Monday, August 29th 2022
AMD Announces Ryzen 7000 Series "Zen 4" Desktop Processors
AMD today announced the Ryzen 7000 series "Zen 4" desktop processors. These debut the company's new "Zen 4" architecture to the market, increasing IPC, performance, with new-generation I/O such as DDR5 and PCI-Express Gen 5. AMD hasn't increased core-counts over the previous-generation, the Ryzen 5 series is still 6-core/12-thread, the Ryzen 7 8-core/16-thread, and Ryzen 9 either 12-core/24-thread, or 16-core/32-thread; but these are all P-cores. AMD is claiming a 13% IPC uplift generation over generation, which coupled with faster DDR5 memory, and CPU clock speeds of up to 5.70 GHz, give the Ryzen 7000-series processor an up to 29% single-core performance gain over the Ryzen 5000 "Zen 3."
At their press event, AMD showed us an up to 35% increase in gaming performance over the previous-generation, and an up to 45% increase in creator performance (which is where it gets the confidence to stick to its core-counts from). The "Zen 4" CPU core dies (CCDs) are built on the TSMC 5 nm EUV (N5) node. Even the I/O die sees a transition to 6 nm (N6), from 12 nm. The switch to 5 nm gives "Zen 4" 62 percent lower power for the same performance, or 49% more performance for the same power. versus the Ryzen 5000 series on 7 nm. The "Zen 4" core along with its dedicated L2 cache is 50% smaller, and 47% more energy efficient than the "Golden Cove" P-core of "Alder Lake."
The "Zen 4" CPU core gets a bulk of its 13% IPC gain from the core's front-end, followed by load-store, branch-prediction, and execution engine. The company also doubled the size of the per-core L2 cache to 1 MB. The core introduces support for AVX-512 instruction set. Eight cores share a 32 MB L3 cache on a CCD. The 6-core and 8-core SKUs in the Ryzen 5 and Ryzen 7 series, come with a single CCD, whereas the 12-core and 16-core Ryzen 9 parts come with two.
AMD introduces a brand new socket with Ryzen 7000, Socket AM5. This is a resilient 1718-pin LGA, with the ability to delivery up to 230 W of power, and comes with next-generation I/O that includes DDR5 and PCIe Gen 5. Physically, the coolers are compatible with Socket AM4 thermal solutions, so you can carry over your old coolers. AMD is promising to launch future generations of Ryzen processors that are AM5-compatible going up to 2025 at least.
There will be four chipset choices with Ryzen 7000, these include the X670E and X670 in the high-end; and the B650 and B650E in the mid-range. Motherboards with X670/E debut in September, and the B650/E in October. AM5 is the first platform with CPU-attached NVMe Gen 5, and the company predicts the first Gen 5 SSDs should arrive by November. We confirmed with AMD that they are not artificially limiting the performance of processors running on the B-Series chipsets vs the X-Series chipsets. The difference between B650 and B650E is that B650E offers support for PCIe Gen 5 for graphics cards and SSDs, while B650 non-E supports PCIe 5.0 SSDs, and PCIe 4 GPUs. AMD is introducing a new memory profile technology called EXPO that eases memory overclocking. It is a royalty-free technology, and includes memory settings specific to the AMD architecture. You are of course able to use Intel XMP-compatible DDR5 memory modules, these might just not have the most perfect settings out of the box. As many as 15 memory kits are being launched at speeds of up to DDR5-6400, from various manufacturers.
The AMD Ryzen 5 7600X is a 6-core/12-thread processor with 4.70 GHz nominal clocks. up to 5.30 GHz boost, 105 W TDP, and is being launched at $299. The Ryzen 7 7700X is 8-core/16-thread, clocked at 4.50 GHz, with up to 5.40 GHz boost, 105 W TDP, and is being launched at $399. The Ryzen 9 7900X is 12-core/24-thread, clocked at 4.70 GHz, with up to 5.60 GHz, 170 W TDP, and is being launched at $549. The top 7950X is 16-core/32-thread, clocked at 4.50 GHz, with up to 5.70 GHz boost, 170 W TDP, launching at $699. All SKUs available to purchase on September 27, 2022. This is an on-shelf date, not a preorder date (we have that confirmed personally).
The complete slide-deck follows.
At their press event, AMD showed us an up to 35% increase in gaming performance over the previous-generation, and an up to 45% increase in creator performance (which is where it gets the confidence to stick to its core-counts from). The "Zen 4" CPU core dies (CCDs) are built on the TSMC 5 nm EUV (N5) node. Even the I/O die sees a transition to 6 nm (N6), from 12 nm. The switch to 5 nm gives "Zen 4" 62 percent lower power for the same performance, or 49% more performance for the same power. versus the Ryzen 5000 series on 7 nm. The "Zen 4" core along with its dedicated L2 cache is 50% smaller, and 47% more energy efficient than the "Golden Cove" P-core of "Alder Lake."
The complete slide-deck follows.
195 Comments on AMD Announces Ryzen 7000 Series "Zen 4" Desktop Processors
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.Wrong.
There is no “7800X” yet.
The 5700X was released at $299, so this is nominally a gen-over-gen RAISE.
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.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.
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.
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 :)
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.
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.
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***)
I wonder how my 5800x will stack against the 7700x. What would be the performance gain in general. It shows around 20%?
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.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…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.
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.
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?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.Uhm ... please re-read that sentence again. Here, I'll quote it to help you: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.... 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.
Edit: foundthis 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.
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.