Meta’s next generation AI silicon is a 5nm chip designed to power the models that provide recommendations to those who use its social network platforms. The new MTIA inference accelerator is part of a “broader full-stack development program for custom, domain-specific silicon that addresses our unique workloads and systems,” Meta says. The next-gen MTIA more than doubles the compute and memory bandwidth of its predecessor, the 7nm MTIA v1 chip introduced in May 2023, resulting in 3x the performance, according to Meta, which says the new silicon is already live in 16 data centers. Continue reading Meta Deploys Gen 2 MTIA AI Accelerator Chip in Data Centers

Microsoft and Quantinuum have improved the logical error rate in quantum computing by 800x, a breakthrough the partners say has the potential to usher in a new era of qubit processing. Using ion-trap hardware from Quantinuum and a qubit-virtualization system from Microsoft, the team ran more than 14,000 experiments with no errors — a huge feat in the notoriously fickle realm of qubits. The system has error diagnostics and corrections built in, identifying which errors need to be fixed and correcting them without destroying the underlying logical qubits, according to the companies. Continue reading Microsoft, Quantinuum Tout Advance in Quantum Computing

Nvidia is investing $30 billion in a new business unit focused on custom chips for high-performance computing. The company already controls about 80 percent of the advanced chip market but wants to avoid losing ground as alternatives spring up. Alphabet, AWS, Intel and AMD market high-end processors to third-parties, and Meta is expected to begin deploying its own Artemis AI chips this year. Nvidia has had discussions with Amazon, Google, Meta, Microsoft and OpenAI about helping them create bespoke chips and is also talking to automakers, cloud service providers (CSPs) and telecom companies, according to reports. Continue reading Nvidia to Launch Unit Devoted to Building Custom HPC Chips

OpenAI CEO Sam Altman’s ongoing effort to fund a new initiative to produce chips to power artificial intelligence has graduated from a billion-dollar venture to a trillion dollar undertaking that aims at nothing less than “to reshape the business of chips and AI,” per recent reports. The United Arab Emirates has joined the list of sources of potential funding for the global project, which seeks to remedy the tight supply of AI chips that Altman is said to view as an obstacle to OpenAI’s effort to develop artificial general intelligence, which he defines as “systems that are generally smarter than humans.” Continue reading Sam Altman Is Reportedly Seeking ‘Trillions’ to Fund AI Chips

Further insights into OpenAI CEO Sam Altman’s global fundraising effort for a multi-billion dollar computer chip venture now appears to be toward a goal establishing a network of semiconductor plants to manufacture AI chips, according to media reports. The plan would see the 38-year-old entering a hotly competitive yet underserved field, dominated by Nvidia and increasingly Intel, AMD and Qualcomm. Apparently, he feels the existing players aren’t set up to produce the amount of chips required to meet the goals of OpenAI and others through 2030, now that many businesses incorporate AI into workflows and consumer products. Continue reading Altman Is Seeking Billions in Global Funding for AI Chip Plants

Qualcomm’s Snapdragon XR2+ Gen 2 chip for extended reality platforms is designed to allow those who incorporate it into their gear to give Apple’s ambitious and technologically advanced Vision Pro headset a run for its money. Qualcomm says as part of the second gen Plus launch announcement that Samsung and Google have committed to using its new chip to power gen two XR experiences. Among the noteworthy XR2+ features is its single-chip architecture for 4.3K spatial computing at 90 frames per second. It supports 4.3K per eye resolution and 12 or more concurrent cameras to VR and mixed reality experiences. Continue reading CES: Qualcomm Chip Enables Faster Mixed Reality Features

Intel formally launched its new Core Ultra CPUs and related products this week at its AI Everywhere event. The company shared new solutions ranging from the data center to the cloud edge and PC. Intel’s new mobile processors are part of its Meteor Lake lineup, all of which will now bear the Ultra imprimatur instead of the “I,” promising greater power efficiency and performance. At the New York City event, Intel CEO Pat Gelsinger said “AI innovation is poised to raise the digital economy’s impact up to as much as one-third of global gross domestic product.” Continue reading Intel Unveils AI-Driven Chips to Compete with Nvidia and AMD

