Question Raptor Lake - Official Thread

Page 84 - 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

Hulk

Diamond Member
Oct 9, 1999
4,191
1,975
136
I am dying to see how that compares to a retail 7950x, but in 9 days we should know. That will save arguments.

But I must says, 42% boost for 45% more power and 343 watts total seems insane. How would you cool that ? AIO are only 250 watt I think. Custom WC only ?

It IS insane if you are considering prolonged use at that power level. But if you are only looking at bursty workload that last for a few seconds here and there, think Photoshop, then the power spikes aren't a huge concern. Then again it's easy to cap the power at more sane levels with only a small decrease in performance. But yes I'm certainly not going to compress video for hours on end at 350W!

As you wrote we'll know more in 9 days.
 

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
It IS insane if you are considering prolonged use at that power level. But if you are only looking at bursty workload that last for a few seconds here and there, think Photoshop, then the power spikes aren't a huge concern. Then again it's easy to cap the power at more sane levels with only a small decrease in performance. But yes I'm certainly not going to compress video for hours on end at 350W!

As you wrote we'll know more in 9 days.
I'm not sure why it's even a topic of discussion. The PL2 is ~250W, not 350W. You'd only see numbers that high if you went out of your way to uncap it, in which case you'd presumably know why.
 
  • Like
Reactions: controlflow

Hulk

Diamond Member
Oct 9, 1999
4,191
1,975
136
Very true. I think I responded because sometimes benchmarks are quoted without power levels. Then someone responds, "Yeah but that's at 350W!" And on and on. Trying to get people thinking that there are usage scenarios that might work better for one CPU over another. Zen 4 and Raptor look to be very competitive, it's gonna come down to specific usage and as always price.
 

scannall

Golden Member
Jan 1, 2012
1,944
1,638
136
Very true. I think I responded because sometimes benchmarks are quoted without power levels. Then someone responds, "Yeah but that's at 350W!" And on and on. Trying to get people thinking that there are usage scenarios that might work better for one CPU over another. Zen 4 and Raptor look to be very competitive, it's gonna come down to specific usage and as always price.
The performance metrics that are important to me may not mean anything to someone else. We all have different tastes, quirks, requirements etc. Cool, quiet and my CPU not be the bottleneck. Others may prefer pure throughput, forget the heat. And that's fine, their needs are theirs. As well as the money they spend.

When the reviews come out pay more attention to the things that are important to you, not what is important to the reviewer.
 
  • Like
Reactions: DAPUNISHER

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
The performance metrics that are important to me may not mean anything to someone else. We all have different tastes, quirks, requirements etc. Cool, quiet and my CPU not be the bottleneck. Others may prefer pure throughput, forget the heat. And that's fine, their needs are theirs. As well as the money they spend.

When the reviews come out pay more attention to the things that are important to you, not what is important to the reviewer.
Yes, and when I comment, many know I am talking about 100% 24/7 MT performance and power usage. Also, for someone to claim (for example) "Raptor lake is king of (insert metric)", but then its at 350 watts, that is just stupid. At todays speeds, aside from what I do, no one needs to be 10% faster for 50% more power usage(example, not necessarily real), thats just wasteful. And yes, heat is also a metric.
 

DrMrLordX

Lifer
Apr 27, 2000
21,582
10,785
136
How would you cool that ? AIO are only 250 watt I think. Custom WC only ?

I think some of the 360mm AiO units can do it, but it might take loud fans. There are some 420mm AiO units. HSF is completely off the table.

It IS insane if you are considering prolonged use at that power level. But if you are only looking at bursty workload that last for a few seconds here and there, think Photoshop, then the power spikes aren't a huge concern.

Honest question, does Photoshop even benefit from e-cores?
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,478
14,434
136
If you pretend that 350W is a stock value, then that's simply wrong. We have more than enough confirmation on that by this point.
I know its not stock. What I really want to see is stock vs stock with an aio (and maybe air also), AND max vs max with an AIO, no custom water.

I was commenting that anyone that uses the 350 watt setting and says "it wins" when not comparing against the max from the competitor is unrealistic. I seen this here before. Any "wins" should be at the same conditions with the same cooling. Maybe even the same watts, but in reality, stock vs stock or max vs max is OK. But insane wattage on either test is unacceptable. IMO.

Even LN2 vs LN2 is an OK test, but does not mean much, as nobody can afford to run that except for a suicide run. And custom or chilled water is VERY expensive, so very few people will be using that. We need tests that are what a mild enthusiast can do, not an insane overclocker. That has its place yes, but most people want realistic results.
 

Hulk

Diamond Member
Oct 9, 1999
4,191
1,975
136
Honest question, does Photoshop even benefit from e-cores?

I haven't specifically checked but I doubt it. My point is this. When I'm working in PS I can hear the fan on my CPU spinning up for like 4 or 5 seconds and then shutting down as I work. It's a "bursty" workload. Running the P's at 5+GHz in my opinion and for my usage pattern doesn't make sense for long periods of time. But, when I'm interacting with the computer in a way that waiting for operations slows down my creative workflow I like having the extra compute even at the expense of a momentary loss of efficiency.

