Intel releases tiny EMIB that assist chips to ‘talk’ with each other

Intel unveiled its Embedded Multi-die Interconnect Bridge (EMIBs) chips that speed the flow of data inside nearly 1 million laptops and field programmable gate array devices worldwide. That number will soon soar and include more products as EMIB technology enters the mainstream. 

EMIB is a cost-effective approach to in-package high density interconnect of heterogeneous chips. It delivers a complex multi-layered sliver of silicon no bigger than a grain of rice, and lets chips fling enormous quantities of data back and forth among adjoining chips at blinding speeds: several gigabytes per second.

The industry refers to this application as 2.5D package integration. Instead of using a large silicon interposer typically found in other 2.5D approaches, EMIB uses a very small bridge die, with multiple routing layers. This bridge die is embedded as part of the substrate fabrication process.

For example, Intel’s Ponte Vecchio processor, a general-purpose GPU the company unveiled this month, contains EMIB silicon.

To meet customers’ unique needs, this innovative technology allows chip architects to cobble together specialized chips faster than ever. And compared with an older, competing design called an interposer — in which chips inside a package sit atop what is essentially a single electronic baseboard, with each chip plugged into it — tiny, flexible, cost-effective EMIB silicon offers an 85 percent increase in bandwidth. That can make tech — laptop, server, 5G processor, graphics card— run faster, and next-generation EMIB could double or even triple that bandwidth.

The silicon interposer in a typical 2.5D package is a piece of silicon larger-than-all interconnecting die. In contrast, the silicon bridge is a small piece of silicon embedded only under the edges of two interconnecting die. This allows for most size die to be attached in multiple dimensions, eliminating additional physical constraints on heterogeneous die attachment within the theoretical limits.

The image shows a difficult yet desirable layout. The industry standard 2.5D solution cannot accommodate this, as the silicon interposer cannot be produced large enough to connect all the die. Yet EMIB allows for the flexibility in this die placement, allowing scaling in both dimensions.

Ambient Scientific debuts DigAn (Digital Analog) AI technology to boost performance and efficiency

Ambient Scientific released its initial Digital Analog (DigAn) AI technology with demonstration of its first DigAn AI processor chip at the Edge AI Summit. 

DigAn AI is an advanced version of Analog AI technology that provides ultra-high performance and efficiency of Analog AI with implementation and commercial advantages of Digital chips. The company also announced low-power on-device AI solution for ‘Wake on Word’ applications.

Ambient Scientific’s DigAn AI Processor is built with multiple fundamental grass root level innovations. These include Analog Matrix Compute Engine using DigAn technology, that performs blazingly fast arithmetic computations with improved power efficiency, ultra-low power embedded SRAM for critical storage, and ultra-low power on-chip interconnect technology that enables massive parallel processing.

Ambient’s DigAn AI Processor computes an entire layer of neurons in a single clock cycle using custom Analog techniques, a task that takes several hundreds or even thousands of clock cycles in traditional implementations. However, DigAn technology uses standard digital transistors to implement its analog functions.

Experts agree that Analog is a great fit for AI computing. However, prior implementations had severe limitations in accuracy and computing range – two important parameters for optimal AI solution. Ambient has eliminated these limitations. 

While prior implementations have struggled to achieve 8-bit accuracy, Ambient’s DigAn (Digital Analog) technology can achieve 32-bit accuracy. This is 16 million times more accurate in computer language.

Accenture, Airbus, GE and Hitachi now part of Intel Neuromorphic Research Community

Intel announced this week an initial list of corporate members – Accenture, Airbus, GE and Hitachi – to join the fast-growing Intel Neuromorphic Research Community (INRC). Launched in 2018, the INRC is dedicated to developing and accelerating the capabilities of neuromorphic computing across commercial and academic environments. 

The community now comprises more than 75 groups from 17 countries, which is a three-times increase since last year, spanning universities around the world, government labs, neuromorphic startup companies, and now Fortune Global 500 members.

