Matching Linear Algebra and Tensor Code to Specialized Hardware Accelerators
Pablo A. Lanzarote Martínez, Jackson Woodruff, Jordi Armengol-Estapé, Gregorio Bernabé, José M. Garcı́a, Michael O’Boyle
Abstract
Dedicated tensor accelerators demonstrate the importance of linear algebra in modern applications. Such accelerators have the potential for impressive performance gains, but require programmers to rewrite code using vendor APIs - a barrier to wider scale adoption. Recent work overcomes this by matching and replacing patterns within code, but such approaches are fragile and fail to cope with the diversity of real-world codes.
Topics & Concepts
Linear algebraComputer scienceVendorCode (set theory)Tensor (intrinsic definition)Matching (statistics)Tensor algebraProgramming languageTheoretical computer scienceParallel computingAlgebra over a fieldComputer engineeringComputational scienceMathematicsAlgebra representationPure mathematicsGeometryStatisticsSet (abstract data type)Jordan algebraMarketingBusinessParallel Computing and Optimization TechniquesSoftware Testing and Debugging TechniquesTeaching and Learning Programming