Monday, March 21st 2022
AMD Announces 3rd Gen EPYC 7003 Processors with 3D Vertical Cache Technology, $4,000 to $8,000
AMD announced the general availability of the world's first data center CPU using 3D die stacking, the 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology, formerly codenamed "Milan-X." Built on the "Zen 3" core architecture, these processors expand the 3rd Gen EPYC CPU family and can deliver up to 66 percent performance uplift across a variety of targeted technical computing workloads versus comparable, non-stacked 3rd Gen AMD EPYC processors.
These new processors feature the industry's largest L3 cache delivering the same socket, software compatibility and modern security features as 3rd Gen AMD EPYC CPUs while providing outstanding performance for technical computing workloads such as computational fluid dynamics (CFD), finite element analysis (FEA), electronic design automation (EDA) and structural analysis. These workloads are critical design tools for companies that must model the complexities of the physical world to create simulations that test and validate engineering designs for some of the world's most innovate products.
"Building upon our momentum in the data center as well as our history of industry-firsts, 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology showcase our leadership design and packaging technology enabling us to offer the industry's first workload-tailored server processor with 3D die stacking technology," said Dan McNamara, senior vice president and general manager, Server Business Unit, AMD. "Our latest processors with AMD 3D V-Cache technology provide breakthrough performance for mission-critical technical computing workloads leading to better designed products and faster time to market."
"Customers' increased adoption of data-rich applications requires a new approach to data center infrastructure. Micron and AMD share a vision of delivering full capability of leading DDR5 memory to high-performance data center platforms," said Raj Hazra, senior vice president and general manager of the Compute and Networking Business Unit at Micron. "Our deep collaboration with AMD includes readying AMD platforms for Micron's latest DDR5 solutions as well as bringing 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology into our own data centers, where we are already seeing up to a 40% performance improvement over 3rd Gen AMD EPYC processors without AMD 3D V-Cache on select EDA workloads."
Leading Packaging Innovations
Cache size increases have been at the forefront of performance improvement, particularly for technical computing workloads relying heavily on large data sets. These workloads benefit from increased cache size, however 2D chip designs have physical limitations on the amount of cache that can effectively be built on the CPU. AMD 3D V-Cache technology solves these physical challenges by bonding the AMD "Zen 3" core to the cache module, increasing the amount of L3 while minimizing latency and increasing throughput. This technology represents an innovative step forward in CPU design and packaging and enables breakthrough performance in targeted technical computing workloads.
Breakthrough Performance
The world's highest performance server processors for technical computing,4 the 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology deliver faster time-to-results on targeted workloads, such as:
In other words, choosing 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology in this deployment would have the environmental sustainability benefit of more than 81 acres of US forest per year in carbon sequestered equivalents.
The full AMD press deck follows:
These new processors feature the industry's largest L3 cache delivering the same socket, software compatibility and modern security features as 3rd Gen AMD EPYC CPUs while providing outstanding performance for technical computing workloads such as computational fluid dynamics (CFD), finite element analysis (FEA), electronic design automation (EDA) and structural analysis. These workloads are critical design tools for companies that must model the complexities of the physical world to create simulations that test and validate engineering designs for some of the world's most innovate products.
"Customers' increased adoption of data-rich applications requires a new approach to data center infrastructure. Micron and AMD share a vision of delivering full capability of leading DDR5 memory to high-performance data center platforms," said Raj Hazra, senior vice president and general manager of the Compute and Networking Business Unit at Micron. "Our deep collaboration with AMD includes readying AMD platforms for Micron's latest DDR5 solutions as well as bringing 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology into our own data centers, where we are already seeing up to a 40% performance improvement over 3rd Gen AMD EPYC processors without AMD 3D V-Cache on select EDA workloads."
