Crystal Disk Benchmark is used to measure read and write performance through sampling of raw (0/1 Fill/compressible) or random data which is, for the most part, incompressible. For these tests, we will display CDM results using highly compressible data to provide validation for our ATTO results. The Toshiba is on the left and Samsung on the right:
It is typical to see CDM results lower than that of ATTO, however, this round goes to the ‘LSI SandForce Driven’ Toshiba as its all around performance is definitely better. Something that we hoped not to see again, but fully expected, was the very low 4k random write results which are similar in both SSDs. In our first report, we had eluded to Apple’s software configuration being responsible for this and this confirms our theory further.
Up until recently, AS SSD was the only benchmark created specifically for SSD testing and it uses incompressible data. AS SSD, for the most part, gives us the worst case scenario in SSD transfer speeds because of its use of incompressible data and many enthusiasts look to AS SSD for their needs. Once again, the Toshiba is left with the Samsung right:
The highlight of AS SSD has to go to the Samsung SSD where high sequential transfer performance of 399GB/s write is definitely hard to beat. We had mentioned at the beginning of this report that we thought the Toshiba SSD would reign in typical computer scenarios while the Samsung would be hard to beat while testing in incompressible data. This is definitely taking shape.
AS SSD Copy Benchmark is an excellent benchmark that mimics ‘true to life’ copying of an .iso, Program and Game. The provided result is simply the maximum transfer speed reached and time it took to move the file. This one definitely goes to the Samsung PM830 SSD, although we weren’t happy as neither SSD reached SATA 3 speeds in this test.