Sign in with
Sign up | Sign in

Test Setup

DDR3 Memory Scaling: Intel's Core 2 Quad Examined
By
System Hardware
Hardware
Details
CPU Intel
Intel Core 2 Extreme QX9770 (45 nm, 3.2 GHz, 12 MB L2 Cache, TDP 130 W, Rev. D0)
Motherboard (Socket 775)
Gigabyte X48T-DQ6 (Rev. 1.0)
Chipset: Intel X48, ICH9R
BIOS: F6D (04/24/2009)
RAM DDR3 (dual)
2 x 2 GB DDR3-1600 (Corsair CM3X2G1600C9DHX)
2 x 1 GB DDR3-1600 (Crucial BL12864BA1608.8SFB)
Graphics
Zotac Geforce GTX 260²
GPU: Geforce GTX 260 (576 MHz)
Graphics RAM: 896 MB DDR3 (1998 MHz)
Stream Processors: 216
Shader Clock: 1242 MHz
Hard Drive
Western Digital VelociRaptor, 300 GB (WD3000HLFS)
10,000 RPM, SATA/300, 16 MB Cache
Blu-Ray Drive
LG GGW-H20L, SATA/150
Power Supply
Fortron Everest 1010, 1010 W
System Software & Drivers
Operating System
Windows Vista Enterprise Version 6.0 x64
Service Pack 2 (Build 6000)
Drivers and Settings
Nvidia GeForce Drivers
Forceware 185.85
Intel Chipset Drivers
Chipset Installation Utility Ver. 9.1.0.1012
Intel Storage Drivers
Matrix Storage Drivers Ver. 8.8.0.1009
3D Games Benchmarks
Far Cry 2
Version: 1.0.1
Far Cry 2 Benchmark Tool
Video Mode: 1280x800
Direct3D 9
Overall Quality: Medium
Bloom activated
HDR off
Demo: Ranch Small
GTA IV
Version: 1.0.3
Video Mode: 1280x1024
- 1280x1024
- Aspect Ratio: Auto
- All options: Medium
- View Distance: 30
- Detail Distance: 100
- Vehicle Density: 100
- Shadow Density: 16
- Definition: On
- Vsync: Off
Ingame Benchmark
Left 4 Dead
Version: 1.0.0.5
Video Mode: 1280x800
Game Settings
- Anti Aliasing none
- Filtering Trilinear
- Wait for vertical sync disabled
- Shader Detail Medium
- Effect Detail Medium
- Model/Texture Detail Medium
Demo: THG Demo 1
Audio Benchmarks and Settings
iTunes
Version: 8.1.0.52
Audio CD ("Terminator II" SE), 53 min.
Convert to AAC audio format
Lame MP3
Version 3.98
Audio CD "Terminator II SE", 53 min
convert wav to mp3 audio format
Command: -b 160 --nores (160 kbps)
Video Benchmarks and Settings
TMPEG 4.6
Version: 4.6.3.268
Video: Terminator 2 SE DVD (720x576, 16:9) 5 Minutes
Audio: Dolby Digital, 48000 Hz, 6-Channel, English
Advanced Acoustic Engine MP3 Encoder (160 kbps, 44.1 KHz)
DiVX  6.8.5
Version: 6.8.5
== Main Menu ==
default
== Codec Menu ==
Encoding mode: Insane Quality
Enhanced multithreading
Enabled using SSE4
Quarter-pixel search
== Video Menu ==
Quantization: MPEG-2
XviD 1.2.1
Version: 1.2.1
Other Options / Encoder Menu -
Display encoding status = off
Mainconcept Reference 1.6.1
Version: 1.6.1
MPEG2 to MPEG2 (H.264)
MainConcept H.264/AVC Codec
28 sec HDTV 1920x1080 (MPEG2)
Audio:
MPEG2 (44.1 kHz, 2 Channel, 16 Bit, 224 kbps)
Codec: H.264
Mode: PAL (25 FPS)
Profile: Settings for eight threads
Adobe Premiere Pro CS4
Version: 4.0
WMV 1920x1080 (39 sec)
Export: Adobe Media Encoder
== Video ==
H.264 Blu-ray
1440x1080i 25 High Quality
Encoding Passes: one
Bitrate Mode: Vbr
Frame: 1440x1080
Frame Rate: 25
== Audio ==
PCM Audio, 48 kHz, Stereo
EncodingPasses: one
Application Benchmarks and Settings
Grisoft AVG Anti-Virus 8
Version: 8.5.287
Virus base: 270.12.16/2094
Benchmark
Scan: compressed ZIP and RAR archives
Winrar 3.9
Version 3.90 x64 BETA 1
Best compression
Benchmark: THG Workload
Winzip 12
Version 12.0 (8252)
WinZIP command line Version 3
Compression = Best
Dictionary = 4096 KB
Benchmark: THG Workload
Autodesk 3D Studio Max 2009
Version: 9.0, x64
Rendering Dragon Image
Resolution: 1920 x 1280 (frame 1-5)
Adobe Photoshop CS 4 (64-bit)
Version: 11
Filtering a 16 MB TIF (15000x7266)
Filters:
Radial Blur (Amount: 10; Method: zoom; Quality: good)
Shape Blur (Radius: 46 px; custom shape: Trademark symbol)
Median (Radius: 1px)
Polar Coordinates (Rectangular to Polar)
Adobe Acrobat 9 Professional
Version: 9.0.0 (Extended)
== Printing Preferences Menu ==
Default Settings: Standard
== Adobe PDF Security - Edit Menu ==
Encrypt all documents (128 bit RC4)
Open Password: 123
Permissions Password: 321
Synthetic Benchmarks and Settings
3DMark Vantage
Version: 1.02
Options: Performance
Graphics Test 1
Graphics Test 2
CPU Test 1
CPU Test 2
PCMark Vantage
Version: 1.00
PCMark Benchmark
Memories Benchmark
SiSoftware Sandra 2009
Version: 2009 SP3
Processor Arithmetic, Cryptography, Memory Bandwidth
Display all 15 comments.
This thread is closed for comments
Top Comments
  • 12 Hide
    cknobman , June 29, 2009 1:22 PM
    To Gin and everyone else bitching about not doing core i7 why dont you actually use your eyes and look for the article. They did a ddr3 scaling article with i7 last week.

