Year: 2015
Type: conference-paper
Abstract: This paper introduces three new compiler transformations for representing and transforming sparse matrix computations and their data representations. In cooperation with run-time inspection, our compiler derives transformed matrix representations and associated transformed code to implement a variety of representations targeting different architecture platforms. This systematic approach to combining code and data transformations on sparse computations, which extends a polyhedral transformation and code generation framework, permits the compiler to compose these transformations with other transformations to generate code that is on average within 5% and often exceeds manually-tuned, high-performance sparse matrix libraries CUSP and OSKI. Additionally, the compiler-generated inspector codes are on average 1.5 faster than OSKI and perform comparably to CUSP, respectively.
Authors: Anand Venkat, Mary Hall, Michelle Strout
Institutions: University of Utah, Colorado State University
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: G222768804, SHF Small: A Compiler-Based Auto-Tuning Framework for Many-Core Code Generation, Foraging Ecology of Crabeater Seals (Lobodon Carcinophagus), G6266972853, TAS::89 0222::TAS NEW-EARLY CAREER; SEPARATING ALGORITHM AND IMPLEMENTATION VIA PROGRAMMING MODEL INJECTION (SAIMI); PI - MICHELLE STROUT
OpenAlex ID: W2049487370