Friday, October 16th 2020

AMD Ryzen 5000 Series Features Three Synchronized Memory Clock Domains

A leaked presentation slide by AMD for its Ryzen 5000 series "Zen 3" processors reveals details of the processor's memory interface. Much like the Ryzen 3000 series "Matisse," the Ryzen 5000 series "Vermeer" is a multi-chip module of up to 16 CPU cores spread across two 8-core CPU dies, and a unified I/O die that handles the processor's memory-, PCIe, and SoC interfaces. There are three configurable clock domains that ensure the CPU cores are fed with data at the right speed, and to ensure that the MCM design doesn't pose bottlenecks to the memory performance.

The first domain is fclk or Infinity Fabric clock. Each of the two CCDs (8-core CPU dies) has just one CCX (CPU core complex) with 8 cores, and hence the CCD's internal Infinity Fabric cedes relevance to the IFOP (Infinity Fabric over Package) interconnect that binds the two CCDs and the cIOD (client I/O controller die) together. The next frequency is uclk, or the internal frequency of the dual-channel DDR4 memory controller contained in the cIOD. And lastly, the mclk, or memory clock is the industry-standard DRAM frequency.
The three clock domains, according to AMD, are in a 1:1:1 synchrony, i.e. DRAM SDR clock is the same as uclk and fclk (for example, DDR4-3600 would see the memory real clock, uclk, and fclk run at 1800 MHz. AMD also appears to have increased the fclk limit to 2000 MHz with "Zen 3," so you can run memory clock at up to DDR4-4000 without having to engage the mclk:fclk 1:2 divider, which means DDR4-4000 on "Vermeer" will fetch as much of a real-world performance dividend as DDR4-3800 did for "Matisse." With AMD Ryzen, memory overclocking has been an effective way to improve overall system performance, due to the synchrony between mclk and fclk. and so, noticeable performance improvements can be had up to DDR4-4000, beyond which, you can still engage the divider to push mclk further up.
Sources: VideoCardz, WCCFTech, Tecnopat
Add your own comment

53 Comments on AMD Ryzen 5000 Series Features Three Synchronized Memory Clock Domains

#1
lynx29
omg my brain hurts... just when i thought I was enjoying ram oc'ing...

@1usmus SAVE US ALL WITH A ZEN 3 DRAM CALCULATOR BY END OF YEAR PLEASE!!!! make a patreon dude, i'd gladly throw a fiver your way and im sure a lot of other people would too. MAKE THAT MONEY BUY A JACUZZI yeeeeeeeeeeeee
Posted on Reply
#2
AusWolf
Hopefully also means that DDR4-4000 XMP modules will work with only a flick of a switch in the bios. Fingers crossed!
Posted on Reply
#3
kapone32
I can't believe that I proposed this (on a high level) in a thread yesterday.
Posted on Reply
#4
tabascosauz
lynx29
omg my brain hurts... just when i thought I was enjoying ram oc'ing...

@1usmus SAVE US ALL WITH A ZEN 3 DRAM CALCULATOR BY END OF YEAR PLEASE!!!! make a patreon dude, i'd gladly throw a fiver your way and im sure a lot of other people would too. MAKE THAT MONEY BUY A JACUZZI yeeeeeeeeeeeee
I imagine it's just going to be worked into the existing DRAM calc the same way it supports Zen, Zen+, Zen2 and Threadripper. The calc already supports B-die up to 3866.

There are some timings that are exclusive to AMD or Intel, but the general know-how, important primaries/secondaries, and IC characteristics carry over between the two camps. B-die and Rev.E have been doing plenty of daily stable 4000MT/s+ in the more hardcore memory OCing Intel community; B-die in particular has been doing it since the 8th gen Intel days, since each generation of Skylake really only improves the memory controller (quite a bit, however). With good B-die, current Comet Lake users are regularly pushing rather close to DDR4-5000 stable, but it does require you to put in the work.

It's the ubiquitous Hynix that has me a bit more concerned, as even recently released "new" CJR/DJR kits generally top out a hair under DDR4-4000, since Hynix does start to struggle at that point with both raw frequency and voltage.
Posted on Reply
#5
lynx29
tabascosauz
I imagine it's just going to worked into the existing DRAM calc the same way it supports Zen, Zen+, Zen2 and Threadripper.

