AMD Announces Ryzen 7000 Series "Zen 4" Desktop Processors

[Valantar]

-the 5800X3D cannibalizes the entire 7000 lineup in gaming.

I see what you're getting at, but the entire lineup? A $450 CPU on an old platform cannibalizing a $300 CPU on a new one? I don't see that, sorry. And, of course, there'll be X3D variants on AM5 soon enough.

-the 2024+ support is probably the most positive thing said on the event.

*2025+

 

[Max(IT)]

Energy efficiency is not the same as power consumption
If a CPU can do 2x the work for 50% more power, its more efficient - a task like rendering a video would finish faster, using less total energy overall.

No one here seems to be worried about power requirements about Zen 4.
No more “65W” TDP CPUs.
Even the 6 core 7600X is a ”105W” TDP model.

We know very well how AMD is lying about their definition of TDP, with a 105W 5800X consuming 140W by default. So everyone here is happy to have a 6 core “140W” CPU ? Not to speak about “170W” 7900X.

Nope, I’m not impressed at all.

And what about cooling ? I’m very curious about how to keep the 7700X cool, with that little 5nm chiplet where all the heat is generated.

Then again the 5800X launched at $450, so this is nominally a gen-over-gen drop. Of course the 5800X was also by far the worst value of the 5000 gen, but that's how things were. If anything, I see that drop as indicative that AMD wants to keep margins high, but are prepared to fight it out with Intel in terms of pricing this time around.

Wrong.
There is no “7800X” yet.
The 5700X was released at $299, so this is nominally a gen-over-gen RAISE.

 

[Valantar]

No one here seems to be worried about power requirements about Zen 4.
No more “65W” TDP CPUs.
Even the 6 core 7600X is a ”105W” TDP model.

We know very well how AMD is lying about their definition of TDP, with a 105W 5800X consuming 140W by default. So everyone here is happy to have a 6 core “140W” CPU ? Not to speak about “170W” 7900X.

Nope, I’m not impressed at all.

And what about cooling ? I’m very curious about how to keep the 7700X cool, with that little 5nm chiplet where all the heat is generated.

Lol, this was a fun read given that I posted this all of 13 minutes ago:

I'm not a fan of the TDP increase

I agree that this is a bad development, but sadly it's likely necessary for them to keep competing against Intel's 125W TDP SKUs - which, for reference, have equally misleading TDPs compared to power consumption. As has been repeated a million times in a million places, TDP is not and has never been meant to be equal to power consumption. That's just not what that number denominates, and it never has been, so calling it "lying" is just hyperbolic nonsense. It's unclear marketing, sure, and it's people conflating one metric for another, but it's nowhere near lying.

Remember, what AMD has launched now is comparable to Intel's initial ADL launch, which was all "125"W parts, with several of them defaulting to a never-ending ~240W boost mode - at Intel's recommended settings. In light of this, AMD's 170W TDP/230W PPT spec is a lot closer to real-world wattage draws. And as with ADL, there'll be lower power SKUs coming - and unlike Intel, Ryzen CPUs have cTDP-down Eco Mode settings baked into them, which can be enabled with a simple BIOS setting if you want it.

I'm very much looking forward to seeing AMD's lower tier 65W CPUs, as well as how these CPUs perform in their (likely 65W TDP/~88W PPT) Eco Mode settings, as that's a lot more interesting to me. But as the PC hardware scene competes on peak performance and benchmark scores, this race towards higher power isn't showing many signs of slowing down, sadly.

Wrong.
There is no “7800X” yet.
The 5700X was released at $299, so this is nominally a gen-over-gen RAISE.

Meh. The 7700X was a late-gen launch with significant price cuts from first-run Ryzen 5000, coming out nearly two years after the initial launch of its architecture. Price comparisons between the two are thus nowhere near like-for-like, rendering them essentially uncomparable. You're right that the naming differs, which begs the question of whether there's a 170W 7800X coming (or if they're saving that tier for a 7800X3D?), or skipping it entirely like with Ryzen 2000. Of course, the 5700X is also a lower-tier TDP part, which further skews comparisons - the 7700X is clearly a top-tier 8c16t part, which the 5700X never was. But then again, naming is ultimately arbitrary, and simply a means of communicating broad rankings and characteristics. The 7700X is very obviously taking over from the 5800X, not the 5700X.

 

[Shatun_Bear]

Concerns.

- Combining the performance and power efficiency comparisons between the 7950X and the 12900K, we can calculate that the 7950X consumes 257W and has a performance per watt 20-30% worse than the 5950X. They claim that perf.per.watt has improved, but I suspect that this is conditional, such as in the case of iso-clock.

