Apax Hierarchical Data Format Storage Library for HPC From Start-Up Samplify

Samplify Systems, Inc., an intellectual property company for accelerating memory, storage, and I/O bottlenecks in computing, consumer electronics and mobile devices, announces the availability of its APAX HDF (Hierarchical Data Format) Storage Library for HPC, big data and cloud computing applications.

HPC users can accelerate disk throughput by 3-8X and reduce the storage requirements of their HDF-enabled applications without having to modify their application software. The APAX HDF Storage Library works with Samplify’s APAX Profiler tool to analyze the inherent accuracy in each dataset being stored, and applies the recommended encoding rate to maximize acceleration of algorithms with no effect on results.

"Our engagements with government labs, academic institutions, and private data centers reveal a continuous struggle to manage an ever increasing amount of data," says Al Wegener, founder and CTO, Samplify. "We have been asked for a simpler way to integrate our APAX encoding technology in big data and cloud applications. By using plug-in technology for HDF, we enable any application that currently uses HDF as its storage format to get the benefits of improved disk throughput and reduced storage requirements afforded by APAX."

At the International Supercomputing Conference (ISC’13), a paper presentation co-authored with Deutsches Klimarechenzentrum (DKRZ) [German Climate Computing Centre], University of Hamburg and Samplify cites: "The most easily obtained benefit from lossy compression of climate datasets is a significant reduction in disk file size and a corresponding increase in disk bandwidth." For increasing disk throughput, the authors observe: "APAX appears to be faster… APAX is a single-pass algorithm which leads to better cache usage." When comparing the quality of the results, the authors note: "APAX averaged 1.6X more compression." The authors conclude: "APAX offers better encoding for most climate variables due to its superior compression or data quality."

About APAX
The APAX technology is a universal numerical data encoder that operates on any integer or floating point data type and can achieve typical encoding rates of 3:1 to 8:1 without affecting the results of computing applications. APAX SDK is a software library which can be linked into any computing application to enable it to operate natively on APAX-encoded data in memory, on disk, or streaming across network interfaces. It is optimized for SIMD execution on SSE/AVX Intel CPUs achieving a throughput of 200MB/s per core, and the API is compatible with the company’s APAX hardware IP core for SoC and FPGA integration, allowing APAX-enabled applications to take advantage of future APAX-enabled hardware in the data center. The web-based APAX Profiler analysis tool analyzes the inherent accuracy in the user’s dataset and makes a recommendation of encoding rates to maximize the acceleration of their algorithm with no effect on results.

Availability and Pricing
Samplify’s APAX HDF Library is available from the company for Linux platforms with annual licensing starting at U.S. $50,000 for data centers with storage requirements of one petabyte.

About Samplify
Samplify is a privately-held company with funding from Charles River Ventures and Formative Ventures and strategic investors such as Schlumberger, Mamiya, and IDT.