Intel to Restructure Chip Design and Manufacturing Divisions

Intel is fine-tuning its corporate reporting as it gears up a foundry operations that will see the longtime manufacturer and designer of its own chips extend services to third-parties. The idea is to create greater separation between its concept and creation divisions. The change comes as Intel deals with a rapidly shifting global market, where demand for chips has increased in sectors like automotive and AI data centers while the PC business that has been the company’s bedrock suffered a major decline in global shipments of nearly 20 percent in Q3. Continue reading Intel to Restructure Chip Design and Manufacturing Divisions

New GPUs Showcased at Intel’s Innovation Developer Event

Intel announced the consumer GPU brand Arc last year, which the company now says will begin delivering in Q4. The Arc A770 Limited Edition desktop gaming card will be available October 12, starting at $329, “the sweet spot of desktop graphics,” according to CEO Pat Gelsinger, who said the GPU “delivers 65 percent better peak performance versus competition on ray tracing.” Intel says other new GPU models, including the Arc Pro A30M for mobile unveiled last month at SIGGRAPH, will also come to market by the end of the year. The new GPUs feature built-in ray tracing hardware, machine learning capabilities and industry-first AV1 hardware encoding acceleration. Continue reading New GPUs Showcased at Intel’s Innovation Developer Event

Nvidia, Intel and ARM Publish New FP8 AI Interchange Format

Nvidia, Intel and ARM have published a draft specification for a common AI interchange format aimed at faster and more efficient system development. The proposed “8-bit floating point” standard, known as FP8, will potentially accelerate both training and operating the systems by reducing memory usage and optimizing interconnect bandwidth. The lower precision number format is a key factor in driving efficiency. Transformer networks, in particular, benefit from an 8-bit floating point precision, and having a common interchange format should facilitate interoperability advances for both hardware and software platforms. Continue reading Nvidia, Intel and ARM Publish New FP8 AI Interchange Format

Microsoft Rolls Out Ampere-Powered ARM-Based Azure VMs

Microsoft’s new Azure Virtual Machines, featuring Ampere Altra ARM–based processors, will be generally available on September 1, debuting in 10 Azure regions and multiple availability zones worldwide. Microsoft says the VMs can also be included in Kubernetes clusters managed using Azure Kubernetes Service (AKS). Engineered to efficiently run scale-out, cloud-native workloads, Microsoft says that since the technology began previewing earlier this year hundreds of customers have tested the ARM-powered VMs “for web and application servers, open-source databases, microservices, Java and .NET applications, gaming, media servers and more.” Continue reading Microsoft Rolls Out Ampere-Powered ARM-Based Azure VMs

Magic Leap Will Target the B2B Market with New AR Headset

The business-oriented Magic Leap 2 AR headsets will debut in three models on September 30 in global territories including the U.S., Canada, France, Germany, Italy, Spain, the UK and Saudi Arabia. The Magic Leap 2 Base starts at $3,299. There is a midrange Magic Leap 2 Developer Pro, working up to the Magic Leap 2 Enterprise, which sells for $4,999. Smaller and lighter than its 2018 predecessor, Magic Leap 2 comes with a hip-worn AMD processor, offers a wide field of view, and has a dimmer that can be applied to background visuals to make virtual objects pop. In the U.S., Magic Leap 2 will be available through IT solutions reseller Insight.  Continue reading Magic Leap Will Target the B2B Market with New AR Headset

Replenished GPU Inventory Results in Return to MSRP Pricing

The graphics processor unit drought may be over as retailers report inventory is plentiful with prices returning to pre-scarcity norms. Nvidia GeForce RTX 3090 Ti’s that were marked up to nearly double the MSRP on sites like eBay are now available for approximately their intended $2,300 price. “GPU prices continue to drop on a monthly basis,” reports Tom’s Hardware, attributing the favorable conditions in part to the cryptocurrency crash, which has “resulted in more mining firms shutting down,” selling off hardware and not competing for new units. The easing of COVID-19 supply chain bottlenecks is another mitigating factor. Continue reading Replenished GPU Inventory Results in Return to MSRP Pricing

The U.S. Is Now Home to the World’s Fastest Supercomputer

In a big win for the United States, the Department of Energy’s Frontier supercomputer at the Oak Ridge National Laboratory (ORNL) in Tennessee was ranked No. 1 in the Top500 worldwide performance contest and the first to top the quintillion operations-per-second (exascale) benchmark in a LINPACK test. The Department of Energy has said it will spend a total of $1.8 billion to build three machines with exascale performance. The Frontier, or OLCF-5, supercomputer (which features a theoretical peak performance of 2 exaflops) was built by Hewlett Packard Enterprise and is powered by AMD chips. Continue reading The U.S. Is Now Home to the World’s Fastest Supercomputer

Nvidia Touts New H100 GPU and Grace CPU Superchip for AI

Nvidia has begun previewing its latest H100 Tensor Core GPU, promising “an order-of-magnitude performance leap for large-scale AI and HPC” over previous iterations, according to the company. Nvidia founder and CEO Jensen Huang announced the Hopper earlier this year, and IT professionals’ website ServeTheHome recently had a chance to see a H100 SXM5 module demonstrated. Consuming up to 700W in an effort to deliver 60 FP64 Tensor teraflops, the module — which features 80 billion transistors and has 8448/16896 FP64/FP32 cores in addition to 538 Tensor cores — is described as “monstrous” in the best way. Continue reading Nvidia Touts New H100 GPU and Grace CPU Superchip for AI

