AMD Tech Day at CES: 2018 Roadmap Revealed, with Ryzen APUs, Zen+ on 12nm, Vega on 7nm
by Ian Cutress on February 1, 2018 8:45 AM ESTRyzen APU Overclocking: A Focus on Memory Support
Also part of the demonstration about the new APUs was overclocking. For a number of years, AMD has hired Sami Makkinen, a well-known former world-record holder in various overclocking categories, to help tune the overclocking on some of its processors. So despite this being an integrated graphics platform, Sami was on hand to show the day-to-day overclocking potential. I was told that liquid nitrogen overclocking might be held at a later date…
Nonetheless, we were shown the system that would be distributed to reviewers for launch day: a mini-ITX motherboard, a Ryzen 5 2400G processor, 2x8 GB of DDR4 memory, and an AMD Wraith cooler. Using the popular benchmarking tool 3DMark Fire Strike, Sami showed a 39% increase over stock performance by overclocking only the memory and the integrated graphics:
- DDR4-2400 + 1250 MHz GPU: 2911 Points - 'stock'
- DDR4-3200 + 1250 MHz GPU: 3322 Points (+14%)
- DDR4-3200 + 1550 MHz GPU: 3596 Points (+24%)
- DDR4-3600 + 1675 MHz GPU: 4048 Points (+39%)
This shows a couple of interesting data points. First, that the DRAM speed directly influences the results a lot: the 14% gain moving to DDR4-3200 and a similar gain again up to DDR-3600 means that we are still dealing with a graphics system that is memory bandwidth limited, even with only 11 compute units. The Infinity Fabric communication pathways are tied to the DRAM speed, so these would also get a speed up – when asked if it would be possible to discern how much of the speedup is due to a pure DRAM improvement and how much from the Infinity Fabric boost, I was told that AMD could do it in house, but it would be impossible for consumers to do.
However, the DRAM speed gains match up with what we have seen with previous generations of AMD APUs, but also it means that Intel’s decision to combine a Vega GPU with high-bandwidth memory is going to be the way forward in this market.
The second point that this data brings is about memory support. One of the major criticisms of AMD’s initial launch of Ryzen was the lack of high-performance memory support, due to a young firmware. AMD has stated that the Ryzen with Vega graphics line of processors have better memory support with newer firmware revisions, capable of driving higher memory speeds. This is, of course, important to APUs. Additional updates will be coming with the new X470 motherboards in Q2.
Facebook
Twitter
RSS
131 Comments
View All Comments
mikabr - Monday, January 8, 2018 - link
What is the status of thunderbolt and AMD today? Can Apple or similar manufacturer take AMD parts and create something that does the same thing as a Macbook pro or iMac today, with thunderbolt ports that has the same functionality as todays Intel based offerings?A5 - Monday, January 8, 2018 - link
In theory, the TB controller is just a hunk of silicon hanging off the PCIe bus. But the fact that Intel is the only manufacturer is a probably an issue.Space Jam - Monday, January 8, 2018 - link
Maybe I haven't been paying attention but i've just started to notice how low quality images on this site actually are, though especially in this article. That image of Lisa Su looks like its from an early 2000s budget digital camera using digital zoom. Why are the slideshow caps horrendously compressed JPEGs?Get well soon Ian.
Ian Cutress - Monday, January 8, 2018 - link
Click through for full resolution.jjj - Monday, January 8, 2018 - link
Vega on 7nm is likely very bad news if it's more than this SKU targeted at machine learning as it implies that Navi is very late and AMD stays utterly uncompetitive in GPU.haukionkannel - Thursday, February 1, 2018 - link
And if Vega7 is small chip. It may be used in self driving cars and other small for factor special cases where the price is not so big problem.wr3zzz - Monday, January 8, 2018 - link
Can mobile Ryzen go down to 4.5W TDP for fanless designs?st_7 - Monday, January 8, 2018 - link
@Ian Cutress. looks like a typo in this line "The Ryzen 5 2200U is the only dual core component in AMD’s entire Ryzen product line", I think it should be "The Ryzen 3 2200U".And also is there any information, if AMD planning to release mobile processors which can go against Intel HQ line of mobile/laptop processors, presuming that these 'U' processors are pitted against Intel 'U' processors. Or these 'U' processors from the AMD are the only mobile/laptop class processors that we gonna see from AMD in the next year or two.
jjj - Monday, January 8, 2018 - link
- so few mobile SKUs, why no 45W SKUs, no 11CU SKUs- so few desktop APU SKUs and what do they have above 170$ and maybe bellow 100$
- Vega on 7nm in 2019 while Navi also in 2019, area you certain that Navi+ is 2020 or is that an assumption, because if seems that if Vega on 7nm goes everywhere, Navi can't be 2019 and Naxi+ wouldn't be 2020
- 7nm+ being a second gen 7nm is your assumption or AMD stated that. in theory could be what comes after 7nm so 5nm
- where are the 150-250$ new gen GPUs, I get that they are too lazy to meet demand with the current ones but perf per $ is atrocious and they'll kill gaming at this pace
- being surprise that Zen 2 is done is odd, AMD might have Epyc 2 on 7nm in late 2019 so ofc the core is done. And ofc , with that in mind, when you say Zen 2 2019, in consumer at least as server could be different
- where is a Rave Ridge refresh in H2 this year? They really don't have one or
- we don't care about efficiency gains with Pinnacle Ridge, we need higher clocks, better memory support, some minimal SoC level gains and maybe same cache changes but we really just need anything from 4.5GHz to 7GHz- where they land in that range defines how open our wallets are. OK we want more PCIe too and if they could support much faster memory, we would even take more then 8 cores.
Anyway, this seems like a rather incomplete roadmap.
jjj - Monday, January 8, 2018 - link
And why so few RR system and mostly 15 in and up