Bookmark and Share


Fusion-io has announced the first software development kit (SDK) to provide software developers with native access to the ioMemory flash platform. By integrating applications directly with this new persistent memory tier, developers will be able to optimize enterprise, web, and big data applications through direct programmatic access to the ioMemory computing layer for the first time.

“The ioMemory SDK and APIs reduce application complexity and speed development while accelerating time to market with fewer engineering requirements. When you get rid of that complexity, the resulting application is much more reliable and can leverage the full potential of ioMemory to run much faster,” said David Flynn, chief executive officer and chairman of Fusion-io.

On only a handful of occasions in the past 60 years have software developers been given fundamentally new programming building blocks for memory or storage devices. Until now, developers have been limited to tuning their applications for flash as storage. The ioMemory SDK libraries unlock direct programmatic access to native flash access patterns and data organization methods. The ioMemory SDK includes application programming interfaces (APIs) within user-space libraries, as well as reference application examples made available as open source. The ioMemory SDK libraries will combine underlying primitives provided by the Fusion-io ioMemory OS Subsystem, such as Fusion-io Atomic Writes and Auto Commit Memory, to accelerate application development cycles and system performance of popular applications.

According to analysts from Gartner, improving the performance of input/output (I/O) bound applications or systems could be more pronounced and cost-effective if the choice of data to hold in flash memory is done in an intelligent and application-aware way.

“Our January demonstration of one billion IOPS running on auto commit memory, and Atomic Writes demonstrated the potential power of running applications natively on ioMemory. With our SDK, we are now making these tools available to software developers,” said Mr. Flynn.

The ioMemory SDK will feature APIs including the key-value store, which will feature interfaces to reduce latency, improve memory efficiency, and reduce code complexity. The directFS API provides native file-access semantics to ioMemory through a POSIX-compliant file system. Like the native API libraries, directFS is implemented directly on ioMemory, significantly reducing latency by entirely bypassing operating system buffer caches, file system and kernel block I/O layers. Fusion-io directFS will be released as a practical working example of an application running natively on ioMemory to help developers explore the use of Fusion-io APIs.

“Direct programmatic access to the ioMemory tier presents a rare and significant leap forward for computing, and the ioMemory SDK makes that integration powerfully simple for application developers. When you consider that Fusion-io is already well known for accelerating applications, it’s exciting that bypassing traditional protocols in favor of direct access to ioMemory would mean an even greater performance boost in Citrusleaf’s NoSQL database for mission critical webscale applications. Our existing real time big data customers require low latency and extraordinary throughput, and with this revolution in application acceleration, end users will start asking if applications can run native on ioMemory,” said Brian Bulkowski, founder and chief technical officer of Citrusleaf.

Select Fusion-io libraries and APIs are now available to early access partners through the new Fusion-io developer program, the first industry program for developers optimizing applications to run natively on ioMemory.

Tags: Fusion-io, SSD, NAND, Flash


Comments currently: 1
Discussion started: 04/21/12 11:26:36 AM
Latest comment: 04/23/12 03:14:48 PM


We need not ask how much one of these babies costs, huh? As seems to always be the case with specialist enterprise class solutions that run in the $10K+ range, the adoption rate for such products will highly depend on availability of lower spec'-ed lower priced test platforms. I'm a software developer and have plenty of experience in GIS and spatial databases and that would have been one piece of equipment that I know would speed things up significantly, but you won't see me or my clients investing in such pricey hardware unless there's immediate benefits. Writing stable and well tested custom routines for any specialist hardware is a daunting task that might take years of man-hours and such APIs should help trim those down significantly, but would still mean it's beyond abilities of small(er) development teams to deliver in time with any significant profit to their customers and not lose their heads over it. Meaning, we'll have to wait on companies like ESRI, Oracle, [pick your rotten apple],... and alike to implement any beneficial changes to the way their solutions use such hardware. By then, of course, this would have been their hardware. Alternatively, give us a sub $1K test platform and before long you'll see your product put to good use in any number of yet unimaginable ways. Awaiting any such related news... until then then
2 0 [Posted by: MyK  | Date: 04/21/12 11:26:36 AM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture