Highest MIPS - screenshots of 7-zip built-in benchmark - Overclock.net - An Overclocking Community

Forum Jump: 

Highest MIPS - screenshots of 7-zip built-in benchmark

Reply
 
Thread Tools
post #1 of 85 (permalink) Old 01-12-2018, 01:53 PM - Thread Starter
Integer Benchmarker
 
Sanmayce's Avatar
 
Join Date: Mar 2012
Location: Sofia
Posts: 399
Rep: 22 (Unique: 19)
The idea of this thread is to present enough stats for drawing a solid picture of what affects (mostly) the results across different systems.
The word 'highest' covers two departments - the 'absolute' highest score and the highest within a specific computer. Thus one will be able to decide for himself what e.g. RAM to buy and to avoid overkill scenarios. Besides, it is ignorant to not know how one machine fares in such a must-have bench. Imagine entering a show or shop and seeing some super-duper flashy and fancy new rig, do I need to listen to some professional fool's narrative or just ask for 7-zip stats. If one knows enough about this bench he even could guess what is inside, right on.
Another aspect is gathering all the CPU-RAM subsystems results under one roof while in parallel giving the specs of the machine used, not as most sites on Internet showing graphs/charts and missing the internal/vital stuff as RAM settings/vendor, CPU and cache frequencies, motherboard and other important need-to-know background.

Personally, I find hurtful and shameful to not know how e.g. the RAM latency, the cache sizes, the cache speeds, the frequencies of cores and so on dictate the performance.
Details matter, as the saying goes "The devil is in the details", words of wisdom.

I hope OCN members to contribute in gathering enough screenshots showing CPU-Z (two screens), AIDA64 (if possible) and other descriptive info about the system used.

Thanks to @DStealth, one good example is this:



And the current highest score comes here thanks to @Jpmboy ([email protected] ram at 4000c16):



My wish is when one needs to compare different machines this thread to serve as a "baseline" repository. thumb.gif

Also, the awesome AMD Threadripper is thrashed in this important bench with a margin, 360MB/s, wanna see its redemption, someone please overclock, tweak and what not but deliver more than 1,286,408 KB/s.

Get down get down get down get it on show love and give it up
What are you waiting on?
Sanmayce is offline  
Sponsored Links
Advertisement
 
post #2 of 85 (permalink) Old 01-12-2018, 02:49 PM
OC...D
 
Jpmboy's Avatar
 
Join Date: Apr 2012
Location: Philadelphia
Posts: 26,508
Rep: 1282 (Unique: 565)
if you want help with how to set up a google sheet for your op (like this) give me a PM.

