch of Perlmutter – aka NERSC-9 – the GPU-accelerated supercomputer built by HPE in partnership with Nvidia and AMD. Read more…

Ahead of ‘Dojo,’ Tesla Reveals Its Massive Precursor Supercomputer

June 22, 2021

In spring 2019, Tesla made cryptic reference to a project called Dojo, a “super-powerful training computer” for video data processing. Then, in summer 2020, Tesla CEO Elon Musk tweeted: “Tesla is developing a [neural network] training computer called Dojo to process truly vast amounts of video data. It’s a beast! … A truly useful exaflop at de facto FP32.” Read more…

Google Launches TPU v4 AI Chips

May 20, 2021

Google CEO Sundar Pichai spoke for only one minute and 42 seconds about the company’s latest TPU v4 Tensor Processing Units during his keynote at the Google I Read more…

CentOS Replacement Rocky Linux Is Now in GA and Under Independent Control

June 21, 2021

The Rocky Enterprise Software Foundation (RESF) is announcing the general availability of Rocky Linux, release 8.4, designed as a drop-in replacement for the soon-to-be discontinued CentOS. The GA release is launching six-and-a-half months after Red Hat deprecated its support for the widely popular, free CentOS server operating system. The Rocky Linux development effort... Read more…

Intel Launches 10nm ‘Ice Lake’ Datacenter CPU with Up to 40 Cores

April 6, 2021

The wait is over. Today Intel officially launched its 10nm datacenter CPU, the third-generation Intel Xeon Scalable processor, codenamed Ice Lake. With up to 40 Read more…

Iran Gains HPC Capabilities with Launch of ‘Simorgh’ Supercomputer

May 18, 2021

Iran is said to be developing domestic supercomputing technology to advance the processing of scientific, economic, political and military data, and to strengthen the nation’s position in the age of AI and big data. On Sunday, Iran unveiled the Simorgh supercomputer, which will deliver.... Read more…

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

Leading Solution Providers


Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from I Read more…

AMD-Xilinx Deal Gains UK, EU Approvals — China’s Decision Still Pending

July 1, 2021

AMD’s planned acquisition of FPGA maker Xilinx is now in the hands of Chinese regulators after needed antitrust approvals for the $35 billion deal were receiv Read more…

GTC21: Nvidia Launches cuQuantum; Dips a Toe in Quantum Computing

April 13, 2021

Yesterday Nvidia officially dipped a toe into quantum computing with the launch of cuQuantum SDK, a development platform for simulating quantum circuits on GPU-accelerated systems. As Nvidia CEO Jensen Huang emphasized in his keynote, Nvidia doesn’t plan to build... Read more…

Microsoft to Provide World’s Most Powerful Weather & Climate Supercomputer for UK’s Met Office

April 22, 2021

More than 14 months ago, the UK government announced plans to invest £1.2 billion ($1.56 billion) into weather and climate supercomputing, including procuremen Read more…

Quantum Roundup: IBM, Rigetti, Phasecraft, Oxford QC, China, and More

July 13, 2021

IBM yesterday announced a proof for a quantum ML algorithm. A week ago, it unveiled a new topology for its quantum processors. Last Friday, the Technical Univer Read more…

Q&A with Jim Keller, CTO of Tenstorrent, and an HPCwire Person to Watch in 2021

April 22, 2021

As part of our HPCwire Person to Watch series, we are happy to present our interview with Jim Keller, president and chief technology officer of Tenstorrent. One of the top chip architects of our time, Keller has had an impactful career. Read more…

Frontier to Meet 20MW Exascale Power Target Set by DARPA in 2008

July 14, 2021

After more than a decade of planning, the United States’ first exascale computer, Frontier, is set to arrive at Oak Ridge National Laboratory (ORNL) later this year. Crossing this “1,000x” horizon required overcoming four major challenges: power demand, reliability, extreme parallelism and data movement. Read more…

Senate Debate on Bill to Remake NSF – the Endless Frontier Act – Begins

May 18, 2021

The U.S. Senate today opened floor debate on the Endless Frontier Act which seeks to remake and expand the National Science Foundation by creating a technology Read more…

  • arrow
  • Click Here for More Headlines
  • arrow