Recent content by JRStern

They need a slogan? How about: The chip for your brain is Intel Computation has its privileges The gigahertz go in before the name goes on We compute harder It gigahertz so good

>risk production When do they start reward production?

I thought they were just messing up GaAs. Really. SMH

So, if you fill it with data and put it in the closet and take it out in a year, is the data still there?

>The EX400U certainly isn't cheap at around $189 for the 2TB model Dude, last time I replaced this workstation I paid that for 256gb, or was it 128gb? Whatever. Let me tell you about 14-inch Winchesters, why I had to carry a 14-high disk pack up an icy hill, do you know what those things...

Good news, especially if true. And it makes a lot of sense, with the huge capital costs. But then why would the company itself have previously cited much higher numbers?

All this for Sonic the Hedgehog?

Well sure, yeah, but we've only been doing this for about twenty years now since SANs started carrying gigabytes of buffer memory to old HDDs and even ten years ago when they started using high speed backbones in server rooms this could be incredibly high speed, I was shocked by it (in a good...

>Seagate also had a proof-of-concept demo that included NVMe HDDs. Wot?

Gelsinger's big problem was that LLM's had not been invented yet in Larrabee days. Bad timing. But Intel did get very lucky in cloud build-out, 2016-2020+. But that's the same time they fell into the quicksand on the fab side. Without the cloud build-out, unexpected though it was, Intel would...

I want moar.

God bless the patent office.

This is not thought through. Yeah, I know that doesn't surprise a lot of people. I already said recently, I'd have chosen non-cash ways to implement the Chips Act too, but just tariffs won't do it. Nations on the other side of the tariff wall will implement their own and trade with each other...

At the time Microsoft thought FPGAs were going to be the hot ticket for AI, which certainly propelled Intel into not only buying Altera but overpaying for it with a sloppy, poorly timed deal. Six months later nobody was doing AI with FPGAs. CXL was begun by Intel to support FPGA's - and...

There have been neuromorphic projects for fifty years, probably longer. It's probably some flavor of in-memory computing. Has to be mapped to existing problems and programs, like LLM. Even then it might turn out to be done better with software on more generic hardware, where generic includes...