IBM Research

In the early 80s, a few curious?IBM?researchers were testing a new excimer laser to see if they could use it for circuit board etching. The laser technology was so accurate, the team hypothesized it could be used on organic material, without any collateral damage. To test the idea, the researchers used their laser on the turkey bones from their #Thanksgiving leftovers. Their intuition was correct: there was no damage beyond where the laser was shot. A few years later, their findings inspired a group of #ophthalmologists to use these lasers in corrective eye surgery, one method of which eventually became #LASIK. Don’t be so quick to throw away your leftovers — you never know what they might inspire! https://lnkd.in/gPNKHBuq ---- #IBM #Research #Hardware #Healthcare #Innovation

Supercharging Training using float8 and FSDP2 ? Read our latest blog to find out how we achieve up to 50% throughput speedup while achieving loss & evaluation benchmark parity in training: https://hubs.la/Q02Zmfvb0

In this week's edition, we explore accelerating discoveries with new AI tools, powerful chips, and turkey. We introduce a new tool designed to speed up the discovery of new materials, discuss adapters intended to manage AI outputs, take a closer look at a Hardware Bring-Up Lab, and reveal how Thanksgiving turkey contributed to the development of LASIK. ? Read more for the latest updates and subscribe here:

So your team of semiconductor researchers designed and built a brand new chip that has the potential to be far more efficient for AI computations, but how do they know if it works as intended? That’s where IBM Research Hardware Engineer JohnDavid Lancaster comes in. ?? In this behind-the-scenes look at his lab in Yorktown Heights, Lancaster demonstrates how he and his team test and validate the “?????????? ????????????” — a “wattage-to-inference” ratio — of IBM’s latest AIU (Artificial Intelligence Unit) chips, which were specifically designed and optimized for #AI applications. “?????? ???? ?????? ?????? ?????????????? ?????? ?????????? ?????? ?????? ?????? ???????? ???? ?????? ?????????? ?????? ?????????? ?????? ?????? ???????? ???????????????????? ?????? ?????? ??????????????.” Lancaster shows how mapping the voltage of the entire card can ultimately help inform sustainable (low-power) #encoder and #decoder model design. ?? - Read more about our AIU here: https://lnkd.in/gRge8QHh ?? - Subscribe and follow for more lab tours: https://lnkd.in/gjytYHxa ---- #IBM #Research #chips

On this day in 1966, IBM researchers announced a major breakthrough in chipmaking, drastically shrinking down the size of memory cores using ancient candle-making techniques. These new experimental cores were just slightly wider than a human hair and were nearly impossible to produce using the traditional pressing technique used to form memory cores at that time. ?????? ???????????????? Fabrication began with a nylon "wick" dipped into a bath of varnish and magnetic powder, the magnetic taper was then passed through a drying oven and the process was repeated until the desired thickness was achieved. In a similar process, a layer of non-magnetic material was added for added strength.? The magnetic taper was subsequently cut into sections and frozen in a block of wax. At this stage, the nylon "wicks" were removed, leaving behind hollow tubes made of magnetic ferrite material. The wax block was then sliced into sections, where thousands of cores could be cut.?Finally, these slices were fired in an oven, which vaporized the wax and sintered the magnetic materials. This led to the development of smaller, packed memory cores, which in turn increased computer memory capacity as well as device processing speeds. ?????? ???????????? Pictured are miniature experimental memory cores created using the techniques of ancient candlemakers, followed by images of standard IBM magnetic-core memory planes. Stay tuned for more highlights from IBM Research's history. ---- #IBM #Research #Compute #IBMHistory

PatCID, a new, open-access database from IBM Research, uses document understanding models to let users search patents for molecular structure images, helping businesses stay on top of what is state of the art, and opening new possibilities for accelerated materials discovery. ?? - Read more about the work, and our collaboration on PatCID with JSR Corporation here: https://lnkd.in/gx396U9w ?? - Try it yourself on GitHub here: https://lnkd.in/ghmKyecc ----- #IBM #Research #AI #DeepSearch #MolecularDiscovery

"We need to look at things that can be turned into a product in the near term, as well as things that could be revolutionary a decade from now.” This week at the IBM Research 2024 AI Hardware Forum at Yorktown Heights, New York,?Mukesh Khare outlined the different research workstreams of the AIU family of accelerators. Unlike a GPU or CPU, AIUs (artificial intelligence units) are built from the ground up to specifically handle AI workloads. These family members are in different stages of maturity, and represent the various ways IBM is thinking about the future of chip design and efficient AI computation:?https://lnkd.in/gRge8QHh ?--- #IBM #Research #chips #AI

The University of Alabama in Huntsville is installing a new computer cluster system containing?IBM?AIU chips for running advanced AI models developed by IBM and NASA: https://lnkd.in/gcHYY2si ?? - IBM Spyre is the first AIU (artificial intelligence unit) production accelerator born out of?IBM Research, and is part of a long-term strategy of developing novel architectures and solutions for the emerging space of generative #AI. ?? - Researchers at #UAH will primarily use this new cluster for deploying the Prithvi?geospatial?and weather and #climate models from IBM and?NASA - National Aeronautics and Space Administration, testing the operational workloads and running throughput-focused workloads. ?? - The cluster will run on Red Hat OpenShift AI, demonstrating the value of a full-stack solution that leverages heterogeneous accelerators. --- #IBM #Research #NASA #semiconductors

We’re exploring where quantum can make the largest impact in energy with E.ON. https://ibm.co/4fobSGB E.ON serves over 47 million customers across 17 countries everyday, powering infrastructure through electricity and gas—and that is no easy task. In years past, E.ON could reasonably predict costs and consumption to ensure these customers would always have the lights on. Now, with changes in technology, sudden weather, and the differing ways we use electricity each day, small variables to supply and demand of energy can drastically impact predictability of costs, resource allocation, and energy delivery. It is a complex problem E.ON faces, but that’s exactly what quantum computing aims to solve—problems with many variables that might take millennia to solve on classical supercomputers might have much more straightforward solutions using quantum computing algorithms. E.ON is exploring how quantum could help them plan for coming fluctuations and predict patterns years into the future, which ultimately lower costs for their customers and keep the lights on for all. Head over to the link above for the full case study and watch the film on https://lnkd.in/exCbDYQ6 for more.

In this week's newsletter, we are exploring the path to more powerful — and efficient — AI systems. We introduce the AIU family, explore IBM Spyre AIU at The University of Alabama in Huntsville, discuss a new toolkit for document conversion, and highlight key moments from the first-ever IBM Quantum Developer Conference. Read more for the latest updates and subscribe here: