Explore cutting-edge techniques for optimizing sparse matrix computations through code specialization in this 14-minute conference talk presented at CTSTA'23. Delve into innovative approaches that leverage specialized code generation to enhance performance and efficiency in handling sparse matrix operations. Gain insights into the latest advancements in high-performance computing and learn how these techniques can be applied to accelerate various computational tasks across scientific and engineering domains.
Overview
Syllabus
[CTSTA'23] Accelerating Sparse Matrix Computations with Code Specialization
Taught by
ACM SIGPLAN
Related Courses
-
FSSpMDM - Accelerating Small Sparse Matrix Multiplications by Run-Time Code Generation
-
Software and Hardware for Sparse Machine Learning
-
Automatic Differentiation for Sparse Tensors
-
Accelerating Sparse Iterative Solvers and Preconditioners Using RACE - Supercomputing Spotlights
-
Coded Matrix Computation: Numerical Stability, Partial Stragglers, and Sparse Input Matrices
-
General Distributed Framework for Contraction of Sparse Tensor with Tensor Network
