Testbed and Methods

To study the CPU utilization as well as video quality in high-definition and typical standard definition we put together a standard testbed with the following configuration:

• Intel Core 2 Extreme X6800 CPU (3.0GHz, FSB 1333MHz x 9)
• DFI LanParty UT ICFX3200-T2R/G mainboard (ATI CrossFire Xpress 3200 for Intel)
• Corsair TWIN2X2048-8500C5 memory (2x1GB, 1066MHz, 5-5-5-15, 2T)
• Maxtor MaXLine III 7B250S0 (250GB, Serial ATA-150, 16MB buffer)
• Enermax Galaxy DXX PSU (EGX1000EWL, 1000W)
• Toshiba SD-H802A HD DVD drive
• Samsung SyncMaster 244T monitor (24”, 1920x1200@75Hz max display mode)
• Microsoft Windows Vista Ultimate 32-bit
• ATI Catalyst 8.38.9.1-rc2
• Nvidia ForceWare 158.24/163.11/163.69
• PowerDVD Ultra 7.3 build 2911

To estimate the CPU utilization during full-HD/1080p content playback we used the following scenes:

• HD DVD Fast & Furious: Tokyo Drift (VC-1) – Title 2, Chapter 2
• HD DVD The Interpreter (H.264) – Title 2, Chapter 2

To estimate the CPU utilization during regular DVD playback we used Gladiator movie (PAL, 720x576, 25 fps interlaced, 9 Mbit/s).

To test the CPU utilization during MPEG2 HD (1080i), DivX (640p, 1080p), WMV HD (720p, 1080p), H.264 (720p), VC-1 (720p) playback we used different movies available for download online:

• MPEG-2 HD 1080i (03:13, 405 MB, 1920x1080, 30 fps interlaced, 20 Mbit/s)
• DivX SD (24:00, 140 MB, 640x480, 24 fps progressive, 1 Mbit/s)
• DivX HD 1080p (224 MB, 03:13, 1920x1080, 25 fps progressive, 9.5 Mbit/s)
• H.264 720p (71 MB, 1:33, 1280x720, 24 fps progressive, 6 Mbit/s)
• VC-1 720p (120 MB, 1:20, 1280x720, 60 fps progressive, 15 Mbit/s)
• WMV HD 720p (97 MB, 2:02, 1280x720, 24 fps progressive, 6 Mbit/s)
• WMV HD 1080p (142 MB, 2:21, 1440x1080, 24 fps progressive, 8 Mbit/s)

The driver settings remained unchanged. However, according to the HQV HD test suite requirements, we set the Edge Enhancement and Noise Reduction to the maximum on Nvidia GeForce graphics solutions.

The following graphics accelerators participated in our today’s test session:

High-end:

• ATI Radeon HD 2900 XT 512MB/1GB
• ATI Radeon X1950 XTX 512MB
• Nvidia GeForce 8800 GTX 768MB
• Nvidia GeForce 8800 GTS 320MB/640MB
• Nvidia GeForce 7950 GX2 2x512MB

Mainstream:

• ATI Radeon HD 2600 XT 256MB
• ATI Radeon X1950 Pro 256MB
• Nvidia GeForce 8600 GTS 256MB
• Nvidia GeForce 7950 GT 512MB
• Nvidia GeForce 7900 GS 256MB

Entry-Level:

• ATI Radeon HD 2400 XT 256MB
• Nvidia GeForce 8500 GT 256MB
• Nvidia GeForce 7600 GT 256MB
• S3 Graphics Chrome S27 256MB

Since we didn’t disable any of Windows processes for the time of this test, the CPU load was fluctuating a little. It means that a difference of 1-2% is insignificant and doesn’t indicate a superiority of one graphics card over another.