ASUS Z370/Z390 Motherboard Support Thread, Coffee Lake OC Guide
GPUs For Sale
X299
(27 items)
x99
(18 items)
Z370
(19 items)
CPU
7980XE
CPU
7740X
CPU
9900X
Motherboard
ASUS Rampage VI Apex
Motherboard
Gigabyte Aorus G9
Motherboard
Rampage VI Extreme Omega
GPU
2x Nvidia Titan V
GPU
GTX 1080
GPU
2 2080Ti FE / EK Vector Blocks
RAM
G. Skill 2x(2x8GB) 3600c15 @4000c16
RAM
Team Group
RAM
Two 4x8GB GS 3600c16 kits @ 4000c16
Hard Drive
INtel Optane 900P
Hard Drive
2x256 Plextor Raid 0
Hard Drive
WD Raptor
Hard Drive
Samsung Sm 961
Power Supply
Corsair AX1500i
Power Supply
EVGA 850 G3
Cooling
Aquacomputer GiGant 1680 (4x420)
Cooling
Koolance EXC-800
Case
Microcool Banchetto 101 (Alu)
Case
Corsair 570X
Operating System
Win 10 Pro
Operating System
Win 7 Pro
Monitor
ROG Swift
Keyboard
Ducky
Mouse
Spatha
CPU
6950X
Motherboard
ASUS Rampage V Extreme-10
GPU
Titan Xp
GPU
Titan Xp
RAM
G Skill 8x8GB 3200c14 @3400c13
Hard Drive
Samsung 960 Pro
Optical Drive
ASUS BR/DVD/CD
Power Supply
Corsair AX1500i
Cooling
2x360 Aq Copper Rads
Cooling
Aquaero 6
Cooling
Koolance ERM-3K3U (9-fan mora)
Cooling
Ek Full Cover MB waterblock
Case
CaseLabs Mercury S8
Operating System
Win 10 Pro
Operating System
Win 7 Pro
Monitor
AGON 32 inch
Keyboard
Das Pro
Mouse
Logitech G700
CPU
8700K
CPU
8086K
Motherboard
ASUS Maximus X Apex
GPU
GTX 1070Ti FTW2
RAM
2x8 GB G.Skill 4400c19
RAM
G.Skill 3600c16 4x6GB
Hard Drive
Intel 750
Optical Drive
PLextor DVD/CD
Power Supply
Corsair AX1500i
Power Supply
Corsair HX 1200i
Power Supply
Seasonic Titanium 850W
Cooling
360Rad + Chiller
Cooling
Koolance ERM-3K3U
Case
Corasir 570
Operating System
Win 10
Operating System
Windows 7 Pro
Monitor
55" 4K
Keyboard
HyperX Alloy FPS Pro
Mouse
SteelSeries Rival
▲ hide details ▲


Jpmboy is offline  
post #3 of 85 (permalink) Old 01-14-2018, 02:32 AM - Thread Starter
Integer Benchmarker
 
Sanmayce's Avatar
 
Join Date: Mar 2012
Location: Sofia
Posts: 399
Rep: 22 (Unique: 19)
Thanks for the suggestion, very good scheme, indeed. Allow me to steal from your style, here is my view how to post (CSV style), properly:

OCN username, CPU, CPU frequency NOMINAL, CPU frequency OC, motherboard, RAM frequency NOMINAL, RAM frequency OC, RAM CAS latency (CL), RAM CR (Command Rate), RAM size, RAM Channels, Decompression MIPS

So, for my humble laptop 'Compressionette':

Sanmayce, Core i5 7200U, 2500MHz, 2712MHz, Lenovo ideapad 310-15IKB, 2133MHz, 2133MHz, 15, 2T, 2x4GB, 2, 9056



@Jpmboy Feel free to post whatever way you want, very glad you dig benchmarking in a useful way thumb.gif I like your rosters/sheets, please apply them here!

A nifty thing is to gather highest MIPS on a particular architecture, thus when we have, say, 4 results on different machines, we could compare them.
Hee-hee, my result gives the bottomline baseline with:

Compression MIPS: 9832 or 8,611 KB/s
Decompression MIPS: 9056 or 101,757 KB/s

Get down get down get down get it on show love and give it up
What are you waiting on?
Sanmayce is offline  
Sponsored Links
Advertisement
 
post #4 of 85 (permalink) Old 01-14-2018, 04:12 PM
Not New to Overclock.net
 
Diablosbud's Avatar
 
Join Date: Aug 2012
Location: The Infernal Gate
Posts: 1,677
Rep: 80 (Unique: 63)
So I ran 10 passes of this on my R5 1600 3.875 GHz with 3200 MHz C14 RAM. Here's the result:


