Core Performance Boost Contributes 14% to Ryzen 5 7600X Cinebench R23 Score

[Makaveli]

They're going to struggle against Raptor Lake in the mid range -- if Cinebench is indicative of overall performance (probably isn't).

View attachment 261164
ALS-S @ 5.2 6/4 ecore - the 13600K should easily stomp on this score - if it's priced around the 7600x it's going to be a huge difference (in this benchmark).

92C is bush league compared what ADL-S hits in cinebench lol.

"if Cinebench is indicative of overall performance (probably isn't)."

The amount of people using cinebench as a guage and don't render at all is hilarious. I know there is a lack of information out until the reviews but since when did CPU Z, CB and GB become the standard at which we rate cpu performance.

 

[Oberon]

To be fair, CB was the be-all, end-all of CPU performance for AMD fans for a few years

 

[phanbuey]

Idk what you're talking about man I play Cinebench all the time. Great game.

To be fair, CB was the be-all, end-all of CPU performance for AMD fans for a few years

Touche.

 

[Tropick]

Idk what you're talking about man I play Cinebench all the time. Great game.


Touche.

Cinebench is good but 3dmark's graphics are such a treat

 

[RandallFlagg]

They're going to struggle against Raptor Lake in the mid range -- if Cinebench is indicative of overall performance (probably isn't).

View attachment 261164
ALS-S @ 5.2 6/4 ecore - the 13600K should easily stomp on this score - if it's priced around the 7600x it's going to be a huge difference (in this benchmark).

92C is bush league compared what ADL-S hits in cinebench lol.

I was going to say, these numbers presented aren't particularly impressive.

You can get a 12700K today for about the same price as a 7600X MSRP, match that 7600X high single core and stomp all over the MC scores without OC, basically without trying at all.

Straight from the benchmark thread on CB23 at this site:

If you OC, you get stuff like this 12600K:

 

[Hossein Almet]

Could'n care less! I'm currently saving for a 77in G2

 

[Pepamami]

To be fair, CB was the be-all, end-all of CPU performance for AMD fans for a few years

I would like to become Intel fan again, but Intel flip me over too many times for past 10 years :C
But dayum it took me 1 week to configure 5800X, and it looks like u have to configure/tune most of 7xxx too, to achive good expirience, thats sucks about zen3/zen4

 

[Daven]

That's 14% over the CPB-off behavior, not over a 5600X. A stock 5600X (4.6 GHz max boost) scores 1540 points in the same test vs 1681 @ 4.7 GHz for the 7600X, which puts the PPC increase at right around the quoted 9%. Actual ST performance increase (not iso-clock) comes in at right around 25% vs the 5600X.

Thank you for the clarification, Oberon. What was actually driving me crazy was my poor reading comprehension.

 

[FeelinFroggy]

Maybe it's just me, but I don't want to have to under volt a desktop CPU (especially just 6 cores) to keep the heat down. You should not have to make that sacrifice with a desktop CPU, even if it is a small form factor build.

I'm not knocking AMD cause Intel has been building mini heaters for while now. But everyone says to just under volt the CPU to get rid of the heat. If you need to do that to keep the heat down then dont buy a $300 CPU. Why buy an expensive CPU if your just going to undervolt and slow down the chip. It's like driving a Ferrari with a governor installed to keep you from speeding.

I have undervolted CPUs in laptops before and it made more sense cause I dont like my chip running at +90C for a sustained gaming session. The CPU will lose long term performance to be under that much heat for extended periods of time. I think it is called electromigration, but I bet someone here knows and will correct me if I'm wrong on the terminology.

 

[ymdhis]

Another clickbait article from TPU. PBO worked like that in every Ryzen so far, it's why I run mine PBO off. And we already got reports that undervolting the Zen 4 chips will greatly reduce the power consumption and heat output while keeping the clockspeeds up... like it did with nearly every high-end CPU (and GPU) released in the last few years.

 

[Jism]

If this kind of problem occur chances that you have to contact computer technician. Before you fixing that kind of problem. Because overheating of cpus can burn your cabinet with motherboard.""""

View attachment 261163

What happens when the CPU temperature is too high? - Quora

lol... Well you can safely remove the Heatsink while running your PC these days.

 

[Vayra86]

Am I the only one that's more impressed by the 60 W score than the 110 W score?
10 W per core, 2166 points per 10 W

Indeed

 

[Oberon]

Another clickbait article from TPU. PBO worked like that in every Ryzen so far, it's why I run mine PBO off. And we already got reports that undervolting the Zen 4 chips will greatly reduce the power consumption and heat output while keeping the clockspeeds up... like it did with nearly every high-end CPU (and GPU) released in the last few years.

