Four-Corner Performance Testing
Comparison Products
To read about our storage tests in-depth, please check out How We Test HDDs And SSDs. Four-corner testing is covered on page six of our How We Test guide.
Sequential Read
Regardless of whether it's complemented by MLC or TLC NAND, Phison's S10 controller blows through large-block sequential workloads. Both the MyDigitalSSD BP5e and Klevv Urbane utilize Toshiba flash. The Urbane comes armed with MLC on a Toggle-mode 2.0 interface, so you'd expect it to be faster. Don't tell that to the BP5e, though, because it's at the top of our chart in this test.
Sequential Write
High performance that maxes out the real-world limits of SATA 6Gb/s carries over to our sequential write test, too. The BP5e doesn't waver much in this benchmark, which is something we often see from TLC-based SSDs.
Random Read
A high entropy rate (that means incompressible data) causes the BP5e's random read performance to suffer. It doesn't help that many of the drives on this chart are higher-end models. There simply aren't a lot of products in the low-cost segment to compare a 960GB BP5e.
Random Write
The BP5e demonstrates weak 4KB random write performance across the queue depth range. It doesn't scale well in our test, mainly because the emulated SLC buffer doesn't get much time to recover. As we see more inexpensive TLC-based drives, we'll look at revising our testing methods to let the buffer replenish fresh cells.