ATTO Disk Benchmark is perhaps one of the oldest benchmarks going and is definitely the main staple for manufacturer performance specifications. ATTO uses RAW or compressible data and, for our benchmarks, we use a set length of 256mb and test both the read and write performance of various transfer sizes ranging from 0.5 to 8192kb. Manufacturers prefer this method of testing as it deals with raw (compressible) data rather than random (includes incompressible data) which, although more realistic, results in lower performance results.
Right off, it was great to see that the Samsung XP941 was recognized and we believed it might yield the highest benchmark results, considering what it is capable of in X4 mode. Unfortunately, it topped out at 821MB/s, a speed well below the 10Gbps ceiling and we had to wonder if this was going to be the highest we would see in PCIe 2.0 X2 performance.
Crystal Disk Benchmark is used to measure read and write performance through sampling of highly compressible data (oFill/1Fill), or random data which is, for the most part, incompressible.
In examining the Crystal DiskMark write performance of the SATA SSDs, we could confirm the typical AMD SATA performance deficiency that has always been present when one compares these speeds to typical Intel based SSD performance.
We would like to identify whether AMD also affects PCIe performance in some way but but there really isn’t enough data just yet. The only true sample we can look at is the Plextor/Lite-On M6e 256GB PCIe X2 M.2 SSD and it is not really a fair comparison as, last we tested it, it boot into its own BIOS prior to testing, whereas now, it boot into the 990FX BIOS which surprised us. As well, performance is a bit less but this drive has undergone significant use prior. Although CDM results appear to be a bit lower, ATTO results are still dead on.