Question Raptor Lake - Official Thread

Page 21 - 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
4,191
1,975
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

dullard

Elite Member
May 21, 2001
24,998
3,325
126
Would there be any noticeable performance difference between a 12700K and a 13900K if all e cores were disabled on both chips? I really doubt there will be any
You confused me a bit with your quote from someone else attributed to me.

To answer your question, I think it comes down to the final turbo speeds of the 13900K. If it is along the lines of the first few rumors, then no there wouldn't be much of a noticeable difference. You might be able to measure a difference, but until it reaches at least 10% faster, it is hard to actually notice. If the 13900K does reach near 6.0 GHz, it will be noticeable but still small. I just don't think the plan that @AlltheWay LeeWhy has is a great idea. The main benefit of the 13900K will be for all the E cores in multithreading tasks, and then to just disable them seems counterproductive.
 

eek2121

Platinum Member
Aug 2, 2005
2,904
3,906
136
Time to update your knowledge of Windows coding especially starting with Visual Studio 2022. Javascript isn't even multithreaded! Heck even if you don't want to touch Windows, Linux started the optimizations in version 5.18.
I think you misunderstood my point so I will restate it. Not all languages expose Windows API specific features to the developer. Most provide a cross platform API.

Javascript isn't multithreaded period. Web workers are kernel threads (processes) + message passing. Typically multithreading refers to user-space threads, since otherwise every language with the ability to run a bash/shell command is trivially multithreaded.

Not even touching this. You should brush up on your JS.
 

Henry swagger

Senior member
Feb 9, 2022
356
235
86
Oh, and you have some kind of proof of this?



Says the one citing rumors as facts. And now your opinion as fact. Others will see right through that if they haven't already. Only a chump (or shill) would believe they are going to hit 6GHz or better yet 5.8GHz multicore when they are doubling the E core total and need to stay at the same TDP on the same node.
Watch your words mr talk big.. who are you calling a chump ?
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
Psst: most OEMs don't throw away the stock cooler, replace it with a high-end cooler, put it in a motherboard that continuously supplies 250W+, and pair it with a power supply that can handle it. Example: The typical Dell Alder Lake computer comes with either a 180 W or a 300 W power supply total. There is no way the 180 W power supply is providing 241 W to the CPU long term. https://www.dell.com/en-us/member/s...desktop/spd/inspiron-3910-desktop/nd3910fjwhs
View attachment 63653

Instead most OEMs are running much closer to the 65W/125W limits that the stock coolers supply. I do realize the K chips don't come with stock coolers, but your run of the mill OEM computer still doesn't dedicate that much power to the CPU.
In other words, they won't come anywhere near in performance to what is benchmarked. At 160 watt, they do OK, but any lower than that, and they lose a lot of performance.
 
  • Like
Reactions: Drazick

dullard

Elite Member
May 21, 2001
24,998
3,325
126
In other words, they won't come anywhere near in performance to what is benchmarked. At 160 watt, they do OK, but any lower than that, and they lose a lot of performance.
Depends on what you consider "anywhere near in performance". TechPowerUp measured an average of 14.1% slower at 125 W than at 241 W for CPU bound tests. https://www.techpowerup.com/review/...er-lake-tested-at-various-power-limits/2.html On the gaming tests their conclusion was: "For gaming, things are completely different. There's virtually no performance difference between the 241 W and 125 W power limit settings, no matter the render resolution."
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
Depends on what you consider "anywhere near in performance". TechPowerUp measured an average of 14.1% slower at 125 W than at 241 W for CPU bound tests. https://www.techpowerup.com/review/...er-lake-tested-at-various-power-limits/2.html On the gaming tests their conclusion was: "For gaming, things are completely different. There's virtually no performance difference between the 241 W and 125 W power limit settings, no matter the render resolution."
But gaming is not the end-all-be-all of computer use. And 14.1% is about what adl was given the crown for, and why the 5800x3d is 15% faster than the 5800. It seems when everyone wants to prove ADL is faster, first they look at single core. Then they look at gaming. And when multi-core sustained use uses too much power, they quote down watted power benchmarks. Its all about excuses, and I for one am sick of it. The P-core is great, but it creates power problems, as well as the problems of e-core. I personally thing ADL and now Raptor lake are flawed in basic design. But lets see when Raptor lake actually comes out and compare it to Zen4.
 