“Our collaborators around the world have made great progress on pioneering the basic tools, algorithms and methods needed to make Intel’s neuromorphic technology useful,” said Mike Davies, director of Intel’s Neuromorphic Computing Lab. “We are now encouraging commercially oriented groups to join the community, and we are thrilled to welcome our first large corporate members to help push the technology forward. These groups bring important perspectives, ideas and challenges that can help advance the research from lab bench to real-world applications.” 

While neuromorphic computing is still in its infancy, the technology is gaining momentum, driven forward by companies large and small around the globe. If all technical challenges are solved in the next few years, analysts forecast the neuromorphic computing market could rise from $69 million in 2024 to $5 billion in 2029 – and $21.3 billion in 2034.

Intel created the INRC – bringing together researchers from academia, industry and government – to collaboratively tackle the challenges facing the field of neuromorphic computing. The addition of the first Fortune Global 500 members reflects a growing commercial interest in the technology, as well as the advancing maturity of the field for solving artificial intelligence (AI) problems that are not well suited to conventional deep learning methods. 

By mimicking the adaptive behavior of natural neural networks, neuromorphic technology promises to provide great gains in computing performance and energy efficiency for demanding applications, ranging from robotics to smart manufacturing to brain-computer interfaces.

Accenture, Airbus, GE and Hitachi are joining forces with Intel and other INRC members to create proof-of-concept applications that will bring the most value to their businesses. Intel will leverage the insights that come from this customer-centric research to inform the designs of future processors and systems. These engagements will ensure Intel remains strategically positioned at the forefront of neuromorphic technology commercialization.

Intel releases new class of AI hardware from cloud to edge to boost AI development, deployment and performance

Intel has updated its artificial intelligence (AI) offerings with new products designed to accelerate AI system development and deployment from cloud to edge. Intel demonstrated its Intel Nervana Neural Network Processors (NNP) for training (NNP-T1000) and inference (NNP-I1000) — Intel’s initial purpose-built ASICs for complex deep learning with incredible scale and efficiency for cloud and data center customers. 

Intel also revealed its next-generation Intel Movidius Vision Processing Unit (VPU) for edge media, computer vision and inference applications.

These products further strengthen Intel’s portfolio of AI solutions, which is expected to generate more than $3.5 billion in revenue in 2019. The broadest in breadth and depth in the industry, Intel’s AI portfolio helps customers enable AI model development and deployment at any scale from massive clouds to tiny edge devices, and everything in between.

Now in production and being delivered to customers, the new Intel Nervana NNPs are part of a systems-level AI approach offering a full software stack developed with open components and deep learning framework integration for maximum use.

The Intel Nervana NNP-T strikes the right balance between computing, communication and memory, allowing near-linear, energy-efficient scaling from small clusters up to the largest pod supercomputers. 

The Intel Nervana NNP-I is power- and budget-efficient and ideal for running intense, multimodal inference at real-world scale using flexible form factors. Both products were developed for the AI processing needs of AI customers like Baidu and Facebook.

“We are excited to be working with Intel to deploy faster and more efficient inference compute with the Intel Nervana Neural Network Processor for inference and to extend support for our state-of-the-art deep learning compiler, Glow, to the NNP-I,” said Misha Smelyanskiy, director, AI System Co-Design at Facebook.

Additionally, Intel’s next-generation Intel Movidius VPU, scheduled to be available in the first half of 2020, incorporates unique, highly efficient architectural advances that are expected to deliver leading performance — more than 10 times the inference performance as the previous generation — with up to six times the power efficiency of competitor processors. 

Intel also announced its new Intel DevCloud for the Edge, which along with the Intel Distribution of OpenVINO toolkit, addresses a key pain point for developers — allowing them to try, prototype and test AI solutions on a broad range of Intel processors before they buy hardware.

With most of the world running some part of its AI on Intel Xeon scalable processors, Intel continues to improve this platform with features like Intel Deep Learning Boost with Vector Neural Network Instruction (VNNI) that bring enhanced AI inference performance across the data center and edge deployments. 

