Emu Technology provides a quantum leap in performance for “Big Data”
Nationally awarded co-founders Dr. Peter Kogge, Dr. Jay Brockman and Dr. Ed Upchurch put together a team of world renowned computer architects at Emu Technology. For the past five years, this team has been developing an Exascale-capable computing architecture designed specifically to tackle the ‘Big Data’ applications that are choking today’s supercomputers. Emu Technology will unveil its revolutionary Migrating Thread Computer at the SC15 supercomputing conference, November 16-19, 2015, in Austin, Texas.
According to Marty Deneroff, COO of EMU, “Today’s computer architectures are basically the same as they were 50 years ago; no one could have predicted then the vast data sets organizations would employ today – it no longer makes sense to move mountains of data in and out of the CPUs. At Emu we dared to conceive a computer that addresses this challenge from the ground up.”
The exponential growth of data, especially unstructured data, will continue to greatly outpace advances predicted by Moore’s law. Applications with large graphs or very sparse matrices, where data locality cannot be assumed, are particularly problematic. Using its new paradigm, Migratory Memory-side Processing, Emu is able to ‘bring the man to the mountain [of data]’ avoiding the bandwidth and latency limitations that bring today’s HPC systems to their knees.
Using Emu’s revolutionary approach, organizations are seeking untapped competitive advantages in extracting knowledge from diverse, unstructured data sets. Problems not solved well by today’s supercomputers are effectively addressed, including social media, fraud detection, genomics, oil exploration, optimization, climate modeling, and critical matters of national security.
Flavio Villanustre, VP of Technology at LexisNexis Risk Solutions, states that “Scored search enables analysts to slice and dice data and build regression models on the fly, making real-time analytics real. CPU cache coherency is paramount to performance and CPU registers are scarce, so streaming unnecessary data through the CPU pipeline should be avoided at all costs.” The novel Emu approach addresses this problem very effectively. Thus the technology from Emu has the potential to make the intractable, tractable.
“Our first customers will be very special ones,” asserted CEO Dr. Ken Jacobsen. “The first systems will be shipped to visionary leaders pushing the frontiers of data analytics.”