[Phoronix] Windows 10 vs. Linux Performance On The AMD Ryzen Threadripper 3970X - Overclock.net - An Overclocking Community
Forum Jump: 

[Phoronix] Windows 10 vs. Linux Performance On The AMD Ryzen Threadripper 3970X

Reply
 
Thread Tools
post #1 of 14 (permalink) Old 12-04-2019, 11:43 AM - Thread Starter
sudo apt install sl
 
Join Date: Dec 2009
Posts: 5,892
Rep: 182 (Unique: 125)
[Phoronix] Windows 10 vs. Linux Performance On The AMD Ryzen Threadripper 3970X

Source: https://www.phoronix.com/scan.php?pa...s-linux&num=10

Quote:
While Windows 10 did come in last place most often and only came in first less than 20% of the time, overall, its performance wasn't too far behind the Linux distributions. When looking at the geometric mean of the 82 benchmarks, it comes in just behind CentOS 8 and Ubuntu 19.10. Ubuntu 19.10 as the slowest Linux distribution tested was just 2.5% faster than Windows 10. Meanwhile Intel's Clear Linux as the fastest Linux OS tbenchmarked was 10% faster than Windows 10 November 2019 Update with these diverse benchmarks carried out on the new AMD Ryzen Threadripper 3970X platform. This spread between Windows 10 and Linux isn't as large as we've seen in past comparisons like with the Threadripper 2990WX, thanks to both hardware architectural advancements as well as Microsoft's improvements to Windows 10 paired with the latest AMD chipset drivers. Additional Windows 10 vs. Linux HEDT benchmarks for further analysis will be up on Phoronix in December.
Clear Linux runs great on 3rd Gen Threadripper.

Silent
(20 items)
CPU
Core i9 9900K... CoffeeTime! @ 5.1Ghz w/ 1.36v
Motherboard
Maximus VIII Formula
GPU
Radeon VII @ 2100Mhz/1250Mhz w/ 1218mV
RAM
TeamGroup Xtreem 32GB 3200Mhz CL15
Hard Drive
HP EX950 2TB
Hard Drive
Samsung 850 Evo 1TB
Hard Drive
Samsung 850 Evo 1TB
Power Supply
EVGA SuperNova 1200w P2
Cooling
EK Supremacy Full Copper Clean
Cooling
XSPC D5 Photon v2
Cooling
Black Ice Gen 2 GTX360 x2
Cooling
EK-Vector Radeon VII - Copper + Plexi
Case
Thermaltake Core X5 Tempered Glass Edition
Operating System
Clear Linux
Monitor
Acer XF270HUA
Keyboard
Cherry MX Board 6.0
Mouse
Logitech G600
Mouse
Alugraphics GamerArt
Audio
Definitive Technology Incline
Audio
SMSL M8A
▲ hide details ▲
WannaBeOCer is online now  
Sponsored Links
Advertisement
 
post #2 of 14 (permalink) Old 12-04-2019, 12:30 PM
mfw
 
ToTheSun!'s Avatar
 
Join Date: Jul 2011
Location: Terra
Posts: 7,394
Rep: 431 (Unique: 216)
Windows 10 took a beating.

CPU
Intel 6700K
Motherboard
Asus Z170i Pro Gaming
GPU
Gigabyte 2070 Super Windforce OC
RAM
G.skill Trident Z 3200CL14 8+8
Hard Drive
Samsung 850 EVO 1TB
Hard Drive
Crucial M4 256GB
Power Supply
Corsair SF600
Cooling
Noctua NH C14S
Case
Fractal Design Core 500
Operating System
Windows 10 Education
Monitor
ViewSonic XG2703-GS
Keyboard
Ducky One 2 Mini
Mouse
Glorious Odin
Mousepad
Cooler Master MP510 L
Audio
Fiio E17K v1.0 + Beyerdynamic DT 1990 PRO (Dekoni pads)
▲ hide details ▲
ToTheSun! is offline  
post #3 of 14 (permalink) Old 12-04-2019, 01:08 PM
New to Overclock.net
 
Mrzev's Avatar
 
Join Date: Feb 2008
Location: Texas
Posts: 2,297
Rep: 96 (Unique: 76)
What bothers me on these tests, is that i dont know the configuration in general. I assume out of the box install. But does that mean that your running the tests with Windows Defender (Security Essentials , or whatever its called now), vs the ubuntu with no AV services? Did they dissable Corta and all the telemetry nonsense? Probably not. When it comes down to it, when comparing you could get stuck in the downward spiral of what should and shouldnt be enabled on both sides.... But in the end, i dont get a good comparison. You dont expect the average person to disable cortana or whatever, but a person who is debating on running a linux distro vs windows would. So, who is this comparison \ configuration data targeted too?