CPU
AMD Ryzen 5 1600 3.875 GHz
Motherboard
ASUS Prime X370-Pro
GPU
EVGA GTX 1080 FTW2 2114 MHz 356 GB/s
RAM
G.SKILL 2x8GB 3126 MHz 12-13-13-32-1T 48 tRC
Hard Drive
Samsung 850 EVO 500 GB
Power Supply
Seasonic Platinum 660XP
Cooling
Noctua NH-D15
Cooling
2 x Cougar CF-V12HP Top Intake
Cooling
Noctua NF-F12 2000 RPM Rear Exhaust
Cooling
2 x Phanteks F140SP Front Intake
Cooling
Thermal Grizzly Kryonaut TIM
Case
Corsair Carbide Air 540
Operating System
Windows 10 Enterprise 64-bit
Monitor
ASUS MG279Q 1440p IPS 150 Hz OC
Keyboard
Ducky Shine 5 MX Brown
Mouse
Logitech G203 Prodigy
Audio
Schiit Asgard 2
Audio
OPPO PM-3
Audio
HIFIMAN HE-560
Audio
Cambridge DacMagic 100
CPU
AMD Phenom 9650 2.83 GHz
Motherboard
Foxconn A74MX-K
RAM
OCZ 1x1GB DDR2 533 MHz 5-4-4-15-1T 15 tRC
Hard Drive
Samsung 840 Pro 128 GB
Power Supply
OCZ StealthXStream 2 500W
Cooling
Ryzen Wraith + Zip Ties
Cooling
Corsair AF140 Quiet Edition
▲ hide details ▲


Diablosbud is offline  
post #5 of 85 (permalink) Old 01-14-2018, 11:20 PM - Thread Starter
Integer Benchmarker
 
Sanmayce's Avatar
 
Join Date: Mar 2012
Location: Sofia
Posts: 399
Rep: 22 (Unique: 19)
Thanks Diablosbud.
Simplified roster is easier to maintain.
Code:
-----------------------------------------------------------------------------------------------------------------
| OCN username | CPU            | Threads | CPU frequency OC | RAM frequency OC | RAM (CL) | Decompression MIPS |
-----------------------------------------------------------------------------------------------------------------
| Jpmboy       | Core i9 7980XE | 36      | 4.5GHz           | 4000MHz          | 16       | 114481             |
| DStealth     | Core i7 8700K  | 12      | 5552MHz          | 4000MHz          | 16       | 49426              |
| Diablosbud   | Ryzen 5 1600   | 12      | 3.875 GHz        | 3200MHz          | 14       | 36784              |
| Sanmayce     | Core i5 7200U  | 4       | 2712MHz          | 2133MHz          | 15       | 9056               |
-----------------------------------------------------------------------------------------------------------------

Get down get down get down get it on show love and give it up
What are you waiting on?
Sanmayce is offline  
post #6 of 85 (permalink) Old 01-29-2018, 10:39 AM
New to Overclock.net
 
Tamalero's Avatar
 
Join Date: Dec 2016
Posts: 322
Rep: 5 (Unique: 5)
Here you go!

With crappy 3000CL15 Corsair Domminator Platinum with Hynix-M modules.

O'ced to 3.925Ghz.

Note that my scores could be a bit bigger as I had a ton of tabs open both on firefox AND chrome (dual screens)
Attached Thumbnails
Click image for larger version

Name:	jQPrcdb.jpg
Views:	103
Size:	430.3 KB
ID:	63561  


Last edited by Tamalero; 01-29-2018 at 10:44 AM.
Tamalero is offline  
post #7 of 85 (permalink) Old 01-29-2018, 12:54 PM - Thread Starter
Integer Benchmarker
 
Sanmayce's Avatar
 
Join Date: Mar 2012
Location: Sofia
Posts: 399
Rep: 22 (Unique: 19)
Thank you Tamalero, very useful and informative!
Code:
---------------------------------------------------------------------------------------------------------------------
| OCN username | CPU                | Threads | CPU frequency OC | RAM frequency OC | RAM (CL) | Decompression MIPS |
---------------------------------------------------------------------------------------------------------------------
| Jpmboy       | Core i9 7980XE     | 36      | 4.5GHz           | 4000MHz          | 16       | 114481             |
| Tamalero     | Threadripper 1950X | 32      | 3.9GHz           | 3066MHz          | 16       | 92922              |
| DStealth     | Core i7 8700K      | 12      | 5552MHz          | 4000MHz          | 16       | 49426              |
| Diablosbud   | Ryzen 5 1600       | 12      | 3.875 GHz        | 3200MHz          | 14       | 36784              |
| Sanmayce     | Core i5 7200U      | 4       | 2712MHz          | 2133MHz          | 15       | 9056               |
---------------------------------------------------------------------------------------------------------------------
Since your utilization is 3094%, you are right, those open tabs undermine the score, maybe by 80-90% - or one thread. Love Threadripper, despite it being thrashed in Compression Department by 113234 KB/s / 56882KB/s = 1.99 or 2x ?! This is quite bad since Threadripper with its 512KB L2 per core should thrash 'em all in compression speed.

