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
iwod - Monday, January 8, 2018 - link
Does Vega 7nm necessarily means GF though? I thought the drop of Vega 12nm+ make sense as it would be competing with Ryzen for GF capacity. Given how AMD is doing well and should be even better now when Meltdown is on Intel.I would have thought moving Radeon back to TSMC would be a much better choice.
Outlander_04 - Tuesday, January 9, 2018 - link
TSMC ? Why?It would also mean higher costs for AMD
Holliday75 - Tuesday, January 9, 2018 - link
Just a guess, but based off his comment he suggested that Radeon would be competing for fab space at GF. If reduced capacity for Zen cuts into profits then the extra costs to move might be worth it.Just basing this off of his comment.
Stuka87 - Monday, January 8, 2018 - link
I sure hope Dell comes out with a Precision laptop with AMD stuff. The Inspirons share a lot with the Precisions.Dragonstongue - Monday, January 8, 2018 - link
so it sounds like a "refresh" to RX 500 series which was claimed for 2018 is not happening, that sucks TBH..need a new GPU and many of the "good" RX 570-580s are out of stock or low in stock ballooning their prices, need replace my 7870 sometime soon, 460/560 will not cut it, and spending ~$80 more than should is a no go for me to replace it. 1280 shader 256 bit bus with a bump in ROP/TMU at 170w maximum (heavily overclocked) 7870 was THE "mainstream" performance card for its generation, have not seen AMD nor Nv release one that is "comparable" either higher performance (higher price) or less performance (similar price) but nothing to supplant it really.
Good news though, just shows that Zen+ (12nm) is/was not Zen2 (was always to be on 7nm) which I told off many a 3rd party "review" site claiming it would be ^.^
Sttm - Monday, January 8, 2018 - link
The GPU roadmap is so sad. AMD barely has a GPU that can top the GTX1080 I bought Summer 2016, and won't have a truly superior offering until 2019.My only hope of a proper upgrade is now Volta, and Nvidia will have no reason not to price gouge with this pathetic competition!
Arbie - Monday, January 8, 2018 - link
@Sttm - I'm also sorry that AMD's graphics wasn't a win in 2017. But I wonder what games you could possibly find good enough to warrant moving "up" from a 1080? The tiny increase in quality or FPS would only be meaningful - maybe - on a game you love that has top-notch graphics AND doesn't look good enough on your current card. I only wish there was something even close to that for me.gerz1219 - Thursday, February 1, 2018 - link
Plenty of modern games play somewhat smoothly at 4K on a 1080 Ti, but could use a bump up in fps. Once you see 4k gaming, it's kind of hard to unsee, which is why I haven't bothered to buy a 1440p gaming panel to complement my professional panel. I'd gladly pay another $700 + the cost of a 4K Gsync/Freesync monitor next year to upgrade the 1080 Ti to something that can crush any game at 4K, but it doesn't look like that product will hit the market in 2019 because AMD is so far behind, and everyone's making tons of money selling GPUs for crypto.sld - Monday, January 8, 2018 - link
Those who buy price gouging items walk into it willingly. Gsync vs Freesync, for example.Santoval - Monday, January 8, 2018 - link
I hope you'll get better soon Ian. I don't think I would be able to type a single sentence if I were in your shoes, I have to admit am impressed by your resilience.