Ryzen 3000 Memory / Fabric (X370/X470/X570) - Overclock.net - An Overclocking Community

Forum Jump: 

Ryzen 3000 Memory / Fabric (X370/X470/X570)

Reply
 
Thread Tools
post #1 of 287 (permalink) Old 07-08-2019, 05:08 AM - Thread Starter
New to Overclock.net
 
elmor's Avatar
 
Join Date: Mar 2014
Posts: 836
Rep: 335 (Unique: 147)
Ryzen 3000 Memory / Fabric (X370/X470/X570)

This is a brief summary with limited testing to highlight changes to memory and fabric behavior on Zen 2 (Matisse).

As you've probably seen, Ryzen 3000 is capable of much higher memory speeds than previous generations. The main reason for this is added circuitry on-chip that allows running the memory clock (MCLK) asynchronous from the fabric clock (FCLK). While this enables higher memory frequency, it also increases access latency because the data travelling across different frequency domains has to be synchronized.

The below tests try to answer the following questions:

  • How high memory frequency can be expected with Ryzen 3000 on X370/X470/X570?
  • How high fabric clock can be expected?
  • Is there a benefit to high memory frequency and high fabric clock?
  • How big is the latency penalty when running MCLK != 2*FCLK?

An issue with these tests is that BIOS releases are at this time very unpolished. There are new AGESA versions and patches released frequently which board vendors struggle to keep up with. Especially X370 and X470 versions are problematic for memory overclocking. Both the AMD memory initialization method and vendor DRAM settings seem not to not be working or lack tuning. At best these tests will be able to hint at how things will be for end users.

CPUs

  • Ryzen 5 3600X
  • Ryzen 9 3900X

Motherboards

  • ROG Crosshair VI Hero (X370) BIOS 7106 AGESA 1.0.0.2
  • ROG Crosshair VII Hero (X470) BIOS 2406 1.0.0.2
  • ROG Crosshair VIII Formula (X570) BIOS 7702 1.0.0.3

Memory kits

  • Gskill F4-3200C14D-16GTR (2x8GB Samsung B Single-Rank)

Settings

  • CPU: Default in RamTest, 4.0G 1.25V in AIDA64 tests
  • SOC Voltage: 1.25V
  • DRAM Voltage: 1.40V (DRAM Boot Voltage = 1.40V)
  • Timings CL16: 16-16-16-16-45-1T-GD En
  • Timings CL18: 18-18-18-18-45-1T-GD En


Issues

  • C6H 7106: DRAM Voltage at the beginning of POST is always 1.200V which limits the max memory frequency. It's possible to work around by first booting with lower DRAM Frequency and higher voltage, then only increasing DRAM Frequency in steps without the board shutting down.
  • C7H 2406: DRAM Vboot is always 1.200V by default, it can be manually set instead. However the setting is lost after standby power is removed from the motherboard.
  • C6H 7106 + C7H 2406: After failing memory overclocking you get stuck at C5 POST code which never seems to recover. The only way to get back is to clear CMOS.

Results and discussion



This shows the highest DRAM Frequency that would pass 100% in RamTest with 2x8GB Samsung B-die. 1.25V SOC and 1.40V DRAM Voltage was used in all cases. These settings are not considered 100% stable and are only an indicator of what's possible without much tuning. I plan to test and update with additional configurations but am currently lacking the time. Above 4000 MHz with 2x16GB has been demonstrated on C8F. The tests were completed at 1733 MHz FCLK, anything higher would cause stability issues. Up to 1900 MHz FCLK is possible on some chips, which will depend on the chip quality. Adjusting SOC and VDDG voltages may help to stabilize higher speeds. The C7H was getting surprisingly close to the C8F, both using "Daisy Chain" memory layout topology. The C6H with its "T" topology is doing much worse, likely because of less time spent tuning signaling parameters at this point. These numbers are expected to improve with the next couple of BIOS releases.





3600X / 1xCCD

Setting MCLK = 2*FCLK (1:1) yields by far the highest read bandwidth at FCLK / MCLK = 1800 / 3600. Increasing DRAM Frequency by one step to 3666 MT/s while keeping the fabric at 1800 MHz reveals the penalty when using asynchronous clock domains. The read bandwidth immediately drops 1.7 GB/s. At higher memory speeds and CAS Latency, it can be seen how fabric and memory clocks scale. Increasing DRAM Frequency from 4266 MT/s to 4333 MT/s at the same 1733 MHz fabric clock doesn't increase read bandwidth. Instead with DRAM Frequency fixed at 4333 MT/s, increasing FCLK from 1733 MHZ to 1800 MHz immediately shows a gain of 1.6 GB/s.

3900X / 2xCCD

With 2xCCD read bandwidth is no longer penalized in asynchronous mode but keeps scaling with both fabric and memory clock.





3600X / 1xCCD

Due to Infinity Fabric redesign between CCD and IOD the memory write bandwidth is half on CPUs with 1xCCD (<=8C) compared to previous generations (see https://hexus.net/tech/reviews/cpu/1...ryzen-7-3700x/). This is clearly reflected in these results, where the bandwidth only seem to depend on the fabric speed.

3900X / 2xCCD

As expected with 2xCCD write bandwidth is approximately doubled. Similarly to the read bandwidth scenario, asynchronous mode does not longer seem to reduce the write bandwidth.





3600X / 1xCCD

Moving away from synchronous memory/fabric clocks doesn't hurt copy bandwidth by much, and it seems to scale nicely both with increased memory and fabric speeds.

3900X / 2xCCD

Copy bandwidth gets a nice boost from the increased write bandwidth with 2xCCD.





As mentioned in AMD's own presentation, the main issue with asynchronous clock domains is the latency penalty. Changing settings from 1800 / 3600 synchronous to 1800 / 3666 asynchronous increases latency by over 10 ns. The difference is slowly reduced as memory and fabric clocks are increased, but never fully recovers.


Summary

  • X370/X470 BIOS is still immature when using Ryzen 3000 (depending on the board)
  • Highest achieved memory frequency was 4333 MT/s on X570, 4200 MT/s on X470 and 3666 MT/s on X370. The results will most likely get closer with BIOS updates.
  • Fabric clock target 1700-1900 MHz
  • Memory latency penalty ~10ns when moving from synchronous to asynchronous memory/fabric clock, which can be reduced by further increasing memory frequency
  • Highest possible fabric clock with memory synchronized (MCLK = 2*FCLK) yields the highest read bandwidth and lowest latency with 1xCCD
  • Write bandwidth only scales with fabric clock with 1xCCD
  • Copy bandwidth benefits from both memory and fabric clock, and is not hurt much by increased latency
  • 2xCCD read, write and copy bandwidth keeps scaling with both memory and fabric clock without being hurt by asynchronous mode. In this case, it comes down to choosing between lower latency or higher bandwidth.

Bonus: PCI-E Gen4 test on X470

With the current available C7H BIOS 2406, PCI-E Gen 4 will work with any PCI-E Gen 4 device connected to the CPU PCI-E lanes without any changes to BIOS settings. Just plug the device and install the driver. Similarly a PCI-E Gen 4 NVMe drive plugged in the CPU M.2-slot should work at Gen 4. The conclusion is that at least on AGESA 1.0.0.2, PCI-E Gen 4 is not actively blocked on non-X570 motherboards. If it will work on your board or in specific slots will be down to the board layout. The closer the slot is to the CPU (shorter trace length) the higher the chance of success. Increased PCB layer count and lack of PCI-E switches will also increase the chance of success.

Proof of concept with Radeon 5700XT:



edit: Added detailed settings
edit2: Added note about 1/2 CCD configurations and write bandwidth
edit3: Added 3900X results and PCI-E Gen 4 test on X470
Attached Thumbnails
Click image for larger version

