IBM, Fujifilm Set New Areal Density Record With 580TB Tape Cartridge

IBM, Fujifilm Set New Areal Density Record With 580TB Tape Cartridge

Fujifilm and IBM have announced a world record in new tape storage density. According to the two companies, breakthroughs like this are necessary if the world’s storage capacity is going to keep up with the demands of future systems.

The global “datasphere” — the total amount of information created, captured, copied, and consumed in a given year — is expected to rise from an estimated 33ZB (zettabytes) in 2018 to 175ZB in 2025, according to estimates from IDC. That’s a much larger figure than the total amount of storage that will ship in 2025 because IDC’s definition also counts data consumption. But the total amount of data storage sold across the entire planet continues to rise as well, driven by everything from cell phones to enterprise storage servers.

Tape drives, as far as I can tell, are the oldest storage technology we still use today, beating out hard drives by a full five years. The new technology enables data densities of up to 580TB per tape (there are no 580TB HDDs expected to be available any time soon). It’s a really interesting technical achievement for IBM and Fujifilm, but it’s not clear how much it will matter in the real world.

Here’s how IBM describes its own history of tape development:

IBM, Fujifilm Set New Areal Density Record With 580TB Tape Cartridge

Based on this image, you’d think we had drive capacities of at least 150TB now, even allowing for a lot of time between technological achievement and practical launch. This is not the case. IBM sells LTO-8 tapes that top out at 30TB compressed, and the just-released LTO-9 standard bumps this to 45TB. There’s nowhere you can buy a 580TB drive or compatible reader, and we’re still far off the 185TB capacity Sony was claiming back in 2014. Companies have been announcing tape breakthroughs for years that claim astonishing improvements in areal density, but never translate directly into shipping products.

If I had to guess, I’d guess that it’s the low-cost implementations of much more expensive techniques that are still driving tape capacities forward at a regular clip, and it’s always possible that we’ll see the tape market grow it’s storage capacities more rapidly in the near future. Hard drive sizes grew rather slowly in the mid-aughts, but are accelerating again. Seagate wants to have a 50TB hard drive in market by 2026, for example.

If IBM or Fujifilm could bring a 580TB tape drive out of the lab and to market today, it’d be a huge leap forward, but the historical record suggests a growth rate of ~1.5x every two years. If that’s true, we can look forward to 512TB tape drives by about 2032.

Feature image by Fujifilm

Continue reading

With Spintronics, Intel Sees Efficiency, Density Scaling Far Beyond CMOS
With Spintronics, Intel Sees Efficiency, Density Scaling Far Beyond CMOS

A new research paper from Intel suggests a new path forward for device scaling and lower power computing. We desperately need one.

Did Tesla Buy Maxwell for Its Ultracapacitors or Higher-Density Batteries?
Did Tesla Buy Maxwell for Its Ultracapacitors or Higher-Density Batteries?

If Tesla wants to jump to 300 watt-hours of power per kilogram of battery material, it needs Maxwell's technology. Ultracapacitors are a nice addition to the portfolio.