Performance Claims of Zen 2

At Computex, AMD announced that it had designed Zen 2 to offer a direct +15% raw performance gain over its Zen+ platform when comparing two processors at the same frequency. At the same time, AMD also claims that at the same power, Zen 2 will offer greater than a >1.25x performance gain at the same power, or up to half power at the same performance. Combining this together, for select benchmarks, AMD is claiming a +75% performance per watt gain over its previous generation product, and a +45% performance per watt gain over its competition.

These are numbers we can’t verify at this point, as we do not have the products in hand, and when we do the embargo for benchmarking results will lift on July 7th. AMD did spend a good amount of time going through the new changes in the microarchitecture for Zen 2, as well as platform level changes, in order to show how the product has improved over the previous generation.

It should also be noted that at multiple times during AMD’s recent Tech Day, the company stated that they are not interested in going back-and-forth with its primary competition on incremental updates to try and beat one another, which might result in holding technology back. AMD is committed, according to its executives, to pushing the envelope of performance as much as it can every generation, regardless of the competition. Both CEO Dr. Lisa Su, and CTO Mark Papermaster, have said that they expected the timeline of the launch of their Zen 2 portfolio to intersect with a very competitive Intel 10nm product line. Despite this not being the case, the AMD executives stated they are still pushing ahead with their roadmap as planned.

AMD 'Matisse' Ryzen 3000 Series CPUs
AnandTech Cores
DDR4 TDP Price
Ryzen 9 3950X 16C 32T 3.5 4.7 8 MB 64 MB 16+4+4 3200 105W $749
Ryzen 9 3900X 12C 24T 3.8 4.6 6 MB 64 MB 16+4+4 3200 105W $499
Ryzen 7 3800X 8C 16T 3.9 4.5 4 MB 32 MB 16+4+4 3200 105W $399
Ryzen 7 3700X 8C 16T 3.6 4.4 4 MB 32 MB 16+4+4 3200 65W $329
Ryzen 5 3600X 6C 12T 3.8 4.4 3 MB 32 MB 16+4+4 3200 95W $249
Ryzen 5 3600 6C 12T 3.6 4.2 3 MB 32 MB 16+4+4 3200 65W $199

AMD’s benchmark of choice, when showcasing the performance of its upcoming Matisse processors is Cinebench. Cinebench a floating point benchmark which the company has historically done very well on, and tends to probe the CPU FP performance as well as cache performance, although it ends up often not involving much of the memory subsystem.

Back at CES 2019 in January, AMD showed an un-named 8-core Zen 2 processor against Intel’s high-end 8-core processor, the i9-9900K, on Cinebench R15, where the systems scored about the same result, but with the AMD full system consuming around 1/3 or more less power. For Computex in May, AMD disclosed a lot of the eight and twelve-core details, along with how these chips compare in single and multi-threaded Cinebench R20 results.

AMD is stating that its new processors, when comparing across core counts, offer better single thread performance, better multi-thread performance, at a lower power and a much lower price point when it comes to CPU benchmarks.

When it comes to gaming, AMD is rather bullish on this front. At 1080p, comparing the Ryzen 7 2700X to the Ryzen 7 3800X, AMD is expecting anywhere from a +11% to a +34% increase in frame rates generation to generation.

When it comes to comparing gaming between AMD and Intel processors, AMD stuck to 1080p testing of popular titles, again comparing similar processors for core counts and pricing. In pretty much every comparison, it was a back and forth between the AMD product and the Intel product – AMD would win some, loses some, or draws in others. Here’s the $250 comparison as an example:

Performance in gaming in this case was designed to showcase the frequency and IPC improvements, rather than any benefits from PCIe 4.0. On the frequency side, AMD stated that despite the 7nm die shrink and higher resistivity of the pathways, they were able to extract a higher frequency out of the 7nm TSMC process compared to 14nm and 12nm from Global Foundries.

AMD also made commentary about the new L3 cache design, as it moves from 2 MB/core to 4 MB/core. Doubling the L3 cache, according to AMD, affords an additional +11% to +21% increase in performance at 1080p for gaming with a discrete GPU.

There are some new instructions on Zen 2 that would be able to assist in verifying these numbers.

Ryzen 3000 and EPYC Rome Windows Optimizations and Security
Comments Locked


View All Comments

  • eek2121 - Wednesday, June 19, 2019 - link

    I think what people are getting at is having an L4 Cache. Such a cache would be slower than L3, but would be much faster than DRAM (for now, DDR 5133 was recently demonstrated, that is 2566 MHz double data rate). HBM2 is a prime candidate for that because you can stick 8 Gb on a CPU for $60 and with some engineering work, it would help performance massively. 8 gb could hold practically everything needed in cache. That being said, there are engineering challenges to overcome and I doubt this will ever be a thing.

    Once JEDEC approves RAM running at DDR 5600 at reasonable timings it won’t matter anyway. AMD can simply bump up the IF speed to 1:1 and with shortened RAM traces, performance penalties can be minimized.
  • jamescox - Saturday, June 22, 2019 - link

    For an interposer based Epyc package for the next generation, I would expect perhaps they do an active interposer with all of the external interface transistors in the interposer. They could do similar things with a passive interposer also though. The passive interposer could be an intermediate between Zen 3 and Zen 4. Then they could place a large number of 7 nm+ chiplets on the interposer. As I said, it is hard to speculate, but an option that I thought of based on AdoredTV 15 chiplet rumor would be to have 4 memory controller chips, each one running 2 channels (128-bit) DDR5. Those chips would just be the memory controller logic if on an active interposer and the interfaces to the interposer connections. That isn’t much so at 7 nm and below, they could place massive L4 SRAM caches on the memory controller chips. Current ~75 square mm Zen 2 chiplets have 16 MB plus 8 cpu cores, so it could be a large amount of cache; perhaps something like 64 or 128 MB per chip. It wouldn’t be a cheap device, but AMD’s goal is to get into the high end market eventually.

