|
|
#1 | |
|
Registered User
Join Date: Dec 2004
Posts: 254
|
Thought I'd check how the performance of my new 6800 compared to other's results.
Did a quick google search and found this: http://www.computerbase.de/news/hard...c_viewperf_801 Ran the 3dsmax test, ran it again without a WM, ran it with nvagp instead of agpgart results varied 0.1 points. Best results I got was: 3dsmax-03 Weighted Geometric Mean = 12.72 why is it that low?!? This is on ubuntu (XFree 6.7, patched a LOT) on a custom kernel without a WM running. Could someone else install and test this? (simple matter of downloading it from spec.org's homepage http://www.spec.org/gpc/downloadindex.html SPECviewperf 8.0.1, note, huge download, not for 56k'ers ), unpack, cd src && ./CONFIGURE && make && cp viewperf ../viewperf and it should work.To run one test instead of all of em run: #./Run_Viewset.csh 3dsmax-03 3dsmax results #grep "Mean" sum_results/3dsmax/summary.txt |
|
|
|
|
|
|
#2 | |
|
Join Date: Jul 2002
Location: Netherlands, Europe
Posts: 2,105
|
A benchmark is never reliable when you run it only once. A more reliable way is to run the benchmark lets say 3 times and take the average or even better is to run it 5 times and then to remove the fastest and slowest result and then also take the average. Further don't vary two things at the same time if you want to know the influence of the agp drivers and the WM.
|
|
|
|
|
|
|
#3 |
|
Registered User
Join Date: Dec 2004
Posts: 254
|
... booting into no WM and running it should make the performance basically identical every time.
either way, I ran it 3 times and saw a 0.1 point difference. I'm not interested in the difference between agpgart/nvagp, I'm interested how he got 5 points more than me on the same hardware (a massive increase in this benchmark). also if anyone has any suggestions on alternate stuff to benchmark, that'd be great. |
|
|
|
|
|
#4 | |
|
Join Date: Jul 2002
Location: Netherlands, Europe
Posts: 2,105
|
As you look well those tests are done on Windows and also with different driver versions. Because of this it is comparing apples with oranges as in the OS lots of things work differently further note it is not 5 points but 5000 points as they use "," instead of ".". Further is your cpu and so the same too?
|
|
|
|
|
|
|
#5 |
|
Registered User
Join Date: Dec 2004
Posts: 254
|
ahh, it showed up in a google search including linux, and it was in german, so I didn't think about checking the OS.
I'd still like to know what results other people are getting though ![]() |
|
|
|
|
|
#6 | |
|
Registered User
Join Date: Nov 2003
Posts: 13
|
Code:
Viewset: maya-01
Vendor System Model: Linux unknown
Graphics Accelerator: GeForce
GRAPHICS HARDWARE CONFIGURATION
-------------------------------
Graphics Accelerator: GeForce
Total Graphics Memory: 13 MB
Image Buffer: 24+24 bits
Overlay/Underlay Buffer: ?/? bits
Depth Buffer: 24 bits
Stencil Buffer: 8 bits
Accumulation Buffer: ? bits or Virtual Memory
Auxiliary Buffer: ? bits or Virtual Memory
Other Buffer: ? bits (0 bits if none)
Display List Memory: ? MB or Virtual Memory
Texture Memory: ? MB or Virtual Memory
Display Manufacturer/Model: ?/?
Display Resolution: 1280x1024
Display Size/Type: ??-Inch/Color
Display Refresh Rate: ? Hz
Swap on Vertical Retrace: Yes or No
SYSTEM HARDWARE CONFIGURATION
-----------------------------
Processor Type: AMD Athlon(tm) XP 2400+
Number of CPUs: 1
Floating Point: Integral or chip desciption/speed
Primary Cache (KB): 256 KB
Secondary Cache (KB): unknown
Tertiary Cache (KB): ? (0 if none)
Memory (MB): 504
Disk (MB): ?
List Price (as of ?/?/????)
--------------------------
$??,??? (includes monitor)
Test Date: 03/2005
General Availability: Now or MM/YYYY
SOFTWARE CONFIGURATION
----------------------
Operating System: Linux 2.4.26 #8 Wed Oct 6 13:00:53 CEST 2004
O/S Type: Unix
Compiler Name: ?
Compiler Version: ?
Window System: X11R6
OpenGL Version: 1.5.3 NVIDIA 71.67
OpenGL Renderer: GeForce FX 5600 Ultra/AGP/SSE/3DNOW!
OpenGL Vendor: NVIDIA CORPORATION
Viewperf Version: 8.0
Driver Version: N/A
Comments
--------
??? (leave blank if none)
maya-01 Viewset
------------------------------------------------------------------------------------------------------------------
Test Weight Frames DLB Visual Level Double Stereo Frame Buffer Depth Stencil Accumulation Buffer
# % Per Sec Sec ID Buffer Enabled Red Green Blue Alpha Buffer Buffer Red Green Blue Alpha
------------------------------------------------------------------------------------------------------------------
1 11.00 13.7 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
2 11.00 9.30 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
3 11.00 5.39 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
4 11.00 3.14 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
5 12.00 3.28 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
6 11.00 18.8 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
7 11.00 13.0 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
8 11.00 12.0 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
9 11.00 8.46 N/A 0X21 N True False 8 8 8 0 24 8 16 16 16 16
------------------------------------------------------------------------------------------------------------------
maya-01 Weighted Geometric Mean = 8.166
![]() |
|
|
|
|
![]() |
| Thread Tools | |
|
|
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| Disk Performance Expectations vs. Reality | News | Latest Tech And Game Headlines | 0 | 05-27-12 03:00 PM |
| Boost Your Performance Goals 10x ' This Week on inside* Publications | News | Latest Tech And Game Headlines | 0 | 05-13-12 05:20 PM |
| How to make the GPU stay in Performance Level 2 on battery? | pjman | NVIDIA Linux | 0 | 05-12-12 12:33 AM |
| NVIDIA Unleashes the GeForce GTX 670 Graphics Card ' Performance Perfected (WCCFTECH) | News | GeForce GTX 670 Reviews | 0 | 05-10-12 08:40 AM |
| My UT2003 Tweak Guide | DXnfiniteFX | Gaming Central | 48 | 10-30-02 11:59 PM |