Overclock.net › Forums › Industry News › Hardware News › [Phoronix] DDR4 Memory Scaling & DDR4-3600 Testing With AMD Threadripper On Linux
New Posts  All Forums:Forum Nav:

[Phoronix] DDR4 Memory Scaling & DDR4-3600 Testing With AMD Threadripper On Linux

post #1 of 13
Thread Starter 
If you are thinking of assembling an AMD Threadripper this holiday season, these results again reiterate that going for quad channel memory is definitely worth it even if it means getting a slower kit than what you would if going for dual channel. Between say DDR4-3200 and DDR4-3600 speeds there wasn't too much of a difference in many of these real-world Linux benchmarks, compared to the price premium of DDR4-3600, so hopefully this information will be of help when shopping.





















Since it's THREADRIPPER leaving all value bs aside, DDR4 3600 is the memory. devil.gif

https://www.phoronix.com/scan.php?page=article&item=threadripper-linux-ddr4&num=1
post #2 of 13
Dayum I didn't know we had already reached quad channel 3600 MHz. Looks good. thumb.gif
Haswell i3
(18 items)
 
  
CPUMotherboardGraphicsRAM
Core i3-4150 @ 3.5 GHz Asus B85M-G Rev 1.01, Bios: 2501 Integrated Intel HD 4400 2x 4GB DDR3 1600 MHz CL9 
Hard DriveHard DriveHard DriveOptical Drive
Samsung 750 EVO 250GB Seagate Barracuda 1TB 7200.14 Seagate 500 GB 2.5" Samsung DVD/RW 
CoolingOSMonitorKeyboard
Corsair H70 Windows 10 64 bit Samsung A300N 20" 1600 x 900 60Hz 5ms 19Watt PS/2 Microsoft Wired Keyboard 500 
PowerCaseMouse
Corsair TX850 V2 CoolerMaster Elite 430 Black Logitech M170 
  hide details  
Reply
Haswell i3
(18 items)
 
  
CPUMotherboardGraphicsRAM
Core i3-4150 @ 3.5 GHz Asus B85M-G Rev 1.01, Bios: 2501 Integrated Intel HD 4400 2x 4GB DDR3 1600 MHz CL9 
Hard DriveHard DriveHard DriveOptical Drive
Samsung 750 EVO 250GB Seagate Barracuda 1TB 7200.14 Seagate 500 GB 2.5" Samsung DVD/RW 
CoolingOSMonitorKeyboard
Corsair H70 Windows 10 64 bit Samsung A300N 20" 1600 x 900 60Hz 5ms 19Watt PS/2 Microsoft Wired Keyboard 500 
PowerCaseMouse
Corsair TX850 V2 CoolerMaster Elite 430 Black Logitech M170 
  hide details  
Reply
post #3 of 13
Interesting to see the differences between 3600 and 3200 though, especially since they kept the timings the same between each of them.
JägerWulfe
(19 items)
 
 
Gigadestroyer
(13 items)
 
CPUMotherboardGraphicsRAM
Intel i7-4770K Gigabyte Z87X-OC MSI GTX 980 Ti Gaming 6G Golden Edition G.Skill Triden-X 16GB DDR3-2400 
Hard DriveHard DriveOptical DriveCooling
Seagate 2TB SATA3 Maxtor 2TB Black LG DVD-RW Cryorig R1 ultimate 
OSMonitorMonitorKeyboard
Windows 7 Home Premium 64 bit BenQ VP2210 BenQ VP2210 Razer BlackWidow Ultimate 
PowerCaseMouseMouse Pad
EVGA SuperNova 1000G2 NZXT Phantom 820 Black Roccat Nyth Steel Series Worgen 
AudioAudioAudio
JDS Labs O2 + ODAC Rev.B AKG K712 Audio Technica ATH-M50X 
CPUMotherboardGraphicsRAM
i7 3770k Maximus V Formula EVGA GTX 780 Classified Corsair Dominator Platinum 1866MHz 
Hard DriveCoolingOSMonitor
Kingston 64GB SSDnow 200 CoolerMaster MasterLiquid Pro 240 Windows 7 64 Bit Dell E2213H 
KeyboardPowerCaseMouse
Logitech G15 v2 EVGA 1000w G2 Open Bench Table Corsair M95 
Mouse Pad
3' wide battle mat 
  hide details  
Reply
JägerWulfe
(19 items)
 
