Testing Notes and System Specs

Core i7 Test System Specs
- Intel Core i7 965 Extreme Edition (LGA1366)
- x3 2GB DDR3-1333 G.Skill (CAS 9-9-9-20)
- ASUS P6T Deluxe (Intel X58)
- OCZ GameXStream (700 watt)
- Corsair P Series 128GB (Samsung RBB)
- OCZ Summit 120GB (Samsung RBB)
- OCZ Vertex Turbo 120GB (Indilinx Barefoot)
- OCZ Vertex 120GB (Indilinx Barefoot)
- A-Data S592 128GB (Indilinx Barefoot)
- OCZ Agility 120GB (Indilinx Barefoot)
- Intel X25-M 80GB (50nm)
- G.Skill Titan 128GB (JMicron JMF602B)
- Samsung Spinpoint F1 640GB 7200-RPM (Serial ATA300)
- ASUS GeForce GTX 285 (1GB)
Software
- Microsoft Windows Vista Ultimate SP1 (64-bit)
- Nvidia Forceware 190.38

For today's roundup we will be focusing on the performance of the OCZ Agility 120GB, OCZ Vertex Turbo 120GB, A-Data S592 128GB and Corsair P Series 128GB SSDs. However the Samsung Spinpoint F1 640GB hard drive, G.Skill Titan 128GB SSD, Intel X25-M 80GB SSD, OCZ Vertex 120GB SSD and OCZ Summit 120GB SSD will also be included for comparison purposes.

In total there will be four (4) SSDs that use the Indilinx Barefoot controller and two (2) that use the Samsung controller. Our testing suite consists of six benchmark programs and our own file copying test using a 6GB sample file. Additionally we will include some performance degradation (fragmentation) testing, intended to show long-term usage effects on performance.

As you should know by now, the problem with SSDs is that while the manufacturer claims impressive peak I/O performance out of the box, this amazing performance starts to disappear over time. Unlike a conventional hard drive, any write operation made to an SSD is a two-step process, as the data block must first be erased and then written to. Obviously if the drive is brand new and unused there will be nothing to erase and therefore the first step can be bypassed, but this only happens once, unless the drive is trimmed.

Therefore, we are going to see just how much performance you can expect to lose from each SSD over time. First we test the SSDs in their clean unused state, and then we run the HD Tach full benchmark several times, which fills the entire drive. This simulates heavy usage and gives us a clear indication of how the performance will be affected once the SSD is in use.