In my opinion the highest values (among all passes) should be used as "Result[ant]", sadly Igor uses as "Result" the value obtained in the first pass/run - which serves no purpose when the highest is sought. For me, it is necessary to manually write down the best score between runs - unacceptable. Anyway, it is what it is. Tamalero, as a side note, noticed your uncached RAM latency is 99ns - probably this is the reason for relatively low score when comparing to the Jpmboy's superscore.

Get down get down get down get it on show love and give it up
What are you waiting on?
Sanmayce is offline  
post #8 of 85 (permalink) Old 01-29-2018, 03:14 PM
Meddling user
 
gupsterg's Avatar
 
Join Date: Jan 2015
Location: Lurking over a keyboard
Posts: 7,160
Rep: 774 (Unique: 354)
Quote: Originally Posted by Sanmayce View Post
Tamalero, as a side note, noticed your uncached RAM latency is 99ns - probably this is the reason for relatively low score when comparing to the Jpmboy's superscore.
Jpmboy has 4 extra threads and higher clock.

Due to "make up" of Threadripper using memory mode Distributed or Local can make difference in some test cases.

Distributed mode 7-Zip link, AIDA64 link.

Local mode 7-Zip link, AIDA64 link.

Last edited by gupsterg; 01-29-2018 at 03:27 PM.
gupsterg is offline  
post #9 of 85 (permalink) Old 01-29-2018, 04:01 PM - Thread Starter
Integer Benchmarker
 
Sanmayce's Avatar
 
Join Date: Mar 2012
Location: Sofia
Posts: 399
Rep: 22 (Unique: 19)
Many thanks gupsterg, didn't know of existence of these modes.

At once the difference is seen:
In Distributed mode, RAM latency is 88ns which directly affects compression rate - 61239 KB/s
In Local mode, RAM latency is 66ns which directly affects compression rate - 51026 KB/s

How come? The greater latency yielded 10MB/s more speed?!
Excuse my dumb question, but at what frequency your Threadripper was overclocked in the test? CPU-Z shows some non-turbo one?

Hate that cannot rep up Tamalero and gupsterg!

Code:
---------------------------------------------------------------------------------------------------------------------
| OCN username | CPU                | Threads | CPU frequency OC | RAM frequency OC | RAM (CL) | Decompression MIPS |
---------------------------------------------------------------------------------------------------------------------
| Jpmboy       | Core i9 7980XE     | 36      | 4.5GHz           | 4000MHz          | 16       | 114481             |
| gupsterg     | Threadripper 1950X | 32      | ?GHz             | 3200MHz          | 14       | 94081              |
| Tamalero     | Threadripper 1950X | 32      | 3.9GHz           | 3066MHz          | 16       | 92922              |
| DStealth     | Core i7 8700K      | 12      | 5552MHz          | 4000MHz          | 16       | 49426              |
| Diablosbud   | Ryzen 5 1600       | 12      | 3.875 GHz        | 3200MHz          | 14       | 36784              |
| Sanmayce     | Core i5 7200U      | 4       | 2712MHz          | 2133MHz          | 15       | 9056               |
---------------------------------------------------------------------------------------------------------------------
Oh, just saw those modes explained, these articles explain the "controversy":
http://www.tomshardware.co.uk/amd-ry...w-33976-2.html
https://www.pcper.com/reviews/Proces...ocality-concer




