This year has been full of delays in the hardware-time continuum, it seems. It feels like forever ago since Maxwell was announced, with Intel's Broadwell and HW-E / X99 platform similarly far behind us. Each of these devices will finally be shipping by the holidays, or so we're told, but that still leaves a major market segment untouched: SSDs. Other than recent innovations in Samsung's NAND lineup, the SSD market has remained relatively silent since our initial SandForce Gen3 controller analysis.
At the Flash Memory Summit in
SSDs are surrounded by terminology that generally isn't understood beyond a relative level. There's this top-level concept that one type of NAND is superior to another, that synchronous is preferable to asynchronous, that endurance is tied to P/E cycles, but a lot of the knowledge halts there. We've worked closely with several SSD and controller engineers over the past year to educate ourselves on the inner workings of the storage world's biggest recent advancement; now it's time to start organizing that education in article form. Over the next weeks, we'll be releasing several "SSD Architecture" postings (so be sure to like / follow / subscribe) that focus on different aspects of solid-state drives, controllers, and NAND.
This installment includes a video component. The video showcases a discussion with LSI's Kent Smith and spoils the basics of what we'll cover throughout this series. I highly recommend watching the video, especially for those who benefit from visual aids. We covered SSD questions pertaining to varying voltage levels on evolving NAND types (SLC, MLC, TLC), cell decay when an SSD goes unused, P/E cycles and endurance, and "what's next" after TLC for Flash types. That's a lot of stuff. Each item is complex in its own way -- hence the chronicle-like release of in-depth article components.
Today we're talking about top-level SSD anatomy and architecture, defining what "NAND Flash" actually is, evolving NAND types (MLC vs. TLC, what's after TLC), capacity calculations, and providing an "SSD primer" of other basic elements. This is what will lay the foundation for our more advanced articles.
SSDs have faced numerous challenges since their fairly recent beginnings. Initial SLC (single-level cell) SSDs were out-of-reach for most consumers, and as evolving Flash memory types allowed production of more affordable consumer SSDs (MLC, TLC), we saw serious endurance concerns. Endurance and stability concerns have subsided as controller manufacturers learn to cope with the hurdles, though we now face other obstacles -- like endurance on TLC and brushing up against the SATA bus bandwidth cap. Other features, like data integrity and redundancy, often hold greater value than pure speed.
Speed is now a largely irrelevant metric for comparison when looking at high-end consumer SATA III SSDs; no SATA III-powered SSD can exceed the 6Gbps cap (which translates to about ~550MB/s in real-world use, accounting for overhead). Going forward, SSD controllers (this is true for Samsung, OCZ, SandForce, etc.) are not the limiting factor for speed -- it's the bus. Time to move to PCI-e.
The SandForce 3700 series controllers are now officially announced and are already in the hands of manufacturers. On a top-level, the new controller should:
With LSI Corporation's (NASDAQ: LSI) new SandForce SF3700 controller impending Q1/Q2 mass production next year, it looks like manufacturers will finally be able to bring PCI-E SSDs to mass consumption and TLC endurance concerns may fade. In this write-up, we'll look at the SF3700 SSD controller's (specifically SF3729/SF3739) specs, SHIELD feature, and PCI-e modularity - specifically as it pertains to Samsung's existing 840 Pro and XP941 controllers.
We moderate comments on a ~24~48 hour cycle. There will be some delay after submitting a comment.