Ahead of next month’s CES, Lenovo has unveiled new ThinkPad and IdeaPad laptops powered by Intel’s latest Core Ultra chipsets. The Lenovo ThinkPad X1 Carbon, ThinkPad X1 2-in-1, and IdeaPad Pro 5i are Intel Evo model laptops, each leveraging the Core Ultra’s three compute engines — a CPU, a GPU and, for good measure, a neural processing unit. Lenovo says that while the three generally work together for optimal efficiency, some tasks wind up offloaded to the GPU or NPU to achieve greater performance and power management. Since both form factors use the Windows 11 OS, the new models support Microsoft’s AI Copilot features. Continue reading Lenovo Unveils Laptops for AI-Enabled Business Computing

IBM has produced two quantum computing systems to meet its 2023 roadmap, one based on a chip named Condor, which at 1,121 functioning qubits is the largest transmon-based quantum processor released to date. Transmon-based chips use a type of superconducting qubit that is more error-resistant than typical qubits, which are notoriously unstable. The second IBM system uses three Heron chips, each with 133 qubits. The more modestly scaled Heron and its successor, Flamingo, play a vital role in IBM’s quantum plan, which boasts major progress as a result of these developments. Continue reading IBM Announces Significant Advances in Quantum Computing

During yesterday’s “Scary Fast” new product event, Apple unveiled its next generation of bespoke processors — the M3, M3 Pro and M3 Pro Max — and some new computers to go with them. Built to the 3-nanometer spec that supports artificial intelligence and advanced graphics, the M3 line has 2.5x the speed of 2020’s M1 series, per Apple, which says the core processing performance is as much as 50 percent faster. New MacBook Pro laptops in 14-inch and 16-inch versions will feature M3 Pro and M3 Pro Max chips. An M3 powered 24-inch iMac series is also debuting. Continue reading Apple’s New M3 Chips Make the MacBook, iMac ‘Scary Fast’

Qualcomm has debuted a new flagship platform, the Snapdragon X Elite series. Built for artificial intelligence and capable of running generative models with over 13 billion parameters, Qualcomm claims it offers “4.5 times faster AI processing power than competitors.” Described as “the most powerful computing processor it has ever created for the PC,” Qualcomm says the chipset is also one of the most efficient, “with up to multiple days of battery life.” Leading OEMs are expected to begin shipping models with the new processors in mid-2024. Continue reading Qualcomm Unveils Snapdragon X Elite Series, Created for AI

Not content with dominating what is currently the hottest processor market in the world — chipsets for artificial intelligence — and leading among GPU suppliers, Nvidia is branching into CPUs. The 30-year-old company, whose market cap passed the $1 trillion mark in May, is said to be “quietly” developing chips to run Microsoft’s Windows OS, tapping into a global market that hovers at about 300 million PC sales per year, 70 percent of which use Windows, according to Statista. Nvidia is reportedly pursuing its plan via a licensing deal with Arm, whose tech powers 200 billion mobile processors shipped each year. Continue reading Nvidia to Pursue Mobile and PC Markets with Arm Processors

Intel has unveiled a new glass substrate technology that it says will “benefit our key players and foundry customers for decades to come.” The result of 10 years and $1 billion in development, the concept substitutes glass for the usual resin in which processors are embedded, enabling greater speed and the ability to accommodate the industry’s move toward packaging numerous “chiplets” into more powerful large processors, a configuration that has proven beneficial for the acceleration that drives artificial intelligence. This technology could potentially vault Intel ahead of competitors, some say. Continue reading Intel Has Plans to Power AI with Glass Substrates for Its Chips

Nvidia announced $7.19 billion in revenue for the first quarter ended April 30. That’s down 13 percent compared to the February through April frame in 2022, but up 19 percent from Q4, which ended January 29. Nvidia has forecast a stunning $11 billion in sales for Q2. That projected 64 percent increase puts Nvidia on track to be the first chip company with a $1 trillion valuation. CEO Jensen Huang attributes the sales spike to exploding demand for GPUs to run artificial intelligence systems. “We are significantly increasing our supply to meet surging demand for them,” Huang said of the processors. Continue reading AI Helps Steer Nvidia Toward $1 Trillion Market Capitalization

Apple has announced new 14- and 16-inch iterations of its MacBook Pro laptops, featuring Apple’s next-generation silicon. The M2 Pro and M2 Max chips turn the MacBook Pro into a portable workstation, able to tackle demanding tasks like effects rendering and color grading. Apple is promising up to 22 hours of battery life, the most ever in a Mac. The smaller model starts at $1,999, while entry level for the 16-inch is $2,499. Pre-orders began last week and delivery starts tomorrow. Apple is also releasing an updated Mac mini with M2 ($599) or M2 Pro ($1,299) chips. Continue reading Apple Debuts MacBook Pros with M2 Pro and M2 Max Chips