- They avoided comparing the MT performance of 7600X vs 12600X and 7700X vs 12700K. This is a combination where Alder lake is considered cheaper and better performing.

- The "IPC uplift" calculation method they use includes the effects of memory access and cache, such as game FPS and Geekbench. Calculated by their method, Raptor lake with DDR5 will get an "IPC uplift" close to 10%.

No the 13% IPC uplift is a geomean across 22 tests using a 4Ghz fixed clock. Some tests show +30% increase some as little as 1%. Raptor Lake at 4Ghz vs Alder Lake 4Ghz is unlikely to show 10% IPC increase using the same methodology.

What we do know is Zen 4 has a massive 16-17% clock increase alongside this IPC increase, whereas the clock increase going from Alder to Raptor is around 2% only. This is how Ryzen 7000 will exceed or match Raptor Lake in gaming, single core and even multithread if the leaked benches are anything to go by.

 

[Valantar]

I do like how AMD included CB23 in their IPC calculations - showing that it has a relatively low improvement overall, below the average - which lends some interesting perspective to those leaked benchmark scores (and underscores why no single benchmark should ever be treated as the be-all, end-all of performance).

 

[Shatun_Bear]

-we get used to count cores and value a product while we should check on the performance only. Why does anyone care if the 7600X is a 6/12 cpu if in the apps they use it performs better than a 5800X or a 12600K?

that’s why the prices don’t look good. At least for the 7600 and 7700.

-it seems that raptor lake will be the leader in performance no matter the consumption levels but it will be pricey…

-the 5800X3D cannibalizes the entire 7000 lineup in gaming.

-the 2024+ support is probably the most positive thing said on the event.

The 5800X3D is almost identical in gaming to the 12900K (please provide source if it is faster). Here, they showed a lowly 7600X beating the 12900K by 5% average in a few games. So by extension the $300 7600X is faster than the $450 5800X3D. Did you just write random bullet points without reading/looking at the presentation?

 

[Dirt Chip]

All in all, seems a very strong lineup for start.
Lot's of bold statements to live up for- can't wait for reviews to see what is actual and what is (a very nice) PR slides.

After 12 years living, working and playing with Sandy-bridge I might move back to AMD

 

[MarsM4N]

Yes 7800X3D will be better in gaming but at what price, $549?

I don't think the 7800X3D will have an surchage as the 5800X3D had, which was the first of it's kind. Guess they won't release them within the next 6-9 months, till then $449 could be possible.

They know a lot of us (gamers) want to see a 3D version of the 7600X, for $349 this would really be a hot seller. Crossing fingers.

 

[gffermari]

I see what you're getting at, but the entire lineup? A $450 CPU on an old platform cannibalizing a $300 CPU on a new one? I don't see that, sorry. And, of course, there'll be X3D variants on AM5 soon enough.

*2025+

The 5800X3D is almost identical in gaming to the 12900K (please provide source if it is faster). Here, they showed a lowly 7600X beating the 12900K by 5% average in a few games. So by extension the $300 7600X is faster than the $450 5800X3D. Did you just write random bullet points without reading/looking at the presentation?

A Zen 1,1+,2, even 3 owner can just drop a 3D in his system and call it a day instead of selling everything, buying everything and get 99% similar gaming performance.

Obviously the new cpus are better in every aspect against the existing 3D.
But this level of performance has been around for long due to alder lake and, thank AMD for that, in the old AM4 platform.

I like the AM5 platform but the 5800Χ3D is like an own goal to AMD.

 

[JrRacinFan]

but they aren't meant for any kind of high performance 3D.

Rdna3 is high performance??

 

[ModEl4]

.

I don't think the 7800X3D will have an surchage as the 5800X3D had, which was the first of it's kind. Guess they won't release them within the next 6-9 months, till then $449 could be possible.They know a lot of us (gamers) want to see a 3D version of the 7600X, for $349 this would really be a hot seller. Crossing fingers.

I'm with you, but not even Goddess Kali can cross that many fingers to make it happen lol jk
They will release in 6 months a $349 part with nearly 10% faster 1080p gaming performance than 7950X, effectively killing all the other Zen4 processors regarding the vast majority of gamers?
(according to AMD 7950X is only 5.7% faster than 7600X at 1080p high (less in Ultra settings), ***AMD claims 7950X is 11% faster than 12900K and also claim 7600X is 5% faster than 12900K, all on 1080p high if I'm not mistaken***)

 

[Valantar]

A Zen 1,1+,2, even 3 owner can just drop a 3D in his system and call it a day instead of selling everything, buying everything and get 99% similar gaming performance.

