AMD "Zen 5c" CCDs Made On More Advanced 3 nm Node Than "Zen 5"

[Metroid]

Fact is fact and Intel top cpu is a little bit faster 3% at most x AMD top cpu in general applications but for 2~3x more power, that is stupid, to this day, I don't know why somebody would ever buy Intel cpus. If AMD wanted they could push more power and make their top CPU faster than Intel but they don't care.

 

[dgianstefani]

Fact is fact and Intel top cpu is a little bit faster 3% at most x AMD top cpu in general applications but for 2~3x more power, that is stupid, to this day, I don't know why somebody would ever buy Intel cpus. If AMD wanted they could push more power and make their top CPU faster than Intel but they don't care.

Peak power ≠ average power. Even then the peaks are nowhere near 2-3x, as Phoronix testing shows.

Again showing that testing large sample counts and averaging results gives more useful information than picking a single number and holding it up as supposed proof of something.

 

[Metroid]

Peak power ≠ average power. As Phoronix testing shows.

View attachment 335420

Again. Showing that testing large sample counts and averaging results gives more useful information than picking a single number and holding it up as supposed proof of something.

I used to have Intel cpus and the power was enormous different than shown on reviews, reviews said that my i7 920 maximum wattage even overclocked to 4.0ghz could not go beyond 220 watts but mine used to go to 400 watts and my voltage was very low compared to my friends. I believe those reviews got golden samples and bragged about with fairy tales. I will never trust Intel concerning that matter and to this date I still believe they are still sending golden samples to reviewers. I had a power meter, reason I knew that, 99% dont have that to see the truth, those apps all cheat too.

Intel Core i7 920 PCSTATS Review - CPU Power Consumption Tests

CPU Power Consumption Tests - PCSTATS.com

www.pcstats.com

 

[dgianstefani]

I used to have Intel cpus and the power was enormous different than shown on reviews, reviews said that my i7 920 maximum wattage even overclocked to 4.0ghz could not go beyond 220 watts but mine used to go to 400 watts and my voltage was very low compared to my friends. I believe those reviews got golden samples and bragged about with fairy tales. I will never trust Intel concerning that matter and to this date I still believe stills ending golden samples to reviewers. I had a power meter, reason I knew that, 99% dont have that to see the truth, those apps all cheat too.

Intel Core i7 920 PCSTATS Review - CPU Power Consumption Tests

CPU Power Consumption Tests - PCSTATS.com

www.pcstats.com

You realise that a power meter is whole system power right? Including the GPU, PSU voltage conversion losses, and every other component in the build drawing power from the wall.

 

[kapone32]

Peak power ≠ average power. Even then the peaks are nowhere near 2-3x, as Phoronix testing shows.

View attachment 335420

Again showing that testing large sample counts and averaging results gives more useful information than picking a single number and holding it up as supposed proof of somet

Multithreading performance is calculated by TechPowerUp, and every other review site, by averaging many tests of many tasks, 43 here on TPU and 173 on Phoronix, this is because singular examples are not representative of general performance. Phoronix is more of a Linux server site, with tests that are relevant to that usage. Your single example of AI upscaling, where a GPU would be more appropriate to use, doesn't change that the Intel chips are faster in multithreading. This statement is true despite your attempts to find examples that support your choice of CPU.


And that's exactly why TPU tests these products.

Marketing ≠ performance.

The testing doesn't lie.

I am confused. The word is used was nuanced. That is the truth. You are trying to justify your 2nd argument to hook it back to your first. That is not my confusion though. This is an AMD thread about upcoming AMD CPUs. What does it have to do with current offerings from Intel.

 

[Metroid]

You realise that a power meter is whole system power right? Including the GPU, PSU voltage conversion losses, and every other component in the build drawing power from the wall.

Yeah, tested only the cpu, nothing else, motherboard and memory use little bit of power, maximum 70w, system was almost 500 watts, 400w only the cpu, lucky me I had a custom watercooling back then in 2008, with a 480 radiator to keep that furnace cooled. That was my last Intel CPU and by the way AMD was worse than Intel back then.

 

[kapone32]

You realise that a power meter is whole system power right? Including the GPU, PSU voltage conversion losses, and every other component in the build drawing power from the wall.

Yep and when MSI Gaming did a livestream using a 14900K and 4090, they were able to draw over 1100 Watts doing benchmarks.

 

[dgianstefani]

I am confused. The word is used was nuanced. That is the truth. You are trying to justify your 2nd argument to hook it back to your first. That is not my confusion though. This is an AMD thread about upcoming AMD CPUs. What does it have to do with current offerings from Intel.

If you read the thread you might be less confused. Technical questions were raised about AMD C cores, then they were compared to Intel E cores, now we're here.

