Write a Blog >>
SPLASH 2017
Sun 22 - Fri 27 October 2017 Vancouver, Canada
Thu 26 Oct 2017 10:30 - 10:52 at Regency C - Optimizing Compilation and Verification Chair(s): Gregor Richards

Tensor algebra is a powerful tool with applications in machine learning, data analytics, engineering and the physical sciences. Tensors are often sparse and compound operations must frequently be computed in a single kernel for performance and to save memory. Programmers are left to write kernels for every operation of interest, with different mixes of dense and sparse tensors in different formats. The combinations are infinite, which makes it impossible to manually implement and optimize them all. This paper introduces the first compiler technique to automatically generate kernels for any compound tensor algebra operation on dense and sparse tensors. The technique is implemented in a C++ library called taco. Its performance is competitive with best-in-class hand-optimized kernels in popular libraries, while supporting far more tensor operations.

Thu 26 Oct
Times are displayed in time zone: Tijuana, Baja California change

10:30 - 12:00
Optimizing Compilation and VerificationOOPSLA at Regency C
Chair(s): Gregor RichardsUniversity of Waterloo
10:30
22m
Talk
The Tensor Algebra Compiler
OOPSLA
DOI
10:52
22m
Talk
TreeFuser: A Framework for Analyzing and Fusing General Recursive Tree Traversals
OOPSLA
Laith SakkaPurdue University, Kirshanthan SundararajahPurdue University, Milind KulkarniPurdue University
DOI
11:15
22m
Talk
Verifying Spatial Properties of Array Computations
OOPSLA
Dominic OrchardUniversity of Kent, UK, Mistral Contrastin, Matthew DanishUniversity of Cambridge, UK, Andrew RiceUniversity of Cambridge, UK
DOI
11:37
22m
Talk
GLORE: Generalized Loop Redundancy Elimination upon LER-Notation
OOPSLA
Yufei DingNorth Carolina State University, Xipeng ShenNorth Carolina State University
DOI