Obviously the new cpus are better in every aspect against the existing 3D.
But this level of performance has been around for long due to alder lake and, thank AMD for that, in the old AM4 platform.

I like the AM5 platform but the 5800Χ3D is like an own goal to AMD.

... or it's a strength through having a diverse range of offerings across use cases and budgets, leaving buyers with the choice to upgrade an existing build, or go all-new for the platform advantages that brings with it. Either way, AMD sells a CPU. Nothing like an own goal about that. Both are attractive propositions, just in different ways.

Rdna3 is high performance??

No, RDNA3 is a GPU architecture. It can be implemented in any number of performance classes, and the performance is entirely dependent on the implementation. If you have two CUs, it's not going to be high performance, no matter the architecture. It's true that RDNA3 (reportedly/expectedly) GPUs are higher performance than RDNA2 GPUs, but that's down to them having more CUs, higher clocks, etc. There might also be per-CU, clock-normalized performance improvements, but those tend to be very minor (anything above 10% is very unusual). And a 10% increase on unusably slow 3D performance will still be unusably slow 3D performance. "This product has a new architecture" is not equal to "this product is meant for high performance", and the iGPU in Ryzen 7000 (non-G/non-APU) has never been meant to be high performance.

 

[Logoffon]

Can AMD just embed their fonts to PowerPoint slides already? The presence of Calibri simply makes everything looks rather illegitimate.

 

[MarsM4N]

I'm with you, but not even Goddess Kali can cross that many fingers to make it happen lol jk
They will release in 6 months a $349 part with nearly 10% faster 1080p gaming performance than 7950X, effectively killing all the other Zen4 processors regarding the vast majority of gamers?
(according to AMD 7950X is only 5.7% faster than 7600X at 1080p high (less in Ultra settings), ***AMD claims 7950X is 11% faster than 12900K and also claim 7600X is 5% faster than 12900K, all on 1080p high if I'm not mistaken***)

Well, who knows maybe they also bring a 7950X3D? But buying a 7950X for for gaming is like burning money anyways.

 

[ratirt]

-the 5800X3D cannibalizes the entire 7000 lineup in gaming.

I'm sure it will not beat the top sku if you only look at the specs of the chip. The 5800x3d was fast in certain games due to L3 cache increase and reduced latency. 7000 series cpus have also increased L3 cache and latency reduced so if it turns out the 5800x3d is faster a bit it would be only in few scenarios not in general. In general, it will be slower in my opinion.

I wonder how my 5800x will stack against the 7700x. What would be the performance gain in general. It shows around 20%?

 

[Shatun_Bear]

I'm sure it will not beat the top sku if you only look at the specs of the chip. The 5800x3d was fast in certain games due to L3 cache increase and reduced latency. 7000 series cpus have also increased L3 cache and latency reduced so if it turns out the 5800x3d is faster a bit it would be only in few scenarios not in general. In general, it will be slower in my opinion.

I wonder how my 5800x will stack against the 7700x. What would be the performance gain in general. It shows around 20%?

The lowest SKU, the 7600X, is apparently 5% faster than the 12900K, which according to TPU, is within 1% of the 5800X3D.

 

[Max(IT)]

Lol, this was a fun read given that I posted this all of 13 minutes ago:

I agree that this is a bad development, but sadly it's likely necessary for them to keep competing against Intel's 125W TDP SKUs - which, for reference, have equally misleading TDPs compared to power consumption. As has been repeated a million times in a million places, TDP is not and has never been meant to be equal to power consumption. That's just not what that number denominates, and it never has been, so calling it "lying" is just hyperbolic nonsense. It's unclear marketing, sure, and it's people conflating one metric for another, but it's nowhere near lying.

No , it is clearly lying, even if maybe is difficult for you to criticize AMD.
Intel TDP is misleading , but at least it is a “real” limitation at their suggested setting (which makes little sense anyway). AMD TDP is just a lie.

Remember, what AMD has launched now is comparable to Intel's initial ADL launch, which was all "125"W parts, with several of them defaulting to a never-ending ~240W boost mode - at Intel's recommended settings. In light of this, AMD's 170W TDP/230W PPT spec is a lot closer to real-world wattage draws. And as with ADL, there'll be lower power SKUs coming - and unlike Intel, Ryzen CPUs have cTDP-down Eco Mode settings baked into them, which can be enabled with a simple BIOS setting if you want it.