In addition, as I've written here many times if I am transcoding video while editing in PS, the e's are efficiently and admittedly rather slowly taking care of this operation in the background while I continue to work with all 8 P's at my disposal. It works well for me.

Having only 4 e's kind of stinks. 16 would be pretty amazing.

Again, this is just my experience. Different strokes for different folks.
 
  • Like
Reactions: DAPUNISHER

DrMrLordX

Lifer
Apr 27, 2000
21,582
10,785
136
I know its not stock. What I really want to see is stock vs stock with an aio (and maybe air also), AND max vs max with an AIO, no custom water.

When AMD's "max" is 230W and Intel's is 350W, that's maybe not a fair comparison unless the target audience is okay with speccing out appropriate cooling. AMD users willing to pony up for the same cooling may be able to use PBO and squeeze out even more performance, who knows?

I haven't specifically checked but I doubt it.

I didn't think so. Stuff like Photoshop already does pretty well on Alder Lake so I doubt that Raptor Lake will show major improvement. Could be wrong though.
 

Det0x

Golden Member
Sep 11, 2014
1,027
2,953
136
If you pretend that 350W is a stock value, then that's simply wrong. We have more than enough confirmation on that by this point.
I think the problem arises when IDL forum posters act like this is performance numbers you will get a with a "stock" 13900k, failing to mention its done with unlimited power limits. (basically overlocked)
How many times have i seen people talk about 40k MT score in Cinebench r23 and not a pip about that 350w power consumption needed and what cooling is required to run that..

I'm totally fine comparing a unlimited Raptor Lake vs a PBO Zen4.
..or stock raptor 253w vs 230w Zen4

But not this 350w vs 230w comparison that is currently doing the rounds

Dont you think that would be a fairer comparison ?








Use of acronym IDL to insult the Intel side. Not allowed, don't do it again.


esquared
Anandtech Forum Director
 
Last edited by a moderator:

coercitiv

Diamond Member
Jan 24, 2014
6,151
11,674
136
I didn't think so. Stuff like Photoshop already does pretty well on Alder Lake so I doubt that Raptor Lake will show major improvement. Could be wrong though.
Photoshop scales well with ST performance for most users, core count increase is a mixed bag, doubly so when you already have 8 P cores. Raptor Lake will show improvements with higher clocks and maybe cache afinity in some benchmarks, but the E core spam will be largely irrelevant for the average PS user.
 
  • Like
Reactions: scineram and Kaluan

Asterox

Golden Member
May 15, 2012
1,026
1,775
136
Honest question, does Photoshop even benefit from e-cores?

No, or example where you can see which CPU has the highest Singlecore performance.

 

Kaluan

Senior member
Jan 4, 2022
500
1,071
96
That s 43% more power, from 240 to 343W, so basically the same perf/watt at these conditions than ADL.
Their 45% was actually spot on (236 to 343 = 45,3% inc)

Raptor Lake may be quite a bit more efficient than Alder Lake under X and Y circumstances, but at least under 100% Intel spec v Intel spec (5,5GHz/4,3GHz P/E core sustained v 4,9/3,9), Raptor Lake comes slightly short of linear scaling. A sign IMHO, that Raptor Lake is (spec-wise) overtuned even more so than Alder.

One also has to factor in the quality of the samples tested. The ADL one (emphasis) seems like a great sample, no idea about the Raptor Lake one. But Intel has been known to seed reviewers with their top silicon before. Not that we have any way of knowing for sure were they got their sample from, but Intel seems to be running a incredibly loose ship... suspicious loose.
 
  • Like
Reactions: DAPUNISHER

Zucker2k

Golden Member
Feb 15, 2006
1,810
1,159
136
I think the problem arises when IDL forum posters act like this is performance numbers you will get a with a "stock" 13900k, failing to mention its done with unlimited power limits. (basically overlocked)
How many times have i seen people talk about 40k MT score in Cinebench r23 and not a pip about that 350w power consumption needed and what cooling is required to run that..

I'm totally fine comparing a unlimited Raptor Lake vs a PBO Zen4.
..or stock raptor 253w vs 230w Zen4

But not this 350w vs 230w comparison that is currently doing the rounds

Dont you think that would be a fairer comparison ?
You know what? It was the pro AMD posters that was denying the fact that 230w PPT was what Zen 4 was going to consume out of the gate. So it's good to see we've accepted the reality that not only did AMD gain a full node advantage, they also increased power consumption by 62% across the board. In view of this, I'm questioning the rationality of calling for a "fairer comparison" between these chips at 230w and 253w respectively. If that were the case, then an even fairer comparison would be 230w vs 230w. Don't you think?