  • Like
Reactions: Drazick

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
But gaming is not the end-all-be-all of computer use. And 14.1% is about what adl was given the crown for, and why the 5800x3d is 15% faster than the 5800. It seems when everyone wants to prove ADL is faster, first they look at single core. Then they look at gaming. And when multi-core sustained use uses too much power, they quote down watted power benchmarks. Its all about excuses, and I for one am sick of it. The P-core is great, but it creates power problems, as well as the problems of e-core. I personally thing ADL and now Raptor lake are flawed in basic design. But lets see when Raptor lake actually comes out and compare it to Zen4.
So you think the only metric that matters is embarrassingly parallel workstation tasks at an arbitrarily lower TDP? And yet the 5800X3D loses in those workloads quite badly, while shining in gaming, and people don't call it a bad product. So why the double standard?
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
So you think the only metric that matters is embarrassingly parallel workstation tasks at an arbitrarily lower TDP? And yet the 5800X3D loses in those workloads quite badly, while shining in gaming, and people don't call it a bad product. So why the double standard?
I did not say that. There are multiples areas of performance, single-thread, multi-thread, gaming and perf/watt. They all matter. My post was in response to "in gaming, power reduction only costs 14.1%". What are the loses in the other areas is what I was saying. LEARN TO READ.
 

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
I did not say that. There are multiples areas of performance, single-thread, multi-thread, gaming and perf/watt. They all matter. My post was in response to "in gaming, power reduction only costs 14.1%". What are the loses in the other areas is what I was saying. LEARN TO READ.
In gaming, the power reduction had no impact on performance. The 14.1% hit was a worst case all-core load, the only workload you apparently think matters.

This was all covered in the original comment, much less the article itself. Ironic that you say I need to learn to read...
 

nicalandia

Diamond Member
Jan 10, 2019
3,330
5,281
136
In gaming, the power reduction had no impact on performance. The 14.1% hit was a worst case all-core load, the only workload you apparently think matters..
If you are going to lower the voltage on a 12900K(to 125 Watts) to keep the same gaming performance while getting your behind handed to you in MT workloads. You might as well get a 12700K.

1656347405695.png
 
Last edited:
  • Like
Reactions: Markfw

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
If you are going to lower the voltage on a 12900K(to 125 Watts) to keep the same gaming performance while getting your behind handed to you in MT workloads. You might as well get a 12700K.
Well yes, if you're buying a chip purely for gaming, the 12900k has never made sense at all. But there's a huge gap between just gaming and embarrassingly parallel compute. Most real-world workstation tasks have at least some single-thread-bound component. Also, people buying a high end enthusiast overclocking chip clearly don't typically care about the power consumption. The motherboard manufacturers figured that out ages ago.
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
Well yes, if you're buying a chip purely for gaming, the 12900k has never made sense at all. But there's a huge gap between just gaming and embarrassingly parallel compute. Most real-world workstation tasks have at least some single-thread-bound component. Also, people buying a high end enthusiast overclocking chip clearly don't typically care about the power consumption. The motherboard manufacturers figured that out ages ago.
The entire DC forum cares a low about power consumption, and they all have high end chips. The 2 most common there ? The 5950x and EPYC. Why ? They are the most power efficient. I don't remember ANYBODY there running a 12900k/ks.Your statement about "high end enthusiast overclocking chip clearly don't typically care about the power consumption" clearly has a fault. The same applies to other areas.
 
  • Like
Reactions: Drazick

dullard

Elite Member
May 21, 2001
24,998
3,325
126
I did not say that. There are multiples areas of performance, single-thread, multi-thread, gaming and perf/watt. They all matter. My post was in response to "in gaming, power reduction only costs 14.1%". What are the loses in the other areas is what I was saying. LEARN TO READ.
Could you please help me clarify my post? Your summary of my post was the exact opposite of what I typed. The average of non-gaming tasks was 14.1% lower performance at 125 W power vs 241 W power.
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
Could you please help me clarify my post? Your summary of my post was the exact opposite of what I typed. The average of non-gaming tasks was 14.1% lower performance at 125 W power vs 241 W power.
Yes, I missed that, sorry. But still, alder lake needs to use less power, and when it does, its does lose out to the competition quite often.
 
  • Like
Reactions: Drazick

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
The entire DC forum cares a low about power consumption, and they all have high end chips. The 2 most common there ? The 5950x and EPYC. Why ? They are the most power efficient. I don't remember ANYBODY there running a 12900k/ks.Your statement about "high end enthusiast overclocking chip clearly don't typically care about the power consumption" clearly has a fault. The same applies to other areas.
Then why are you getting an overclocking-oriented chip just to power limit it? You can do that with the 12900 just as well. And as usual, you've gone right back to claiming that the only thing that matters is power-limited, embarrassingly parallel workloads.

