| Author |
Message |
rallynavvie
internal affairs
Joined: 10 Sep 2002
Location: Minnesotan in Texas
|
|
| Quote: |
Top results returned as of 11/05/05: (stock results only)
26 seconds - btrager (Manchester 4600X2)
48 seconds - funsoul (2x Prestonia 2.4)
55 seconds - BJ_M (Northwood 2.66)
65 seconds - cryolock (Prescott 3.0) and waheed (Newcastle 3500) |
To help those of us new to encoding who want to build a new system and for the curiosity in all of us let's make our own benchmarking results page!
What you need to participate:
A PC (sorry, no Mac users allowed yet  )
CPU-Z
TMPGEnc 2.5x
The source AVI file Self-Extractable part 1 and part two to go with above
(thanks to BJ_M for the clips!)
The TMPGEnc settings file
What to do:
1. Download each of the above files.
2. Install TMPGEnc 2.5x and open it up. Use the guides for TMPGEnc on this website to optimize it for your system (basically by checking every option available on the CPU tab of the "Environmental Settings").
3. Run CPU-Z to identify your system properly. Post your processor speed (bus/cache/core if known), amount and speed of memory (timings if known), and your system chipset (found under the Mainboard tab of CPU-Z).
4. Next go back to TMPGEnc and load up the clip to encode using the supplied settings file. If possible encode to a different hard drive than the one where the original file resides. Post what model/speed of hard drive you reading from and encoding to, or if you have only one in your system than just that drive's information.
5. Make sure your system is free to run the benchmark (limit what processes are running if you can) and run the encode of the file!
6.When the batch log pops up at the end note the total time elapsed and the times for the file and then post them here with everything else!
I'll take the time to cull the results and make up some sort of chart to display them all once we get a lot of posts up. If you have more than one system then please benchmark them all! If you notice a setting that makes for faster marks (like enabling/disabling HT) share it with us! We aren't going to ask for proof of the marks so we're trusting you to give us real results. The purpose of this isn't to show whose computer is faster (since we all know different systems are good at doing different things better than other systems) but since this is a video-oriented site this may prove pretty useful to some of us.
mine is faster 
Have fun!
_________________
NE CEDE MALIS SED CONTRA AUDENTIOR ITO
Last edited by rallynavvie on Nov 05, 2005 01:20, edited 6 times in total
|
|
thecoalman
Member
Joined: 25 Feb 2004
Location: Pennsylvania
|
|
Couldn't figure out how to do a batch nor did I get a log file but anyway.....
After loading the template the elapsed time is reported as 39 seconds for the first file and 43 seconds for the second file in TMPGenc interface.
That's from a 120G Seagate Bar. 7200 SATA to the same... Also I disable some processes without getting crazy. I had about 29 going
I got this by gong to the last tab in cpuz and outputting a html file, cut and paste.... 
Name Intel Pentium 4
Code Name Northwood
Specification Intel(R) Pentium(R) 4 CPU 3.00GHz
Family / Model / Stepping F 2 9
Extended Family / Model 0 0
Brand ID 9
Package mPGA-478
Core Stepping D1
Technology 0.13 µ
Supported Instructions Sets MMX, SSE, SSE2
CPU Clock Speed 3014.6 MHz
Clock multiplier x 15.0
Front Side Bus Frequency 201.0 MHz
Bus Speed 803.9 MHz
L1 Data Cache 8 KBytes, 4-way set associative, 64 Bytes line size
L1 Trace Cache 12 Kµops, 8-way set associative
L2 Cache 512 KBytes, 8-way set associative, 64 Bytes line size
L2 Speed 3014.6 MHz (Full)
L2 Location On Chip
L2 Data Prefetch Logic yes
L2 Bus Width 256 bits
CPU#2 APIC ID = 1
CPU Name Intel Pentium 4 (logical unit)
Mainboard and chipset
Motherboard manufacturer Gigabyte Technology Co., Ltd.
Motherboard model 8IPE1000P, 1.x
BIOS vendor Award Software International, Inc.
BIOS revision FC
BIOS release date 03/03/2004
Chipset Intel i865P/PE/G/i848P rev. A2
Southbridge Intel 82801EB (ICH5) rev. 2
Sensor chip FFFF
FSB Select 800 MHz
Performance Mode disabled
Graphic Interface AGP
AGP Status enabled, rev. 3.0
AGP Data Transfert Rate 8x
AGP Max Rate 8x
AGP Side Band Addressing supported, enabled
AGP Aperture Size 128 MBytes
Memory
DRAM Type DDR-SDRAM
DRAM Size 1024 MBytes
DRAM Frequency 201.0 MHz
FSB:DRAM 1:1
CAS# Latency 2.5 clocks
RAS# to CAS# 3 clocks
RAS# Precharge 3 clocks
Cycle Time (TRAS) 8 clocks
# of memory modules 2
Module 0 Corsair DDR-SDRAM PC3200 - 512 MBytes
Module 1 Corsair DDR-SDRAM PC3200 - 512 MBytes
Software
Windows version Microsoft Windows XP Home Edition Service Pack 2 (Build 2600)
DirectX version 9.0c
| Quote: |
| Performance Mode disabled |
What is this Rally and how do I enable it? Or do I want to enable it?