I've been in this forum for a long while now, and yet it amazes me how far the pro AMD posters would go in order to try to skew or discredit the competitor chip. Well, I have news for you, Intel isn't going to wave a magic wand and overcome the laws of physics. They have a competitive product already, but if the competition is going to raise power consumption by 62% across the board, on top of the full node advantage they enjoy, then the last thing I'll be arguing is power consumption.
With its process disadvantage, Intel is always going to be the more power-demanding platform. That's not new news. What matters at the end of the day is whether Raptor Lake is able to dissipate 350w better than Zen 4 with its 230w. I'm here for how this all plays out.

In other news AVX-512 is now all the rave as soon as AMD implemented it and Intel dropped it. Let's see if the pro AMD posters would ask for benchmarks scores with AVX-512 boost be disregarded like they used to do not so long ago. I won't hold my breath.





You seem to find new and clever ways of insulting the AMD crowd by not saying "fanboy".
You only edited ADL out when you got caught.
Just so everyone knows, ADL and IDL are derisive, derogatory terms only meant to insult and
inflame the other side.
The use of these terms is not allowed and If you folks don't want to play by the rules we set forth here,
be prepared for the consequences.


esquared
Anandtech Forum Director
 
Last edited by a moderator:
  • Like
Reactions: ondma

Exist50

Platinum Member
Aug 18, 2016
2,445
3,043
136
I think the problem arises when IDL forum posters act like this is performance numbers you will get a with a "stock" 13900k, failing to mention its done with unlimited power limits. (basically overlocked)
How many times have i seen people talk about 40k MT score in Cinebench r23 and not a pip about that 350w power consumption needed and what cooling is required to run that..

I'm totally fine comparing a unlimited Raptor Lake vs a PBO Zen4.
..or stock raptor 253w vs 230w Zen4

But not this 350w vs 230w comparison that is currently doing the rounds

Dont you think that would be a fairer comparison ?
Who in this thread or the original source has claimed those numbers as representative of performance at stock? Where are you claiming to see this behavior? Because as things stand, it reads mostly like a strawman. Ironically so given the effort needed to convince some people about each chip's actual TDP...
 

TESKATLIPOKA

Platinum Member
May 1, 2020
2,329
2,811
106
.....
I'm totally fine comparing a unlimited Raptor Lake vs a PBO Zen4.
..or stock raptor 253w vs 230w Zen4
....
Isn't the max socket power 230 W for AM5?
7900x and 7950x has 170W TDP and 230W PPT, right?
Then even If you activate PBO the limit still will be 230W?

I want to see a comparison between a standard 13900K vs 13900T. How much lower It needs to be clocked to fit in 35W sustained.
AMD most likely won't release such a low TDP product for desktop, so 13900T will be the most efficient CPU for desktop out of the box.
The question is price and If It's worth the lost performance.
 

Det0x

Golden Member
Sep 11, 2014
1,027
2,953
136
Isn't the max socket power 230 W for AM5?
7900x and 7950x has 170W TDP and 230W PPT, right?
Yes default PPT values for the 7950x should be 230PPT according to all leaks.
Stock value for my 5950x is 142w, but i have no problem drawing over 300w from the AM4 socket when i want.. (think ive been upto 360w PPT)

Then even If you activate PBO the limit still will be 230W?
That depends on the "stock motherboard PBO limits".
Simply turning on PBO allows the cpu to consume more than stock 142 PPT limits for the 5950x
I'm very sure the same will be the case with highend x670e motherboard..

Like i said above, i'm all for comparing performance with unlocked/higher powerlimits between Raptor Lake and Zen4, but it seem disingenuous to only allow Intel to run with unlimited power limits compared to a stock PPT Zen4 for the "performance crown".

Either run CPU's at stock powerlimits (253w vs 230w).
..Or if you want to enable the unlimited power option for the 13900k, you should also enable PBO for the 7950x.

But it seem like certain parties dont want this... I wonder why ?
It makes me wonder what the 7950x would score with PBO enabled when we know it reaches 39k at stock 230w.
1663527305642.png

*edit*
I just tested auto PBO limits for my x570s MSI unify x max running a 5950x --> 1000w PPT limit
Unlimited power value for Intel is 2048w i think ? or was it 4k w ?
1663527564614.png
 
Last edited:

biostud

Lifer
Feb 27, 2003
18,193
4,674
136
If that difference in price between N7 dies and N6 dies is even remotely true, and TSMC's own statements about the portability of N7 designs to N6, its almost baffling that AMD hasn't done an N6 version of Zen3 as an in place upgrade to their line of N7 based Zen3 products just to decrease their own cost per working CCD. I realize that there would still be an R&D overhead to such a move, but, in volume, it should be more than made up in short order unless TSMC is flat out lying about the ease of porting those designs. We already see the improvements in Rembrandt's CCX over Cezanne while using what is essentially the same design. With a higher power budget, it seems logical that desktop CCDs should show an even better MT performance improvement.
They do have 6xxx mobile zen3+ APU on 6nm :p