Title:
Near-memory primitive support and infratructure for sparse algorithm

Thumbnail Image
Author(s)
Garg, Kartikay
Authors
Advisor(s)
Yalamanchili, Sudhakar
Young, Jeffrey
Advisor(s)
Editor(s)
Associated Organization(s)
Supplementary to
Abstract
This thesis introduces an approach to solving the problem of memory latency performance penalties with traditional accelerators. By introducing simple near-data-processing (NDP) accelerators for primitives such as SpMV (Sparse Matrix Multiplication of Vectors) and DGEMM (Double Precision Dense Matrix Multiplication) kernels, applications can achieve a considerable performance boost. We evaluate our work for SuperLU application for the HPC community. Thesis Statement: Reevaluating core primitives such as DGEMM, SCATTER, and GATHER for 3D-stacked PIM architectures that incorporate re-configurable fabrics can deliver multi-fold performance improvements for SUPERLU and other sparse algorithms.
Sponsor
Date Issued
2017-04-28
Extent
Resource Type
Text
Resource Subtype
Thesis
Rights Statement
Rights URI