 
Gigadestroyer
(13 items)
 
CPUMotherboardGraphicsRAM
Intel i7-4770K Gigabyte Z87X-OC MSI GTX 980 Ti Gaming 6G Golden Edition G.Skill Triden-X 16GB DDR3-2400 
Hard DriveHard DriveOptical DriveCooling
Seagate 2TB SATA3 Maxtor 2TB Black LG DVD-RW Cryorig R1 ultimate 
OSMonitorMonitorKeyboard
Windows 7 Home Premium 64 bit BenQ VP2210 BenQ VP2210 Razer BlackWidow Ultimate 
PowerCaseMouseMouse Pad
EVGA SuperNova 1000G2 NZXT Phantom 820 Black Roccat Nyth Steel Series Worgen 
AudioAudioAudio
JDS Labs O2 + ODAC Rev.B AKG K712 Audio Technica ATH-M50X 
CPUMotherboardGraphicsRAM
i7 3770k Maximus V Formula EVGA GTX 780 Classified Corsair Dominator Platinum 1866MHz 
Hard DriveCoolingOSMonitor
Kingston 64GB SSDnow 200 CoolerMaster MasterLiquid Pro 240 Windows 7 64 Bit Dell E2213H 
KeyboardPowerCaseMouse
Logitech G15 v2 EVGA 1000w G2 Open Bench Table Corsair M95 
Mouse Pad
3' wide battle mat 
  hide details  
Reply
post #4 of 13
Quote:
Originally Posted by WhiteWulfe View Post

Interesting to see the differences between 3600 and 3200 though, especially since they kept the timings the same between each of them.

Well you can get CL14 for 3200 which you probably mean no difference.
Ishimura
(21 items)
 
Silent Knight
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel Core i7 3770K @ 4.6GHz ASRock Z77E-ITX eVGA GTX 1080 Ti Hybrid AVEXIR Blitz 1.1 16GB DDR3-2400MHz CL10 
Hard DriveHard DriveCoolingCooling
SanDisk Ultra II 960GB Toshiba X300 5TB Corsair H100i GTX eVGA Hybrid Water Cooler  
CoolingOSMonitorKeyboard
4x GentleTyphoon AP-15 Windows 10 Pro 64-Bit LG OLED55C7P  Razer BlackWidow Chroma  
PowerCaseMouseMouse Pad
eVGA SuperNOVA 750 G3 Define Nano S Logitech G502 Proteus Core PECHAM Gaming Mouse Pad XX-Large 
AudioAudioAudioAudio
Audioengine D1 DAC Mackie CR Series CR3 Audio-Technica ATH-M50 Sennheiser HD 598 
Audio
Sony XB950BT 
CPUMotherboardGraphicsRAM
AMD Phenom II X4 955 @ 4.2GHz ASUS M4A79XTD EVO AMD Radeon HD 7970 3GB @ 1200/1500 2x 4GB G.SKILL Ripjaws X DDR3-1600 
Hard DriveHard DriveHard DriveCooling
OCZ Agility 3 60GB WD Caviar Green 1.5TB 2 x Seagate Barracuda 2TB XSPC Raystorm 
CoolingCoolingOSPower
EK-FC7970 XSPC RS360 Windows 10 Pro 64-Bit Corsair TX750 
Case
NZXT Switch 810  
  hide details  
Reply
Ishimura
(21 items)
 