There are some timings that are exclusive to AMD or Intel, but the general know-how, important primaries/secondaries, and IC characteristics carry over between the two camps. B-die and Rev.E have been doing plenty of daily stable 4000MT/s+ in the more hardcore memory OCing Intel community; B-die in particular has been doing it since the 8th gen Intel days, since each generation of Skylake really only improves the memory controller (quite a bit, however). With good B-die, current Comet Lake users are regularly pushing rather close to DDR4-5000 stable, but it does require you to put in the work.

It's the ubiquitous Hynix that has me a bit more concerned, as even recently released "new" CJR/DJR kits generally top out a hair under DDR4-4000, since Hynix does start to struggle at that point with both raw frequency and voltage.
i have 32gb 2x16gb b-die at 3600 cas-14-14-14 overclocked from 3200 14-14-14 --- tightened with dram calculator... going to leave it like that until the calculator gets a zen 3 update. hoping i can get 4000 at cas 16-17-17 at 1:1 - or 17-17-17 at worst... if i have to go to cas 18 or 19... im just gonna stick with 3600 cas 14-14-14
Posted on Reply
#6
kapone32
lynx29
i have 32gb 2x16gb b-die at 3600 cas-14-14-14 overclocked from 3200 14-14-14 --- tightened with dram calculator... going to leave it like that until the calculator gets a zen 3 update. hoping i can get 4000 at cas 16-17-17 at 1:1 - or 17-17-17 at worst... if i have to go to cas 18 or 19... im just gonna stick with 3600 cas 14-14-14
I am for sure preordering the 5600X. This insane. I better get some 4000 MHZ RAM before it jumps higher than it already is.
Posted on Reply
#7
Zach_01
The principal is exactly the same with ZEN2, and if true, the only thing changing is the 3800MHz -->> 4000MHz (2000MHz) upper limit for 1:1:1 synchronization.

And I believe that DRAMcalc will probably need an update for the new 5000. But dont expect it to be updated upon Nov5th. These things need time...
Posted on Reply
#8
lynx29
Zach_01
The principal is exactly the same with ZEN2, and if true, the only thing changing is the 3800MHz -->> 4000MHz (2000MHz) upper limit for 1:1:1 synchronization.

And I believe that DRAMcalc will probably need an update for the new 5000. But dont expect it to be updated upon Nov5th. These things need time...
www.newegg.com/g-skill-16gb-288-pin-ddr4-sdram/p/N82E16820232968

this is it boys!!!! 4000 cas 15 for $160

mmmm Zen 3 will love that ram right there... I want it so bad... my mobo has QVL with it too... eeeek
Posted on Reply
#10
Nater
Not a lot of options at 2x16Gb though is there..? $254. Extra capacity vs Speed.
Posted on Reply
#12
M00nsun
Notice the "good luck", def going to be silicon lottery dependent just like 3800/1900 was.
Posted on Reply
#13
Zach_01
M00nsun
Notice the "good luck", def going to be silicon lottery dependent just like 3800/1900 was.
I cant say definately, but could be. Or could be better than ZEN2 because now the 7nm node is more mature and final printed silicon is higher quality than ZEN2.

But this is just speculations for both cases. Time will tell...
Posted on Reply
#14
Chrispy_
That bodes well for gaming - FCLK increases had some pretty decent gains on Zen2.

Zen3 6 and 8-core chips probably won't get such a gain from FCLK increases since they'll have a single CCX that doesn't need to use the infinity fabric to communicate with any other CCXs
Posted on Reply
#16
Nater
TheLostSwede
Keep in mind that at least the current Ryzen 3000-series memory controller doesn't seem to like odd CAS latencies, so 15 might be a no go.
Kinda all there is to choose from. Bet it'll do 14 with some voltage anyways.
Posted on Reply
#17
Chrispy_
TheLostSwede
Keep in mind that at least the current Ryzen 3000-series memory controller doesn't seem to like odd CAS latencies, so 15 might be a no go.
I'd forgotten that was a thing.
Any idea why that is, though? I'm no expert when it comes to memory controllers.
Posted on Reply
#18
TheLostSwede
Chrispy_
I'd forgotten that was a thing.
Any idea why that is, though? I'm no expert when it comes to memory controllers.
No idea, I guess it's just the way their memory controller currently works. Maybe they've fixed that too. I guess we'll know soon enough.
Posted on Reply
#19
MxPhenom 216
ASIC Engineer
lynx29
www.newegg.com/g-skill-16gb-288-pin-ddr4-sdram/p/N82E16820232968

