Nvidia Patents a Way for GPU Thread Groups to Share Memory Directly
Nvidia has filed a patent for a low-level API that lets separate groups of GPU workers read each other's memory without going…
From processors and AI accelerators to the packaging and cooling that hold them together, this is where the silicon race lives. Every chip filing, decoded without the jargon.
Nvidia has filed a patent for a low-level API that lets separate groups of GPU workers read each other's memory without going…
Every 3D scene is made of millions of tiny triangles, and the order in which your GPU processes them matters enormously. Nvidia…
Ray tracing looks incredible, but it forces your GPU to constantly rebuild complex data structures from scratch. Nvidia's new patent describes a…
Nvidia is patenting a way to carve a single chip into walled-off sections with different safety rules, so a software crash in…
Intel is patenting a way to send data between chips using beams of light instead of electrical signals, and the trick is…
Sony is filing patents on a way to build image sensors from separate stacked layers, each handling a different part of the…
Samsung has patented a memory chip stack with a specially shaped cap layer designed to keep the whole structure from cracking or…
Ray tracing looks incredible but it's brutally expensive on memory bandwidth. Apple's new patent describes a way to store 3D geometry in…
Camera chips are normally fixed at the factory, doing the same image cleanup steps every time. Nvidia has patented a way to…
Samsung has filed a patent describing a two-stage filtering process that lets a UWB chip figure out exactly where a signal's useful…
Samsung thinks it can speed up one of the most repeated math operations in every modern wireless chip by replacing a complex…
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.