I would really love to see these two tests run by a person who has configured the system to a normal use case. Like a software dev with identical enviroments 1 being windows and other being zbuntu or whatever. With stupid stuff disabled or additional needed tools enabled. ... i.e i would never run windows without Windows Defender running, but would you run a linux distro without one in a professional enviroment?



Mrzev is offline  
Sponsored Links
Advertisement
 
post #4 of 14 (permalink) Old 12-04-2019, 07:21 PM
Overclocker
 
JackCY's Avatar
 
Join Date: Jun 2014
Posts: 10,353
Rep: 345 (Unique: 244)
Considering most people will not use those apps they used for testing, how relevant is this test anyway not even taking into account the configuration issues mentioned above. I could not find details on the test pages either about anti virus or defender. It's likely as is installed by default.
Sadly Phoronix uses some kind of "test suite" and doesn't really represent well regular nor development usage.
JackCY is offline  
post #5 of 14 (permalink) Old 12-04-2019, 08:04 PM
New to Overclock.net
 
matthew87's Avatar
 
Join Date: May 2010
Posts: 224
Rep: 5 (Unique: 5)
Then you need to factor in what software they tested with, most not being native Windows applications and largely being tailored / optimised for Nix environments.

Finally, you have margin of error. So many of the tests its ball park between every OS, talking 1-3% delta at best, you can't conclude jack from that.

All this really demonstrates is Linux and the new Ryzen TR3 series are getting along fine.
matthew87 is offline  
post #6 of 14 (permalink) Old 12-04-2019, 08:08 PM - Thread Starter
sudo apt install sl
 
Join Date: Dec 2009
Posts: 5,892
Rep: 182 (Unique: 125)
Quote: Originally Posted by JackCY View Post
Considering most people will not use those apps they used for testing, how relevant is this test anyway not even taking into account the configuration issues mentioned above. I could not find details on the test pages either about anti virus or defender. It's likely as is installed by default.
Sadly Phoronix uses some kind of "test suite" and doesn't really represent well regular nor development usage.
Which type of workloads do you expect to be running on a high core count workstation processor? No I do not expect an anti-virus to be used on a Linux workstation.

They've already showed the performance uplift of Clear Linux on Epyc Rome with a variety of data centric workloads.

https://www.phoronix.com/scan.php?pa...me-clear&num=6

Silent
(20 items)
CPU
Core i9 9900K... CoffeeTime! @ 5.1Ghz w/ 1.36v
Motherboard
Maximus VIII Formula
GPU
Radeon VII @ 2100Mhz/1250Mhz w/ 1218mV
RAM
TeamGroup Xtreem 32GB 3200Mhz CL15
Hard Drive
HP EX950 2TB
Hard Drive
Samsung 850 Evo 1TB
Hard Drive
Samsung 850 Evo 1TB
Power Supply
EVGA SuperNova 1200w P2
Cooling
EK Supremacy Full Copper Clean
Cooling
XSPC D5 Photon v2
Cooling
Black Ice Gen 2 GTX360 x2
Cooling
EK-Vector Radeon VII - Copper + Plexi
Case
Thermaltake Core X5 Tempered Glass Edition
Operating System
Clear Linux
Monitor
Acer XF270HUA
Keyboard
Cherry MX Board 6.0
Mouse
Logitech G600
Mouse
Alugraphics GamerArt
Audio
Definitive Technology Incline
Audio
SMSL M8A
▲ hide details ▲
WannaBeOCer is online now  
post #7 of 14 (permalink) Old 12-04-2019, 08:30 PM
professional curmudgeon
 
looniam's Avatar
 
Join Date: Apr 2009
Posts: 9,901
Rep: 808 (Unique: 457)
Quote: Originally Posted by WannaBeOCer View Post
Which type of workloads do you expect to be running on a high core count workstation processor?

crysis. which they didn't test for so all the results are invalid.

