// WIRED US/UK — INTELLIGENZA ARTIFICIALE
A Stealth Startup Thinks It Just Hacked the Memory Shortage
An ambitious chip startup that has spent more than seven years quietly trying to redesign the architecture for computer memory has just come out of stealth mode and believes its new approach can help ease the global memory-chip shortage—provided it can produce its technology at scale.
Kepler Computing, a San Jose, California–based startup founded in 2018 by a team of physicists and computer scientists, says it has developed a new architecture for high-bandwidth memory (HBM) that directly addresses some of the chip supply bottlenecks that are constraining the computing market.
While chipmakers typically rely on expensive extreme ultraviolet lithography (EUV) to shrink the transistors on a chip, thereby packing more technology into the same amount of space, Kepler claims that its “3D stacking” approach and a proprietary new material allow it to increase density without relying on EUV at all—and it can work with existing semiconductor fabrication plants.
Kepler says it has made similar gains for the high-speed cache memory typically used in CPUs, GPUs, and XPUs. This so-called SRAM sits within the core of a chip die in order to cut down on data transfer times. HBM, by contrast, uses stacks of DRAM, which is a separate memory component of chips.
The company has raised $468 million in funding over the past few years from big-name backers. This includes GlobalFoundries, Intel Capital, AMD Ventures, the British investment fund Baillie Gifford, and Bill Gates, through his private Gates Frontier fund. In July, the US Department of Commerce committed to give Kepler up to $245 million to “develop in the US a new class of high-performance AI memory technology, enabled by innovative 3D and ferroelectric technologies.”
For now, much of Kepler’s testing is happening in Singapore, which is where GlobalFoundries—a manufacturing partner and investor of $50 million—has a facility. Over the past two years Kepler has been building out what it refers to as “mini fabs,” where it produces its memory chips in conjunction with Global Foundries’ 28-nanometer chips. (It has also been running tests in GlobalFoundries’ facilities in Burlington, Vermont.)
Kepler and its investors say the startup’s new approach to building memory chips couldn’t come at a better time. The global memory chip shortage has reaffirmed at least two realities about the market: Building new fabs is hugely expensive and painstaking, and the demands around certain kinds of memory tend to be cyclical. In a data-center-driven, AI-crazed world, HBM has become the memory du jour.
A semiconductor process chamber used by Kepler in its dedicated fab for developing next-generation memory devices.
Some of the world’s leading memory makers, including SK Hynix and Micron, have been racing to build multibillion-dollar fabs in order to meet demand, wagering that even by the time those facilities are operational, the industry will still be looking for high-bandwidth memory.
“For a long time our thinking was that we’d work on SRAM first and then follow up with DRAM and HBM,” says Debo Olaosebikan, a Kepler Computing cofounder and its chief executive officer. “But with the launch of ChatGPT [in 2022] and the explosion of demand for an HBM alternative, we started working on our HBM road map. Now we’re making SRAM and HBM in parallel.”