Intel's Pentium 4 3.06GHz Processor
Intel breaks 3GHz barrier and  introduces Hyperthreading to the mainstream

By, Dave Altavilla
and Chris Angelini
November 14, 2002
 

 
Recently, eTesting Labs released a new patch for Business Winstone 2002, as well as a full revision release for Content Creation Winstone 2003.  Unfortunately, we were unable to get the systems (either AMD based or Intel based) to complete the CC Winstone 2003 tests, without crashing during the benchmark.  As a result, we only have Business Winstone 2002 numbers and the older version of Content Creation 2002.

Winstone Benchmarks
Business Apps and a little Content Creation

Applications used in the Business Winstone tests include:

  • Five Microsoft Office 2002 applications (Access, Excel, FrontPage, PowerPoint, and Word)
  • Microsoft Project 2000
  • Lotus Notes
  • WinZip 8.0
  • Norton AntiVirus
  • Netscape Communicator

Here we've tested the 3GHz P4 with Hyperthreading enabled and disabled.  This test does run some applications simultaneously and as a result, we do see an ever so slight performance edge for the HT enabled P4.  However, the scores are close enough to be within the test's margin of error and this performance gain is negligible.  However, we do see the new 3GHz P4 overtakes the 2.8GHz chip as well as the Athlon XP 2800+ .  The Athlon still makes a very strong showing however, as we've seen this test favors Athlons in general. 

Applications used in the Content Creation Winstone tests include:

  • Adobe Photoshop 6.0.1

  • Adobe Premiere 6.0

  • Macromedia Director 8.5

  • Macromedia Dreamweaver UltraDev 4

  • Microsoft Windows Media Encoder 7.01.00.3055

  • Netscape Navigator 6/6.01

  • Sonic Foundry Sound Forge 5.0c (build 184)


Here's a situation that we theorized could in fact come to pass, with certain legacy code and Hyperthreading.  As you can see, the HT enabled P4 actually scores lower than its non-Hyperthreaded counterpart.  This could be in part due to the fact that, certain weightings of the benchmark scores, depending on the application that is running in the foreground within the test suite, are also being affected by another application that is running in the background.  In this scenario, although the system has perhaps a more balanced load on its overall resources with HT enabled, since the test wasn't written to understand this distribution of CPU resources, the overall score is actually represented lower.

Again this is just a theory of ours and we are looking into this question further.  However, we've been told that Content Creation Winstone 2003 handles Multitasking much better.  It's too bad we were unable to get that benchmark to run on any of our test systems.

Video Encoding With XMPEG And Main Concept