PPT-Finding Optimum Abstractions in Parametric Dataflow Analysis

Finding Optimum Abstractions in Parametric Dataflow Analysis Xin Zhang Georgia Tech Mayur Naik Georgia Tech Hongseok Yang University of Oxford A Key Challenge for Static Analysis Precision Scalability. All Programmable Abstractions push beyond traditional RTL design methodologies to automate all aspects of system development and algorithm deployment into all programmable FPGAs SoC and 3D ICs Xilinx and its Alliance members are working together to Mayur Naik. Georgia Tech. Xin. Zhang. (Georgia Tech). Hongseok. . Yang. (. Oxford) . Percy . Liang. (. Stanford). Mooly. . Sagiv. (. Tel-Aviv U). J. oint . work . with:. Static . Analysis: 70’s to 90’s. (and the Naiad system). Frank McSherry. , Derek G. Murray,. Rebecca Isaacs, . Michael Isard. Microsoft Research, Silicon Valley. Data-parallel dataflow. 1. 2. 3. 4. 5. 1. 4. 2. 3. 6. 6. 5. A. B. C. D. via Dataflow Flattening. Bertrand Anckaert. Ghent University/. Boston . Consulting Group. The Third International Conference on Emerging Security. Information, Systems and Technologies. . SECURWARE 2009. Xin Zhang. Georgia Tech. Mayur. . Naik. Georgia Tech. Hongseok. Yang. University of Oxford. A Key Challenge for Static Analysis. Precision. Scalability. Our setting. Query q. Program p. Static Analysis S. th. March. Geir Helgesen. Sales –Director . 1. The Abbon value proposition . . The Abbon performance monitoring system . ”Making real-time flow rates per well available in the operation center” . Yuan Lin. 1. , Yoonseo Choi. 1. , Scott Mahlke. 1. , Trevor Mudge. 1. , . Chaitali. Chakrabarti. 2. 1. Advanced Computer Architecture Lab, University of Michigan at Ann Arbor. 2. Department of Electrical Engineering, Arizona State University. Building Relational Web-Applications. Avraham . Leff. James T. . Rayfield. IBM T.J. Watson Research Center. {. avraham,jtray. }@us.ibm.com. OOPSLA’07. Presented by David Gonzalez. Key Insights:. Derek G. Murray. Michael Isard. Frank McSherry. Paul Barham. Rebecca Isaacs. Martín Abadi. Microsoft Research. 1. Batch processing. Stream processing. Graph processing. Timely dataflow. In. ⋈. #x. Frank McSherry. , Derek G. Murray,. Rebecca Isaacs, Michael Isard. Microsoft Research, Silicon Valley. Data-parallel dataflow. 1. 2. 3. 4. 5. 1. 4. 2. 3. 6. 6. 5. A. B. C. D. E. k1:. k2:. k3:. Data-parallel dataflow. William D. O’Neil. Analysis for Decision. March 2010. Parametric analysis for engineered. systems. System parameters. Independent variables. Some set by designer, others by operator. Design parameters collectively define design. Val & Aly. April 201. 4. Overview. Regression Analysis: . Mediation. Moderation. Non-parametric tests. When? Why? How?. Example 1. Bumble . wants to know whether the relationship between children’s negative affect and self esteem can be explained by children’s bad behavior. . Claus Brabrand. IT University of Copenhagen. Universidade Federal de Pernambuco. [ brabrand@itu.dk ]. Márcio Ribeiro. Universidade Federal de Alagoas. Universidade Federal de Pernambuco. [ mmr3@cin.ufpe.br ]. To perform optimizations like constant propagation or dead code elimination, we must. Analyze program to find opportunities for performing optimizations safely. Transform program. Analysis is called .