As far as I understand, the rest 2/4 CCXes (core complex) are cut off and stall:
- "The memory latency between the four cores on each CCX was around 40ns, while the latency between any two cores on opposing CCXs was near 140ns."
- "What is most important to understand is that there are four distinct levels of latency on the Threadripper CPU: per-core, per-CCX, per-die, and cross-die. When running at DDR4 2400 MHz memory speeds (which directly relates to the speed of the Infinity Fabric), the memory latency for threads sharing the same core is ~21ns and for threads on the same CCX about ~48ns. When we cross from a CCX to another CCX on the same physical die, latency jumps to ~143ns, identical to what we measured on the Ryzen 7/5/3 family of CPUs. However, once memory accesses need to cross from one die to the next, latency jumps to over 250ns."





Simply, by looking at graph below, we can see that using more than 16 threads (cross-die) on Threadripper (as our case which enforces 32 threads) we are penalized by some 100ns, nasty.



"Remember, each Zeppelin die has its own memory and PCIe controllers. That means that if a workload executing on a die needs to access data resident in the memory of the other die (remote memory), it has to traverse a much larger gap. This introduces a level of latency we haven't seen from previous Ryzen models, and its effect on gaming performance is profound. The impact isn't as severe with most professional workloads, but some do suffer. "

Get down get down get down get it on show love and give it up
What are you waiting on?

Last edited by Sanmayce; 01-29-2018 at 05:27 PM. Reason: Adding the possible reason for 2x decrease in compression rate
Sanmayce is offline  
post #10 of 85 (permalink) Old 01-29-2018, 06:11 PM
New to Overclock.net
 
Tamalero's Avatar
 
Join Date: Dec 2016
Posts: 322
Rep: 5 (Unique: 5)
Quote: Originally Posted by Sanmayce View Post
Thank you Tamalero, very useful and informative!
Code:
---------------------------------------------------------------------------------------------------------------------
| OCN username | CPU                | Threads | CPU frequency OC | RAM frequency OC | RAM (CL) | Decompression MIPS |
---------------------------------------------------------------------------------------------------------------------
| Jpmboy       | Core i9 7980XE     | 36      | 4.5GHz           | 4000MHz          | 16       | 114481             |
| Tamalero     | Threadripper 1950X | 32      | 3.9GHz           | 3066MHz          | 16       | 92922              |
| DStealth     | Core i7 8700K      | 12      | 5552MHz          | 4000MHz          | 16       | 49426              |
| Diablosbud   | Ryzen 5 1600       | 12      | 3.875 GHz        | 3200MHz          | 14       | 36784              |
| Sanmayce     | Core i5 7200U      | 4       | 2712MHz          | 2133MHz          | 15       | 9056               |
---------------------------------------------------------------------------------------------------------------------
Since your utilization is 3094%, you are right, those open tabs undermine the score, maybe by 80-90% - or one thread. Love Threadripper, despite it being thrashed in Compression Department by 113234 KB/s / 56882KB/s = 1.99 or 2x ?! This is quite bad since Threadripper with its 512KB L2 per core should thrash 'em all in compression speed.

In my opinion the highest values (among all passes) should be used as "Result[ant]", sadly Igor uses as "Result" the value obtained in the first pass/run - which serves no purpose when the highest is sought. For me, it is necessary to manually write down the best score between runs - unacceptable. Anyway, it is what it is. Tamalero, as a side note, noticed your uncached RAM latency is 99ns - probably this is the reason for relatively low score when comparing to the Jpmboy's superscore.
Here is my score with only basic background aps running (antivirus, firewall)

The highest MIPS before settling was around 89,500 in the compress test and around 110,000 on the decompress.

Also, forgot to say.. I'm in creator's mode (Distributed).
Attached Thumbnails
Click image for larger version

Name:	jQPrcdbb.jpg
Views:	52
Size:	208.5 KB
ID:	64025  

Tamalero 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