I'm very much looking forward to seeing AMD's lower tier 65W CPUs, as well as how these CPUs perform in their (likely 65W TDP/~88W PPT) Eco Mode settings, as that's a lot more interesting to me. But as the PC hardware scene competes on peak performance and benchmark scores, this race towards higher power isn't showing many signs of slowing down, sadly.

when you are using a new node, you are supposed to improve. I’m not expecting raptor lake to consume less than alder lake, based on the same node with more cores, but AMD after 2 years of development is launching new CPUs with the same core numbers, more advanced node and higher power consumption.
No, I’m not impressed at all.
I’m very curious about how much power the 7900X will really consume…

Meh. The 7700X was a late-gen launch with significant price cuts from first-run Ryzen 5000, coming out nearly two years after the initial launch of its architecture. Price comparisons between the two are thus nowhere near like-for-like, rendering them essentially uncomparable. You're right that the naming differs, which begs the question of whether there's a 170W 7800X coming (or if they're saving that tier for a 7800X3D?), or skipping it entirely like with Ryzen 2000. Of course, the 5700X is also a lower-tier TDP part, which further skews comparisons - the 7700X is clearly a top-tier 8c16t part, which the 5700X never was. But then again, naming is ultimately arbitrary, and simply a means of communicating broad rankings and characteristics. The 7700X is very obviously taking over from the 5800X, not the 5700X.

Top tier ? The 7700X still is a 8C/16T CPU, nothing impressive in 2022.
Funny how you think the 5700X is not comparable, while it exactly is the CPU replaced by 7700X, while the 5800X is not.
5800X has the same TDP of 5900X.
7700X has the same TDP of 7600X.
So, again, wrong.

 

[ratirt]

Top tier ? The 7700X still is a 8C/16T CPU, nothing impressive in 2022.
Funny how you think the 5700X is not comparable, while it exactly is the CPU replaced by 7700X, while the 5800X is not.
5800X has the same TDP of 5900X.
7700X has the same TDP of 7600X.
So, again, wrong.

5800x has the same number of cores as 7700x. Can that be also a factor in what it actually replaces?
To follow up with your notion, if hypothetically 7950x 16c32t had a TDP of 105watts like 5800x would it mean it is replacing a 5800x?
And hypothetically, if in the future we would have a 7700x3d with a power 65watts max would it mean it replaces a 5600x since they have the same tdp?

Forgive me but what you are saying makes no sense.

I disagree with 7700x being not impressive just by the sheer number of cores. If what advertised is true it will be a much faster CPU than a 5800x or 5700x. What's the point of having a 5900x with 12 cores when 7700x with 4 cores less can beat it in ST and MT no problem? It is not the number of cores that should be impressive but the performance you get and how those cores are being utilized.
What if, 7700x having less core still beat the 12900K? What would core matter here if it is faster anyway? Adding cores just to add them like ecores (which are not as fast) just to boosts the marketing number of cores just to advertise as such due to competition. That is what Intel did since they could not produce 16c32t desktop CPU based only on pcores. Remember how 10th gen had 10c product and 11th had only 8c? So a number of cores is a relative subject but the performance is what really matters at the end. Of course, putting into consideration the power consumption as well at least for me.
So if you want to know who is wrong here is actually you, because what you are saying makes absolutely no sense.

If by some miracle Intel or AMD came up with a CPU 4c that mops the floor with 12900k or 5950x in St and MT performance across the board in literally every benchmark, would it matter if it was a 4 core part really? The performance is that matter and 1 core's performance is not equal to another. 1800x is an 8c chip and 5800x is an 8c chip. Look at the difference in performance here yet both are 8core 16thread parts.

 

[Valantar]

No , it is clearly lying, even if maybe is difficult for you to criticize AMD.
Intel TDP is misleading , but at least it is a “real” limitation at their suggested setting (which makes little sense anyway). AMD TDP is just a lie.

... what? How is Intel's TDP a "real" limitation? Are you confusing TDP with PL1? 'Cause they are not the same thing, even if the numbers match.

I have absolutely no trouble criticizing AMD - I'd say I do so quite frequently on these forums. You, on the other hand, do seem a bit too eager to do so, as your interpretations here are ... let's say ungenerous at best, focusing solely on perceived weaknesses and negatives and ignoring the positives. That's hardly a fair or balanced view, is it?

when you are using a new node, you are supposed to improve. I’m not expecting raptor lake to consume less than alder lake, based on the same node with more cores, but AMD after 2 years of development is launching new CPUs with the same core numbers, more advanced node and higher power consumption.
No, I’m not impressed at all.
I’m very curious about how much power the 7900X will really consume…

A maximum sustained power of 230W, as that is PPT for 170W AM5 SKUs (from what's been published so far, at least). That's obviously in all-core loads.