Name:	1DPC SR DRAM Frequency.png
Views:	1333
Size:	21.2 KB
ID:	278488  

Click image for larger version

Name:	Read Bandwidth FCLK _ MCLK.png
Views:	172
Size:	20.7 KB
ID:	278490  

Click image for larger version

Name:	Write Bandwidth FCLK _ MCLK.png
Views:	129
Size:	20.2 KB
ID:	278492  

Click image for larger version

Name:	Copy Bandwidth FCLK _ MCLK.png
Views:	141
Size:	20.9 KB
ID:	278494  

Click image for larger version

Name:	Memory Latency FCLK _ MCLK.png
Views:	152
Size:	19.6 KB
ID:	278496  


Last edited by elmor; 07-10-2019 at 01:09 PM.
elmor is offline  
Sponsored Links
Advertisement
 
post #2 of 287 (permalink) Old 07-08-2019, 05:21 AM
Realist
 
chakku's Avatar
 
Join Date: Mar 2016
Posts: 375
Rep: 3 (Unique: 3)
Quote:
Above 4000 MHz with 2x16GB has been demonstrated on C8F.
By demonstrated do you mean observed by those who were testing it or has it been published online somewhere? Would personally love to see more on this as I have my finger crossed on getting my 2x16GB B-Die kit to 3600 on the new processors with the C7H.

Also glad to see a post from yourself again!

PC
(19 items)
CPU
AMD Ryzen R7 3700X
Motherboard
ASUS ROG Crosshair VII Hero (Wi-Fi)
GPU
ASUS ROG Strix GTX 1080 Ti OC
RAM
G.Skill Ripjaws V F4-3200C14D-32GVK
Hard Drive
Samsung 970 Pro 512GB NVMe
Hard Drive
Samsung 860 EVO 1TB
Hard Drive
STOREMI (Intel 730 Series 240GB + Hitachi Ultrastar 7K4000 4TB)
Power Supply
EVGA SuperNOVA 850 P2
Cooling
Noctua NH D15 SE-AM4
Case
Phanteks Enthoo Evolv X Satin Black
Operating System
Windows 10 Pro 1809 64-bit
Monitor
Dell P2715Q
Monitor
Dell P2715Q
Keyboard
Topre Realforce 87U 55g Uniform (Norbaforce/BT-500 Bluetooth)
Mouse
Logitech G Pro Wireless
Mousepad
Artisan Hayate Kou
Audio
Benchmark DAC2 HGC
Audio
JBL LSR305
Audio
Sennheiser HD6XX
▲ hide details ▲
chakku is offline  
post #3 of 287 (permalink) Old 07-08-2019, 05:31 AM - Thread Starter
New to Overclock.net
 
elmor's Avatar
 
Join Date: Mar 2014
Posts: 836
Rep: 335 (Unique: 147)
Quote: Originally Posted by chakku View Post
By demonstrated do you mean observed by those who were testing it or has it been published online somewhere? Would personally love to see more on this as I have my finger crossed on getting my 2x16GB B-Die kit to 3600 on the new processors with the C7H.

Also glad to see a post from yourself again!
I've seen it myself, though it was at benchmark settings with high memory voltage. See below. I would have tested it, but one of the sticks in my Dual-Rank kit didn't want to play along.

edit: Booted up the system with one stick and works with 4000CL18 1.4V. But it's not 100% stable.

edit2: MSI lists the 4000 MT/s 2x16GB kit CMT32GX4M2K4000C19 in their QVL: https://www.msi.com/Motherboard/supp...support-mem-19

edit3: Similarly Asus lists a 4000 MT/s 4x8GB kit CMK32GX4M4K4000C19 in their QVL: https://dlcdnets.asus.com/pub/ASUS/m...Memory_QVL.pdf . I believe the "Spectek" listing in the Asus QVL refers to Micron E-die.
Attached Thumbnails
Click image for larger version

Name:	4000dr.png
Views:	238
Size:	502.6 KB
ID:	278500  

Click image for larger version

Name:	4000_dr_sc.png
Views:	278
Size:	191.2 KB
ID:	278506  


Last edited by elmor; 07-08-2019 at 05:50 AM.
elmor is offline  
Sponsored Links
Advertisement
 
post #4 of 287 (permalink) Old 07-08-2019, 05:44 AM
Realist
 
chakku's Avatar
 
Join Date: Mar 2016
Posts: 375
Rep: 3 (Unique: 3)
Quote: Originally Posted by elmor View Post
I've seen it myself, though it was at benchmark settings with high memory voltage. See below. I would have tested it, but one of the sticks in my Dual-Rank kit didn't want to play along.

edit: Booted up the system with one stick and works with 4000CL18 1.4V. But it's not 100% stable.
Looks very promising! Also yeah can't imagine the voltage you'd need for 4000+ at CL12 is usable daily.