While that will continue to serve as a strong AI foundation for years, the most advanced deep learning training needs for Intel customers call for performance to double every 3.5 months, and those types of breakthroughs will only happen with a portfolio of AI solutions like Intel’s. Intel is equipped to look at the full picture of computing, memory, storage, interconnect, packaging and software to maximize efficiency, programmability and ensure the critical ability to scale up distributing deep learning across thousands of nodes to, in turn, scale the knowledge revolution.

Fortinet’s FortiGate 60F sets new benchmark for security compute ratings; boosts performance for integrated security and SD-WAN

Fortinet announced the FortiGate 60F Next-Generation Firewall, its latest desktop secure SD-WAN appliance. With over 1.5 million units sold worldwide, the FortiGate 60 series is the best-selling next-generation firewall and now includes Fortinet’s purpose-built system on a chip 4 (SOC4) security processor to achieve the highest Security Compute Ratings in the industry to support customers’ WAN edge transformation.

Digital innovation and rapid cloud adoption is changing the face of today’s business and has created significant challenges for organizations, such as poor user experience due to network bandwidth constraints and increased security risks with branches connected to the internet. 

Software-defined wide area networks (SD-WANs) have emerged as the favored solution to solve these issues while also reducing the costs associated with MPLS connections. 

However, not all SD-WAN solutions have risen to the requirements of existing WAN edge. Many SD-WAN solutions on the market are incomplete and do not adequately provide the right performance, visibility, or security to ensure a secure connection and high quality of user experience.

To continue its focus on supporting enterprises’ WAN edge transformation and delivering Secure SD-WAN, Fortinet is announcing the latest next-generation firewall to include its patented SOC4 security processor - the FortiGate 60F. 

FortiGate 60F now consolidates SD-WAN, advanced routing, and advanced security capabilities into a single appliance that enables network leaders to deploy Secure SD-WAN, while reducing complexity by consolidating point products into a single offering. This allows high performance and improved user experience at an optimal total cost of ownership (TCO).
 

To help customers maintain high quality user experience for their business critical traffic (be it SaaS, multi-cloud, or unified communications), FortiGate 60F delivers ideal application steering, giving visibility to all traffic (even if encrypted) without impacting performance and ensuring all critical applications are routed to their best path.
 

FortiGate 60F leverages Security-Driven Networking principals – powered by Fortinet’s patented SOC4 security processor – to deliver the fastest deep inspection of SSL/TLS encrypted traffic (including the industry’s first support for TLS 1.3) at 750Mbps, 11 times greater than the industry average. 

The FortiGate 60F offers comprehensive threat prevention with IPS, application control, and anti-malware at 700Mbps, four times greater than the industry average, to help customers protect their network without impacting performance.

Fortinet security processors radically increase the performance, scalability, and value of Fortinet solutions while greatly improving user experience and shrinking space and power requirements. Security Compute Rating is a benchmark that compares the performance of Fortinet’s purpose-built ASIC-based next-generation firewall appliance to other NGFW and SD-WAN vendors in that same price range that utilize generic CPUs for networking and security capabilities. 

“We hear from an increasing number of customers who are struggling to achieve the required level of user experience, visibility, and security at their WAN edge to support key business applications,” said John Maddison, EVP of Products and CMO at Fortinet. “With today’s introduction of the FortiGate 60F powered by our latest security processor, Fortinet continues its commitment to security innovation, setting industry records for performance to empower network leaders to truly transform their WAN edge.”

Supermicro boosts performance using high-density, embedded servers with the Intel Xeon E-2200 processors

Super Micro Computer enhanced on Thursday performance on a range of servers, workstations, and motherboards that leverage the new Intel Xeon E-2200 processors. 

In addition to refreshed four- and six-core processors, Intel has introduced new eight-core processors where the top frequency rate can increase to 5 GHz from 4.5 GHz on specific processors with Turbo Boost, bringing up to a 16 percent gain in multi-threaded integer operations. 