Silent Knight
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel Core i7 3770K @ 4.6GHz ASRock Z77E-ITX eVGA GTX 1080 Ti Hybrid AVEXIR Blitz 1.1 16GB DDR3-2400MHz CL10 
Hard DriveHard DriveCoolingCooling
SanDisk Ultra II 960GB Toshiba X300 5TB Corsair H100i GTX eVGA Hybrid Water Cooler  
CoolingOSMonitorKeyboard
4x GentleTyphoon AP-15 Windows 10 Pro 64-Bit LG OLED55C7P  Razer BlackWidow Chroma  
PowerCaseMouseMouse Pad
eVGA SuperNOVA 750 G3 Define Nano S Logitech G502 Proteus Core PECHAM Gaming Mouse Pad XX-Large 
AudioAudioAudioAudio
Audioengine D1 DAC Mackie CR Series CR3 Audio-Technica ATH-M50 Sennheiser HD 598 
Audio
Sony XB950BT 
CPUMotherboardGraphicsRAM
AMD Phenom II X4 955 @ 4.2GHz ASUS M4A79XTD EVO AMD Radeon HD 7970 3GB @ 1200/1500 2x 4GB G.SKILL Ripjaws X DDR3-1600 
Hard DriveHard DriveHard DriveCooling
OCZ Agility 3 60GB WD Caviar Green 1.5TB 2 x Seagate Barracuda 2TB XSPC Raystorm 
CoolingCoolingOSPower
EK-FC7970 XSPC RS360 Windows 10 Pro 64-Bit Corsair TX750 
Case
NZXT Switch 810  
  hide details  
Reply
post #5 of 13
Quote:
Originally Posted by ZealotKi11er View Post

Well you can get CL14 for 3200 which you probably mean no difference.

Latency and bandwidth are not equivalent. It looks like threadripper loves bandwidth.
post #6 of 13
The tests that see more than a linear increase in performance from 3200 to 3600 have to be limited by the fabric interconnect as well as memory. May also be some infinity fabric vs. IMC straps/ratios at play.
Primary
(15 items)
 
Secondary
(13 items)
 
In progress
(10 items)
 
CPUMotherboardGraphicsRAM
5820K @ 4.2/3.5GHz core/uncore, 1.175/1.15v Gigabyte X99 SOC Champion (F22n) Gigabyte AORUS GTX 1080 Ti (F3P) @ 2025/1485, 1... 4x4GiB Crucial @ 2667, 12-12-12-28-T1, 1.34v 
Hard DriveHard DriveHard DriveCooling
Plextor M6e 128GB (fw 1.06) M.2 (PCI-E 2.0 2x) 2x Crucial M4 256GB 4x WD Scorpio Black 500GB Noctua NH-D15 
OSMonitorKeyboardPower
Windows 7 Professional x64 SP1 BenQ BL3200PT Filco Majestouch Tenkeyless (MX Brown) Corsair RM1000x 
CaseMouseAudio
Fractal Design Define R4 Logitech G402 Realtek ALC1150 + M-Audio AV40 
CPUMotherboardGraphicsRAM
X5670 @ 4.4/3.2GHz core/uncore, 1.36 vcore, 1.2... Gigabyte X58A-UD5 r2.0 w/FF3mod10 BIOS Sapphire Fury Nitro OC+ @ 1053/500, 1.225vGPU/1... 2x Samsung MV-3V4G3D/US @ 2000, 10-11-11-30-T1,... 
RAMHard DriveHard DriveHard Drive
1x Crucial BLT4G3D1608ET3LX0 @ 2000, 10-11-11-3... OCZ (Toshiba) Trion 150 120GB Hyundai Sapphire 120GB 3x Hitachi Deskstar 7k1000.C 1TB 
CoolingOSPowerCase
Noctua NH-D14 Windows 7 Pro x64 SP1 Antec TP-750 Fractal Design R5 
Audio
ASUS Xonar DS 
CPUMotherboardGraphicsRAM
i7-6800K @ 4.3/3.5GHz core/uncore, 1.36/1.2v ASRock X99 OC Formula (P3.10) GTX 780 (temporary) 4x4GiB Crucial DDR4-2400 @ 11-13-12-28-T2, 1.33v 
Hard DriveHard DriveCoolingOS
Intel 600p 256GB NVMe 2x HGST Travelstar 7k1000 1TB Corsair H55 (temporary) Windows Server 2016 Datacenter 
PowerCase
Seasonic SS-860XP2 Corsair Carbide Air 540 
  hide details  
Reply
Primary
(15 items)
 
