Toshiba Showcases QLC NAND Development Platform At Flash Memory Summit

[Guest]

Tucked in the back of the Microsemi booth we found Toshiba's BiCS Gen 3 768Gbit NAND running. With the show floor closed due to a fire Microsemi gets the credit for showing the first working QLC.

Toshiba Showcases QLC NAND Development Platform At Flash Memory Summit : Read more

 

[Brian_R170]

Will this be the last NAND product we ever see from Toshiba?

 

[2Be_or_Not2Be]

QLC - great, more storage at the expense of much less durability and less performance. I see the merit of the technical accomplishment, but I don't see any performance jump for the end-user. Which is sad when you see these seemingly advances in storage tech.

 

[Guest]

Half the controllers time will be spent correcting all the garbage errors present in every single page. QLC has less than 1000 P/E cycles, SLC over 100 000 P/E cycles.

So what if I have to pay 4x the price, if it's 100x more reliable, and has 4-10x less latency?

 

[hannibal]

The marging of error is so slim in there... so easy to corrupt the files, because one "shade" of change shange to something else... Yep very bright future in ahead... and SLC has allready faded out of production MLC if fading. Soon the stop manufacturing TLCs... then we have only QLCs and PLCs... nice...

 

[derekullo]

It's not as bad as everyone makes it out to be. (Assuming Toshiba is telling the truth)

http://www.anandtech.com/show/11590/toshiba-768-gb-3d-qlc-nand-flash-memory-1000-p-e-cycles

Don't forget that the larger the drive the longer each P/E cycle takes

A hypothetical 1 terabyte drive @ 3000 p/e cycles would theoretically be able to write the same amount of data as a 3 terabyte drive @ 1000 p/e.

QLC is slower per cell versus ... all the others, but don't forget about the parallelization from 3 terabytes of QLC.

The same arguement was made from the transition from SLC to MLC, and MLC to TLC.

If anything going from SLC to MLC was the biggest jump 100,000 P/E to 10,000 P/E, but we of course welcomed the doubling of capacity with open arms.

With TLC at 3000 P/E and now QLC at 1000 P/E to make it all complete.



Toshiba: We choose to make QLC NAND and do the other things, not because they are easy, but because they are hard; because that goal will serve to hold all of your movies, music, documents and text messages, because that challenge is a highly profitable one that we are willing to accept, one we are unwilling to postpone due to Samsung beating us to the punch in so many other areas, and one we hope to ... ahh ... maybe win.

 

[grape1829]

Toshiba will just be a brand name like Kodak and Polaroid soon... This will be their final achievement in semiconductors as true Toshiba.

 

[Sakkura]

QLC - great, more storage at the expense of much less durability and less performance. I see the merit of the technical accomplishment, but I don't see any performance jump for the end-user. Which is sad when you see these seemingly advances in storage tech.

The end user doesn't need a jump in performance, the end user needs a jump in capacity per dollar. Especially with the current short supply of flash memory that has caused SSD prices to increase. QLC will increase the bit output of the fabs, helping to alleviate the supply shortage in the market. That'll tend to drive prices down, even if you stick to SSDs based on MLC or TLC.

 

[farmeunit]

I just need more storage. I have a 2TB drive just for my Steam library. Would love to get that only an SSD, but not paying $500-$600 for the luxury.