BiGNoC: Accelerating Big Data Computing with Application-Specific Photonic Network-on-Chip Architectures

• Published in: IEEE transactions on parallel and distributed systems Vol. 29; no. 11; pp. 2402 - 2415
• Main Authors: Chittamuru, Sai Vineel Reddy, Dang, Dharanidhar, Pasricha, Sudeep, Mahapatra, Rabi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytics; Architecture; Big Data; big data computing; Clusters; Computation; Computer architecture; Data analysis; Data management; Iterative methods; Machine learning; Manganese; Mathematical analysis; Multicast communication; Multicasting; Networks; Optical waveguides; photonic channel sharing; Photonic networks-on-chip; Photonics; System on chip; Waveguides
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2018.2833876

In the era of big data, high performance data analytics applications are frequently executed on large-scale cluster architectures to accomplish massive data-parallel computations. Often, these applications involve iterative machine learning algorithms to extract information and make predictions from large data sets. Multicast data dissemination is one of the major performance bottlenecks for such data analytics applications in cluster computing, as terabytes of data need to be distributed frequently from a single data source to hundreds of computing nodes. To overcome this bottleneck for big data applications, we propose BiGNoC , a manycore chip platform with a novel application-specific photonic network-on-chip (PNoC) fabric. BiGNoC is designed for big data computing and exploits multicasting in photonic waveguides. For high performance data analytics applications, BiGNoC improves throughput by up to <inline-formula><tex-math notation="LaTeX">{{9.9}}\times</tex-math> <inline-graphic xlink:href="chittamuru-ieq1-2833876.gif"/> </inline-formula> while reducing latency by up to 88 percent and energy-per-bit by up to 98 percent over two state-of-the-art PNoC architectures as well as a broadcast-optimized electrical mesh NoC architecture, and a traditional electrical mesh NoC architecture.