Seen & Heard at the Flash Memory Summit
Attendance at FMS broke records for the fourth year in a row – truly remarkable, given our current economic situation. I think even the organizers were pleasantly surprised by the confirmation that FMS is now the venue of choice for flash industry leaders to come together and for the rest of the industry to learn what is new in the world of flash technology. As a sponsor of the show since its inception, Datalight contributed to the Summit by organizing a half-day executive update, presenting on wear-leveling, moderating a round-table on endurance at the beer & pizza forum, and delivering a product demonstration at the FMS Theater.
Once again SSDs, thought by many to be the savior of the beleaguered flash industry, dominated the agenda. This year talk of application-specific SSDs was everywhere, specifically optimizations for interfaces like SAS, SATA, and fiber channel.
Presumably, the idea behind application-specific SSDs is to drive faster adoption by tuning them for the use cases presented by different applications. For example, in a random write intensive application, additional RAM may be added to mitigate lackluster random write performance by buffering writes.
As expected, there was a fair amount of preaching to the choir about the benefits of SSDs over HDDs, including read/write performance and the power savings. Intel touted 17% longer battery life and reduced failure rates (less than .5% for SSD vs. 5% for HDD). Other manufacturer’s boasted instant-on boot time, smaller footprint, and lower DRAM requirements.
On the topic of barriers to adoption, SSDs were declared still too expensive for mass market appeal. Also, many of the benefits promised by SSDs are being undone by bottlenecks in the OS (and file system!). As a result, it was postulated that SSDs will cannibalize 15k RPM HDDs, where customers are willing to pay a premium for speed, rather than replacing HDDs as a whole, at least in the short term,
In the emerging technologies track, 3-D NAND was promoted by both Micron and SanDisk, in part because they are able to leverage the technology used to build DRAM for manufacturing 3-D NAND, making it easier and cheaper to produce. It was particularly interesting to hear SanDisk say that 4 bit per cell will have limited application in the future, especially since it had been speculated that the 4 b/c technology was a key reason for them to acquire M-Systems. PCM and FeRAM were also discussed as next generation flash technologies. Overall, we were impressed by the level of participation from across the industry and we’re already looking forward to next year’s Summit!
RobHart | August 19, 2009 | Flash Industry Info