A Closer Look At Silicon Motion's SM2256
SSD vendors who partner with Silicon Motion have the option to use its reference design or build their own configuration.
At this year's CES, we saw three SM2256-based R&D boards first-hand. At this time, Silicon Motion is preparing three TLC flash types for use with its controller. Again, today we have one with Samsung's 19nm TLC. The company has also demonstrated the SM2256 with Toshiba A19 TLC and SK Hynix's second-gen 1xnm flash.
Today marks the second time I've tested an early sample with the SM2256. At Flash Memory Summit last year Paul Alcorn, Jon Coulter and I had 24 hours with this controller paired with Toshiba A19 TLC. Samsung's 19nm TLC is a little faster, and the controller is more mature this time around.
I was a bit surprised when Silicon Motion displayed the first early sample at CES with Samsung TLC flash. With its own successful line of SSDs, Samsung doesn't just hand flash out to competitors. I’ve tested many client SSDs over
If you have a really heavy workload though, by all means get a high-end unit.
While they're making 3d nand, why don't they add an extra layer for parity and then use the raid-5 algorithm?
e.g. 8 layers for data, adding 1 extra for parity. Not that much extra overhead, but data will be much more reliable.
No you don't. Each sector has CRC right?
So if the sector read fails CRC, simply calculate CRC replacing each layer in turn with the raid parity bit.
All of them will be off except for one with the faulty bit.
And these CRC's can all be calculated in parallel so there would be 0 overhead with regard to time.
In the case of a silent error though, which is what you get if you have an even-count bit error when using parity alone, you have no idea where the error is or even that there ever was an error in the first place. That's why more complex error detection and correction block codes exist and are used wherever read/receive errors carry a high cost, such as performance, reliability, monetary cost or loss of data.
BUT, one significant critique I have was the density limitation. Everything here was based on the ~250 GB drives. Comparing a drive with the exact name, but in a different density, is akin to comparing two entirely different drives.
I realize producing the data can be time consuming, but having the same information at three density points would be extremely helpful for purchasing decisions - lowest, highest, and middle densities.