Testbed and Methods
We tested the aforementioned processors on a testbed that included the following hardware components:
- ASUS P4P800 (Socket 478, i865PE chipset) or ASUS A7N8X-E (Socket A, NVIDIA nForce2 Ultra 400 chipset) mainboard;
- 2 x 256MB DDR400 SDRAM (2-2-2-5 timings);
- ASUS RADEON 9800 XT graphics card (Catalyst 4.10 driver);
- Western Digital WD400JB hard disk drive.
We ran the benchmarks in Windows XP with Service Pack 1 and DirectX 9.0b installed. The BIOSes of the mainboards were set up for the maximum performance.
Note that although we review value processors, the testbeds include expensive and high-performing components (mainboards with a dual-channel memory controller, an expensive RADEON 9800 XT-based graphics card). We have reasons for that: by using such hardware we minimize its influence on the benchmark results and have a better view of the performance of the processor proper.
Office and Content-Creation Applications
We traditionally post here the results of the Winstone benchmarking suite.
Business Winstone 2004 shows the averaged performance of the platform in everyday office applications. The test simulates the user’s working in popular office programs and calculates the results basing on the time it took the programs to solve the required tasks. The benchmark uses an extensive list of applications, including Microsoft Access 2002 SP-2, Microsoft Excel 2002 SP-2, Microsoft FrontPage 2002 SP-2, Microsoft Outlook 2002 SP-2, Microsoft PowerPoint 2002 SP-2, Microsoft Project 2002, Microsoft Word 2002 SP-2, WinZip 8.1 SR-1 and Norton AntiVirus Professional Edition 2003.
Multimedia Content Creation Winstone 2004 works along the same guidelines as Business Winstone 2004, but with another set of applications. It uses multimedia applications, which serve for creating and processing images, audio and video. The full list includes popular and professionally used products: Adobe Photoshop 7.0.1, Adobe Premiere 6.50, Macromedia Director MX 9.0, Macromedia Dreamweaver MX 6.1, Microsoft Windows Media Encoder 9 Version 9.00.00.2980, NewTek LightWave 3D 7.5b and Steinberg WaveLab 4.0f.
Business Winstone 2004 clearly tells about a superiority of the Athlon XP team over the Celerons. Judging by the results of the Pentium 4 1.8A, the basic brake for the Celeron’s performance is the insufficient amount of cache memory. Thus, the Pentium 4 with 512KB of L2 cache and 1.8GHz clock rate proves to be as fast as the 2.7GHz Celeron.
Note also that the Athlon XP 2100+ and faster models outperform any Pentium 4 model that works at 2.4GHz! Thus, this test suggests that the Athlon XP architecture is highly efficient in office applications.
We see nearly the same picture in content-creation applications. Again, the Athlon XP family is all ahead of the Celeron line, including top-end Celeron models. This time the low results of the Celerons are due to the low FSB clock rate: just compare the results of the Pentium 2 2.4GHz processors with 533 and 800MHz FSB. The Pentium 4 1.8A can’t impress in this test: it shows the same performance as the Celeron 2.3GHz, but costs like the Celeron 2.8GHz!