PPT-Formal Metrics for Large-Scale Parallel Performance

ISC 2015 Kenneth Moreland and Ron Oldfield Sandia National Laboratories Parallel Algorithm Speedup Parallel Algorithm Speedup Serial time for large problem sizes Cannot be measured in practice. Unlike sequential algorithms parallel algorithms cannot be analyzed very well in isolation One of our primary measures of goodness of a parallel system will be its scalability Scalability is the ability of a parallel system to take advantage of incr Hardware Parallelism. Computing: execute instructions that operate on data.. Flynn’s . taxonomy (Michael Flynn, 1967) classifies computer architectures based on the number of instructions that can be executed and how they operate on data.. Graph . Mining Tasks. 1. Outline. Introduction to Performance Metrics. Supervised Learning Performance . Metrics. Unsupervised . Learning Performance . Metrics. Optimizing Metrics. Statistical Significance Techniques. Project and Process Metrics. Why do we measure?. Assessing project status. Allows us to track risks. Before they go critical. Adjust workflow. See if the team can control the quality of artifacts. Example metric. Software. Steve Teixeira. Product Unit Manager. Microsoft Corporation. Session Code. : DEV401. My Assumptions About You. You have some knowledge of parallel development issues. You’d like to focus on the new stuff: Visual Studio 2010 and .NET 4.0. Andrew Lumsdaine. Indiana University. lums@osl.iu.edu. My Goal in Life. Performance with elegance. Introduction. Overview of our high-performance, industrial strength, graph library. Comprehensive features. Improving Computer Performance. What performance translates into:. Time taken to do computation. Improving performance . → reducing time taken. What key benefits improving performance can bring:. Can solve “now-computationally-attainable” problems in . Statisitcs. API. draft-huang-xrblock-rtcweb-rtcp-xr-metrics-02. Rachel Huang (rachel.huang@huawei.com). Varun Singh(. varun@comnet.tkk.fi. ). Roni Even (. roni.even@mail01.huawei.com. ). Dan Romascanu (dromasca@avaya.com). 6/16/2010. Parallel Performance. 1. Performance Considerations. I parallelized my code and …. The code slower than the sequential version, or. I don’t get enough speedup . What should I do?. 6/16/2010. Peter Andras. School of Computing Science. Newcastle University. peter.andras@ncl.ac.uk. Overview. Introduction. Research metrics. Science domains and evolution of science. Quality and performance. Science management. Loss Episode Metrics for IPPM. Nick Duffield, . Al Morton. , AT&T. Joel Sommers, Colgate University. IETF 79, Beijing, 11/8/2010. Agenda. Changes since IETF 77. One page summary of draft. Q&A from last IETF. ?. Metrics . are . units of . measurement . that . are used to characterize. :. software engineering . products. , e.g., designs, source code, and test cases,. software engineering . processes. , e.g., the activities of analysis, designing, and coding, and. Model . Metrics . and Reporting Sub-team. 1 August 2014. Why a metrics program?. Goals of a metrics program. Types of metrics. Further analytics on metrics. Metrics program design. Metrics program implementation. Parallel Processing, Multicores. Prof. Gennady . Pekhimenko. University of Toronto. Fall 2017. The content of this lecture is adapted from the lectures of . Onur. . Mutlu. @ CMU. Summary . Parallelism.