Question Raptor Lake - Official Thread

Page 134 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Hulk

Diamond Member
Oct 9, 1999
4,525
2,518
136
Since we already have the first Raptor Lake leak I'm thinking it should have it's own thread.
What do we know so far?
From Anandtech's Intel Process Roadmap articles from July:

Built on Intel 7 with upgraded FinFET
10-15% PPW (performance-per-watt)
Last non-tiled consumer CPU as Meteor Lake will be tiled

I'm guessing this will be a minor update to ADL with just a few microarchitecture changes to the cores. The larger change will be the new process refinement allowing 8+16 at the top of the stack.

Will it work with current z690 motherboards? If yes then that could be a major selling point for people to move to ADL rather than wait.
 
  • Like
Reactions: vstar

Thunder 57

Platinum Member
Aug 19, 2007
2,992
4,569
136
Yup, the guy who buys things with the intention of returning one. You did the same crap when Zen 2 came out. This is why we can't have nice things.

People buy and do all sorts of stupid and dangerous things.

Companies should be more responsible and not sell the product at a ridiculous and dangerous setting just to be able to top the charts.

View attachment 69942

I quickly cut the irrelevant low power part of the table off. Even at 250W it performs as high as 7950X. I will run my CPU capped at 180W, that is what my air cooler can handle. I am now playing with 13600K and 13700K, not sure which one I will keep.

I meant to quote that.
 

Hulk

Diamond Member
Oct 9, 1999
4,525
2,518
136
Now that we've had over a year to test and discuss Intel's hybrid approach with both Alder and Raptor Lake I think we can come to some reasonable conclusions as to why they went down this path. Here's my version of this "story."

First, we have to assume they had a pretty good idea of their performance targets Zen 2, 3, 4.. at the time these parts were on the drawing board and they also had a pretty good idea of the transistor density they could achieve. It would have been obvious to them that they were not going to be able to compete on a core-for-core basis given the node deficit without creating huge parts and impacting the financial bottom like significantly.

With a die the size of the current 8+16 Raptor Lake die they could fit about 13.1 P cores, which would score about 35,000 in Cinebench R23, MT. Good but not enough to beat Zen 4. Furthermore using all E cores they could achieve a score of over 47,000, which would win the MT Cinebench war but of course lose in so many applications requiring ST performance.

This is where I think the Intel designers got it right. They figured that most applications currently that are not highly parallel don't use more than 8 or so cores at once so they went with the hybrid approach to mitigate their node deficiency. Whether or not you like it, given their fabrication limitations it is a good solution and has kept them competitive with AMD, who have equally good big core architecture and better process.

There is no doubt that in order to be competitive they not only had to employ the hybrid approach but also do the best they could from an efficiency point of view because AMD (TSMC) had them there as well. The final piece of the puzzle is because Intel has their own fabs and a significant war chest they could also confront AMD on price. When you put all of this together you see how we've come to the point where we have to very good brand choices at a variety of price points.

The data in the attachment were recorded with max power PL1 and PL2 set at 175W, which I think is reasonable, especially on air cooling. You can see that the E's do quite a bit for efficiency in terms of both area for the compute they generate as well as compute for the power they consume.
 

Attachments

  • Untitled-1.jpg
    Untitled-1.jpg
    508.2 KB · Views: 21

dullard

Elite Member
May 21, 2001
25,510
4,004
126
With a die the size of the current 8+16 Raptor Lake die they could fit about 13.1 P cores, which would score about 35,000 in Cinebench R23, MT. Good but not enough to beat Zen 4. Furthermore using all E cores they could achieve a score of over 47,000, which would win the MT Cinebench war but of course lose in so many applications requiring ST performance.
I agree, especially with the quoted part. I might have posted this before, but I too keep Excel calculations with various scenarios going. See the image below. This particular one is just a simple take from Chips And Cheese's analysis of efficiency (https://i0.wp.com/chipsandcheese.com/wp-content/uploads/2022/01/image-151.png?ssl=1). I took a major assumption that isn't quite correct, that 4 E cores and 1 P core were the same area. But, it is pretty close to accurate.
1667396271342.png

In all power cases, given roughly equal area, you want as many E cores as possible. I hear a ton of people wanting an all P-core CPU and you can see that it would absolutely suck on Intel's node for anything multithreaded. This is pretty much the same as your conclusion if you look at your 164W data, the ones with the most E cores win in every single grouping.

But, there is a big tradeoff that you mention: an all E core CPU sucks at single threaded performance. Which, despite the lack of attention it gets in reviews, ST is what most people use in their day-to-day tasks. So, a hybrid approach given Intel's limitations is the best move that they have. Once we get to 32+ E cores it will be all very clear. Much more clear than the 8+4 ugly stepchild that we have in some Intel chips now.
 
  • Like
Reactions: Carfax83

nicalandia

Diamond Member
Jan 10, 2019
3,331
5,282
136
Do you guys know any results for DDR4 OC on the Z790 platform? I'm trying to gauge what to expect from 4 sticks of B-die.
Not worth the Upgrade to Raptor Lake if you are using DDR4, If I had to chose from Tuned Alder Lake with DDR5 vs Raptor Lake with DDR4... Alder Lakes hands down all the time. Invest in DDR5 and GPU.
 
