Adata revealed a brilliant little bit of technology to SemiAccurate at Computex, “psuedo-SLC” mode for MLC flash. This little trick is easy to explain and also succinctly lays out how they managed to get to UHS-1 SC3 speeds.
You might recall the Adata XPG SD cards from a few weeks ago which claim 95MBps read and 85MBps writes out of a humble SD form factor. This is seriously fast, faster than anything on the market can probably use at the moment. How did Adata get those speeds out of pedestrian MLC flash? SLC would be both shatteringly expensive and very limited in capacities so that is obviously out. XPG cards cap out at 64GB and while not cheap are hardly SLC device expensive.
The idea is pretty simple to explain, treat MLC flash like SLC, instead of two bits per cell, treat it as one bit. This speeds up reads and writes but also halves capacity, one step forward one step back. Given the speeds they could coax out of the devices, we consider this a serious win even with the lowered storage space.
In the end Adata just did some serious outside the box thinking with their pseudo-SLC mode. Internal data paths are effectively twice as wide as they need to be, writing a cell probably takes a bit less time, buffers are effectively doubled, and reads are probably less error prone too. All this for losing half the capacity, something most enthusiasts would gladly give up for a massive speed gain. Simple and brilliant, all from a bit of firmware coding.S|A
Have you signed up for our newsletter yet?
Did you know that you can access all our past subscription-only articles with a simple Student Membership for 100 USD per year? If you want in-depth analysis and exclusive exclusives, we don’t make the news, we just report it so there is no guarantee when exclusives are added to the Professional level but that’s where you’ll find the deep dive analysis.
Latest posts by Charlie Demerjian (see all)
- HyperX ships it’s 60 millionth enthusiast memory module - Oct 15, 2018
- Bittware/Nallatech water cools 300W of Xilinx FPGA - Oct 12, 2018
- More on Intel’s 10nm process problems - Sep 17, 2018
- Intel puts out another 14nm 2020 server platform - Sep 11, 2018
- Why Can’t Intel Supply Enough 14nm Xeons? - Sep 10, 2018