Abstract
This chapter presents the concept of batched computing, which consists of the division of a large problem into smaller portions and can be applied to both dense and sparse linear algebra. Two examples, general matrix-matrix multiplication (GEMM) and general triangular solver (GTSV), are used to present different approaches depending on the problem to solve. The GEMM example focuses on multi-core platforms, and it is also used to introduce the concept of auto-tunning. In the case of GTSV, the targeted device is a GPU. Moreover, given that this is a sparse operation, an analysis of the data layout is presented to see the impact of this aspect.