 

[john_]

And that's exactly why TPU tests these products.

Because 99% of consumers read TPU tests.
Great argument.

 

[kapone32]

If you read the thread you might be less confused. Questions were raised about C cores, then they were compared to E cores, now we're here.

We already know E cores are nowhere as fast as Z cores. That brings me back to what does the 14900K have to do with Zen5c. These are not bulldozer chips on Ryzen. For me there is nothing that should influence this thread to discuss the benefits of chips that can't fit on AM5 MBs.

 

[john_]

If AMD wanted they could push more power

AMD DID increased power with Zen 4. AMD was trying to stay at lower wattage and sell efficiency, but tech press and consumers where pushing that +1% performance of Intel CPUs at much higher power consumption as "Intel win". We can see this mentality in some posts in this thread.
So, with Zen 4 AMD increased wattage to 170W/230W.

 

[dgianstefani]

Because 99% of consumers read TPU tests.
Great argument.

The facts are available whether consumers bother to educate themselves or not. Uninformed consumers are precisely why marketing can get away with false claims. What exactly is your point here? TPU shouldn't test because most consumers aren't techies?

We already know E cores are nowhere as fast as Z cores. That brings me back to what does the 14900K have to do with Zen5c. These are not bulldozer chips on Ryzen. For me there is nothing that should influence this thread to discuss the benefits of chips that can't fit on AM5 MBs.

Z cores?

 

[kapone32]

The facts are available whether consumers bother to educate themselves or not. Uninformed consumers are precisely why marketing can get away with false claims. What exactly is your point here? TPU shouldn't test because most consumers aren't techies?


Z cores?

That is what I like to call them since they are not full Zen cores. Since they are not even real yet. I can call them whatever I want. You are again moving the goal posts though.

 

[john_]

The facts are available whether consumers bother to educate themselves or not. Uninformed consumers are precisely why marketing can get away with false claims. What exactly is your point here? TPU shouldn't test because most consumers aren't techies?

You are uninformed, I am uninformed, everyone is uninformed because people do have lives to live. Others know how to choose the correct CPU, others the correct GPU, others the correct refrigerator, others the correct car, others spot the fresh meat next to the bad, others choose the correct paint for the job, others the correct fabric for their clothes. NO ONE knows EVERYTHING, NO ONE spends a lifetime of searching before buying something. They just go in a shop, ask the employee, buy what they employee will tell them, go home.
You still keep throwing the ball outside the court.

 

[dgianstefani]

Why would an Epyc processor with Zen 5c have only six chiplets? That’s an odd arrangement. Wouldn’t eight chiplets for a total of 256 cores make more sense? That’s how Bergamo is arranged.

Maybe RAM bandwidth. You have to feed the cores with memory, these cores already have a quarter of the cache of the normal ones. Perhaps the platform can't efficiently feed 256 cores with the channels it has.

 

[Metroid]

AMD DID increased power with Zen 4. AMD was trying to stay at lower wattage and sell efficiency, but tech press and consumers where pushing that +1% performance of Intel CPUs at much higher power consumption as "Intel win". We can see this mentality in some posts in this thread.
So, with Zen 4 AMD increased wattage to 170W/230W.

Those famous bags of money sent overnight with the cpus to reviewers all paid by Intel, all golden samples, famous overclockers at that time showing off their golden samples while the people falling for the lie. What made me not to ever buy Intel was when they limited overclocking on cheap cpus and mandatory motherboard purchase every year for new cpus, they would not make a bios available for 2 or more years old motherboards, disgraceful.

 

[Noyand]

It is marketing. How do you think AMD started winning market share? By offering more cores than Intel, even when those cores where lower IPC cores. That's how Ryzen became a success. Where Intel was offering 4 cores, AMD started offering 6 and 8 cores.
It's not about feelings.
Thinking that every post is about feelings, only shows how YOU think and why YOU post, in this case. It's not about me. Don't project yourself on me. It doesn't work.


They do. Marketing. They can't sell a 16 core CPU when Intel will be selling a "24 core" or a "32 core" CPU at the same price point, or even at a little higher price.

My feelings ? Which feelings am I supposed to have about AMD when I'm happy to buy from them whenever their products are the best for my use cases ? Early Ryzen had the mindshare for productivity, (I bought a 1700x even though in gaming it didn't bring anything over the haswell core i5 that I had back then. But those 8 core + smt at such a low price made my life easier in a lot of stuff) but Intel stayed the gaming CPU of choice until zen 3. AMD gained marketshare because they had a massive lead over intel in MT at a price point that was unbeatable, meanwhile intel HEDT was getting old and expensive for what it offered. Then X3D offered high gaming performance at a low price relative to the competition.