This is not PBO.

 

[Valantar]

Am I missing something? AMD claims Zen 4 had a 9% IPC increase over Zen 3 in 1T Cinebench. But this benchmark run only shows a 14% increase with a 15% increase in clock speed.

Yes, you're missing something: The comparison is the same Zen4 CPU with and without CPB, not between Zen3 and Zen4.

I run a 180-200W chip in an SFF build - many modern SFF cases (meshilicious, sliger cases, nr200P, etc) can dissipate this heat + 350W/400W gfx cards without any issues. The main problem here isn't the heat generated (at all 110W is very reasonable) -- it's the dissipation capability. If it's running at 92C at 110W that means it would absolutely melt at 150W never-mind the 241W/288W that intel chips suck down.

That's exactly why I said "this class of SFF", and not just "SFF" - we quite clearly weren't talking full performance SFF, though I guess that's not as visible to someone who isn't familiar with @AusWolf's builds. My own Meshlicious has zero trouble handling my 5800X+6900XT, even when I haven't tuned them for efficiency, so I'm well aware that it's entirely possible to run full power hardware in SFF - but running those in my secondary Densium 4+ (even if I could fit the GPU, which definitely isn't possible) would be a no-go. We were talking specifically about SFF cases with notably limited cooling, that can't fit water cooling, etc.

 

[AnotherReader]

The IPC increase is not uniform, but depends upon the application. AMD's own slides note a 1% increase for Cinebench R23. It isn't even a surprise as AMD hasn't mentioned any improvements to the backend. As it isn't limited by the frontend or the cache, Cinebench won't benefit from the improvements that Zen 4 has compared to an equivalently clocked Zen 3.

I have to edit my post due to a mea culpa. I misread the slides due to the low resolution of the device I was using; it's indeed a 9% increase. Now, AMD has been relatively vague about the microarchitecture improvements in Zen 4. However, looking at the Zen 3's bottlenecks article over at Chips and Cheese, we can see that increasing the out of order window would be more beneficial than front end improvements.

Going deeper into the dispatch stalls reveals that the ROB (reorder buffer), load and store queues, and FP registers are the most important factors affecting Cinebench IPC. There are rumours that the ROB size has increased by 25%. AMD has mentioned load/store improvements; these should affect Cinebench as well.

 

[phanbuey]

That's exactly why I said "this class of SFF", and not just "SFF" - we quite clearly weren't talking full performance SFF, though I guess that's not as visible to someone who isn't familiar with @AusWolf's builds. My own Meshlicious has zero trouble handling my 5800X+6900XT, even when I haven't tuned them for efficiency, so I'm well aware that it's entirely possible to run full power hardware in SFF - but running those in my secondary Densium 4+ (even if I could fit the GPU, which definitely isn't possible) would be a no-go. We were talking specifically about SFF cases with notably limited cooling, that can't fit water cooling, etc.

What I was saying is even on airflow constrained cases with low profile coolers - these chips are pretty low wattage at max temps. Basically they will sit at 92C and throttle down as CPB allows, even a restrictive SFF case won't have issues dissipating 110W. I mean unless you're putting it in an EXTREMELY restrictive case in which case 7600x isn't really the chip you want anyways.

 

[Makaveli]

To be fair, CB was the be-all, end-all of CPU performance for AMD fans for a few years

lol I always love this "AMD Fans" all that means is those fan boys were clueless.

If you buy cpu's based on CB*, CPU Z and GB scores you are doing this very wrong. *for those that actually render however most the people that rant about CB scores are just gamers

People that know what they are going usually buy based on their workflows. Well adults at least.

 

[Valantar]

What I was saying is even on airflow constrained cases with low profile coolers - these chips are pretty low wattage at max temps. Basically they will sit at 92C and throttle down as CPB allows, even a restrictive SFF case won't have issues dissipating 110W. I mean unless you're putting it in an EXTREMELY restrictive case in which case 7600x isn't really the chip you want anyways.

That is absolutely true. It just depends how comfortable you are with letting your chips run hot. Personally I don't really mind - laptops often sit at or near 100°C constantly after all, so we know the silicon can handle it (and unlike cramped laptops the higher core temperatures are unlikely to correlate to matching high VRM temperatures). If the CPU is hot because of high thermal density rather than high thermal load, then the problem is an inability to dissipate heat out from the core, so it kind of by default can't hurt surrounding components. Still, most of us PC builders are used to much lower temperatures than that, and I get that it's uncomfortable in certain ways. Still, if we want aggressive boosting in small form factor cases, that's just how it is. And tbh, it'll be that way in a lot of larger cases too.

