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 ESTOver the years we have seen various attempts from AMD and Intel to try and help improve storage performance on their mainstream platforms. Because of the solid user experience benefits that solid state storage can bring, these attempts come in two forms: to make the most of a small amount of super-fast storage, or to expand the amount of super-fast storage available. Most attempts at this have been laborious, such as Intel’s caching technology that allows a SSD or 32GB of Optane Memory to act as a quick read/write cache for a rotational drive.
AMD’s latest attempt to boost the storage performance is Enmotus FuzeDrive, a collaborative piece of software that is designed to combine several storage devices into one big disk. The principle is fairly simple: take any combination of rotational hard drive, SATA SSD, NVMe SSD, and even DRAM, and this software will create a single drive that addresses them all. The software and drivers will manage what data goes where for quicker access, rather than it appearing as one big JBOD.
The obvious red flags from the press were about DRAM, which we were told will only act as a read-cache from prepared data taken from the other drives. The other flag was about if one drive in that system fails, whether all the data is lost. The answer was a likely yes, and so the risk of such a system might be in-line with a JBOD array or similar to a RAID-0, but without the predictable speedup a RAID-0 array might bring.
Predictive caching technologies to help speed up read/write access times are, on paper, a good idea. Some SSDs already do this, by having a small amount of fast SLC cache to act as a write buffer, which the controller can then move the data around to empty the cache when the drive is idle. The difference between having something like a controller manage an embedded system and a general software package in play is that the embedded system has to work for a single drive, albeit millions of units. That arrangement is going to be as defined and engineered as much as that SSD vendor wants it to be. For a software package, it has to work across a variety of environments that might be badly configured, or in situations that the software might not be able to identify properly. As the software stretches over three or four different drives, it sounds like a potential failure in the making of one of those drives decides to die.
AMD lists several benefits of FuzeDrive: no Windows reinstall required, drives can be added to the pool at any point, or removed from the pool if sufficient spare space exists. Pools with DRAM added can be configured manually if some more DRAM is needed. AMD lists that in its testing, comparing a 500 GB hard-drive to a system with a Samsung 960 Pro added to the pool, they recorded a 578% faster Adobe Premiere launch, and a 931% faster Adobe Photoshop launch.
I could see FuzeDrive being useful in two particular scenarios: If a user as a small (32-128 GB) NVMe drive and a 1TB SSD/HDD, a single pool can be made. Users with a single large drive (SATA or HDD) could use the software to add DRAM, enabling an automatic RAM disk.
Enmotus FuzeDrive will be available for Ryzen Desktop systems, and will cost $20.
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