• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Post your Tiny Memory Benchmark results

acraft

New Member
Joined
Oct 22, 2020
Messages
5 (0.11/day)
Hi,

I recently bought AMD Ryzen 9 3950x - 32 GB system and I found that some of my applications are running 2x slower on this machine comparing with Intel i7-8750H 6 core - 32 GB system. 3950x's performance results are consistent what I see on the website. For example, AIDA64 cache and memory results are consistent. I tried to figure out why 3950x performing 2x slower and I found that some memory operations are much slower than intel.

I used tiny memory benchmark to figure out what is going on. i7-8750H 6-core CPU with 32 GB ram results are much higher than 3950x. I sometime think why AMD 3950 much cheaper than Intel and it looks they cut the power of some of the instructions to reduce the cost.

Here how you can compile and run the tiny memory benchmark under linux. (Or with WSL2 under windows also works) Instructions:

$ sudo apt update
$ sudo apt install clang make git
$ mkdir tmb
$ cd tmb
$ git clone https://github.com/ssvb/tinymembench .
$ CC=clang CFLAGS="-no-integrated-as" make
$ ./tinymembench


AMD Ryzen 9 3950x - 32 GB Ram

AMD 3950x Results.png


Here is the intel i7-8750H - 32 GB Ram Results:

Intel i7-8750H Results.png


Can you please run and post your results here.

AMD Ryzen 9 3950X System Spec:


AMD-ROG-1.png

AMD-ROG-2.png

AMD-ROG-3.png

AMD-ROG-4.png

AMD-ROG-5.png



INTEL i7-8750H System Spec:


Intel-ROG-1.jpg

Intel-ROG-2.jpg

Intel-ROG-3.jpg

Intel-ROG-4.jpg

Intel-ROG-5.jpg


Thanks!
 
Last edited:
Joined
Nov 7, 2009
Messages
3,608 (0.89/day)
Location
Denmark
System Name The work PC /4790 fold&WCG /2700x fold&WCG/2700x full time WCG
Processor 3900X stock/ 4790K 4.4/2x2700x stock
Motherboard Gigabyte AORUS Master X570/Maximus Hero/2xMSI X470 M7 AC
Cooling Custom WC/Noctua NH-D15/ 2xNH-U12S SE
Memory G Skill Trident Z F4-4000C18D-16GTZ 3800 CL 16 /8 GB Corsair Vengance/2x16 GB XSkill Flare CL14
Video Card(s) 2070 Super X MSI/2070 Z/2060 X MSI + 2060 Ventus MSI/GTX 970 MSI
Storage 1 TB SSD / 480 GB SSD/2x250 GB SSD
Display(s) Dell UltraSharp U2518D/2408WFP
Case Corsair 800D / none/Lian test bench/NZXT 500 crap
Power Supply AX 850/AX 860/AX 860i/AX 760
Software Dual boot/Win 7/Linux for AMD
Benchmark Scores Cherry pie at one point ;)
If you provide your settings for your two sets (speed and timings) I will consider. In general no post considering performance will be answered unless you fill in your system specification.
 

phill

Moderator
Staff member
Joined
Jun 8, 2011
Messages
8,764 (2.53/day)
Location
Somerset, UK
System Name Not so complete or overkill
Processor Ryzen 3900X
Motherboard Asus Crosshair 8 Hero (Non Wi-Fi)
Cooling Air :(
Memory Patriot 3200MHz 64GB
Video Card(s) 2 x EVGA GTX 1080 Ti SC Black Edition
Storage 1 250GB Crucial SSD for OS/Programs, 2 500GB Crucial SSD for Steam and Epic stores
Display(s) 3 x 23" LG IPS panels (can't remember model!!)
Case 10mm thick MDF on plastic risers.. It's kinda a case??
Audio Device(s) Onboard
Power Supply EVGA P2 1200w
Mouse Corsair thingy
Keyboard Logitec K120......
Software Windows 10
Benchmark Scores I've actually never benched it!! Too busy with WCG and FAH and not gaming!! :( :(
IT does seem to be that the 3 series of AMD wasn't the best for handling memory timings etc so the results aren't much of a shock. Intel's CPU clock speed pushes them in first place for that...

You'll need to put a little more information down for what cooling, RAM, motherboards you use for the fact that there's so many variences that the test would be pointless unless we know what your timings etc were. Can you not put a CPU-Z CPU, memory and motherboard tab with the results for better clarity?
 
