Fpga'19: Proceedings of the 2019 ACM / SIGDA International Symposium on Field-Programmable Gate Arrays

We are delighted to welcome you to the 2019 ACM International Symposium on Field-Programmable Gate Arrays (ACM FPGA 2019). ACM FPGA is the premiere forum for the presentation of new and exciting research on all aspects of FPGA technology, which include: Novel FPGA architectures and circuits. Advances in CAD tools for FPGAs, in areas such as technology mapping, placement, routing, and others. High-level design methodologies that permit FPGA design at higher levels of abstraction. New applications for FPGAs, particularly for energy efficient and high performance computation.



Aside from the technical sessions, the conference provides the opportunity for FPGA researchers and practitioners from around the world to network with long-time friends and make new connections in a beautiful setting. This year the conference venue has moved a short distance to Seaside, California, but remains close to the spectacular coastline of the Monterey Bay and the attractions in the cities of Monterey and Pacific Beach.



This year the program committee received 161 paper submissions, of which 139 papers met submission guidelines and were reviewed. This represents an increase of almost 40% from last year. As a result, we've extended the conference program to 3 full days, consisting of 24 full research papers (10 pages), 6 short research papers (6 pages), and 2 peer-reviewed tutorials (10 pages). Overall 23% of reviewed papers were accepted. 63 submissions were selected to be presented as posters and appear in these proceedings in abstract form. In addition, 3 invited tutorials will also be presented, with accompanying material published in the proceedings.



At FPGA 2019, we continue to see a huge interest in using FPGAs for Machine Learning, particularly for efficient inference of Deep Neural Networks. This year over 40% of submissions were related to Machine Learning. Invited industry keynotes and tutorials will highlight new tools and architectures for maximizing the efficiency of Deep Neural Networks. The field of deep learning continues to change rapidly and FPGAs seem well positioned for many new applications, in both data center and in embedded environments.



The other big trend for FPGAs in the past year has been towards widespread deployment in data centers, with almost all major data center providers enabling access to FPGAs-as-a-Service. At the same time, CPUs and GPUs continue to dominate Supercomputer deployments. The panel discussion, at the Monday evening banquet, will consider whether FPGAs can impact other high performance computing applications. The panel will include representatives from the FPGA and Supercomputing communities. We expect a lively exchange among the panelists!