The SX-Aurora TSUBASA AI Platform for big data analytics and machine learning is the flagship NEC X product being commercialized in the Americas. This platform brings supercomputer scalar- and vector-processing performance, along with a large memory subsystem, to a broad range of applications. Its compact and cost-effective PCIe card form factor fits in everything from workstation towers for a single card, to rack-mounted servers for multiple cards.
Interested in trying the platform? NEC X launched the Vector Engine Data Acceleration Center (VEDAC) in Silicon Valley. VEDAC enables users to experience vector processing benefits for big data analytics on the SX-Aurora TSUBASA AI Platform with Frovedis framework, compliant with Apache Spark and Cloudera quality assurance test suite.
The NEC Vector Engine Processor was developed for high performance and low power consumption. The Vector Engine Processor has the world’s first implementation of one processor with six HBM2 memory modules using Chip-on-Wafer-on-Substrate technology, leading to the world-record memory bandwidth of 1.2 TB/s. The NEC Vector Engine Processor provides optimal sustained performance. Within, there are multiple hardware configurations for the NEC SX-Aurora TSUBASA AI Platform.
Open Source! github.com/frovedis
In combination with single instruction, multiple data (SIMD), pipelining, and NEC’s Frovedis middleware, this AI Platform accelerates data analysis operations on top of the Apache Spark MLlib and DataFrame framework, while maintaining compatibility with standard programming languages such as C, C++ and Fortran. This unique architecture significantly increases speeds and reduces power consumption for memory-intensive statistical machine learning and data frame applications, such as large scale e-commerce recommendation engines, high-throughput financial and document transactions, fraud detection, enterprise governance, and authentication.