TSMC Posts Record Q1 Profits Despite Continuing Shortages

TSMC (Taiwan Semiconductor Manufacturing Company) is reporting first quarter 2022 revenue between $17.6 billion and $18.2 billion, a 35.5 percent increase year-over-year. Compared to Q4 2021, the first quarter results represent a 12.1 percent revenue uptick and 22 percent growth in net income. This, despite ongoing fallout from supply chain shortages that company CEO C.C. Wei says he expects will continue triggering production constraints. Russia’s invasion of Ukraine and the COVID-19 lockdown in Shanghai, where the company has a plant, were cited as the most significant stressors to the company’s semiconductor output. Continue reading TSMC Posts Record Q1 Profits Despite Continuing Shortages

Magic Leap 2 Lighter with Better Field of View Than Original

Announced in 2019, the Magic Leap 2 augmented reality headsets are now being demoed for reviewers, with a commercial launch set for later this year. In 2020 the company shelved consumer plans to focus on enterprise clients in areas like healthcare, manufacturing and defense, where it will compete against Microsoft’s HoloLens. Offering a significantly improved field of view compared to the original 2018 Magic Leap, the new Magic Leap 2 is also lighter and more powerful than its predecessor. The new goggles are wired to a disc-shaped processor that must be carried or clipped on for mobility. Continue reading Magic Leap 2 Lighter with Better Field of View Than Original

Apple’s M1 Ultra Is Power and Performance ‘Game Changer’

Apple says its new M1 Ultra chip will give Nvidia’s RTX 3090 — currently the fastest processor on the market — a run for its money. Introduced last week as the power inside the new Mac Studio desktop, the M1 Ultra has a unique architecture, dubbed UltraFusion, which connects two M1 Max chips for an SoC with 114 billion transistors, the most ever in a personal computer chip, according to the company. “M1 Ultra is another game-changer for Apple silicon that once again will shock the PC industry,” said Apple senior vice president of hardware technologies Johny Srouji. Continue reading Apple’s M1 Ultra Is Power and Performance ‘Game Changer’

Intel Clocks 70 Percent Faster Speeds with Alder Lake Chips

Intel is looking to deliver a big performance boost with its new ultraportable Alder Lake U and P-series chips, unveiled last week. The Core i7-1280P, Intel’s fastest 28-watt P-series CPU, is said to deliver up to 70 percent faster multithreaded performance compared to last year’s i7-1195G7. Intel says it even offers better multithread benchmarks than the Core i9-11980HK, one of the company’s fastest 2021 processors. This, despite the fact that it uses only about half as much power. According to some tests, the Intel i7-1280P also bested AMD’s 2021 Ryzen 7 5800U. Continue reading Intel Clocks 70 Percent Faster Speeds with Alder Lake Chips

CES: Intel on AV Overdrive, Touts Fastest Mobile Game Chip

Intel laid claim to the ‘world’s best mobile gaming platform’ with its 12th generation Alder Lake H-series GPUs at CES 2022, then shifted to overdrive to focus on autonomous driving, introducing its Mobileye EyeQ Ultra, AV-on-chip supercomputer offered as a full-stack AV driving solution. Intel in December announced plans to spin off Mobileye in an IPO sometime this year and used its CES press conference stage to demonstrate it is prepared to deliver, announcing a partnership with Zeekr to create all-electric AVs for the Chinese market, due to roll off the assembly line in 2024. Continue reading CES: Intel on AV Overdrive, Touts Fastest Mobile Game Chip

Apple Is Hiring New Team to Develop Wireless Chips in SoCal

Apple plans to set up a new office in Irvine, California to develop wireless chips. Job listings indicate the company is looking for individuals experienced with modem chips and other semiconductors. The new components could eventually replace those provided by third-party suppliers such as Broadcom and Skyworks Solutions. In a move that is part of a larger initiative by Apple to develop more tech in-house, engineers will reportedly work on RF integrated circuits, wireless radios, wireless SoC, and semiconductors for connecting to Bluetooth and Wi-Fi. Continue reading Apple Is Hiring New Team to Develop Wireless Chips in SoCal

AWS re:Invent Showcases Sizzling Chips, New Tools for Cars

The 10th Amazon Web Services re:Invent cloud computing conference showcased faster chips, better developer tools, smarter AI and two new automotive initiatives. AWS CEO Adam Selipsky’s keynote led with the company’s next-generation processor, the Arm-based Graviton3, and culminated with a peek under the hood at AWS Automotive and AWS IoT FleetWise. Collecting data and spotting trends are enterprise priorities, and AWS is doing its part to advance artificial intelligence and machine learning across that matrix in the cloud. “We know your data is on a journey — and all the stops on this journey matter,” Selipsky said. Continue reading AWS re:Invent Showcases Sizzling Chips, New Tools for Cars