 

[ymbaja]

I wonder what cooler they used. I don't like that 92.1 °C with only 110 W one bit. This is why I hated the R5 3600 that I gave away after a week or so. Either the IHS design hasn't improved despite the switch to LGA, or chiplets will always run hot.

I never thought about it before, but I wonder if the pin array actually kind of worked as an upside down heat sink? Seems like they would have a thermal advantage over LGA.

 

[freeagent]

What kind of cooling is being used? Looks a bit lowend, or its harder to cool because its a smaller CPU? Boost looks good, power is still lowish, even compared to my 5600X which can do ~130w with PBO/CO and boost override, but of course caps at 4850. What's with all the haters? ADL wont last forever, at least Zen 3 got solid run time.. you should be happy that it was AMD that got Intel to make a better CPU, because they weren't doing it on their own. Now there is good competition between the two brands, they win with money, we win with performance. What's not to like?

 

[QuietBob]

The temperature with CBP on looks disturbing to me. 92c @ 110w with an AIO is a lot, and this isn't even for the full 8c CCD. For reference, my 5800X3D - a full single CCD/CCX - goes up to 76c @ 107w in R23. This is achieved with the best air cooler available. Of course, all core clocks are higher on the 7600X, yet it seems that LC could be mandatory.

If the leak is reliable, I cannot even imagine the temps on the 7700X. It may be extremely hard for single CCD Zen 4 SKUs to reach maximum performance with MT loads, due to thermal throttling.

On the other hand, this 6c/12t 7600X scores 10% higher in ST than a max tweaked 5950X, and gets the same score in MT as an 8c/16t Zen 3. So there's definitely progress in IPC.

 

[Punkenjoy]

The temperature with CBP on looks disturbing to me. 92c @ 110w with an AIO is a lot, and this isn't even for the full 8c CCD. For reference, my 5800X3D - a full single CCD/CCX - goes up to 76c @ 107w in R23. This is achieved with the best air cooler available. Of course, all core clocks are higher on the 7600X, yet it seems that LC could be mandatory.

If the leak is reliable, I cannot even imagine the temps on the 7700X. It may be extremely hard for single CCD Zen 4 SKUs to reach maximum performance with MT loads, due to thermal throttling.

On the other hand, this 6c/12t 7600X scores 10% higher in ST than a max tweaked 5950X, and gets the same score in MT as an 8c/16t Zen 3. So there's definitely progress in IPC.

Well remember that this feature "Core performance boost" is there to push the chip to the maximum. it's not the base behavior. It's designed to grab every single once of performance the chip can get.

Your comments ont the 7700x would be valid if that were the stock settings, but pushing at 8 core binned for slighly higher frequency will certainly provide better performance.

 

[HD64G]

I cannot get why people are surprised with the 92C@110W. Even 5600(X) can get there with the same exact power draw and a $30 cooler. 5nm made chiplets even smaller and so, harder to cool. So, I think the cooling won't be a problem with coolers of good quality (>$40) and a case with good airflow.

 

[Deleted member 185158]

I was going to say, these numbers presented aren't particularly impressive.

You can get a 12700K today for about the same price as a 7600X MSRP, match that 7600X high single core and stomp all over the MC scores without OC, basically without trying at all.

Straight from the benchmark thread on CB23 at this site:

View attachment 261168

If you OC, you get stuff like this 12600K:

View attachment 261169

Floating in the same boat of thoughts as you actually.

My budget Intel build, at a lower frequency (be it only 4.6ghz 100mhz less) seems to have an upper hand.

I mean this 12400F is hardly challenged. And this is the stock cooler. Maybe squeeze 4.8ghz from it even.

 

[Dr. Dro]

If you're able to cool 110W then it won't throttle. Like I said temperature is unrelated. If the person thinks 110W is unacceptable for CPUs when we are heading towards 200W then sure, but again nothing to do with the temperature.

So the problem is cooling 110W. What is the alternative? Intel CPUs use even more power. You could undervolt this CPU and it would use 90W or less. R5 3600 was a 65W TDP and that somehow was a problem for you too.

You're missing the point entirely. These CPUs have extraordinarily high heat density. To cool 110W over a large area is a much easier feat than extracting 110W of heat out of a tiny chiplet, and real estate is a luxury in an SFF build.