Do you still need GDM enabled for dual rank sticks or do they play better with true 1T command rates on the new IMC?

PC
(19 items)
CPU
AMD Ryzen R7 3700X
Motherboard
ASUS ROG Crosshair VII Hero (Wi-Fi)
GPU
ASUS ROG Strix GTX 1080 Ti OC
RAM
G.Skill Ripjaws V F4-3200C14D-32GVK
Hard Drive
Samsung 970 Pro 512GB NVMe
Hard Drive
Samsung 860 EVO 1TB
Hard Drive
STOREMI (Intel 730 Series 240GB + Hitachi Ultrastar 7K4000 4TB)
Power Supply
EVGA SuperNOVA 850 P2
Cooling
Noctua NH D15 SE-AM4
Case
Phanteks Enthoo Evolv X Satin Black
Operating System
Windows 10 Pro 1809 64-bit
Monitor
Dell P2715Q
Monitor
Dell P2715Q
Keyboard
Topre Realforce 87U 55g Uniform (Norbaforce/BT-500 Bluetooth)
Mouse
Logitech G Pro Wireless
Mousepad
Artisan Hayate Kou
Audio
Benchmark DAC2 HGC
Audio
JBL LSR305
Audio
Sennheiser HD6XX
▲ hide details ▲
chakku is offline  
post #5 of 287 (permalink) Old 07-08-2019, 05:48 AM - Thread Starter
New to Overclock.net
 
elmor's Avatar
 
Join Date: Mar 2014
Posts: 836
Rep: 335 (Unique: 147)
Quote: Originally Posted by chakku View Post
Looks very promising! Also yeah can't imagine the voltage you'd need for 4000+ at CL12 is usable daily.

Do you still need GDM enabled for dual rank sticks or do they play better with true 1T command rates on the new IMC?
~2.0 I've not tested that, but even the SR results above are using the default setting 1T Geardown=Enabled.
elmor is offline  
post #6 of 287 (permalink) Old 07-08-2019, 06:33 AM
Manual breath enabled
 
Streetdragon's Avatar
 
Join Date: Apr 2013
Location: In my celler
Posts: 1,209
Rep: 26 (Unique: 22)
so tldr:
1800/3600 and tight the timings as low as possible?

Gameingcube
(18 items)
CPU
Ryzen 3900X
Motherboard
Aorus X570 Master
GPU
1080 TI Founders Edition
GPU
1080 TI Founders Edition
RAM
F4-3600C16Q-32GTZR
Hard Drive
2000GB Seagate Barracuda Compute ST2000DM008 256MB
Hard Drive
2000GB Seagate Barracuda Compute ST2000DM008 256MB
Hard Drive
samsung m2 970 evo
Power Supply
Leadex 80 Plus Platinum Netzteil, schwarz - 1200 Watt
Cooling
heatkiller IV pro
Cooling
EK-FC1080 GTX Ti - Nickel
Cooling
EK-FC1080 GTX Ti - Nickel
Cooling
Alphacool Eisbecher D5 250mm Plexi
Cooling
Alphacool NexXxoS XT45 Full Copper 480mm
Cooling
XSPC Multiport Radiator EX240
Cooling
Scythe Grand Flex 4Pin PWM
Case
thermaltake core x9
Operating System
Windows 10
▲ hide details ▲
Streetdragon is offline  
post #7 of 287 (permalink) Old 07-08-2019, 08:03 AM
New to Overclock.net
 
VPII's Avatar
 
Join Date: Dec 2014
Location: Hout Bay, Cape Town, South Africa
Posts: 656
Rep: 9 (Unique: 8)
@elmor I noticed on some review that showed the memory performance that the 3900X had double the write speed of the 3700X. Is it possibly to do with 3900X being two chips and thus dual or two IF?