And frankly, given how blatantly you've fabricated stats about Alder Lake vs Ryzen for compute, why should anyone take your word on what people run or care about? Do you have a source for your claims?

Oh, and I guess you're just going to ignore completely misreading the benchmarks about Alder Lake power vs performance. You know, the things you claim to care so much about...
 

nicalandia

Diamond Member
Jan 10, 2019
3,330
5,281
136
Yes, I missed that, sorry. But still, alder lake needs to use less power, and when it does, its does lose out to the competition quite often.
Alder Lake it's on its way out. Raptor Lake has a daunting task ahead of them, Redwood cove with it's smaller(7nm) process might take advantage of the process node and be more efficient(might not be required to be pushed to the limit to compete)
 
  • Like
Reactions: Hotrod2go

nicalandia

Diamond Member
Jan 10, 2019
3,330
5,281
136
Then why are you getting an overclocking-oriented chip just to power limit it?
Overclocking is DEAD..

Today's Chips(Specially Intel) are pushed to their limits. Which brings us back to the subject. You are getting a Pushed to the Limits CPU for the performance, but it's way power inefficient so what you do about it? Nothing, since lowering the voltages/power will be like a downgrade(from 12900K to 12700K)
 
Last edited:
  • Like
Reactions: Thunder 57

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
Then why are you getting an overclocking-oriented chip just to power limit it? You can do that with the 12900 just as well. And as usual, you've gone right back to claiming that the only thing that matters is power-limited, embarrassingly parallel workloads.

And frankly, given how blatantly you've fabricated stats about Alder Lake vs Ryzen for compute, why should anyone take your word on what people run or care about? Do you have a source for your claims?

Oh, and I guess you're just going to ignore completely misreading the benchmarks about Alder Lake power vs performance. You know, the things you claim to care so much about...
What overclocking chip ? And no I am not saying parallel workloads are all that matter. I was commenting on your statement that "high end enthusiast overclocking chip clearly don't typically care about the power consumption". This is the second time I have had to remind you of that. The 5950x is not an overclocking chip, and EPYC certainly is not.

As to Alder lake is going out and Raptor lake coming in, I am really hoping that it is better.
 
  • Like
Reactions: Drazick

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
Overclocking is DEAD..
Ok, if that's your belief, then save your money and don't buy a K-series chip. Sounds like a win-win, no?

You are getting a Pushed to the Limits CPU for the performance, but it's way power inefficient so what you do about it? Nothing, since lowering the voltages/power will be a like a downgrade(from 12900K to 12700K)
Ok? Clearly people are generally quite happy to do nothing about it, since they don't perceive it as a problem. And at the same power limit, a 12900k would outperform a 12700k, so I'm not sure what your argument is there either.
 

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
What overclocking chip ?
The 12900k/ks you explicitly referenced in your post. If all you want to do is power limit the chip, then a 12900 serves just as well. You're basically complaining that if people go out of their way to get a product with capabilities they don't want, then it's a bad purchase. No duh.

And care to apologize for not reading the article and insulting people who did?
 

nicalandia

Diamond Member
Jan 10, 2019
3,330
5,281
136
At the same power limit, a 12900k would outperform a 12700k, so I'm not sure what your argument is there either.

A stock 12700K(PL1: 125 Watts and PL2: 190 Watts) has better performance than a 125/125 watts restricted CPU and also a smaller performance lead on 125/240 12900K with lower CPU power consumption.
 

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
A stock 12700K(PL1: 125 Watts and PL2: 190 Watts) has better performance than a 125/125 watts restricted CPU and also a smaller performance lead on 125/240 12900K with lower CPU power consumption.
Yes, an extra 65W trumps another 4 GRT cores. But that's a silly comparison. Either you insist on power limiting both to the same (in which case the 12900k will win), or leaving them uncapped (12900k will also win).
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
A stock 12700K(PL1: 125 Watts and PL2: 190 Watts) has better performance than a 125/125 watts restricted CPU and also a smaller performance lead on 125/240 12900K with lower CPU power consumption.
In addition, due the the characteristics of the e-cores and the loss of avx512, I get better performance with no e-cores at all for what I do on my 12700F.
 
  • Like
Reactions: Drazick