Eriko Nurvitadhi
ABSTRACT
The continued rapid growth of data, along with advances in Artificial Intelligence (AI) to extract knowledge from such data, is reshaping the computing ecosystem landscape. With AI becoming an essential part of almost every end-user application, our current computing platforms are facing several challenges. The data-intensive nature of current AI models requires minimizing data movement. Furthermore, interactive intelligent datacenter-scale services require scalable and real-time solutions to provide a compelling user experience. Finally, algorithmic innovations in AI demand a flexible and programmable computing platform that can keep up with this rapidly changing field. We believe that these trends and their accompanying challenges present tremendous opportunities for FPGAs. FPGAs are a natural substrate to provide a programmable, near-data, real-time, and scalable platform for AI analytics. FPGAs are already embedded in several places where data flows throughout the computing ecosystem (e.g., "smart" network/storage, near image/audio sensors). Intel FPGAs are System-in-Package (SiP), scalable with 2.5D chiplets. They are also scalable at datacenter-scale as reconfigurable cloud, enabling real-time AI services. Using overlays, FPGAs can be programmed through software without needing long-running RTL synthesis. With further innovations, and leveraging their existing strengths, FPGAs can leap forward to realize their true potentials in AI analytics. In this talk, we first discuss the current trends in AI and big data. We then present trends in FPGA and opportunities for FPGAs in the era of AI and big data. Finally, we highlight selected research efforts to seize some of these opportunities: (1) 2.5D SiP integration of FPGA and AI chiplets to improve the performance and efficiency of AI workloads, and (2) AI overlay for FPGA to facilitate software-level programmability and compilation-speed.
- E. Nurvitadhi, G. Venkatesh, J. Sim, et. al., "Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Neural Networks?" International Symposium on Field-Programmable Gate Arrays (ISFPGA), 2017. Google Scholar
Digital Library
- E. Nurvitadhi, J. Sim, D. Sheffield, et. al., "Accelerating recurrent neural networks in analytics servers: Comparison of FPGA, CPU, GPU, and ASIC," Field Programmable Logic and Applications (FPL), 2016.Google Scholar
- E. Nurvitadhi, D. Sheffield, J. Sim, et. al., "Accelerating Binarized Neural Networks: Comparison of FPGA, CPU, GPU, and ASIC," International Conference on Field-Programmable Technology (FPT), 2016.Google Scholar
- S. Shumarayev, "Heterogeneous Modular Platform," Hot Chips, 2017.Google Scholar
- A. Putnam, A Caulfield, E. Chung, et. al., "A Reconfigurable Fabric for Accelerating Large-Scale Datacenter Services," International Symposium on Computer Architecuture (ISCA), 2014. Google ScholarDigital Library
- E. Chung, J. Fowers, K. Ovtcharov, et. al., "Accelerating Persistent Neural Networks at Datacenter Scale," Hot Chips, 2017.Google Scholar
- J. Ouyang S. Lin, W. Qi, "SDA: Software-defined accelerator for large-scale DNN systems," Hot Chips, 2014.Google Scholar
- E. Nurvitadhi, J. J. Cook, A. Mishra, et. al., "In-Package Domain-Specific ASICs for Intel® Stratix® 10 FPGAs: A Case Study of Accelerating Deep Learning Using TensorTile ASIC TensorRAM," Field Programmable Logic and Applications (FPL), 2018. Google ScholarDigital Library
- E. Nurvitadhi, D. Kwon, A. Jafari, et. al., "Evaluating and Enhancing Intel® Stratix® 10 FPGAs for Persistent Real-Time AI," International Symposium on Field-Programmable Gate Arrays (ISFPGA), 2019. Google ScholarDigital Library
Index Terms
- FPGA-based Computing in the Era of AI and Big Data
Recommendations
Responsible Big Data Analytics for E-Business Services
ICBDR '21: Proceedings of the 5th International Conference on Big Data ResearchThis paper examines responsible big data analytics for e-business services and looks at how to use responsible big data analytics to obtain responsible e-business services. It addresses why responsibility matters to big data analytics and e-business ...
The anatomy of big data computing
Advances in information technology and its widespread growth in several areas of business, engineering, medical, and scientific studies are resulting in information/data explosion. Knowledge discovery and decision-making from such rapidly growing ...
Big Data with Ten Big Characteristics
ICBDR '18: Proceedings of the 2nd International Conference on Big Data ResearchThis paper reveals ten big characteristics (10 Bigs) of big data and explores their non-linear interrelationships through presenting a unified framework of big data. The framework has three levels: fundamental level, technological level, and socio-...
Comments