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 (https://www.dkube.io) 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 https://deep-aitech.com.


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!

NASA Uses Supercomputing to Measure Carbon in the World’s Trees

October 22, 2020

Trees constitute one of the world’s most important carbon sinks, pulling enormous amounts of carbon dioxide from the atmosphere and storing the carbon in their trunks and the surrounding soil. Measuring this carbon sto Read more…

By Oliver Peckham

Nvidia Dominates (Again) Latest MLPerf Inference Results

October 22, 2020

The two-year-old AI benchmarking group MLPerf.org released its second set of inferencing results yesterday and again, as in the most recent MLPerf training results (July 2020), it was almost entirely The Nvidia Show, a p Read more…

By John Russell

With Optane Gaining, Intel Exits NAND Flash

October 21, 2020

In a sign that its 3D XPoint memory technology is gaining traction, Intel Corp. is departing the NAND flash memory and storage market with the sale of its manufacturing base in China to SK Hynix of South Korea. The $9 Read more…

By George Leopold

HPE, AMD and EuroHPC Partner for Pre-Exascale LUMI Supercomputer

October 21, 2020

Not even a week after Nvidia announced that it would be providing hardware for the first four of the eight planned EuroHPC systems, HPE and AMD are announcing another major EuroHPC design win. Finnish supercomputing cent Read more…

By Oliver Peckham

HPE to Build Australia’s Most Powerful Supercomputer for Pawsey

October 20, 2020

The Pawsey Supercomputing Centre in Perth, Western Australia, has had a busy year. Pawsey typically spends much of its time looking to the stars, working with a variety of observatories and astronomers – but when COVID Read more…

By Oliver Peckham

AWS Solution Channel

Live Webinar: AWS & Intel Research Webinar Series – Fast scaling research workloads on the cloud

Date: 27 Oct – 5 Nov

Join us for the AWS and Intel Research Webinar series.

You will learn how we help researchers process complex workloads, quickly analyze massive data pipelines, store petabytes of data, and advance research using transformative technologies. Read more…

Intel® HPC + AI Pavilion

Berlin Institute of Health: Putting HPC to Work for the World

Researchers from the Center for Digital Health at the Berlin Institute of Health (BIH) are using science to understand the pathophysiology of COVID-19, which can help to inform the development of targeted treatments. Read more…

DDN-Tintri Showcases Technology Integration with Two New Products

October 20, 2020

DDN, a long-time leader in HPC storage, announced two new products today and provided more detail around its strategy for integrating DDN HPC technologies with the enterprise strengths of its recent acquisitions, notably Read more…

By John Russell

Nvidia Dominates (Again) Latest MLPerf Inference Results

October 22, 2020

The two-year-old AI benchmarking group MLPerf.org released its second set of inferencing results yesterday and again, as in the most recent MLPerf training resu Read more…

By John Russell

HPE, AMD and EuroHPC Partner for Pre-Exascale LUMI Supercomputer

October 21, 2020

Not even a week after Nvidia announced that it would be providing hardware for the first four of the eight planned EuroHPC systems, HPE and AMD are announcing a Read more…

By Oliver Peckham

HPE to Build Australia’s Most Powerful Supercomputer for Pawsey

October 20, 2020

The Pawsey Supercomputing Centre in Perth, Western Australia, has had a busy year. Pawsey typically spends much of its time looking to the stars, working with a Read more…

By Oliver Peckham

DDN-Tintri Showcases Technology Integration with Two New Products

October 20, 2020

DDN, a long-time leader in HPC storage, announced two new products today and provided more detail around its strategy for integrating DDN HPC technologies with Read more…

By John Russell

Is the Nvidia A100 GPU Performance Worth a Hardware Upgrade?

October 16, 2020

Over the last decade, accelerators have seen an increasing rate of adoption in high-performance computing (HPC) platforms, and in the June 2020 Top500 list, eig Read more…

By Hartwig Anzt, Ahmad Abdelfattah and Jack Dongarra

Nvidia and EuroHPC Team for Four Supercomputers, Including Massive ‘Leonardo’ System

October 15, 2020

The EuroHPC Joint Undertaking (JU) serves as Europe’s concerted supercomputing play, currently comprising 32 member states and billions of euros in funding. I Read more…

By Oliver Peckham

ROI: Is HPC Worth It? What Can We Actually Measure?