    The other chiplets could be 1 or two die to manage connections out to the cpu chiplets. This would just be the logic with an active interposer. With a regular interposer, it would need to have the IO transistors also, but the interfaces are quite small. A single infinity fabric switch chip handling all cpu chiplets could provide very low latency. They may have another chip with a switch to tie everything together or they could actually place a couple cpu chiplets on the interposer. Two extra cpu chiplets or one 16 core chiplet could be where the 80 core rumor came from. A possible reason to do that is to allow an HBM based gpu to be mounted on either side. That would make an exceptional HPC product with 16 cores (possible 64 threads if they go to 4 way SMT) and 2 HBM gpus. Another way to get 80 core would be to just make a 3 CCX chiplet with 12 cores. It looks like the Epyc package will not fit all 12 core die though. A mixture of 4 12-core and 4 8-core looks like it would fit, but it wouldn’t be symmetric though. That would allow a quick Zen 2+ style upgrade. Desktop might be able to go to 24 cores and Epyc to 80. The confusion could be mixing up a Zen 2+ rumor and a Zen 3 rumor or something like that. The interposer makes a lot of sense for the giant IO die that cannot be easily implemented at 7 nm. The yields probably don’t support that large of die, so you use an interposer and make a bunch of 100 square mm sized die instead.

    I can’t rule out placing HBM on an IO interposer, but due to the latency not really being that much better than off package DRAM, especially at DDR5 speeds, it just doesn’t seem like they would do it.
  • nandnandnand - Sunday, July 7, 2019 - link

    "That being said, there are engineering challenges to overcome and I doubt this will ever be a thing."

    Putting large amounts of DRAM ever closer to the CPU will definitely be a thing:

    Intel is already moving in this direction with Foveros, and AMD is also working on it:

    It doesn't matter how fast DDR5 is. The industry must move in this direction to grab performance and power efficiency gains.
  • AdrianMel - Sunday, June 16, 2019 - link

    I would like these AMD chips to be used on laptops. It would be a breakthrough in computing power, low consumption. I think that if a HBM2 memory or a larger memory is integrated into the processor, I think it will double the computing power. It would be a study and implementation of 2 super ports, the old expresscard 54 in which we can insert 2 video cards in laptops
  • nandnandnand - Sunday, July 7, 2019 - link

    AMD needs to put out some 6-8 core Zen 2 laptop chips.
  • peevee - Monday, June 17, 2019 - link

    Does it mean that AVX2 performance doubles compared to Zen+? At least on workloads where data for the inner loop fits into L1D$ (hierarchical dense matrix multiplication etc)?
  • peevee - Monday, June 17, 2019 - link

    "AMD manages its L3 by sharing a 16MB block per CCX, rather than enabling access to any L3 from any core."

    Does it mean that for code and shared data caches, 64MB L3 on Ryzen 9 behaves essentially like 16MB cache (say, all 12/16 cores run the same code as it usually is in performance-critical client code and not 4+ different processes/VMs in parallel)? What a waste it is/would be...
  • jamescox - Saturday, June 22, 2019 - link

    The caches on different CCXs can communicate with each other. In Zen 2, those one the same die probably communicate at core clock rather than at memory clock; there is no memory clock on the cpu chiplet. The speeds between chiplets have essentially more than doubled the clocks vs. Zen 1 and there is a possibility that they doubled the widths also. There just about isn’t any way to scale to such core counts otherwise.

    An intel monolithic high core count device will have trouble competing. The latency of their mesh network will go up with more cores and it will burn a lot of power. The latency of the L3 with a mesh network will be higher than the latency within a 4-core CCX. Problems with the CCX architecture are mostly due to OS scheduler issues and badly written multithreaded code. Many applications performed significantly better on Linux compared to windows due to this.

    The mesh network is also not workable across multiple chiplets. A 16-core (or even a 10 core) monolithic device would be quite large for 10 nm. They would be wasting a bunch of expensive 10 nm capacity on IO. With the large die size and questionable yields, it will be a much more expensive chip than AMD’s MCM. Also, current Intel chips top out at 38.5 MB of L3 cache on 14 nm. Those are mostly expensive Xeon processors. AMD will have a 32 MB part for $200 and a 64 MB part for $500. Even when Intel actually gets a 10 nm part on the desktop, it will likely be much more expensive. They are also going to have serious problems getting their 10 nm parts up to competitive clock speeds with the 14 nm parts. They have been tweaking 14 nm for something like 5+ years now. Pushing the clock on their problematic 10 nm process doesn’t sound promising.
  • peevee - Monday, June 17, 2019 - link

    "One of the features of IF2 is that the clock has been decoupled from the main DRAM clock....

    For Zen 2, AMD has introduced ratios to the IF2, enabling a 1:1 normal ratio or a 2:1 ratio that reduces the IF2 clock in half."

    I have news for you - 2:1 is still COUPLED. False advertisement in the slides.

    And besides, who in their right mind would want to halve IF clock to go from DDR3200 to even DDR4000 (with requisite higher timings)?
  • BMNify - Saturday, June 22, 2019 - link

    the only real world test that matters in the UHD2/8K Rec. 2020/BT.2020 LIVE NHK/bbc broadast of the 2020 Summer Olympics will begin on Friday, 24 July and related video streams is can AMD Zen 2 do it can any pc core do realtime x264/x265/ffmpeg software encoding and x264/x265 compliant decoding (notice how many hw assisted encoders today dont decode to spec as seen when you re-enode them with the latest ffmpeg), how many 8k encodes and what overheads are remaining if any can even do one...

Log in

Don't have an account? Sign up now