Live data from Hacker News

Intel Core Ultra Series 3 Debut as First Built on Intel 18A

newsroom.intel.com

131–140 of 187 posts

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#131

Earlier quoted context omitted.

And as far as I can see, it's a total waste of silicon. Anything running in it will anyway be so underpowered that it doesn't matter. It'd be better to dedicate the transistors to the GPU. The latest Ryzen mobile CPU line didn't improve performance compared to its predecessor (the integrated GPU is actually worse), and I think the NPU is to blame.

If you ask NVIDIA, inference should always run on the GPU. If you ask anybody else designing chips for consumer devices, they say there's a benefit to having a low-power NPU that's separate from the GPU.

Okay, yeah, and those manufacturers’ opinions are both obvious reflections of market position independent of the merits, what do people who actually run inference say?

(Also, the NPUs usually aren't any more separate from the GPU than tensor cores are separate from an Nvidia GPU, they are integrated with the CPU and iGPU.)

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#132
post #26
post #23

The list of claims and what was tested in the comparison can be found here https://edc.intel.com/content/www/us/en/products/performance...

I was surprised by that defiant tone there in an official page. But it's missing actual numbers, which makes it all pretty strange.

The numbers and the benchmarking conditions are in the PDF linked on that page:

https://download.intel.com/newsroom/2026/CES2026/Intel-CES20...

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#133
post #85

Earlier quoted context omitted.

Apple had the same problem before they launched the M1. Unless your workloads are extremely bursty the i9 MacBook is almost guaranteed to be slower than the base i7.

Even thier ultra efficent silicon didn't fully solve this; a 16" M4 Pro often outperforms a 14" M4 Max stuck throttling.

I can’t comment on that.

But at least you always know an A7 is better than an A6 or an A4. The M4 is better than the M3 and M1.

The suffixes make it more complicated, but at least within a suffix group the rule still holds.

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#134

Earlier quoted context omitted.

Remove background from an image. Summarize some text. OCR to select text or click links in a screenshot. Relighting and centering you in your webcam. Semantic search for images and files. A lot of that is in the first party Mac and Windows apps.

Selecting text in a photo is a game changer. I love it.

Wasn’t built in OCR an amazing feature?

We probably could have done it years earlier. But when it showed up… wow.

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#135
post #52

“With Series 3, we are laser focused on improving power efficiency, adding more CPU performance, a bigger GPU in a class of its own, more AI compute and app compatibility you can count on with x86.” – Jim Johnson, Senior Vice President and General Manager, Client Computing Group, Intel A laser focus on five things is either business nonsense or optics nonsense. Who was this written for?

It's all the things Apple's processors are excellent at and AMD is not far behind Apple. So unless Intel delivers on all those things they can't hope to gain the market share they have lost.

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#136
post #96

Earlier quoted context omitted.

> cost cutting on Lunar Lake It's... the launch vehicle for a new process. Literally the opposite of "cost cutting", they went through the trouble of tooling up a whole fab over multiple years to do this. Will 18A beat TSMC and save the company? We don't know. But they put down a huge bet that it would, and this is the hand that got dealt. It's important, not something to be dismissed.

Lunar Lake integrated DRAM on the package, which was faster and more power efficient, this reverts that. They also replaced part of the chip from being sourced from TSMC to from themselves. And if their foundry is competitive, they should be shaking other foundry customers down the way TSMC is. If they have actually mostly caught up to TSMC, props, but also, I wish they hadn't given up on EUV for so long. Instead the…

> Lunar Lake integrated DRAM on the package, which was faster and more power efficient, this reverts that.

On package memory is slightly more power efficient but it isnt any faster, it still uses industry standard LPDDR. And Panther Lake supports faster LPDDR than Lunar Lake, so its definitely not a regression.

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#137

Earlier quoted context omitted.

You were saying that Apple is very consistent. I’m pointing out they aren’t particularly. > It never got weird. After 10.9.5 came 10.10.0. Version numbers are not decimals. They turned one of the numbers into a letter then started numbering again. There was Mac OS 9, then Mac OS X. That got incremented up past 10. You say they don’t mess around with model numbers. Yes they do, with software and hardware. I like using…

> They turned one of the numbers into a letter then started numbering again. They did not. It has been MacOS X 10.0 through macOS 10.15. In never was X.1 or anything like that.

Right. MacOS X was the marketing name. But it was pronounced 10, just a stylization with Roman numerals.

The version number the OS reported always said 10.whatever. Exactly as you said.

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#138
post #52

“With Series 3, we are laser focused on improving power efficiency, adding more CPU performance, a bigger GPU in a class of its own, more AI compute and app compatibility you can count on with x86.” – Jim Johnson, Senior Vice President and General Manager, Client Computing Group, Intel A laser focus on five things is either business nonsense or optics nonsense. Who was this written for?

Somewhat ironically if they were laser focused using infared lasers, wouldn't that imply the company was not very specific at all? Infared is something like 700 nm, which would be huge in terms of transistors

State of the art lithography currently uses extreme ultraviolet, which is 13.5nm. So maybe they are EUV laser-focused, just with many mirrors pointing it in 5 different directions?

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#139

Earlier quoted context omitted.

> I assume 9 is better than 7 right? Right? Oh, the number of times I’ve heard someone assume their five- or ten-year-old machine must be powerful because it’s an i7… no, the i3-14100 (released two years ago) is uniformly significantly superior to the i7-9700 (released five years before that), and only falls behind the i9-9900 in multithreaded performance. Within the same product family and generation, I expect 9 is…

>>Within the same product family and generation, I expect 9 is better than 7 Ah the good old Dell laptop engineering, where the i9 is better on paper, but in reality it throttles within 5 seconds of starting any significant load and the cpu nerfs itself below even i5 performance. Classic Dell move.

I had an X1 Carbon like this, only it'd crash for no apparent reason. The internet consensus that Lenovo wouldn't own up to was that the i7 CPUs were overpowered for the cooling, so your best bet is either underthrottling them or getting an i5.

Re: Intel Core Ultra Series 3 Debut as First Built on Intel 18A

#140

Earlier quoted context omitted.

If you ask NVIDIA, inference should always run on the GPU. If you ask anybody else designing chips for consumer devices, they say there's a benefit to having a low-power NPU that's separate from the GPU.

Okay, yeah, and those manufacturers’ opinions are both obvious reflections of market position independent of the merits, what do people who actually run inference say? (Also, the NPUs usually aren't any more separate from the GPU than tensor cores are separate from an Nvidia GPU, they are integrated with the CPU and iGPU.)

Depends on how big the NPU is and how much power/memory the inference model needs.
Post reply on HN