iXBT Labs - Computer Hardware in Detail

Platform

Video

Multimedia

Mobile

Other

Intel Core 2 Extreme QX9770 in Real-Life Apps

How memory speed affects CPU performance.

September 30, 2008



<< Previous page

     Next page >>

In this article we return to memory speed and its effect on PC performance in real-life applications. Last time we were interested in Phenom X4 9850. Today we'll analyze a top processor from the other company -- Intel Core 2 Extreme QX9770. We decided to leave test conditions as they were in the previous review: first we run tests with fast memory, then we halve memory frequency in BIOS and run tests again.



In order to preserve the principle of reducing memory frequency precisely by half, we ran first tests with DDR3-1600 memory (800 MHz), even though our memory modules could do better. However, we witnessed an interesting effect: having compared results of the QX9770 processor with DDR3-1800 and DDR3-1600 memory, we found out that the latter turned out to perform... better. Probably owing to better "synchronism" of memory and FSB frequencies. For that matter we did a "silent update" of QX9770 results in this review. So if you want to see where QX9770 wins another point or two, you are welcome.



So, the second round of tests was run with DDR3-800 memory. Some of our readers may note that such memory makes no practical sense at all. But in this case we are not interested in practical sense, we just recreate a situation, when CPU's access to memory is artificially slowed down twofold, so our choice is well justified. It goes without saying that we use our Corsair CMX3X1024-1800C7DIN memory modules, we just modified their operating frequency in BIOS.



Tests

As always in such cases, we are particularly but not exclusively interested in performance results obtained in real-life applications, so we replaced diagrams with tables again, and virtual points with raw test results. The "Gain" column shows performance gains for Intel Core 2 Extreme QX9770. The "X4 9850" column shows performance gains, demonstrated in similar conditions by AMD Phenom X4 9850.

3D modeling and rendering


  DDR3-800 DDR3-1600 Gain X4 9850
3ds max
CPU Render 9.80 10.16 4% 1%
Graphics 4.42 4.47 1% 1%
Hardware Shaders 11.67 11.91 2% 2%
Maya
GFX 3.99 4.22 6% 6%
CPU 7.59 8.10 7% 5%
Render 0:04:48 0:04:47 0% 0%
Lightwave 0:06:42 0:06:42 0% 0%
Group score 129 132 3% 2%

It's worth mentioning an unusual 4% render performance gain on QX9770. As a rule, render speed does not depend much on memory bandwidth. In other respects, Intel and AMD processors demonstrate similar performance gains in the same tests. By the way, their performance gains are far from huge.

CAD/CAM


  DDR3-800 DDR3-1600 Gain X4 9850
UGS NX
Total CPU 4.33 4.46 3% 3%
Total Graphics 2.14 2.18 2% 5%
Pro/ENGINEER
CPU Related tasks 524 515 2% 1%
Graphics Related tasks 701 675 4% 4%
SolidWorks
Graphics 53.29 51.27 4% 5%
CPU 41.02 39.03 5% 2%
Group score 126 130 3% 3%

Both QX9770 and X4 9850 demonstrate the average performance gain of 3%, but this result is formed differently in each case: the X4 9850 gets the biggest gain in the graphics part of UGS NX test, while the Intel system accelerates noticeably in the CPU test of SolidWorks. We are not aware of any "commentable" details in this case, so we'll just write it off to "application specifics".

Compiling


  DDR3-800 DDR3-1600 Gain X4 9850
VisualStudio 0:22:56 0:22:29 2% 3%
Group score 130 132 2% 3%

The system based on the processor from Intel is less sensitive to memory performance. Probably owing to larger caches.

Professional photo processing


  DDR3-800 DDR3-1600 Gain X4 9850
Photoshop
Blur 0:04:28 0:04:10 7% 5%
Color 0:00:56 0:00:56 0% 0%
Filters 0:03:42 0:03:40 1% 1%
Light 0:01:26 0:01:26 0% 1%
Rotate 0:02:06 0:01:56 9% 6%
Sharp 0:02:02 0:01:44 17% 6%
Size 0:00:42 0:00:40 5% 3%
Transform 0:01:34 0:01:28 7% 6%
Group score 138 146 6% 3%

Adobe Photoshop takes advantage of faster memory more effectively with the QX9770 processor -- twice as efficiently as with Phenom X4 9850. Alas, "twice as efficiently" in this case means just 6% versus 3%, that is very little at best.


Write a comment below. No registration needed!


Next page >>

Article navigation:

Page 1: Introduction, tests

Page 2: More tests, conclusions



blog comments powered by Disqus

  Most Popular Reviews More    RSS  

AMD Phenom II X4 955, Phenom II X4 960T, Phenom II X6 1075T, and Intel Pentium G2120, Core i3-3220, Core i5-3330 Processors

Comparing old, cheap solutions from AMD with new, budget offerings from Intel.
February 1, 2013 · Processor Roundups

Inno3D GeForce GTX 670 iChill, Inno3D GeForce GTX 660 Ti Graphics Cards

A couple of mid-range adapters with original cooling systems.
January 30, 2013 · Video cards: NVIDIA GPUs

Creative Sound Blaster X-Fi Surround 5.1

An external X-Fi solution in tests.
September 9, 2008 · Sound Cards

AMD FX-8350 Processor

The first worthwhile Piledriver CPU.
September 11, 2012 · Processors: AMD

Consumed Power, Energy Consumption: Ivy Bridge vs. Sandy Bridge

Trying out the new method.
September 18, 2012 · Processors: Intel
  Latest Reviews More    RSS  

i3DSpeed, September 2013

Retested all graphics cards with the new drivers.
Oct 18, 2013 · 3Digests

i3DSpeed, August 2013

Added new benchmarks: BioShock Infinite and Metro: Last Light.
Sep 06, 2013 · 3Digests

i3DSpeed, July 2013

Added the test results of NVIDIA GeForce GTX 760 and AMD Radeon HD 7730.
Aug 05, 2013 · 3Digests

Gainward GeForce GTX 650 Ti BOOST 2GB Golden Sample Graphics Card

An excellent hybrid of GeForce GTX 650 Ti and GeForce GTX 660.
Jun 24, 2013 · Video cards: NVIDIA GPUs

i3DSpeed, May 2013

Added the test results of NVIDIA GeForce GTX 770/780.
Jun 03, 2013 · 3Digests
  Latest News More    RSS  

Platform  ·  Video  ·  Multimedia  ·  Mobile  ·  Other  ||  About us & Privacy policy  ·  Twitter  ·  Facebook


Copyright © Byrds Research & Publishing, Ltd., 1997–2011. All rights reserved.