_________________
Nepadigital Video Articles
|
|
Tommyknocker
Banned
Joined: 27 Apr 2002
Location: The State of Frustration
|
|
You may want to number your steps to make your guide more user friendly.
_________________
Deck the halls with boughs of holly;
Fa la la la la la la la la!!!
|
|
rallynavvie
internal affairs
Joined: 10 Sep 2002
Location: Minnesotan in Texas
|
|
Steps numbered.
Make sure to enable everything you can in the TMPGEnc "Environmental Settings" under the CPU tab as these are the instruction sets specific to our processors and will give better performance. Those with HT (be it the Intel or AMD version) let us know if it was enabled or not when you ran the test. Try running it without HT and see if it's any faster! You may learn something about your own system you didn't even know.
I have no idea what the "Performance Mode" thing is under the memory tab of CPU-Z. There are some issues with CPU-Z reading memory sometimes so the most important part of that tab is the speed and the timings.
_________________
NE CEDE MALIS SED CONTRA AUDENTIOR ITO
|
|
Cobra
Moderator
Joined: 06 May 2002
Location: UK
|
|
BJ_M
Patron
Joined: 30 Jul 2002
Location: Canada
|
|
here are both files above as one file - split w/ winrar (self extracting)
part1.exe
part2.rar
_________________
"Each problem that I solved became a rule which served afterwards to solve other problems." - Rene Descartes (1596-1650)
|
|
BJ_M
Patron
Joined: 30 Jul 2002
Location: Canada
|
|
| Cobra wrote: |
| AMD doesn't have a system like HyperThreading, does it? |
no
_________________
"Each problem that I solved became a rule which served afterwards to solve other problems." - Rene Descartes (1596-1650)
|
|
Cobra
Moderator
Joined: 06 May 2002
Location: UK
|
|
rallynavvie
internal affairs
Joined: 10 Sep 2002
Location: Minnesotan in Texas
|
|
HyperTransport, that's not HTT is it? All I know is it was something I had read about when researching Opteron systems.
When are we gonna get some results from your new rig Cobra? I'm kinda interested to see what that core can do for encoding. It's gotta absolutely fly for gaming though 
edit: HTT = HyperTransport Technology. When I had read of it I saw the diagram showing 3 HTT links to the processor and likened it to HyperThreading. It's similar but is implemented more like what the Mac processors have had for years. Now THAT is exciting. Macs have had processor throughput like the Amazon for years and now the x86 market is finally following. Fun
_________________
NE CEDE MALIS SED CONTRA AUDENTIOR ITO
|
|
rallynavvie
internal affairs
Joined: 10 Sep 2002
Location: Minnesotan in Texas
|
|
Come on folks, it's hard to put together results with only one return. Unfortunately I have to have coalman do it again with the new single file just to make sure it fits with the rest of the marks we'll see. 
_________________
NE CEDE MALIS SED CONTRA AUDENTIOR ITO
|
|
thecoalman
Member
Joined: 25 Feb 2004
Location: Pennsylvania
|
|
Cobra
Moderator
Joined: 06 May 2002
Location: UK
|
|
Rally,
I will run the benchmarks now.
I am thinking about making a sticky for the Computer forum explaining why it is that Intel CPUs (specifically the Pentium 4) are better for video encoding, and AMD chips are better for applications such as gaming. Do you think it would help?
_________________
Forum Rules :: PM me with any questions/problems/suggestions!
|
|
Cobra
Moderator
Joined: 06 May 2002
Location: UK
|
|
rallynavvie
internal affairs
Joined: 10 Sep 2002
Location: Minnesotan in Texas
|
|
| Cobra wrote: |
I am thinking about making a sticky for the Computer forum explaining why it is that Intel CPUs (specifically the Pentium 4) are better for video encoding, and AMD chips are better for applications such as gaming. Do you think it would help? |
No, you've got the Intel zealot here to keep folks in line
Maybe talk to Flaystus and have it added to the FAQ sticky. Speaking of whom I haven't seen him around lately...
_________________
NE CEDE MALIS SED CONTRA AUDENTIOR ITO
|
|
Faustus
insane.
Joined: 11 Apr 2002
Location: Dallas, TX
|
|
Last I checked AMD cpus were better for gaming and video and Intels were better of draining your wallet.
Processes were NOT disabled because I'm lazy. About 34 were loaded at the time.
Encode Time:
1:09 (One Minute and nine seconds)
Hard Drive: WD1200JB 120gb 7200rpm 8mb cache.