Leading Packaging Innovations
Cache size increases have been at the forefront of performance improvement, particularly for technical computing workloads relying heavily on large data sets. These workloads benefit from increased cache size, however 2D chip designs have physical limitations on the amount of cache that can effectively be built on the CPU. AMD 3D V-Cache technology solves these physical challenges by bonding the AMD "Zen 3" core to the cache module, increasing the amount of L3 while minimizing latency and increasing throughput. This technology represents an innovative step forward in CPU design and packaging and enables breakthrough performance in targeted technical computing workloads.
Breakthrough Performance
The world's highest performance server processors for technical computing,4 the 3rd Gen AMD EPYC processors with AMD 3D V-Cache technology deliver faster time-to-results on targeted workloads, such as:
- EDA - The 16-core, AMD EPYC 7373X CPU can deliver up to 66 percent faster simulations on Synopsys VCS, when compared to the EPYC 73F3 CPU.
- FEA - The 64-core, AMD EPYC 7773X processor can deliver, on average, 44 percent more performance on Altair Radioss simulation applications compared to the competition's top of stack processor.
- CFD - The 32-core AMD EPYC 7573X processor can solve an average of 88 percent more CFD problems per day than a comparable competitive 32-core count processor, while running Ansys CFX.
The full AMD press deck follows:
37 Comments on AMD Announces 3rd Gen EPYC 7003 Processors with 3D Vertical Cache Technology, $4,000 to $8,000
I've done some quit math and by the posted prices it looks like the 3D V-cache layer is adding on average around $100 per chiplet, so a theoretical 5900/5950X3D would cost $200 more.
Plus like your said it would make R9s very expensive.
They are still gathering experience on the process. Also, on desktop, most workload will not benefits from the additional cache and could be impacted by the lower clock. Gaming on the other side can benefits from it but i doubt a dual CCD would get way more performance than a 8 core with that.
The thing is it is as fast to do a ram access than accessing the other CCD L3 cache, so it wouldn't help for CCD to CCD communication. I suspect it would only be a tiny fraction faster in some rare game but for most game, unless it clock higher, it wouldn't make any difference. Some of the gain of the R9 series are due to the fact they also clock higher.
And it's expensive for lower sku. this is why it's mostly on Epyc CPU where the margin are super high and the added cost is probably marginal.
And i think it's fine. R7 5800X3D is a tech demo and a place holder while we wait for Zen 4 that will get out soon.
I'm curious to see how much complex emulators like rps3 improve!
AMD can survive without consumer chips, while the opposite is not very likely.Not worth it, and I don't mean in terms of end user price. First of all you have to look at the current 16 core sales to see that it's not a huge market, and then you have Zen4 six months from now, and you need the server chips to keep AMD going. Add maybe ten more factors that we don't know about and you're starting to have picture of which is the right thing to do.
Sell a 5950X3D for five months on a dying platform, and after that point the small number of sold units will start dropping,
or sell Milan-X that has no competition for quite a while and make much more money..Do we really know that? Do you know for sure that all that extra cache is that useful? For some types of engineering, yes, and for a few other things, but there are a lot of other types of work that relies more on GPU's, for instance.
Over and over I see all these comments from people drooling all over that beefy cache, yet none of us knows how useful it is yet. Just wait for reviews.
Also, AMD want's to sell Threadripper PRO's. :D
But, don't underestimate the power of hyping higher numbers!I meant, is there really a market for that kind of chip? Of all Ryzens sold, how many are 16 core? 1 %? 3 %? Out of those 16 cores sold, how many would be used for work in your link where the X3D would be substantially faster? That would most likely be less than 1 %.
So yeah, of course there are benefits to the extra cache, the question is for how many potential buyers? 1 % out of 3 % is maybe not worth a separate SKU, and all the required firmware work to make that chip supported in ALL those motherboards.
If you're studying FEM you don't have to make that kind of advanced analyzing, and if you work with it you'll most likely have better resources available than your desktop for that.
Otherwise the 5800X3D will be a total waste of silicon...
But there's always the PR aspects of having a halo product like the i7-8086K was, for example :)
As for the BIOS support I don't think it would be a big deal, they do have to make a new version for 5800X3D anyway.
We have a saint here. Please less hypocrisy