Joined
Mar 26, 2012
Messages
46 (0.01/day)
System Name Mixed Bag of OC
Processor AMD FX-Series FX-9590 @ 5 Ghz
Motherboard ASRock Fatal1ty 990FX Killer
Cooling Alphacool Eisberg 240 Push/Pull + 6 Case Fans on a fan controler
Memory G.Skill Sniper DIMM Kit 16GB 1866 Mhz CL11 @ 2133 Mhz CL10
Video Card(s) 2 X R9 290X CF @ 1150/1600 Mhz
Storage 2X SSD Kingston SSDNow V300 120 GB + 2X SanDisk Ultra Plus 128GB @ Raid0
Display(s) Toshiba 32SL736G 32" 1080P TV
Case Sharkoon Rebel12 Economy
Audio Device(s) Onboard Realtek ALC1150 Optical
Power Supply EVGA SuperNOVA 1300 G2
Software Windows 10 technical preview
Benchmark Scores Cinebench R15 @ 776
3600XT + 32GB @ 3753Mhz CL16 ... Read will be full speed but all Write Operations should be half of a 3900x because of cut off CCX
tinymem.JPG
 
Joined
Jan 8, 2017
Messages
6,163 (4.32/day)
System Name Good enough
Processor AMD Ryzen R7 1700X - 4.0 Ghz / 1.350V
Motherboard ASRock B450M Pro4
Cooling Deepcool Gammaxx L240 V2
Memory 16GB - Corsair Vengeance LPX - 3333 Mhz CL16
Video Card(s) OEM Dell GTX 1080 with Kraken G12 + Water 3.0 Performer C
Storage 1x Samsung 850 EVO 250GB , 1x Samsung 860 EVO 500GB
Display(s) 4K Samsung TV
Case Deepcool Matrexx 70
Power Supply GPS-750C
This is to be expected, each CCX can read 32 bytes/clock or write 16 bytes/clock. In total the two CCXs can achieve the same write performance like any other Intel CPU just not using a single thread because then the instructions are issued from just one CCX and therefore limited to 16 bytes/clock. I suspect AIDA64 is multi-threaded and this benchmark isn't, you need multiple threads (that are scheduled on different CCXs) to get the full throughout. It wasn't really a cost saving measure, it's just how the I/O was configured.
 
Last edited:
Joined
Jul 11, 2015
Messages
273 (0.14/day)
System Name Harm's Rig's
Processor 5800X /2700x / AMD 8370e 4500
Motherboard Asus Prime x470 Pro / Msi GD80 990fxa
Cooling Enermax LIQMAX III ARGB 360 AIO/ Zalman cooler fan 110mm
Memory TRIDENT Z F-43600V15D-16GTZ /G.SKILL DDR4 3333CL14 FASTEST PRESET 32GB /EVGA 16Gb 2400 DDR3
Video Card(s) 1080 Ti / 290x/290a cfx
Storage 1 Sabrent Rocket NVMe 512GB / 1 SSD 250GB / 1 HHD 3 TB
Display(s) 40"TV / 24" Asus
Case TT 37 VIEW 200MM'S/ NZXT Tempest custom
Audio Device(s) Sharp Aquos
Power Supply EVGA 1300G2/Corsair w750
Mouse G502
Keyboard G413
Try this !
Capturetrythid.PNG
Capture5900x.PNG
 

Attachments

Last edited:
Joined
Jul 14, 2006
Messages
2,236 (0.43/day)
System Name It's just a computer
Processor i9-9900K
Motherboard eVGA Z390 Dark
Cooling Dual D5T Vario in XSPC BayRes, Nemesis GTR560, Noctua NF-A14-iPPC2000 (x8), HK IV Pro Nickel
Memory G.Skill F4-4500C19D-16GTZKKE or G.Skill F4-3600C16D-16GTZ
Video Card(s) eVGA RTX2080 FTW3 Ultra
Storage Samsung 960 EVO M.2
Display(s) LG 32GK650F
Case Thermaltake Xaser VI
Audio Device(s) Auzentech X-Meridian 7.1 2G/Z-5500
Power Supply Corsair AX1200
Mouse Logitech
Keyboard Logitech
Software Win7 Ultimate x64 SP1

acraft

New Member
Joined
Oct 22, 2020
Messages
5 (0.11/day)
This is to be expected, each CCX can read 32 bytes/clock or write 16 bytes/clock. In total the two CCXs can achieve the same write performance like any other Intel CPU just not using a single thread because then the instructions are issued from just one CCX and therefore limited to 16 bytes/clock. I suspect AIDA64 is multi-threaded and this benchmark isn't, you need multiple threads (that are scheduled on different CCXs) to get the full throughout. It wasn't really a cost saving measure, it's just how the I/O was configured.
The application I used (not tiny memory benchmark) is multi-threaded. I tried on Intel 6-core system and Intel 32 core system. It's very scalable on Intel based systems. The application is 100% scalable, no disk operations, no wait on synchronizations etc.. i7-8750H runs 2x faster than AMD 3950x. It scales as expected on intel core system without any issues.