I used to think that AMD would bring c core to the desktop as well, but mostly because Ryzen mid-range was suffering from the comparison against a 13600k/13700k. But the leaks so far, and them already reserving zen4c to the datacenter/low power laptop seems to suggest that as long as the Ryzen 9 are staying competitive, they are not interested to fight Intel on the core count. Even though their chiplet design makes this really easy. They would rather fight them with "real cores", and from what I've seen on various comment section or discord, AMD having more "real cores" is already a win marketing wise over intel's "cinebench accelerators". (Even though their mid-range using c-core would make them a better match against Intel, but I got called stupid for saying that, go figure! )

My general feeling is that the core count marketing advantage in 2024 is blown out of proportion, especially when the hottest, best-selling mainstream CPU is an 8 core that's more expensive than competing 12 or 16 cores CPUs. I've talked with "normies" back when Intel had a core count deficit, and they still liked Intel more because they just had more trust over seeing the brand more often on high-end SKU (hello dell XPS, alienware laptops etc... flagships are still being paired with an Intel CPU, even in the zen 3 era) From what I've seen normies are more sensitive to overall brand perception than shallow specs. That's how Apple manage to sell their computers, even though they always looked underpowered for the price.

I'm not arguing against you specifically, just the general perception that the e-cores are only there to accelerate benchmarks, padding the marketing material when they do bring tangible benefits irl. Yes it's a fix because Intel couldn't make smaller p cores, but that fix is doing what it's supposed to do : competing with AMD on performance rather than just being a pure marketing ploy to increase the core count on the spec list for cheap. But I'm also just a weird dude, who like exotic stuff, Ryzen chiplets already fascinated me just for being different from what Intel was doing for a more than a decade. Now I'm more interested to see where Intel is going with the exotic stuff that they've been pulling lately. If they hit a wall, that's that. I'm just going to buy AMD again.

 

[Steevo]

Feels like the ATI of old, newer mid/low end chips on new process to fine tune to make the big ones profitable out of the gate.

 

[kondamin]

Sounds expensive, maybe they cut in rdna4 and had to replace the reserved capacity

 

[Minus Infinity]

Why would an Epyc processor with Zen 5c have only six chiplets? That’s an odd arrangement. Wouldn’t eight chiplets for a total of 256 cores make more sense? That’s how Bergamo is arranged.

Way back when leaks about Turin dense came out it was alwasy said it would come with up to 256 5c cores. However, that was predicated on TSMC getting 3nm up to scratch. Later rumours said Zen 5c would have to be on 4nm as N3B was crap and thus the 192 core max. However it was said they would develop for both 4nm and 3nm in case TSMC got 3nm fit for AMD standards. If AMD is now using 3nm I assume N3E node, so not sure why they would still be sticking to 192 cores.

 

[energia]

Can't wait for the 9000X3D with the rumored 20% single and +40% IPC in multi-core performance that should come in May 2024

You mean May 2025.

 

[Minus Infinity]

You mean May 2025.

If the leaks are true regular Zen 5 is faster in gaming than Zen 4 X3D and no suffering large loss in productivity score. Only reason I'd buy X3D is for efficiency. Not enough games benefit a great amount from 3D cache and the returns at 4K are minimal anyway.

Personally I can't wait for Zen 5 vs Arrow Lake tests.

 

[chrcoluk]

Don't bother. I mean 3% faster on average, if you choose specific apps, at probably 50-100% more power consumption and having to train the OS to manage multiple types of cores, is a great design. Go figure.....

Just to chime in here as some can have very selective memory.

AMD has its own special Windows scheduler to manage their issues with lopsided CCD performance in games. Special schedulers apply to both vendors.

 

[Count von Schwalbe]

Just to chime in here as some can have very selective memory.

AMD has its own special Windows scheduler to manage their issues with lopsided CCD performance in games. Special schedulers apply to both vendors.

CPPC, been around forever and works with every CPU. Native to the OS.

AMD's driver is for user-level control of CPPC.

 

[dgianstefani]

Just to chime in here as some can have very selective memory.

AMD has its own special Windows scheduler to manage their issues with lopsided CCD performance in games. Special schedulers apply to both vendors.

CPPC, been around forever and works with every CPU. Native to the OS.

AMD's driver is for user-level control of CPPC.

Sure. But the 3DVCache "driver" is still something you have to install if you don't want issues. Even then it only works most of the time because it's just a predefined manual games list, not anything universally context sensitive, and it's legitimately a better solution to just use Process Lasso and create rules rather than being tied to having Game Bar enabled. I do this anyway even though I only have one CCD. Being able to choose your slowest boosting cores to pin background tasks to and keep your fastest cores exclusively for whatever you're doing is great.