Schedule Data, Not Code
Schedule Data, Not Code by Micah J Best BSc (Honours), University of Victoria, 2004 MSc, Simon Fraser University, 2007 A THESIS SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF Doctor of Philosophy in THE FACULTY OF GRADUATE AND POSTDOCTORAL STUDIES (Computer Science) The University of British Columbia (Vancouver) Octorber 2020 © Micah J Best, 2020 The following individuals certify that they have read, and recommend to the Fac- ulty of Graduate and Postdoctoral Studies for acceptance, the dissertation entitled: Schedule Data, Not Code submitted by Micah J Best in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science. Examining Committee: Alexandra Fedorova, Associate Professor, Electrical and Computer Engineering, UBC Supervisor Arvind Gupta, Professor, Computer Science, University of Toronto Supervisory Committee Member Ronald Garcia, Associate Professor, Computer Science, UBC University Examiner Chen Feng, Assistant Professor, School of Engineering, UBC Okanagan University Examiner Additional Supervisory Committee Members: Ivan Beschastnikh, Associate Professor, Computer Science, UBC Supervisory Committee Member Sathish Gopalakrishnan, Associate Professor, Electrical and Computer Engineer- ing, UBC Supervisory Committee Member ii Abstract Parallel programming is hard and programmers still struggle to write code for shared memory multicore architectures that is both free of concurrency errors and efficient. Tools have advanced, but for tasks that are not embarrassingly parallel, or suitable for a limited model such as map/reduce, there is little help. We aim to address some major aspects of this still underserved area. We construct a model for parallelism, Data not Code (DnC), by starting with the observation that a majority of performance and problems in parallel program- ming are rooted in the manipulation of data, and that a better approach is to sched- ule data, not code.
[Show full text]