Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server

Towards Optimal Matrix Partitioning for Data Parallel Computing on a Hybrid Heterogeneous Server

Optimal partitioning of a square computational domain over several heterogeneous processors, balancing the load of the processors and minimizing the inter-processor communication cost, is crucial for data parallel dense linear algebra and other applications having similar communication pattern on mo...

Full description

Bibliographic Details
Main Authors: Tania Malik, Alexey Lastovetsky
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Data partitioning
communication optimization
non-rectangular partitioning
matrix multiplication
heterogeneous computing
performance model
Online Access:https://ieeexplore.ieee.org/document/9328411/

Internet

https://ieeexplore.ieee.org/document/9328411/

Similar Items