Hifn Debuts Hardware De-Dupe Accelerator

Hifn introduced the industry’s first hardware-accelerated, data de-duplication platform – a simple turnkey, drop-in solution – that combines unprecedented ‘de-dupe’ performance with a fast time-to-market advantage. Hifn’s family of De-Dupe Accelerators are designed to make it fast and easy for OEMs, system builders and system integrators currently selling data de-duplication solutions as well as vendors who are considering bringing data de-duplication products to market to gain a competitive advantage.

Express DR 250/255 Data Reduction Board

Hifn customers wishing to be fast to market with hardware-accelerated de-duplication for storage devices, such as NAS, can use the new De-Dupe Accelerator family of products combined with standard servers to create robust, real-time de-duplication solutions. OEMs looking to optimize and differentiate their current de-duplication solutions can now simply and easily upgrade their current customer base with the latest in hardware acceleration technology.

The new Hifn De-Dupe Accelerator 250 and 255 are the first products in a family of data de-duplication solutions that extend Hifn’s leadership in accelerating capacity optimization and data security solutions. The De-Dupe Accelerator 250 and 255 includes the company’s Express DR 250 PCI card and the Express DR 255 PCI-Express card, respectively, for off-loading and accelerating the data de-duplication function. The Hifn De-Dupe Accelerator products also include the new Hifn De-Dupe Accelerator software that provides an additional de-duplication performance boost with an innovative approach to indexing and unique ‘fingerprinting’ capabilities.    

“Hifn’s hardware-acceleration advantage supports real-time, data de-duplication processing, an absolute requirement for deploying data de-duplication into a wide range of storage environments,” said John Matze, vice president of systems engineering, Hifn. “Other solutions are typically limited to post-processing de-duplication, requiring the data to first be written to disk and then removing redundancies after the fact.  And, as more and more corporations implement de-duplication techniques, performance will be an issue.”   

Data de-duplication is a technique for eliminating redundant data. In the de-duplication process, data is scanned and unique patterns are identified, assigned corresponding unique data ‘fingerprints’, indexed and stored. Duplicate copies of data already ‘fingerprinted’ are deleted, leaving only one stored copy of each unique data pattern along with its corresponding fingerprint. At the heart of the ‘fingerprinting’ process is a computational process called a ‘checksum’ or ‘hash.’ Data de-duplication product manufacturers employ cryptographic hash functions to perform checksum processing because of their ability to produce unique fingerprints from unique data patterns.  

Hifn’s unique index processing also enhances read performance by enabling data to be transferred directly from the underlying disk storage to the application without invoking de-duplication. For data that was stored in an encrypted and/or compressed format, passing the data stream through the decompression and decryption hardware engines is performed without an impact on performance. High performance reads are important for primary storage and NAS applications, in which writes are typically a smaller portion of the workload.

Hifn’s new De-Dupe Accelerator 250 and 255 solutions will be available for beta OEM customers this quarter, with general availability in the first quarter of 2009.  The new solutions supports Suse and RedHat Linux with future OS support, including Microsoft Windows, scheduled for 1H09. List price starts at $1995 per unit with OEM volume discounts available.