Secondary
(13 items)
 
In progress
(10 items)
 
CPUMotherboardGraphicsRAM
5820K @ 4.2/3.5GHz core/uncore, 1.175/1.15v Gigabyte X99 SOC Champion (F22n) Gigabyte AORUS GTX 1080 Ti (F3P) @ 2025/1485, 1... 4x4GiB Crucial @ 2667, 12-12-12-28-T1, 1.34v 
Hard DriveHard DriveHard DriveCooling
Plextor M6e 128GB (fw 1.06) M.2 (PCI-E 2.0 2x) 2x Crucial M4 256GB 4x WD Scorpio Black 500GB Noctua NH-D15 
OSMonitorKeyboardPower
Windows 7 Professional x64 SP1 BenQ BL3200PT Filco Majestouch Tenkeyless (MX Brown) Corsair RM1000x 
CaseMouseAudio
Fractal Design Define R4 Logitech G402 Realtek ALC1150 + M-Audio AV40 
CPUMotherboardGraphicsRAM
X5670 @ 4.4/3.2GHz core/uncore, 1.36 vcore, 1.2... Gigabyte X58A-UD5 r2.0 w/FF3mod10 BIOS Sapphire Fury Nitro OC+ @ 1053/500, 1.225vGPU/1... 2x Samsung MV-3V4G3D/US @ 2000, 10-11-11-30-T1,... 
RAMHard DriveHard DriveHard Drive
1x Crucial BLT4G3D1608ET3LX0 @ 2000, 10-11-11-3... OCZ (Toshiba) Trion 150 120GB Hyundai Sapphire 120GB 3x Hitachi Deskstar 7k1000.C 1TB 
CoolingOSPowerCase
Noctua NH-D14 Windows 7 Pro x64 SP1 Antec TP-750 Fractal Design R5 
Audio
ASUS Xonar DS 
CPUMotherboardGraphicsRAM
i7-6800K @ 4.3/3.5GHz core/uncore, 1.36/1.2v ASRock X99 OC Formula (P3.10) GTX 780 (temporary) 4x4GiB Crucial DDR4-2400 @ 11-13-12-28-T2, 1.33v 
Hard DriveHard DriveCoolingOS
Intel 600p 256GB NVMe 2x HGST Travelstar 7k1000 1TB Corsair H55 (temporary) Windows Server 2016 Datacenter 
PowerCase
Seasonic SS-860XP2 Corsair Carbide Air 540 
  hide details  
Reply
post #7 of 13
Quote:
Originally Posted by sumitlian View Post

Dayum I didn't know we had already reached quad channel 3600 MHz. Looks good. thumb.gif

Same here. Unfortunately not much seems to have changed (see below). The last time I had checked was with mainstream Ryzen and 3200 Mhz had pretty much stabilized and some people were managing 3466 Mhz, but Threadripper can go to 3600 Mhz? That would be pretty good... if it wasn't seemingly a hit or miss thing:

(page 5)
Quote:
The most interesting real-world memory test used for this article was Open Porous Media that is relevant to gas/oil industries and has proven to be quite a demanding benchmark. These G.SKILL DDR4-3600 memory modules had worked fine in every other workload tossed at it besides OPM. When running at DDR4-3600, the OPM workload was enough to cause memory corruption and crashes. So unfortunately with these cheap G.SKILL DDR4-3600 memory modules I could only run them here up to DDR4-3200, but at least the 4 x 8GB DDR4-3200 memory modules ran fine up to their rated speeds.

https://www.phoronix.com/scan.php?page=article&item=threadripper-linux-ddr4&num=5

3600 Mhz seems like golden sample material, just as before. For a high multi-core system like Threadripper, I'd say that 32 GB of 3200 Mhz RAM are a better bet than 16 GB of 3600 Mhz anyway, so not a big problem.

Hopefully the next Ryzen chips next year bring an IMC capable of 4 Ghz.
 
Metro 2033 review
Metro 2033
CPUMotherboardGraphicsRAM
Core i7-3820 Asus Sabertooth X79 MSI GTX 1060 6 GB Gaming X 16 GB Corsair DDR3 1866 Mhz Dominator 
Hard DriveOptical DriveCoolingOS
Samsung SSD 830 128GB + WD Caviar Black 2TB Sony Optiarc DVD-RW Corsair A70 + Noiseblocker M12-P Windows 7 Home Premium 64-bit 
MonitorKeyboardPowerCase
BenQ RL2455HM Cooler Master Octane Corsair AX750 Professional Modular 80 Plus Gold Cooler Master HAF 912 Plus 
Mouse
Cooler Master Octane 
  hide details  
Reply
 
Metro 2033 review
Metro 2033
CPUMotherboardGraphicsRAM
Core i7-3820 Asus Sabertooth X79 MSI GTX 1060 6 GB Gaming X 16 GB Corsair DDR3 1866 Mhz Dominator 
Hard DriveOptical DriveCoolingOS
Samsung SSD 830 128GB + WD Caviar Black 2TB Sony Optiarc DVD-RW Corsair A70 + Noiseblocker M12-P Windows 7 Home Premium 64-bit 
MonitorKeyboardPowerCase
BenQ RL2455HM Cooler Master Octane Corsair AX750 Professional Modular 80 Plus Gold Cooler Master HAF 912 Plus 
Mouse
Cooler Master Octane 
  hide details  
Reply
post #8 of 13
Thread Starter 
post #9 of 13
I got some 4000mhz 18-18-18-36 ram coming, would like to see how it scales up to that lol.
Taint3d
(18 items)
 
  
CPUMotherboardGraphicsRAM
8700k 5Ghz Asus z370 Maximus X Apex EVGA 1080 Ti G.Skill Trident Z 4000 RGB 
RAMHard DriveHard DriveHard Drive
G.Skill Trident Z 4000 RGB Samsung 960 Evo Samsung 840 Pro Samsung 850 Evo 
CoolingOSMonitorKeyboard
Custom Koolance/EK Watercooler Windows 10 Acer Predator X34 G-Sync @ 100hz Bloody B820R 
PowerCaseMouseMouse Pad
EVGA supernova 1300 g2 Rosewill Blackhawk Ultra R.A.T 7 Corepad 
AudioOther
SoundBlaster ZXR Philips SPH 9500 Headphones 
  hide details  
Reply
Taint3d
(18 items)
 
  
CPUMotherboardGraphicsRAM
8700k 5Ghz Asus z370 Maximus X Apex EVGA 1080 Ti G.Skill Trident Z 4000 RGB 
RAMHard DriveHard DriveHard Drive
G.Skill Trident Z 4000 RGB Samsung 960 Evo Samsung 840 Pro Samsung 850 Evo 
CoolingOSMonitorKeyboard
Custom Koolance/EK Watercooler Windows 10 Acer Predator X34 G-Sync @ 100hz Bloody B820R 
PowerCaseMouseMouse Pad
EVGA supernova 1300 g2 Rosewill Blackhawk Ultra R.A.T 7 Corepad 
AudioOther
SoundBlaster ZXR Philips SPH 9500 Headphones 
  hide details  
Reply
post #10 of 13
Quote:
Originally Posted by Blameless View Post

The tests that see more than a linear increase in performance from 3200 to 3600 have to be limited by the fabric interconnect as well as memory. May also be some infinity fabric vs. IMC straps/ratios at play.

The fabric interconnect must be the bottleneck. 7 zip compression is not a benchmark I remember being very responsive to memory bandwidth.

Even compiling the linux kernel has a measurable benefit, and that is an application that is certainty not memory strapped.
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [Phoronix] DDR4 Memory Scaling & DDR4-3600 Testing With AMD Threadripper On Linux