Remember the golden rule of statistics: A personal sample size of one is a sufficient basis upon which to draw universal conclusions.
Upload the computer to Dropbox and provide a link to it so others may download it to examine and give advice for repairs.
loon 3.2
(18 items)
CPU
i7-3770K
Motherboard
Asus P8Z77-V Pro
GPU
EVGA 980TI SC+
RAM
16Gb PNY ddr3 1866
Hard Drive
PNY 1311 240Gb
Hard Drive
1 TB Seagate
Hard Drive
3 TB WD Blue
Optical Drive
DVD DVDRW+/-
Power Supply
EVGA SuperNova 750 G2
Cooling
EKWB P280 kit
Cooling
EK-VGA supremacy
Case
Stryker M [hammered and drilled]
Operating System
Win X
Monitor
LG 24MC57HQ-P
Keyboard
Ducky Zero [blues]
Mouse
corsair M65
Audio
SB Recon3D
Audio
Klipsch ProMedia 2.1
▲ hide details ▲


looniam is offline  
post #8 of 14 (permalink) Old 12-05-2019, 08:37 AM
Overclocker
 
JackCY's Avatar
 
Join Date: Jun 2014
Posts: 10,353
Rep: 345 (Unique: 244)
Real workloads from real usage, not some bench apps they've collected for their test suite that no on uses for real work. Be it a workstation usage, server usage, etc.

Are you using ParaView at work?
DaCapo Benchmark?
Renaissance?
SPECjbb 2015?
Playing Crafty chess on your server to kill time until 5pm strikes?
Benching chess performance with TSCP benchmark to see how fast your server or expensive workstation is for avoiding work and playing chess?
Stockfish?
asmFish?
Do a crap load of de/compression? 7zip, XZ, Zstd?
Using GraphicsMagick?
Embree?
Using some obscure AV1 made in Rust?
Or Intel's AV1?
Finding a working and usable AV1 is a miracle in itself since it's still very much in development. Who the heck uses it for encoding videos on their service? Nearly no one if anyone at all.
Intel's VP9 encoder? Nah most just use ffmpeg instead or make their own encoder.
x264, sure it has some use even though it's obsolete.
Intel denoise, kidding right?
And the list goes on and on, there are barely any programs that one would use on a workstation let alone server, there are some but it's very little compared to the amount of benches that no one will ever use for anything but benching.
JackCY is offline  
post #9 of 14 (permalink) Old 12-05-2019, 09:14 AM
New to Overclock.net
 
Mrzev's Avatar
 
Join Date: Feb 2008
Location: Texas
Posts: 2,297
Rep: 96 (Unique: 76)
Quote: Originally Posted by JackCY View Post
Intel's VP9 encoder? Nah most just use ffmpeg instead or make their own encoder.
x264, sure it has some use even though it's obsolete.
ffmpeg just has a ton of codecs installed to encode. You could use Intel Quick Sync video codec to encode a video in x264. I wouldn't call x264 obsolete either. Is there better alternatives, sure, but not obsolete. AV1 seems to be the direction in the future, but x265 is definitely not the next step.

Transcoding with ffmpeg or whatever really depends on the codec though, and more so what hardware the codec is trying to use. All processors or boards will have an embedded h264 processing chip or section or whatever its called. Like take raspbery pi 2 and i transcoded a video with it defaults, and it took like 12 minutes, but using a build with a codec that targets the onboard h264 processor, it took like 3 minutes. But in any case, thats really only matters more with the processor itself. ..hmm..

So really, this is a comparison of the quality of drivers and codecs as well as excess running processes between the OS's Lets try to run a game on there and lets see how linux nvidia drivers compare to windows or mac.



Mrzev is offline  
post #10 of 14 (permalink) Old 12-05-2019, 09:19 AM
New to Overclock.net
 
finalturismo's Avatar
 
Join Date: Oct 2009
Location: Dallas
Posts: 883
Rep: 56 (Unique: 50)
Almost every Linux distro completely destroys Windows in terms of memory management and CPU efficiency. Graphics performance is now almost on par with Windows if you tune your Linux distro with the correct packages and configs.


Low latency kernel config, latest drivers, latest wine, latest dxvk, latest esync, etc.....


Once you go Linux you don't go back.

Quote:
The quieter you become, the more you are able to hear.


finalturismo 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