this is it boys!!!! 4000 cas 15 for $160

mmmm Zen 3 will love that ram right there... I want it so bad... my mobo has QVL with it too... eeeek
1.5v what in the actual f****

So with Ryzen, is 2 sticks better than 4? I know with Intel systems there isn't really an issue with 4 sticks and running high speeds and lower latency.
Posted on Reply
#20
AusWolf
Just had a quick look... The price difference between 3600 and 4000 MHz RAM is massive (at least here in the UK). Will have to wait for benchmarks to see if it's worth it.
Posted on Reply
#21
Zach_01
MxPhenom 216
1.5v what in the actual f****
Why is this so odd to you? These are probably samsung B-dies that can take up to 2.0V (with cooling of course).
I work mine with 1.45V
MxPhenom 216
So with Ryzen, is 2 sticks better than 4? I know with Intel systems there isn't really an issue with 4 sticks and running high speeds and lower latency.
Less ranks is the right to say. 2 ranks are better than 4 in terms of OC and achieving high speeds. Less ranks = less load to UMC (mem cotroller).
Other than OC if used in stock, 4 ranks may give a slight advantage in performance against same spec sticks with 2 ranks overall.

The way ZEN2 is build it doesnt care too much for high speed memory past the 3200MHz point. Other than memory benchmarks you dont see/feel the difference.
Posted on Reply
#22
kapone32
M00nsun
Notice the "good luck", def going to be silicon lottery dependent just like 3800/1900 was.
I don't think that is fair as I keep saying the only CPU that gives us a glimpse is the 3300X.
Posted on Reply
#23
MxPhenom 216
ASIC Engineer
Zach_01
Why is this so odd to you? These are probably samsung B-dies that can take up to 2.0V (with cooling of course).
I work mine with 1.45V


Less ranks is the right to say. 2 ranks are better than 4 in terms of OC and achieving high speeds. Less ranks = less load to UMC (mem cotroller).
Other than OC if used in stock, 4 ranks may give a slight advantage in performance against same spec sticks with 2 ranks overall.

The way ZEN2 is build it doesnt care too much for high speed memory past the 3200MHz point. Other than memory benchmarks you dont see/feel the difference.
Because with at least Intel IMC, anything really over 1.4v for 24/7 can kill it.
Posted on Reply
#24
Zach_01
MxPhenom 216
Because with at least Intel IMC, anything really over 1.4v for 24/7 can kill it.
Well apples and oranges.
AMD CPUs had the same issue (too much RAM voltage killed the CPU) pre 2010. I killed a Phenom CPU like that and instantly, not in long term.
Posted on Reply
#25
Chrispy_
MxPhenom 216
I know with Intel systems there isn't really an issue with 4 sticks and running high speeds and lower latency.
Ryzen systems can run really high memory speeds too, but the goal is to try and run the Infinity fabric clock at exactly the same speed as the memory.

At Zen2's launch there were LN2 overclockers pushing RAM speeds up well over 5GHz but in doing so they had to decouple the fabric clock (FCLK) and DDR4 clock. Yes, they set frequency records, but no it wasn't actually that much faster because doing so required a halving of the FCLK.

There's nothing to stop you from running DDR4-4666 in an X570 board right now - but nobody does it because although you get extra RAM bandwidth it genuinely doesn't do much for performance and is about as good as much, much cheaper DDR4-3600. If you are running some niche application that needs bandwidth, AM4 isn't the answer - you should just pony up for a Threadripper (or any other quad-channel platform).
Posted on Reply
Add your own comment