Intel Patents a Trick That Cuts Shared Memory Wait Times in Half
When multiple chips share the same pool of memory, the slowest part is often just fetching the data in the first place.…
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.
When multiple chips share the same pool of memory, the slowest part is often just fetching the data in the first place.…
Intel is patenting a GPU design that keeps a smaller, power-sipping engine on standby for AI tasks — so the full chip…
Every modern processor constantly guesses which code path to run next — and when it guesses wrong, it pays a steep penalty.…
Every time your computer fetches data, its processor has to look up where that data lives before it can retrieve it. Intel's…
AMD is patenting a way for its GPUs to quietly spin up or down their own graphics cores depending on what you're…
Running a big AI model across multiple GPUs can spike power draw so hard it trips a circuit breaker — or forces…
AMD is patenting a dedicated slice of silicon — a purpose-built processing core — whose entire job is to handle the math…
Matrix multiplication is the heartbeat of every AI model — and Nvidia is patenting a way for chips to know exactly how…
Matrix multiplication is the heartbeat of every AI model — and Nvidia is patenting a way to give software explicit control over…
Nvidia is patenting a technique that watches how pieces of code get linked together at runtime — and uses that knowledge to…
Random noise in rendered images isn't all bad — but the wrong kind of noise creates ugly, flickering artifacts. Nvidia's new patent…
Nvidia is patenting a way to let its processors start crunching matrix math before all the input data has even finished loading…
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.