Here perf stat result which could be helpful:
Screen Shot 2020-10-22 at 4.23.20 PM.png


Just look at how bad the IPC is on AMD.
 
Joined
Jul 11, 2015
Messages
273 (0.14/day)
System Name Harm's Rig's
Processor 5800X /2700x / AMD 8370e 4500
Motherboard Asus Prime x470 Pro / Msi GD80 990fxa
Cooling Enermax LIQMAX III ARGB 360 AIO/ Zalman cooler fan 110mm
Memory TRIDENT Z F-43600V15D-16GTZ /G.SKILL DDR4 3333CL14 FASTEST PRESET 32GB /EVGA 16Gb 2400 DDR3
Video Card(s) 1080 Ti / 290x/290a cfx
Storage 1 Sabrent Rocket NVMe 512GB / 1 SSD 250GB / 1 HHD 3 TB
Display(s) 40"TV / 24" Asus
Case TT 37 VIEW 200MM'S/ NZXT Tempest custom
Audio Device(s) Sharp Aquos
Power Supply EVGA 1300G2/Corsair w750
Mouse G502
Keyboard G413
Joined
Nov 22, 2014
Messages
69 (0.03/day)
System Name I could say remaining parts or something like that...
Processor i5 2500k @ 4,8 ghz/Xeon x5650
Motherboard Asus Z68 gene-z/G1 Assassin
Cooling 240mm radiator/212+
Memory 8gb ddr3-1333/16gb ddr3-1866
Video Card(s) Nitro RX460 4gb/2x RX570 Red Devil
Storage Many
Display(s) Samsung TV/Topsync 2560*1440
Audio Device(s) onboard
Power Supply Seasonic 620w/Corsair 860i
Software 10 64 bit ultimate
You should try to compare your memory using the same timings (ideally the same sticks). The Intel system is running tightier timings, this could explain at least some part of the difference...
 
Joined
Sep 10, 2016
Messages
625 (0.40/day)
Location
Riverwood, Skyrim
System Name Storm Wrought | Blackwood (HTPC)
Processor AMD Ryzen 7 3700x @stock ~4.25GHz boost speed | i7 2600k
Motherboard Gigabyte X570 Aorus Pro WIFI m-ITX | Some POS gigabyte board
Cooling BQ Dark Rock Slim, CM MF Pro 120 Air Balance, stock 180mm |BQ Shadow rock LP + 4x120mm Noctua redux
Memory G.Skill Trident 2x8GB 3600MHz 16-15-15-35 | 2x4GB 2000MHz @1866
Video Card(s) Gigabyte GTX 1080ti Aorus Xtreme Edition | MSI LP GT 1030
Storage SX8200 Pro 1TB, 850EVO 500GB, 2TB Seagate Barracuda, LG Blu-ray | 120GB Sandisk SSD, 4TB WD red
Display(s) Samsung UJ590UDE 32" UHD monitor | Sammy 1080p 55" TV
Case Silverstone TJ08B-E | Custom built wooden case (Aus native timbers)
Audio Device(s) Onboard, HD 599 cans | Logitech z163's
Power Supply Corsair RMx 550 | Corsair SF 450
Mouse Rapoo (can't remember the model number) | Some logitech one
Keyboard Rapoo v56 | Some logitech one
Software Win 10 Edu | Ubuntu 20.04
Benchmark Scores Look in the various benchmark threads
The application I used (not tiny memory benchmark) is multi-threaded. I tried on Intel 6-core system and Intel 32 core system. It's very scalable on Intel based systems. The application is 100% scalable, no disk operations, no wait on synchronizations etc.. i7-8750H runs 2x faster than AMD 3950x. It scales as expected on intel core system without any issues.

Here perf stat result which could be helpful:
View attachment 172991

Just look at how bad the IPC is on AMD.
The IPC isn't bad on 3000 series Ryzen at all, it seems more likely that this particular benchmark uses an instruction that Ryzen doesn't have and that's what makes all the difference here
 
Top