9 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum Clark Johnson has had a 7-decade career as an engineer, inventor, and entrepreneur that continues to this day. Chuck Weinstock Clark Johnson says he has wanted to be a scientist ever since he was 3. At age 8, he got bored with a telegraph-building kit he received as a gift and repurposed it into a telephone. By age 12, he set
Walking into Jun Ye’slab at the University of Colorado Boulder is a bit like walking into an electronic jungle. There are wires strung across the ceiling that hang down to the floor. Right in the middle of the room are four hefty steel tables with metal panels above them extending all the way to the ceiling. Slide one of the panels to the side and you’ll see a dense mesh of vacuum chambers, mirrors, magnetic
3 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum BrainChip’s Akida Pico could be used with their AI model architecture in devices like smartwatches. Neuromorphic computing draws inspiration from the brain, and Steven Brightfield, chief marketing officer for Sydney-based startup BrainChip, says that makes it perfect for use in battery-powered devices doing AI processing. “The reason for that is evolution,” Brightfield says. “Our brain had a power budget.” Similarly, the
3 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum Flow Computing In an era of fast-evolving AI accelerators, general purpose CPUs don’t get a lot of love. “If you look at the CPU generation by generation, you see incremental improvements,” says Timo Valtonen, CEO and co-founder of Finland-based Flow Computing. Valtonen’s goal is to put CPUs back in their rightful, ‘central’ role. In order to do that, he and his
3 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum Diraq’s quantum computing chip is made of qubits that are similar to transistors and can be manufactured using CMOS technology. A team in Australia has recently demonstrated a key advance in metal-oxide-semiconductor-based (or MOS-based) quantum computers. They showed that their two-qubit gates—logical operations that involve more than one quantum bit, or qubit—perform without errors 99 percent of the time. This number
6 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum Nvidia’s Blackwell chip was submitted to MLPerf for the first time, showing the best per GPU performance in the LLM Q&A benchmark. While the dominance of Nvidia GPUs for AI training remains undisputed, we may be seeing early signs that, for AI inference, the competition is gaining on the tech giant, particularly in terms of power efficiency. The sheer performance of Nvidia’s
5 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum J. Wang/NIST and Shutterstock Today, almost all data on the Internet, including bank transactions, medical records, and secure chats, is protected with an encryption scheme called RSA (named after its creators Rivest, Shamir, and Adleman). This scheme is based on a simple fact—it is virtually impossible to calculate the prime factors of a large number in a reasonable amount of time,
4 min read Dina Genkina is the computing and hardware editor at IEEE Spectrum Cerebras’ second-generation Wafer-Scale Engine (WSE-2) is a massive chip tailored for AI applications. Cayce Clifford/The New York Times/Redux As large supercomputers keep getting larger,Sunnyvale, California-based Cerebras has been taking a different approach. Instead of connecting more and more GPUs together, the company has been squeezing as many processors as it can onto one giant wafer. The main advantage is in the
3 min read Germany’s JEDI supercomputer is the world’s most efficient supercomputer, operating at a trim 72.7 gigaflops per watt. Ralf-Uwe Limbach/Forschungszentrum Jülich Over just the past couple of years, supercomputing has accelerated into the exascale era—with the world’s most massive machines capable of performing over a billion billion operations per second. But unless big efficiency improvements can intervene along its exponential growth curve, computing is also anticipated to require increasingly impractical and unsustainable amounts
3 min read Forty-eight SpiNNaker2 chips, each of which contains an ARM microprocessor and various accelerators, work together on this high-performance board to enable efficient neuromorphic and traditional AI processing. SpiNNCloud Systems Today Dresden, Germany–based startup SpiNNcloud Systems announced that its hybrid supercomputing platform, the SpiNNcloud Platform, is available for sale. The machine combines traditional AI accelerators with neuromorphic computing capabilities, using system-design strategies that draw inspiration from the human brain. Systems for purchase vary