October 15, 2020

HPC enables innovation and discovery. We all seem to agree on that. Is there a good way to quantify how much that’s worth? Thanks to a sponsored white pape Read more…

By Addison Snell, Intersect360 Research

Preparing for Exascale Science on Day 1

October 14, 2020

Science simulation, visualization, data, and learning applications will greatly benefit from the massive computational resources available with future exascal Read more…

By Linda Barney

Supercomputer-Powered Research Uncovers Signs of ‘Bradykinin Storm’ That May Explain COVID-19 Symptoms

July 28, 2020

Doctors and medical researchers have struggled to pinpoint – let alone explain – the deluge of symptoms induced by COVID-19 infections in patients, and what Read more…

By Oliver Peckham

Nvidia Said to Be Close on Arm Deal

August 3, 2020

GPU leader Nvidia Corp. is in talks to buy U.K. chip designer Arm from parent company Softbank, according to several reports over the weekend. If consummated Read more…

By George Leopold

Intel’s 7nm Slip Raises Questions About Ponte Vecchio GPU, Aurora Supercomputer

July 30, 2020

During its second-quarter earnings call, Intel announced a one-year delay of its 7nm process technology, which it says it will create an approximate six-month shift for its CPU product timing relative to prior expectations. The primary issue is a defect mode in the 7nm process that resulted in yield degradation... Read more…

By Tiffany Trader

Google Hires Longtime Intel Exec Bill Magro to Lead HPC Strategy

September 18, 2020

In a sign of the times, another prominent HPCer has made a move to a hyperscaler. Longtime Intel executive Bill Magro joined Google as chief technologist for hi Read more…

By Tiffany Trader

HPE Keeps Cray Brand Promise, Reveals HPE Cray Supercomputing Line

August 4, 2020

The HPC community, ever-affectionate toward Cray and its eponymous founder, can breathe a (virtual) sigh of relief. The Cray brand will live on, encompassing th Read more…

By Tiffany Trader

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…

By Doug Black

Aurora’s Troubles Move Frontier into Pole Exascale Position

October 1, 2020

Intel’s 7nm node delay has raised questions about the status of the Aurora supercomputer that was scheduled to be stood up at Argonne National Laboratory next year. Aurora was in the running to be the United States’ first exascale supercomputer although it was on a contemporaneous timeline with... Read more…

By Tiffany Trader

European Commission Declares €8 Billion Investment in Supercomputing

September 18, 2020

Just under two years ago, the European Commission formalized the EuroHPC Joint Undertaking (JU): a concerted HPC effort (comprising 32 participating states at c Read more…

By Oliver Peckham

Leading Solution Providers

Contributors

Is the Nvidia A100 GPU Performance Worth a Hardware Upgrade?

October 16, 2020

Over the last decade, accelerators have seen an increasing rate of adoption in high-performance computing (HPC) platforms, and in the June 2020 Top500 list, eig Read more…

By Hartwig Anzt, Ahmad Abdelfattah and Jack Dongarra

Nvidia and EuroHPC Team for Four Supercomputers, Including Massive ‘Leonardo’ System

October 15, 2020

The EuroHPC Joint Undertaking (JU) serves as Europe’s concerted supercomputing play, currently comprising 32 member states and billions of euros in funding. I Read more…

By Oliver Peckham

Google Cloud Debuts 16-GPU Ampere A100 Instances

July 7, 2020

On the heels of the Nvidia’s Ampere A100 GPU launch in May, Google Cloud is announcing alpha availability of the A100 “Accelerator Optimized” VM A2 instance family on Google Compute Engine. The instances are powered by the HGX A100 16-GPU platform, which combines two HGX A100 8-GPU baseboards using... Read more…

By Tiffany Trader

Microsoft Azure Adds A100 GPU Instances for ‘Supercomputer-Class AI’ in the Cloud

August 19, 2020

Microsoft Azure continues to infuse its cloud platform with HPC- and AI-directed technologies. Today the cloud services purveyor announced a new virtual machine Read more…

By Tiffany Trader

Oracle Cloud Infrastructure Powers Fugaku’s Storage, Scores IO500 Win

August 28, 2020

In June, RIKEN shook the supercomputing world with its Arm-based, Fujitsu-built juggernaut: Fugaku. The system, which weighs in at 415.5 Linpack petaflops, topp Read more…

By Oliver Peckham

DOD Orders Two AI-Focused Supercomputers from Liqid

August 24, 2020

The U.S. Department of Defense is making a big investment in data analytics and AI computing with the procurement of two HPC systems that will provide the High Read more…

By Tiffany Trader

Oracle Cloud Deepens HPC Embrace with Launch of A100 Instances, Plans for Arm, More 

September 22, 2020

Oracle Cloud Infrastructure (OCI) continued its steady ramp-up of HPC capabilities today with a flurry of announcements. Topping the list is general availabilit Read more…

By John Russell

Joliot-Curie Supercomputer Used to Build First Full, High-Fidelity Aircraft Engine Simulation

July 14, 2020

When industrial designers plan the design of a new element of a vehicle’s propulsion or exterior, they typically use fluid dynamics to optimize airflow and in Read more…

By Oliver Peckham

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This