(encoding to 2nd drive on the same channel made NO difference in encode speeds)
Zcpu:
Number of CPUs 1
Name AMD Athlon XP
Code Name Barton
Specification AMD Athlon(tm) XP 3000+
Family / Model / Stepping 6 A 0
Extended Family / Model 7 A
Package Socket A
Technology 0.13 µ
Supported Instructions Sets MMX, Extended MMX, 3DNow!, Extended 3DNow!, SSE
CPU Clock Speed 2162.7 MHz
Clock multiplier x 13.0
Front Side Bus Frequency 166.4 MHz
Bus Speed 332.7 MHz
L1 Data Cache 64 KBytes, 2-way set associative, 64 Bytes line size
L1 Instruction Cache 64 KBytes, 2-way set associative, 64 Bytes line size
L2 Cache 512 KBytes, 16-way set associative, 64 Bytes line size
L2 Speed 2162.7 MHz (Full)
L2 Location On Chip
L2 Data Prefetch Logic yes
L2 Bus Width 64 bits
Mainboard and chipset
Motherboard manufacturer Shuttle Inc
Motherboard model AN35,
BIOS vendor Phoenix Technologies, LTD
BIOS revision 6.00 PG
BIOS release date 05/30/2003
Chipset nVidia nForce2 400 rev. C1
Southbridge nVidia nForce2 MCP rev. A4
Sensor chip FFFF
Graphic Interface AGP
AGP Status enabled, rev. 3.0
AGP Data Transfert Rate 8x
AGP Max Rate 8x
AGP Side Band Addressing supported, enabled
AGP Aperture Size 128 MBytes
Memory
DRAM Type DDR-SDRAM
DRAM Size 512 MBytes
DRAM Frequency 166.4 MHz
FSB:DRAM 1:1
CAS# Latency 2.0 clocks
RAS# to CAS# 3 clocks
RAS# Precharge 3 clocks
Cycle Time (TRAS) 7 clocks
# of memory modules 1
Module 0 Corsair DDR-SDRAM PC2700 - 512 MBytes
Software
Windows version Microsoft Windows XP Professional Service Pack 2 (Build 2600)
DirectX version 9.0c
|
|
Cobra
Moderator
Joined: 06 May 2002
Location: UK
|
|
thecoalman
Member
Joined: 25 Feb 2004
Location: Pennsylvania
|
|
| Flaystus wrote: |
Encode Time:
1:09 (One Minute and nine seconds)
|
OK WTF am I doing wrong, I could see if there was a marginal difference but comsidering all my shit is faster than yours. Is that for both videos? Am I missing something here, I'm not too familiar with the numbers and exactly whjat they represent.
_________________
Nepadigital Video Articles
|
|
rallynavvie
internal affairs
Joined: 10 Sep 2002
Location: Minnesotan in Texas
|
|
Did you get 1:22 total for the new file with both videos joined? Did you check all the boxes under the CPU tab in the settings for TMPGEnc? Until more folks post their findings I won't know if yours is out of the ordinary.
_________________
NE CEDE MALIS SED CONTRA AUDENTIOR ITO
|
|
BJ_M
Patron
Joined: 30 Jul 2002
Location: Canada
|
|
Number of encode frame = 214
Length of GOP = Average 32.92 field(s), MAX 36 field(s)
Average bitrate of video = 6999.80 kbps
VBV buffer size = 304 KB
Finished encoding video
--> 57 seconds first time i tried it
--> 59 seconds second time i tried it (with log file displayed this time)
---> 55 seconds , third time (this time i shut down everything running)
-------------------------------------------------------------
tmpgenc 2.512.52.161 - file and settings from above
source and target different drives .
Nothing special system -
ASUS P4P800SE
512 memory
2.66 P4 (no overclock on this one)
_________________
"Each problem that I solved became a rule which served afterwards to solve other problems." - Rene Descartes (1596-1650)
|
|
BJ_M
Patron
Joined: 30 Jul 2002
Location: Canada
|
|
I have found that the intel cpu to be better for encoding - nothing wrong with amd , i like them also ..
_________________
"Each problem that I solved became a rule which served afterwards to solve other problems." - Rene Descartes (1596-1650)
|
|
Delerious
Member
Joined: 22 Aug 2003
|
|
| rallynavvie wrote: |
I have no idea what the "Performance Mode" thing is under the memory tab of CPU-Z. There are some issues with CPU-Z reading memory sometimes so the most important part of that tab is the speed and the timings. |
Also known as Performance Acceleration Technology (PAT) , Memory
Acceleration Mode (on ASUS). Here's what Intel says about it:
http://www.intel.com/design/chipsets/pat.htm
J
|
|
thecoalman
Member
Joined: 25 Feb 2004
Location: Pennsylvania
|
|
| rallynavvie wrote: |
| Did you get 1:22 total for the new file with both videos joined? Did you check all the boxes under the CPU tab in the settings for TMPGEnc? Until more folks post their findings I won't know if yours is out of the ordinary. |
I got 1:24, I had a few things running though. HT is enabled. Now I compared the second screenshot of Cobra's to mine and I noticed two differences. His voltage is higher (Mine :1.52 His:1.6) and the multiplier id higher mine is 15x his is 20x. They are the same processor.Obviously some room for improvement, my system is running at 29 degrees idle and never got above 42 degrees while running the encode, fan never went higher than 2500.
_________________
Nepadigital Video Articles
|
|
Cobra
Moderator
Joined: 06 May 2002
Location: UK
|
|
You can't make me....