  • Like
Reactions: Kaluan

Grimnir

Member
Jun 8, 2020
27
10
51
Not worth the Upgrade to Raptor Lake if you are using DDR4, If I had to chose from Tuned Alder Lake with DDR5 vs Raptor Lake with DDR4... Alder Lakes hands down all the time. Invest in DDR5 and GPU.
The performance difference between DDR4 and DDR5 isn't that big. Considering I'll be upgrading from Coffee Lake, I reckon it'll be well worth it.

Either way, I would like to see some results overclocking DDR4 on Z390.
 
Jul 27, 2020
20,040
13,738
146
Either way, I would like to see some results overclocking DDR4 on Z390.

#188 · 12 h ago
Picked up Pro z790-A WIFI (for the SPDIF on rear I/O). DDR4 is as expected for an 13700kf that apparently did not win the silicon lottery (won't go over 4000 gear1 at reasonable vccSA.) A couple days tuning and I think I'm at my daily setting for the RAM at 2x16 1.58v 4000 gear1 15-15-15-30-270-2T and getting 66.2 GB/s read and 45.5ns in AIDA.

Not really surprising, but no real reason to go z790 for DDR4.

I chose the z790 since z690 with BIOS flashback weren't really any cheaper, and why not go z790?

Still stuck at 4000 MT/s. Intel doesn't care about DDR4.
 
  • Like
Reactions: Tlh97 and Carfax83

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
`13900K needs DDR5-7200 CL34 to beat 5800X3D in this game.

That review is totally GPU bottlenecked. As I and many others have said before, you can't take 13th gen or Zen 4 game performance reviews with anything less than an RTX 4090 seriously. They are just too bottlenecked.

Just look how bunched up those scores are.
 

Hitman928

Diamond Member
Apr 15, 2012
6,186
10,693
136
That review is totally GPU bottlenecked. As I and many others have said before, you can't take 13th gen or Zen 4 game performance reviews with anything less than an RTX 4090 seriously. They are just too bottlenecked.

Just look how bunched up those scores are.

It’s 1440p, not sure why he didn’t post the 1080p results which are more interesting.
 

ondma

Diamond Member
Mar 18, 2018
3,005
1,528
136
I agree, especially with the quoted part. I might have posted this before, but I too keep Excel calculations with various scenarios going. See the image below. This particular one is just a simple take from Chips And Cheese's analysis of efficiency (https://i0.wp.com/chipsandcheese.com/wp-content/uploads/2022/01/image-151.png?ssl=1). I took a major assumption that isn't quite correct, that 4 E cores and 1 P core were the same area. But, it is pretty close to accurate.
View attachment 70252

In all power cases, given roughly equal area, you want as many E cores as possible. I hear a ton of people wanting an all P-core CPU and you can see that it would absolutely suck on Intel's node for anything multithreaded. This is pretty much the same as your conclusion if you look at your 164W data, the ones with the most E cores win in every single grouping.

But, there is a big tradeoff that you mention: an all E core CPU sucks at single threaded performance. Which, despite the lack of attention it gets in reviews, ST is what most people use in their day-to-day tasks. So, a hybrid approach given Intel's limitations is the best move that they have. Once we get to 32+ E cores it will be all very clear. Much more clear than the 8+4 ugly stepchild that we have in some Intel chips now.
Wont they eventually need more than 8 P cores though? Perhaps for gaming, as gpus get stronger and stronger? I understand the hybrid approach, and it seems to have worked so far to compensate for the node and core size disadvantages, but 32 E cores? I would hope that eventually with a tiled approach and better process, they can increase P cores as well. Just a wild idea, but if MTL has a 6P 8E tile, how about putting 2 of those together for 12P/16E?
 

LightningZ71

Golden Member
Mar 10, 2017
1,798
2,156
136
Wont they eventually need more than 8 P cores though? Perhaps for gaming, as gpus get stronger and stronger? I understand the hybrid approach, and it seems to have worked so far to compensate for the node and core size disadvantages, but 32 E cores? I would hope that eventually with a tiled approach and better process, they can increase P cores as well. Just a wild idea, but if MTL has a 6P 8E tile, how about putting 2 of those together for 12P/16E?
In my time of following game development and benchmarks, it is highly typical that games becomes performance constrained on roughly four threads or less. This is why, in most reviews, you see very little clock normalized performance difference between 6 and 8 core processors with HT. Typically, when you find a notable difference, it's often because the 8 core part on Intel has more L3 cache. This is also why you can almost always get PLAYABLE frame rates on 4/8 processors with a decent video card in most games. Those quad core processors typically come with a notable frequency deficit against the 6 and 8 core parts and half the L3 cache, so there's a lot going on to hurt their performance, but having 4 real cores is usually enough to keep things. This is also why you find that the dual core celerons and pentiums have been taking a real beating in the benchmarks and are usually just stutterfests to use in real life. They often don't have markedly less L3 than the quad cores, but having to swap multiple main threads it a back breaker.

All of that to say that a 6P/24E processor with other modest improvements, more L3, and higher clocks would likely have even better game performance than the 13900K does, and is why I don't doubt that meteor lake will perform quite well.
 
  • Like
Reactions: Carfax83

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
It’s still with just officially supported memory speed and timings for both platforms, so these results are not that interesting either.

I agree that higher speed memory would have been better, but these results are still valid and computerbase's test methodology is always top notch.

It just goes to show that when you add an RTX 4090 into the equation, the 13900K takes off like a rocket; especially in games that utilize the CPU heavily. AMD is definitely going to need the Zen 4 3D parts to take the gaming crown from Intel.