• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Discussion Intel Nova Lake in H2-2026: Discussion Threads

Page 70 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
In some ways kinda, yeah.
For more memory channels next "-WS" platform(2028 tentatively) looks interesting with "consumer" compute tiles.
That is indeed interesting but why the actual F it has a NPU with more TOPS than PTL
 
Almost nobody needs 52 C with limited membw. Intel is in for a rude awakening if it thinks that halo part will sell buckets.

On the flip side, 4 P + 4 LPE cores is probably not enough in today's market.

The question is, what clocks will Zen 6 hit? If we're talking +10% fmax +8% IPC then overall +20% ST is reasonable. Zen 5 and ARL are basically the same, so Zen 6 should have a 10% or so lead over NVL in ST (assuming NVL fmax is the same as ARL).
Totally agree, and it's obvious. So much chat about SKUs that will be 5% of sales, at best. Limited sales of 24c AMD and 52c Intel. Hardly anyone needs that, if you actually do need throughout you but big boy platforms. The real chat here should be about the single tile Intel SKUs and AMD single ccd chips as that's the upgrade that almost everyone will see.
 
The inflection between the 32MB L3 8 core CCD zen 5 and the 48MB 12 core CCD zen 6 should be impressive. I don't think the X3D parts will show quite the improvement as I'm beginning to think that they're bottlenecking elsewhere in many cases.
 
We are like 6-9 Months away and we had PTL not reaching 5 Ghz to it being 5.1 so maybe 200-300Mhz more is possible have to see

Intel had to move heaven and Earth just to get 5.1 GHz. And 5.1 GHz was NOT the goal or even close to it, Intel probably wanted at least 5.3 GHz and couldn't get there. Let's not give them too much credit.

Totally agree, and it's obvious. So much chat about SKUs that will be 5% of sales, at best. Limited sales of 24c AMD and 52c Intel. Hardly anyone needs that, if you actually do need throughout you but big boy platforms. The real chat here should be about the single tile Intel SKUs and AMD single ccd chips as that's the upgrade that almost everyone will see.

Enthusiast forums are always obsessed with top-end parts. Look at all the people around here using 9800X3Ds and 9950X3Ds etc. It's a disproportionate number compared to the average even in the DiY space.
 
Intel had to move heaven and Earth just to get 5.1 GHz. And 5.1 GHz was NOT the goal or even close to it, Intel probably wanted at least 5.3 GHz and couldn't get there. Let's not give them too much credit.
All Intel first node had this issue 22nm/14nm/10nm(it was something else but anyway)/Intel 4
 
Intel had to move heaven and Earth just to get 5.1 GHz. And 5.1 GHz was NOT the goal or even close to it, Intel probably wanted at least 5.3 GHz and couldn't get there. Let's not give them too much credit.



Enthusiast forums are always obsessed with top-end parts. Look at all the people around here using 9800X3Ds and 9950X3Ds etc. It's a disproportionate number compared to the average even in the DiY space.
Oh I get that, it's in my post history. And that's totally fine and all well and good. It's when people talk about what will be relevant or important in the market and forget that they are in a niche that I'm commenting on. There are a lot of 9800X3D in the diy space though. Very good part
 
Back
Top