Recent content by dkanter

Ladies and Gentlemen, I have a new article up at RWT! Previously, Apple’s iPhones and iPads used PowerVR GPUs from Imagination Technologies for graphics. Based on our analysis, Apple has created a custom GPU that powers the A8, A9, and 10 processors, shipping in the iPhone 6 and later models...

http://www.realworldtech.com/tile-based-rasterization-nvidia-gpus/ Starting with the Maxwell GM20x architecture, Nvidia high-performance GPUs have borrowed techniques from low-power mobile graphics architectures. Specifically, Maxwell and Pascal use tile-based immediate-mode rasterizers that...

A few folks asked about the second part of my article, discussing what I believe will be in Knights Landing...thought I'd share the link: http://www.realworldtech.com/knights-landing-details/ David

In-order issue isn't really a problem with a retry buffer and a single AGU. David

http://www.realworldtech.com/knights-landing-cpu-speculation/ Thought you guys might enjoy reading my take on what is inside of Knights Landing. David

Silvermont is OOOE is for integer and memory, the FPU is in-order. David

OOOE helps you get better bandwidth, by increasing the amount of MLP available. Look at how many misses you can sustain in Jaguar, that's probably what you want to know (as well as L2 bandwidth). David

I agree that it doesn't really make sense to have a compute vs. workstation card for AMD. If you look at Nvidia, the ASIC is the same. It's not like you want to change the # of cores, the memory controllers or anything. You want the highest performance, and both should have ECC options. The...

Actually, I'd say the largest intangible asset that AMD has is the ability to effectively design and validate x86 CPUs. There is only one other company in existence with that ability. And no, ARM will never buy AMD. ARM makes IP. AMD makes chips. ARM doesn't wish to compete with its...

It's not clear how much of the IP is Apple's. They are using an ImgTec GPU, but I don't know if future CPUs are custom designs or licensed cores (in the future). Also, TSMC only has issues with 28nm. Most of Apple's SoCs are still 40nm. I'm not convinced that Samsung is really ahead of TSMC...

What did you use to create that image? DK

GK110 was always planned for AFTER GK104 AFAIK. However, it sounds like there was a one quarter delay or so. The good news is that Nvidia learned their lesson regarding taping out huge chips on new process technology! DK

How are you sure that those people were cut? They might have chosen to leave on their own. DK

That's funny. I wrote an article a while back why AMD won't do this: http://www.realworldtech.com/amd-mobile-strategy/ AMD might play around with ARM, but giving up x86 is utter madness. DK

I bet they will launch a professional product soon. AFDS will be a logical venue. DK