which processor for avisynth encoding

[foxyshadis]

A too-old version of mvtools.

[mooms]

A too-old version of mvtools.


i have 0.9.9.1 and i think is the latest version isn't it ?

[Pookie]

http://avisynth.org.ru/mvtools/mvtools.html

[mooms]

thanks Pookie that do the trick!

Specification AMD Athlon(tm) 64 Processor 3500+
L1 Data cache 64 KBytes, 2-way set associative, 64-byte line size
L1 Instruction cache 64 KBytes, 2-way set associative, 64-byte line size
L2 cache 512 KBytes, 16-way set associative, 64-byte line size

Total Memory Installed=1024 MB

256MB memory
bench: utime=292.438s

512MB memory
bench: utime=156.484s

960MB memory
bench: utime=95.578s

....with kaspersky emule sygate firefox and some others programs running in the background
i will test with no other proggies later

[BigDid]

New config E4300 Core2duo + Asrock 775 DualVSTA + 2*512 DDR 400 RAM (same as old config). No memory manager

Specification Intel(R) Core(TM)2 CPU 4300 @ 1.80GHz
L1 Data cache 2 x 32 KBytes, 8-way set associative, 64-byte line size
L1 Instruction cache 2 x 32 KBytes, 8-way set associative, 64-byte line size
Core Stepping L2
L2 cache 2048 KBytes, 8-way set associative, 64-byte line size
Total Memory Installed= 1024MB

Same avisynth config as in this post http://forum.doom9.org/showthread.php?p=937879#post937879 except avisynth 2.57.3 from TSP http://www.tsp.person.dk/avisynthMT257.3.zip and MT 0.5 http://www.avisynth.org/tsp/MT_05.zip

With 15 frames (trim 100,114) and trays programs:
E4300@1800Mhz
256MB memory
bench: utime=29.187s
512MB memory
bench: utime=25.484s
960MB memory
bench: utime=25.641s

E4300@2400Mhz
256MB memory
bench: utime=20.031s
512MB memory
bench: utime=19.953s
960MB memory
bench: utime=19.843s

E4300@2400Mhz + SetMt(2)
256MB memory
bench: utime=9.890s
512MB memory
bench: utime=9.500s
960MB memory
bench: utime=9.640s

With 30 frames (trim 100,129) and trays programs
E4300@2400Mhz + SetMt(2)
256MB memory
bench: utime=19.906s
512MB memory
bench: utime=19.953s
960MB memory
bench: utime=19.688s

Did

Edit: to get more info on the config, see this thread: http://forum.doom9.org/showthread.php?goto=newpost&t=120509

[Pookie]

You're beating the 6600s ?:confused:

[BigDid]

You're beating the 6600s ?:confused:
It seems so :D

Keep in mind this is not my final XP as I had to install a fresh one. I actually have the SP2, the MS corrections and updates, my MB and ATI drivers and dx9, Virus-scan8, the .Net 1.1,the RM clock utility, Supercopier, netmeter and that's all.

Also the first thing I tuned was the memory: see the hardware thread. I believe the 1t and mem@200 gains a lot.
Following is a partial dump of the cpuzinfo report:

CPU-Z version 1.38
-------------------------
Processors Map
------------------------------------------------------------------------------------
Number of processors 1
Number of threads 2

Processors Information
------------------------------------------------------------------------------------
Processor 1 (ID = 0)
Number of cores 2
Number of threads 2 (max 2)
Name Intel Core 2 Duo E4300
Codename Conroe
Specification Intel(R) Core(TM)2 CPU 4300 @ 1.80GHz
Package Socket 775 LGA (platform ID = 0h)
CPUID 6.F.2
Extended CPUID 6.F
Core Stepping L2
Technology 65 nm
Core Speed 1596.9 MHz (6.0 x 266.1 MHz)
Rated Bus speed 1064.6 MHz
Stock frequency 1800 MHz
Instructions sets MMX, SSE, SSE2, SSE3, SSSE3, EM64T
L1 Data cache 2 x 32 KBytes, 8-way set associative, 64-byte line size
L1 Instruction cache 2 x 32 KBytes, 8-way set associative, 64-byte line size
L2 cache 2048 KBytes, 8-way set associative, 64-byte line size
FID/VID Control yes
FID range 6.0x - 9.0x
max VID 1.213V

Chipset
------------------------------------------------------------------------------
Northbridge VIA PT880 Pro rev. 00
Southbridge VIA VT8237A rev. 00
Graphic Interface AGP
AGP Revision 3.0
AGP Transfer Rate 8x
AGP SBA supported, enabled
Memory Type DDR
Memory Size 1024 MBytes
Memory Frequency 199.6 MHz (4:3)
DRAM Interleave 4-way
CAS# 3.0
RAS# to CAS# 3
RAS# Precharge 3
Cycle Time (tRAS) 8
Command Rate 1T

Memory SPD
------------------------------------------------------------------------------
DIMM #1
General
Memory type DDR
Manufacturer (ID) Corsair (7F7F9E0000000000)
Size 512 MBytes
Max bandwidth PC3200 (200 MHz)
Part number CMX512-3200C2
Attributes
Number of banks 2
Data width 64 bits
Correction None
Registered no
Buffered no
EPP no
Timings table
Frequency (MHz) 200
CAS# 3.0
RAS# to CAS# delay 3
RAS# Precharge 3
TRAS 8

DIMM #2 (same as dimm1)

Monitoring
------------------------------------------------------------------------------
Sensor Chip Winbond W83697HF

