Cerebras Systems has unveiled its Andromeda AI supercomputer. With 13.5 million cores, it can calculate at the rate of 1 exaflop — roughly one quintillion (1 followed by 18 zeroes) operations — per second using a 16-bit floating point format. Andromeda’s brain is built of 16 linked Cerebras CS-2 systems, AI computers that use giant Wafer-Scale Engine 2 chips. Each chip has hundreds of thousands of cores, but is more compact and powerful than servers that use standard CPUs, according to Cerebras, which is making Andromeda available for commercial and academic research. Continue reading Cerebras Supercomputer Calculates at 1 Exaflop per Second

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

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

The immersive experiences Meta Platforms has planned for the metaverse will require processing power beyond what’s possible today, tipping into the quintillions of operations-per-second. But the company has a fix for that. Meta announced Monday that it has been working on a new artificial intelligence supercomputer called the AI Research SuperCluster, that will be the fastest in the world when fully built this summer. Drawing on resources from partners like Nvidia, Penguin Computing and Pure Storage, the effort took two years and involved several hundred people who collaborated remotely through the COVID-19 pandemic for much of the project. Continue reading Meta AI Research Supercomputer Aims to Be World’s Fastest

Australian researchers have had a breakthrough in quantum computing, proving that nearly error-free processing is possible, which could lead to the possibility of silicon-based quantum machines whose manufacture could be compatible with today’s semiconductor manufacturing technology. “Our operations were 99 percent error-free,” said University of New South Wales (UNSW Sydney) professor Andrea Morello, who led the work with partners in the U.S., Japan, Egypt, and at the University of Technology Sydney (UTS) and the University of Melbourne. “When the errors are so rare, it becomes possible to detect them and correct them when they occur.” Continue reading Quantum Computing in Silicon Achieves 99 Percent Accuracy

Quantum startup QuEra Computing has emerged from stealth mode with a splashy announcement of $17 million in funding and completion of a 256-qubit device the company says “will be soon accessible to customers.” Launched in 2019 by scientists from Harvard and MIT, the Boston-based firm claims to have already generated $11 million in revenue from its scalable machines in a white-hot quantum space that includes tech giants including Amazon, IBM and Google jockeying for position. QuEra’s approach leverages what the company calls “nature’s perfect qubits,” based on 256-qubit atoms. Continue reading Startup QuEra Is Making Major Strides in Quantum Computing

As the race to commercialize quantum computing heats up, IBM has unveiled its Eagle 127-qubit processor, positioning it as the first quantum chip that can’t be simulated by a classic supercomputer. Speaking at the IBM Quantum Summit, executives said the Eagle is the first IBM quantum processor to contain more than 100 qubits. It follows the 65-qubit Hummingbird processor debuted by IBM in 2020 and the 27-qubit Falcon of 2019. Eagle is the latest step on the scaling path to the “quantum advantage,” the point at which quantum systems can outperform their classical counterparts in a meaningful way. Continue reading Eagle Chip: 127-Qubit Milestone in IBM’s Quantum Roadmap

Nvidia and the National Energy Research Scientific Computing Center (NERSC) debuted Perlmutter, an AI supercomputer that features 6,144 Nvidia A100 Tensor Core GPUs. Named for astrophysicist Saul Perlmutter, the supercomputer has been dubbed by Nvidia as “the fastest on the planet,” at processing with the 16-bit and 32-bit mixed-precision math used in AI applications, said the company’s global HPC and AI product marketing lead Dion Harris. Its first job will be to create the largest-ever 3D map of the visible universe. Continue reading Nvidia and NERSC Unveil a New Supercomputer for AI Tasks

China’s top quantum research group said its Jiuzhang quantum computer produced results in minutes that would take 2+ billion years by the world’s No. 3 powerful supercomputer. That exceeds Google’s prototype quantum computer which, last year, came up with a result in minutes that it estimated would take a supercomputer 10,000 years. The two quantum computers work differently: China’s University of Science and Technology’s computer manipulates photons, whereas Google’s builds quantum circuits via super-cold superconducting metal. Continue reading Chinese Researchers Create Quantum Computing Benchmark

The world’s fastest supercomputers are ranked twice a year, and Innovative Computing Laboratory director Jack Dongarra, one academic behind the rankings, noted that the Top500 list of the world’s fastest high-performance computing (HPC) systems is showing “flattening performance” due to the slowdown of Moore’s Law. In the most recent ranking, Japan’s Fugaku ARM-based supercomputer set a record of 442 petaflops. In 2021, however, the first exascale — 1,000 petaflops — supercomputers are expected to appear, including one from the Oak Ridge National Laboratory in Tennessee. Continue reading ARM-Based Supercomputer Earns Top Spot in Global Ranking

Cerebras Systems and its partner, the Department of Energy’s National Energy Technology Laboratory (NETL), revealed that its CS-1 system, featuring a single massive chip that features an innovative design, is 10,000+ times faster than a graphics processing unit (GPU). The CS-1, built around Cerebas’ Wafer-Scale Engine (WSE) and its 400,000 AI cores, was first announced in November 2019. The partnership between the Energy Department and Cerebras includes deployments with the Argonne National Laboratory and Lawrence Livermore National Laboratory. Continue reading The Cerebras CS-1 Chip Is 10,000 Times Faster Than a GPU

While the United States and China compete to create the world’s most powerful computers, a Japanese supercomputer, dubbed Fugaku, took first place in Top500’s speed ranking. At the Kobe-based RIKEN Center for Computational Science, Fugaku achieved 2.8 times more calculations per second than the previous speediest system, IBM’s at Oak Ridge National Laboratory in Tennessee. Fugaku, which pushed another IBM computer at Lawrence Livermore National Laboratory in California to third place, is based on ARM chip technology. Continue reading ARM-Based Japanese Supercomputer Now No. 1 on Top500

Although millions of Americans are at home, the Senate did not include money for broadband infrastructure in the $3 trillion stimulus package under consideration. However, the current bill does include some funding to deploy mobile hot spots around the country. Proponents of accessible broadband will try to add that to any upcoming stimulus package. Meanwhile, the U.S. government, along with several Big Tech companies, is providing global access to 16 supercomputers to help researchers discover vaccines to combat the coronavirus. Continue reading Federal Government Considers Plans For Broadband Access

Intel will debut Pohoiki Springs, an experimental research system for neuromorphic computing that simulates the way human brains work and computes more quickly and with less energy. It will first be made available, via the cloud, to the Intel Neuromorphic Research Community, which includes about a dozen companies (such as Accenture and Airbus), academic researchers and government labs. Intel and Cornell University jointly published a paper on the Loihi chip’s ability to learn and recognize 10 hazardous materials from smell. Continue reading Intel to Unveil Experimental Neuromorphic Computing System

In three months, Honeywell International will roll out an “early stage” quantum computer for “commercial experiments,” with JPMorgan Chase as its first public user. Honeywell Quantum Solutions president Tony Uttley stated it will speed up calculations and develop new materials and trading strategies for financial services firms, but it could also be used to power machine learning calculations by aerospace, oil and gas companies. IBM, Google and Microsoft are also at work on quantum computing solutions. Continue reading Honeywell Prepares Launch of Powerful Quantum Computer