CAMPBELL, Calif., Nov. 13, 2017 (GLOBE NEWSWIRE) — Wave Computing™, the Silicon Valley start-up that is revolutionizing artificial intelligence and deep learning with its dataflow-based solutions, today announced Dr. Samit Chaudhuri will be presenting details of the company’s innovative “SAT Solver” technology at the International Conference on Computer Aided Design (ICCAD), on November 15, 2017, in Irvine, Calif.
Wave Computing has leveraged several years of advanced research and development in dataflow technology to optimize SAT Solver technology, also known as Boolean Satisfiability or Propositional Satisfiability technology, for use in its machine learning solutions. Wave Computing’s patented implementation of SAT Solver technology represents a novel approach to accelerating deep learning algorithms on the company’s non-Von Neumann, statically scheduled Dataflow Processor Unit (DPU) architecture. Wave Computing’s DPU solutions eliminate the need for CPUs and co-processors, such as GPUs and FPGAs, making them capable of delivering hundreds of times the performance and enhanced scalability compared to traditional offerings.
- SAT-Based Compilation to a Non-Von Neumann Processor
- Phase-Based Power/Performance Prediction of Heterogeneous Systems via Neural Networks
- Fast and Accurate Performance Estimation for FPGA HLS
- A Streaming Clustering Approach Using a Heterogeneous System for Big Data Analysis
Date: Wednesday, November 15, 2017
Time: 1.45 pm PT
Location: ICCAD 2017 – Irvine Marriott, 18000 Von Karman Ave., Irvine, Calif.
About Dr. Samit Chaudhuri
Chaudhuri is the Vice President of Software Engineering at Wave Computing. In this role, he contributes to and helps lead the development of the WaveFlow™ DPU software stack, which accelerates dataflow programs on Wave Computing’s Course Grain Reconfigurable Array (CGRA) architecture. Prior to joining Wave Computing, Chaudhuri, who is best known for his expertise on compilers and hardware synthesis, led software and algorithm development teams for multiple technology companies and startups, including Cadence Design Systems, Magma (now a part of Synopsys), and Oasys (now a part of Mentor Graphics). He received his PhD in Computer Engineering from Rensselaer Polytechnic Institute, with a research focus on compilers and high-level synthesis.
In this increasingly compute centric world, there is increased demand for electronic design automation (EDA) with exciting changes and challenges being faced in the way we design, compute, and deploy systems. For over 35 years, ICCAD has been a premier forum which has paved the way in creating systems which are fast, small, power efficient, low cost, correct, manufacturable, and reliable. Recent keynotes, papers, tutorials, and workshops at ICCAD have addressed novel technologies, the exciting prospects offered by deep learning, newer memories, IoT, approximate computing, and security concerns amongst others.
About Wave Computing
Wave Computing, Inc. is the Silicon Valley start-up that is revolutionizing artificial intelligence and deep learning with its dataflow-based solutions. The company’s solutions leverage its native dataflow technology to outperform machine learning products available today. Wave Computing, one of CIO Application Magazine’s Top 25 Artificial Intelligence Providers, is offering its solutions to customers globally.
Wave Computing and WaveFlow are trademarks of Wave Computing, Inc. All other trademarks are used for identification purposes only and are the property of their respective owners. ©2017 Wave Computing, Inc. All rights reserved.