Intel Core i7 Memory Performance

January 26, 2009 | 10:11

Tags: #benchmarks #channel #compare #comparison #controller #core #ddr3 #dual #i7 #integrated #performance #single #testing #triple #x58

Companies: #corsair #intel

Paint.NET x64

Website: Paint.NET

This is the 64-bit version of the popular free image editing software, Paint.NET. It's not as advanced as something like Adobe Photoshop CS3 or Corel Paint Shop Pro Photo X2, but it does serve well for most image editing tasks.

We used the PDNBench script to test the processing times for a range of images and filters. The multi-threaded software also takes advantage of multi-core processors quite effectively.

For more information on what the benchmark script entails, please see this thread on the Paint.NET forums.

Timings: Paint.NET 3.20

  • 1708MHz OC 9-9-9-24-2T
  • 1600MHz 8-8-8-21-2T
  • 1333MHz 6-6-6-15-1T
  • 1066MHz 5-5-5-15-1T
  • 1600MHz 9-9-9-24-1T
  • 1066MHz 9-9-9-24-1T
  • 1333MHz 7-7-7-18-1T
  • 1600MHz 8-8-8-21-1T
  • 1066MHz 6-6-6-15-1T
  • 1066MHz 7-7-7-18-1T
  • 1333MHz 9-9-9-24-1T
  • 1333MHz 8-8-8-21-1T
  • 1066MHz 8-8-8-21-1T
  • 13.3
  • 14.0
  • 14.0
  • 14.0
  • 14.0
  • 14.1
  • 14.1
  • 14.1
  • 14.1
  • 14.1
  • 14.1
  • 14.1
  • 14.1
0
3
5.5
8
10.5
13
15.5
Seconds

Paint.NET is clearly CPU dependent here and changing the memory timings from the slowest to fastest possible does virtually nothing - maybe increments in the hundredths to thousandths of a second, but it's a completely arbitrary difference. Only the memory clocked to 1,708MHz makes a difference because the CPU is running at 3.4GHz, not 3.2GHz due to the slight elevation in base clock from 133MHz to 142MHz.

GIMP Image Editing

Website: GUN Image Manipulation Program (GIMP)

Our GIMP image editing test simulates how well a PC can manipulate a collection of large digital photos, and to achieve a low time requires a PC with a powerful CPU, plenty of quick memory and efficient hard disk drive access.

Timings: GIMP Image Editing Test

CustomPC Benchmark

  • 1708MHz OC 9-9-9-24-2T
  • 1600MHz 8-8-8-21-2T
  • 1600MHz 8-8-8-21-1T
  • 1066MHz 5-5-5-15-1T
  • 1066MHz 7-7-7-18-1T
  • 1066MHz 6-6-6-15-1T
  • 1066MHz 8-8-8-21-1T
  • 1333MHz 6-6-6-15-1T
  • 1333MHz 8-8-8-21-1T
  • 1600MHz 9-9-9-24-1T
  • 1333MHz 7-7-7-18-1T
  • 1066MHz 9-9-9-24-1T
  • 1333MHz 9-9-9-24-1T
  • 260
  • 262
  • 263
  • 265
  • 266
  • 266
  • 266
  • 266
  • 269
  • 269
  • 270
  • 272
  • 272
0
50
100
150
200
250
300
Seconds

There's virtually no difference in GIMP image editing either and while it benefits from the 1,600MHz and above clock speeds the most, 2T is a second quicker than 1T and the 1,066MHz frequencies are all faster than the 1,333MHz by a few seconds. Basically, there are greater differences in the system below the fastest memory performance possible that overrule any optimising of the memory subsystem.

Handbrake H.264 Encoding

Website: HandBrake
Our test uses Handbrake - an open-source, GPL-licensed, multiplatform, multithreaded video transcoder, available for MacOS X, Linux and Windows - to encode a high resolution MPEG-2 video using the H.264 codec. This primarily tests multi-threaded CPU and memory subsystem performance.

Timings: Handbreak x.264 Video Encoding

CustomPC Benchmark

  • 1708MHz 9-9-9-24-2T
  • 1600MHz 8-8-8-21-1T
  • 1600MHz 9-9-9-24-1T
  • 1333MHz 6-6-6-15-1T
  • 1333MHz 7-7-7-18-1T
  • 1066MHz 6-6-6-15-1T
  • 1600MHz 8-8-8-21-2T
  • 1066MHz 5-5-5-15-1T
  • 1066MHz 7-7-7-18-1T
  • 1066MHz 8-8-8-21-1T
  • 1333MHz 8-8-8-21-1T
  • 1066MHz 9-9-9-24-1T
  • 1333MHz 9-9-9-24-1T
  • 309
  • 326
  • 326
  • 327
  • 327
  • 328
  • 328
  • 328
  • 328
  • 328
  • 328
  • 330
  • 333
0
50
100
150
200
250
300
350
Seconds

Video encoding sees benefits more in line to what we expect - lower latencies improve performance slightly, and so does faster clock speeds. The overclocked memory shaving off a few seconds more than the normal performance curve, but we expect that is more to do with the 200MHz extra clock speed for the CPU. The four second gap between fastest 1,600MHz score and slowest 1,066MHz means very little for real world differences, and the 1,333MHz C9 average result tells us that there's likely to be greater differentiation in test to test than there is a notable performance advantage.
Discuss this in the forums
YouTube logo
MSI MPG Velox 100R Chassis Review

October 14 2021 | 15:04

TOP STORIES

SUGGESTED FOR YOU