2016/03/10 by Salvador Tamarit, Julio Mariño, Tamarit, Salvador +5
Computer Science · Decision Sciences · #Distributed #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #Parallel #Programming Languages (cs.PL) #Scientific Computing and Data Management #Software Engineering (cs.SE) #Software System Performance and Reliability #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.1603.03488
openalex publication_date 2016/03/10 · openalex created_date 2022/10/06 · openalex updated_date 2026/07/28
This volume contains the proceedings of PROHA 2016, the first workshop on\nProgram Transformation for Programmability in Heterogeneous Architectures, held\non March 12, 2016 in Barcelona, Spain, as an affiliated workshop of CGO 2016,\nthe 14th International Symposium on Code Generation and Optimization.\nDeveloping and maintaining high-performance applications and libraries for\nheterogeneous architectures while preserving its semantics and with a\nreasonable efficiency is a time-consuming task which is often only possible for\nexperts. It often requires manually adapting sequential, platform-agnostic code\nto different infrastructures, and keeping the changes in all of these\ninfrastructures in sync. These program modification tasks are costly and\nerror-prone. Tools to assist in and, if possible, automate such transformations\nare of course of great interest. However, such tools may need significant\nreasoning and knowledge processing capabilities, including, for example, being\nable to process machine-understandable descriptions of the semantics of a piece\nof code is expected to do; to perform program transformations inside a context\nin which they are applicable; to use strategies to identify the sequence of\ntransformations leading to the best resulting code; and others.\n