    Some people are too quick to bitch and criticize around here.
Other Comments
  • 0 Hide
    doomtomb , June 29, 2009 6:30 AM
    Good read, but shouldn't this article have been done like last year with Core 2 Quad?
  • -4 Hide
    Gin Fushicho , June 29, 2009 9:09 AM
    agreed. you guys have Core i7's laying around , use those.
  • 3 Hide
    scook9 , June 29, 2009 12:42 PM
    the reason they did this using the core 2 quad and not a core i7 is that each processor/chipsets handles its memory differently, so they wanted to see what core 2 quads would do this time.

    I would like to see (or would have liked in the past?) a good comparison between ddr2 and ddr3 on an otherwise identical platform - I assume you would have to use one of those p35/45 boards with both sets of DIMMs.
  • -2 Hide
    raptor550 , June 29, 2009 1:09 PM
    Even 6 months ago was too late. I wouldn't buy 775 because its days of development are limited. Since I am poor I chose the AM3 because at least in a few years AMD will still be developing the platform and I can upgrade my CPU and memory, etc.
  • 0 Hide
    bunz_of_steel , June 29, 2009 1:20 PM
    Not alot of diff in encodeing times. Looks like better off bumping up cpu or putting the $ into terabytes.
  • 12 Hide
    cknobman , June 29, 2009 1:22 PM
    To Gin and everyone else bitching about not doing core i7 why dont you actually use your eyes and look for the article. They did a ddr3 scaling article with i7 last week.

    Some people are too quick to bitch and criticize around here.
  • 6 Hide
    cknobman , June 29, 2009 1:23 PM
    They did a core i7 scaling article last week you morons.