As for the rest of what you're saying here: have you perhaps noticed a slight uptick in clock speeds? Like, perhaps, ~1GHz in both ST and MT clocks across the board? Isn't that, even on a new node, a reasonable explanation for an increase in power draw? Remember, TSMC 5nm isn't that much more efficient than 7nm, its biggest gains are in density.

Top tier ? The 7700X still is a 8C/16T CPU, nothing impressive in 2022.

Uhm ... please re-read that sentence again. Here, I'll quote it to help you:

the 7700X is clearly a top-tier 8c16t part

Where, exactly, did I say it was a "top tier part"? Oh, right, said it was a top-tier 8c16t part, in a discussion of variously binned 8c16c parts - i.e. high clocked, high power, not cut down in any way. If your reading comprehension is so weak that you think I was saying this was a top tier SKU among the whole CPU lineup, you really, really need to work on those reading skills.

Funny how you think the 5700X is not comparable, while it exactly is the CPU replaced by 7700X, while the 5800X is not.
5800X has the same TDP of 5900X.
7700X has the same TDP of 7600X.
So, again, wrong.

... and? Is ... uh, I don't know "TDP kinship" with same-gen CPUs somehow a delineation of which previous-gen CPUs they are successors of? You're performing some damn impressive logical gymnastics here, but please stop. The 7700X has the same TDP as the 7800X. The 7700X has clocks so high that there's no reasonable path for a higher clocked 8c16t part in its generation, save a silicon re-spin or other mid-gen refresh. The 7700X launches day 1. All of these are major, defining characteristics that it shares with the 5800X. Compared to the 5700X? It's clocked lower, has a lower TDP, and launched very late in its generation. And, crucially, AMD has a history of using both 7 and 8 as tier indicators for their top-end 8c16t CPUs.

 

[BorisDG]

Those Powerpoint presentations from what I'm remembering wasn't exactly "true" when 5950X was compared to 3950X. So I'll wait for real results.

 

[Valantar]

Those Powerpoint presentations from what I'm remembering wasn't exactly "true" when 5950X was compared to 3950X. So I'll wait for real results.

Anandtech at least confirmed AMD's +19% IPC claims for Zen3 over Zen2, and their promised gaming increases held up too (though there were some notably weird differences depending on the GPU used). I can't find any slide decks from the Zen3 launch, but from TPU's liveblog it was mainly being compared to Intel. Their press release did much of the same. I'm expecting some differences in real-world testing - not least because of different configurations and test scenarios - but over the past few years AMD's CPU performance data has been reasonably reliable overall - for first party data, that is.

Edit: found this slide in Anandtech's live blog from the Zen3 launch event. That's about as concrete as they got with gen-on-gen comparisons (outside of gaming), and it's just four apps with no details on the specific workloads, so it's hardly much to go by outside of broad ballpark numbers.

 

[mb194dc]

Let's see the reviews.

My intuition is they'll be little point in upgrading from prior few gens except for some really narrow use case scenarios for home office use. Like 240hz gaming at 1080p or lower.

Any "normal" user won't be able to tell the difference.

It's in servers and data centers where new EPYC chips can be really useful. They're ultra slow to upgrade or especially change platforms though.

 

[Asni]

@W1zzard Can you please add the 7950x with HT off in you cpu test suite?

 

[Valantar]

Let's see the reviews.

My intuition is they'll be little point in upgrading from prior few gens except for some really narrow use case scenarios for home office use. Like 240hz gaming at 1080p or lower.

Any "normal" user won't be able to tell the difference.

It's in servers and data centers where new EPYC chips can be really useful. They're ultra slow to upgrade or especially change platforms though.

Pretty much, as with nearly all launches, upgrading from the previous - or even second previous - generation just doesn't make much sense overall. And IMO that's not a goal to be working towards either - the longer our hardware stays useful for, the better. It's good that things get faster so that more can be done with them, but we still need to combat our tendency to fetishize hardware for its own sake - that just drives monetary waste, environmental waste, general overconsumption, and has a bunch of knock-on effects, none of which are particularly good.

 

[BorisDG]

Let's see the reviews.

My intuition is they'll be little point in upgrading from prior few gens except for some really narrow use case scenarios for home office use. Like 240hz gaming at 1080p or lower.

Any "normal" user won't be able to tell the difference.

I wonder who will get 10900K++ CPU and play at 1080p. I think most has moved to at least 1440p or more. Imo those CPU are kinda pointless. We need more GPU power at this point.