PCI Device List
------------------------------------------------------------------------------
Host Bridge
bus 0 (0x00), device 0 (0x00), function 0 (0x00)
Common header
Vendor ID 0x1106
Model ID 0x0308
Revision ID 0x00
PI 0x00
SubClass 0x00
BaseClass 0x06
Cache Line 0x08
Latency 0x08
Header 0x80
PCI header
Address 0 (memory) 0xD0000000
Subvendor ID 0x1849
Subsystem ID 0x0308
Int. Line 0x00
Int. Pin 0x00
Capabilities
AGP Capability
Version 3.5
Status enabled
Transfer rate 8x (max 8x)
Queue lenght 2 (max 32)
Dump
00 01 02 03 04 05 06 07 08 09 0A 0B
02 50 35 00 1B 0A 00 1F 02 03 00 00
Power Management Capability
Version 1.1
Dump
00 01 02 03 04 05 06 07
01 00 02 00 00 00 00 00

DMI
------------------------------------------------------------------------------
DMI BIOS
--------
vendor American Megatrends Inc.
version P2.10
date 10/27/2006
DMI System Information
----------------------
manufacturer To Be Filled By O.E.M.
product 775Dual-VSTA
version To Be Filled By O.E.M.
serial To Be Filled By O.E.M.
UUID 00020003-00040005-00060007-00080009
DMI Baseboard
-------------
vendor unknown
model 775Dual-VSTA
revision unknown
serial unknown
DMI System Enclosure
--------------------
manufacturer To Be Filled By O.E.M.
chassis type Desktop
chassis serial To Be Filled By O.E.M.
DMI Processor
-------------
manufacturer Intel
model Intel(R) Core(TM)2 CPU 4300 @ 1.80GHz
clock speed 2400.0MHz
FSB speed 200.0MHz
multiplier 12.0x
DMI Memory Controller
---------------------
correction 64-bit ECC
Max module size 2048MBytes
DMI Memory Module
-----------------
designation DIMM0
size 512MBytes (double bank)
DMI Memory Module
-----------------
designation DIMM1
size 512MBytes (double bank)
DMI Extension Slot
------------------
designation PCI1
type PCI
width 32 bits
populated no
DMI Extension Slot
------------------
designation PCI2
type PCI
width 32 bits
populated no
DMI Extension Slot
------------------
designation PCI3
type PCI
width 32 bits
populated no
DMI Extension Slot
------------------
designation PCI4
type PCI
width 32 bits
populated no
DMI Extension Slot
------------------
designation PCIE1
type A5
populated no
DMI Physical Memory Array
-------------------------
location Motherboard
usage System Memory
correction None
max capacity 4096MBytes
max# of devices 2
DMI Memory Device
-----------------
designation DIMM0
format DIMM
type SDRAM
total width 64bits
data width 64bits
size 512MByte
DMI Memory Device
-----------------
designation DIMM1
format DIMM
type SDRAM
total width 64bits
data width 64bits
size 512MBytes

Software
------------------------------------------------------------------------------
Windows Version Microsoft Windows XP Professional Service Pack 2 (Build 2600)
DirectX Version 9.0c

Did

[BigDid]

Update!

1 change but big effect: changed net framework 1.1 (quicker) to net framework 2.0 (slower)
same config as post 155 above

With 30 frames (trim 100,129) and trays programs
.net 2.0
256MB memory
bench: utime=71.719s
512MB memory
bench: utime=39.657s
960MB memory
bench: utime=21.313s
.net 3.0
256MB memory
bench: utime=67.984s
512MB memory
bench: utime=33.562s
960MB memory
bench: utime=23.110s
Same in windows safe mode:
256MB memory
bench: utime=20.704s
512MB memory
bench: utime=20.422s
960MB memory
bench: utime=20.453s

Did

[Terka]

so which framework is faster? im not sure what results from your posts compare.

[Pookie]

BigDid, I suspect the transcoding is failing for you in Safe Mode. Might be interesting to note the size of the transcoded output file in normal and safe modes - betcha the Safe Mode one is small, maybe even 0 bytes ?

Aside from that, pretty nice to have a dual core that runs on DDR1 RAM. I've got tons of the stuff myself.

[BigDid]

so which framework is faster? im not sure what results from your posts compare.
Hi,

1.1 is faster than 2.0
Will install the 3.0 (2.0 compatible) and report if better.

If not 2 solutions: encode in safe mode or use the utility Pookie pointed out: FSautostart http://forum.doom9.org/showthread.php?p=943039#post943039

Edit: @Pookie
The files test.avi (258Mb) and out.avi (7.42Mb) have same size in normal or safemode for 15 frames.
Aside from that, pretty nice to have a dual core that runs on DDR1 RAM. I've got tons of the stuff myself. with (it seems) no real speed penalty for common use and an AGP slot.

Did

[Adub]

Oh, on my results, I was using .net version 3.0. In case that helps.

[BigDid]

Oh, on my results, I was using .net version 3.0. In case that helps.
Hi,

I updated the previous post http://forum.doom9.org/showthread.php?p=948720#post948720

Seems more or less same results (differences due to progs running or not, test run at Win startutp or not etc...)

I'll go for .net 3.0 or maybe not will see for encoding tests not just the avisynth script...

Did

Edit: Back to .net 2.0, a few percent better for encodes; once .net 3.0 is installed, you should have net 2.0 and below net 3.0
-> uninstall net 3.0 only and you will have net 2.0 still installed

[Pookie]

30 frame test = 15MB Resulting File
15 frame test = 7.5MB Resulting File

How would .NET versions affect the results of the test ?

E4300 selling for $180. Not bad ;)

[BigDid]

30 frame test = 15MB Resulting File
15 frame test = 7.5MB Resulting File
Hi,

It was for 15 frames, I edited the previous post.
How would .NET versions affect the results of the test ?
Cause it was the only change I made (1.1 to 2.0) and there is a process called "FrameworkService.exe" (and maybe others related I am not aware) running in background

Did

[Pookie]

Gotcha...