Our testing methods
All tests were run three times, and their results were averaged, using the following test systems.

ProcessorAMD Opteron 246 2.0GHz (1 processor)
Front-side busHT 16-bit/800MHz downstream
HT 16-bit/800MHz upstream
MotherboardTyan Thunder K8W
North bridgeAMD-8151 AGP tunnel
AMD-8131 PCI-X tunnel
South bridgeAMD-8111 I/O hub
Chipset driversAMD chipset driver pack 2.10
Memory size1GB (2 DIMMs)
Memory typeCorsair CM72SD512RLP-3200/S Registered PC3200 DDR SDRAM
GraphicsNVIDIA GeForce FX 5200
Graphics driverForceWare 61.76
Storage Controllers

Adaptec 29320-R

LSI 21320

SIIG Serial ATA PCI

Storage Driver

Adaptec 3.00S4

LSI 1.10.02

Silicon Image 1.0.0.44

Storage

Maxtor Atlas 10K IV 147GB
Maxtor Atlas 10K V 300GB
Seagate Cheetah 10K.6 147GB
Seagate Savvio 37GB

Seagate Cheetah 10K.6 147GB
Seagate Savvio 37GB

Western Digital Raptor WD360GD 37GB
Western Digital Raptor WD740GD 74GB

Operating SystemWindows XP Professional SP2 with DirectX 9.0c

Since the Savvio is the world's only 2.5" SCSI drive, it doesn't really have any direct competition. To see how its performance stacks up against 3.5" drives, I've assembled a collection of 10K-RPM SCSI and Serial ATA alternatives. To make the graphs clearer, I've left out Maxtor and Seagate's 15K-RPM drives. You can check out how their performance compares in our review of Maxtor's Atlas 10K V.

When I first started testing the Savvio, I noticed that the drive's performance was significantly lower than expected on our Adaptec 29320-R SCSI adapter. LSI was kind enough to hook me up with its 21320 controller, which improved the Savvio's performance dramatically, suggesting that initial performance problems are related to the Adaptec card. I've provided Savvio performance scores with both the Adaptec and LSI cards to show the difference between them. I also tested the Cheetah 10K.6 on the LSI card to directly compare with the Savvio results.

The Serial ATA and SCSI cards were used in different PCI-X slots on different PCI-X busses. Each card had an entire PCI-X bus to itself, so bandwidth sharing shouldn't be an issue.

A special thanks goes out to the Computer Repair Shop and KickAss Gear for kicking in the Western Digital Raptor WD360GD and WD740GD drives we used for testing.

We used the following versions of our test applications:

The test systems' Windows desktop was set at 1280x1024 in 32-bit color at a 75Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests. All of the 3D gaming tests used the high detail image quality settings.

All the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.