The Intel Xeon E-2200 family also supports 128GB of 2666 MHz memory, double the amount from the previous processor generation.  

Supermicro's X11SC-series motherboards for Intel Xeon E-2100 will also support the new Intel Xeon E-2200 processors with eight different models in Micro-ATX, Mini-ITX, and Wide I/O (WIO) form factors for a variety of end markets. Customers can use these motherboards for entry-level servers, SMB systems, workstations, edge computing, and other appliances. 

By installing motherboards based on the Intel Xeon E-2200, customers can increase computing power without additional system reconfiguration requirements, whether they are using an optimized Supermicro chassis, or one of their own. The new Intel Xeon E-2200 processors include Intel Software Guard Extensions (Intel SGX) for enhanced application code and data security.

The Intel Xeon E-2200 processors will instantly increase the computing capability of selected Supermicro systems across several product families. Enterprise and SMB customers can get more performance out of their entry-level 5019C-series servers and 5039C-series workstations.

Data centers that implement MicroBlade and MicroCloud high-density systems, as well as users of the SuperBlade GPU Blade, will also benefit greatly from the additional cores and higher frequency in their multi-node implementations. 

As edge computing continues to grow with IoT and 5G deployments, the Intel Xeon E-2200 processors will enable the addition of more end devices and local processing to support new services with 1019C and 5019C rackmount servers.

"At Supermicro, we design our building block motherboards, chassis, and system solutions to enable a rapid transition to the latest processors," said Ivan Tay, vice president, product management, Supermicro. "With the latest Intel Xeon E-2200 processors running up to eight cores and up to 5 GHz, our customers can quickly realize performance gains in their power-efficient systems."

D-Wave Leap Quantum Cloud Site comes to Europe; delivers open source development tools, interactive demos, coding examples

Quantum computing provider D-Wave Systems announced that it will house its first Leap quantum cloud-based system outside of North America at the Forschungszentrum Jülich Supercomputing Center in Jülich, Germany. The system marks the cornerstone of the new Jülich UNified Infrastructure for Quantum computing (JUNIQ) lab designed to offer practically usable quantum computers to researchers in Germany and throughout Europe. 

Forschungszentrum Jülich and their government and academic customers will access the system via D-Wave’s Leap quantum cloud service. European business customers can also purchase access to the D-Wave Leap service and systems, including the Leap system located at Jülich.

The D‑Wave Leap Quantum Application Environment (QAE) is cloud-based, providing real-time access to a live quantum computer. In addition to access, Leap provides open-source development tools, interactive demos and coding examples, educational resources, and knowledge base articles. 

Designed for developers, researchers, and forward-thinking enterprises, Leap enables collaboration through its online community, helping Leap users write and run quantum applications to accelerate the development of real-world applications.

Long known for its multi-disciplinary approach and commitment to real-world applications, Forschungszentrum Jülich is a large-scale national research facility in the Helmholtz Association of German Research Centers. 

By conducting research on the global challenges currently facing society, their scientific and engineering research is inspired by the notion of utilization with a view to application development. Jülich will benefit from the mid-2020 release of the Advantage quantum system, accelerating their work by providing Leap quantum cloud access to a processor with the new, highly connected Pegasus topology, lower noise, and increased qubit count. 

D-Wave’s Leap cloud service will also feature expanded hybrid software and tools available in Leap’s Ocean SDK.

Business customers in Europe can access the D-Wave 2000Q through Leap and will benefit from the ongoing innovations that D-Wave continues to put into the cloud as the company gets closer to the mid-2020 release of Advantage. 

With the new European Leap site, customers will be able to choose to run their quantum and hybrid applications on any Leap system, including the Leap Advantage quantum system located at Jülich. In addition, government and academic customers will be able to choose to either directly access Leap through D-Wave or benefit from the guidance of Jülich experts as they develop quantum algorithms and applications.