Title:
Near-memory primitive support and infratructure for sparse algorithm
Near-memory primitive support and infratructure for sparse algorithm
dc.contributor.advisor | Yalamanchili, Sudhakar | |
dc.contributor.advisor | Young, Jeffrey | |
dc.contributor.author | Garg, Kartikay | |
dc.contributor.committeeMember | Krishna, Tushar | |
dc.contributor.committeeMember | Vuduc, Richard | |
dc.contributor.department | Electrical and Computer Engineering | |
dc.date.accessioned | 2017-06-07T17:49:45Z | |
dc.date.available | 2017-06-07T17:49:45Z | |
dc.date.created | 2017-05 | |
dc.date.issued | 2017-04-28 | |
dc.date.submitted | May 2017 | |
dc.date.updated | 2017-06-07T17:49:45Z | |
dc.description.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. | |
dc.description.degree | M.S. | |
dc.format.mimetype | application/pdf | |
dc.identifier.uri | http://hdl.handle.net/1853/58343 | |
dc.language.iso | en_US | |
dc.publisher | Georgia Institute of Technology | |
dc.subject | Processing in memory (PIM) | |
dc.subject | Near data processing (NDP) | |
dc.subject | 3D-stacked memory | |
dc.subject | HMC | |
dc.subject | FPGA | |
dc.subject | SuperLU | |
dc.title | Near-memory primitive support and infratructure for sparse algorithm | |
dc.type | Text | |
dc.type.genre | Thesis | |
dspace.entity.type | Publication | |
local.contributor.corporatename | School of Electrical and Computer Engineering | |
local.contributor.corporatename | College of Engineering | |
relation.isOrgUnitOfPublication | 5b7adef2-447c-4270-b9fc-846bd76f80f2 | |
relation.isOrgUnitOfPublication | 7c022d60-21d5-497c-b552-95e489a06569 | |
thesis.degree.level | Masters |