    Quit being so quick to bitch and criticize.
  • 0 Hide
    snarfies , June 29, 2009 1:55 PM
    I should like to point out that Core 2 has been around for VERY much longer than i7 - a LOT more people, myself included, are still using Core 2 quads. And I see no compelling reason to upgrade anytime soon, since there just isn't much out there that require more power than that.
  • 0 Hide
    bounty , June 29, 2009 2:26 PM
    I had this same issue with Anandtech's recent memory scaling article. With DDR3 1600 at 999-24 going for 85$ with free shipping, why buy the slower stuff? Sure you can get DDR3 1333 for 10$ less (without free shipping, and only 1 product at that price on newegg 3x2GB ) but I think you're sacrificing some flexibility when overclocking and some speed in games etc. If you're buying DDR3 then you don't have a slow cpu probably... If it was more than 10$ I could understand.
  • 0 Hide
    avericia , June 29, 2009 5:28 PM
    Great article I got a q9550 last November and I have been curious how much gains faster ddr3 would be with this chip and now i know :p 

    I just got a Gskill 4g kit of ddr2 1100 5-5-5-15 1.8v to replace my dieing corsair sticks and so far it seems to be running great on my 780iftw.

    I'm still very happy with my purchase of my q9550 because only very recently can you build a i7 platform for the same price as the 775 setup cost 9 months ago and the difference in fps for most games going to the i7 from a core2 quad is minimal for running sli 55nm @65nm 260 216 @666 at 1920x1200 in most games so I will hold over until the gulftown comes out and ddr3 is even cheaper and faster :p 
  • 0 Hide
    Proximon , June 29, 2009 5:43 PM
    I agree that LGA 775 is not completely useless just yet, although others make excellent points about AM3 and LGA 1156. I do think that any discussion like this ought to consider the lifespan of DDR3 and the possibility that some future processor will make better use of increased memory speeds.
    CAS 7 DDR3 1600 is quite inexpensive actually, and if there is a possibility it might be more useful in the future, wouldn't it be worth the 5 bucks extra today?
  • 0 Hide
    Honis , June 29, 2009 9:36 PM
    I'd like to see the DDR3 1600 under clocked to 800 levels and see how low the latency can be set. I'm sure clock speed is more prevalent than latency but would be interesting to see latencies of 4 again.
  • -1 Hide
    stefanrp97 , June 29, 2009 10:41 PM
    This article fails to test an important point. LOW LATENCY. If the best latencies at the designated speeds were used, that would give me a much better idea on what to spend my money on. It doesn't help me to show DDR1066 at DDR1600 latencies. Which will be better at those settings? The answer is obvious.
  • 0 Hide
    Anonymous , June 30, 2009 2:07 AM
    Great Article. DDR2 Vs. DDR3 is the typical conundrul, "Winds of Change", question on many core 2, and core 2 quad owner's minds. Do I upgrade my current system, or go with the new platform for performance per dollar gains? I understand that DDR3 is the future, but it would be nice to see DDR2 added to the test platform so that the DDR2 loyalists are given a reason to upgrade that they can not resist, or perhaps a reason not to. Like most computer subsystems that are not responsible for sales hype, memory, (whoops, other than triple channel coreI7), are often overlooked it seems in the coding world, as bandwidth gains on the hardware front rarely, if ever are realized by software. If given a bottle that might contain a genie, I'd give it a rub and ask,"Please ask Tomshardware, gifted with the best testers and hardware that money can buy, not only test the speed/latency of top memory chips, but spend some time in BIOS pushing the memory sub-system cycle to its limit per clock". In doing so, we would all have clear evidence to email the coders, and I expect by next year, we'd see the benifit of the highspeed/low latency memory that this article shows we now lack.
  • 0 Hide
    hotbbq , July 1, 2009 3:22 PM
    There really isn't a premium on high-bandwidth, low latency DDR3 these days. I picked up 4GB of DDR3-1600 with 7-6-6-24 timings from Newegg last month. Price after MIR was $55. It replaced my 4GB of DDR3-1333 with almost the same timings that I originally bought for $300. The faster rate memory allowed me much more head room to over clock my Q9450.