Sent from my SM-G960F using Tapatalk

AMD
(9 items)
CPU
AMD Ryzen 2700X
Motherboard
Asus Crosshair VII Hero
GPU
GALAX RTX 2080 TI OC
RAM
G.Skill f4-3200c14d-16gtzr tridentz rgb
Hard Drive
Crucial MX300 M.2 SSD
Power Supply
Corsair HX1200i
Cooling
CoolerMaster MLW-D24M-A20PC-R1 MasterLiquid ML240L 240mm RGB Liquid CPU Cooler
Operating System
Windows 10 Pro
Monitor
Dell U2717D 27" UltraSharp InfinityEdge LED Monitor
▲ hide details ▲
VPII is offline  
post #8 of 287 (permalink) Old 07-08-2019, 09:10 AM - Thread Starter
New to Overclock.net
 
elmor's Avatar
 
Join Date: Mar 2014
Posts: 836
Rep: 335 (Unique: 147)
Quote: Originally Posted by Streetdragon View Post
so tldr:
1800/3600 and tight the timings as low as possible?

Yes, unless you want higher copy bandwidth.


Quote: Originally Posted by VPII View Post
@elmor I noticed on some review that showed the memory performance that the 3900X had double the write speed of the 3700X. Is it possibly to do with 3900X being two chips and thus dual or two IF?

Sent from my SM-G960F using Tapatalk

I suppose theoretically, since each has 16-bit width lanes for writes (32 bits for reads) which makes 2x16=32 bits total. It will depend on the application and if it uses both dies to access memory. From what I remember AIDA64 always tests memory using core 0 which wouldn't show any improvement, but that could have changed. I re-do these tests with 3900X when I get my hands on one.

Attached Thumbnails
Click image for larger version

Name:	5cea865f-c72c-435d-97f3-38205479cd30.png
Views:	1244
Size:	331.2 KB
ID:	278538  

elmor is offline  
post #9 of 287 (permalink) Old 07-08-2019, 12:13 PM
New to Overclock.net
 
Jackalito's Avatar
 
Join Date: Feb 2014
Location: Spain
Posts: 278
Rep: 43 (Unique: 22)
Thank you so much for sharing your wisdom with us, elmor.
It's great seeing you so active around here again!

In space no one can hear you scream.
Ryzen 9 Rig
(18 items)
CPU
Ryzen 9 3900X
Motherboard
ASUS Crosshair VIII Hero X570
GPU
AMD Radeon RX 5700 XT 8GB. GDDR6 Sapphire Pulse
RAM
G.Skill 16GB (2x8) DDR4 3600MHz @3733 TridentZ F4-3600C15D-16GTZ
Hard Drive
Samsung 970 EVO Plus SSD M.2 NVMe PCI 1 TB.
Hard Drive
Samsung 850 EVO SSD SATA3 ACHI 1TB.
Hard Drive
Toshiba X300 SATA3 7200RPM 5TB.
Power Supply
Corsair RM-850 850W Fully Modular
Cooling
Noctua NH-U12A
Case
Corsair Obsidian 750D Airflow Edition
Operating System
Windows 10 x64 Pro for Workstations
Monitor
LG UltraWide 34UC79G-B 34" Curved IPS 144Hz FreeSync
Keyboard
Logitech Gaming G513 Carbon
Mouse
Logitech G903
Mousepad
ASUS ROG Stealth
Audio
Realtek ALC1220 + Logitech Z625 2.1 Speaker Set
Other
Fan Cases: 5x Noctua NF-P14s Redux 140mm 1500 RPM PWM
Other
APC Back 1400VA
▲ hide details ▲
Jackalito is online now  
post #10 of 287 (permalink) Old 07-08-2019, 12:24 PM
⤷ αC
 
AlphaC's Avatar
 
Join Date: Sep 2012
Posts: 11,185
Rep: 908 (Unique: 590)
Thanks for confirming what AMD wrote: 3600C16 is probably the best compromise for most people

► Recommended GPU Projects: [email protected] , [email protected] (FP64) (AMD moreso) ► Other notable GPU projects: [email protected] (Nvidia), GPUGrid (Nvidia) ► Project list


AlphaC is offline  
Reply

Quick Reply
Message:
Options

Register Now

In order to be able to post messages on the Overclock.net - An Overclocking Community forums, you must first register.
Please enter your desired user name, your email address and other required details in the form below.
User Name:
If you do not want to register, fill this field only and the name will be used as user name for your post.
Password
Please enter a password for your user account. Note that passwords are case-sensitive.
Password:
Confirm Password:
Email Address
Please enter a valid email address for yourself.
Email Address:

Log-in



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may post new threads
You may post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off