Heterogeneous Computing
|
[ Overview ]
- Multi-core/Many-core
- P2P Scheduling for Multi-thread/Multi-core nodes
- Symbiotic Scheduling : how to predict contention effects on shared resources?
- How to exploit residual resources effectively?
- GPGPU/Accelerator
- Characterization on GPU applications
- Resource Management on Various Resource Types
- Contention Effects on a GPU platform
|
[ Publication ]
- Jaehwan Lee, Pete Keleher and Alan Sussman, "Supporting Computing Element Heterogeneity in P2P Grids", IEEE 2011 Cluster Conference (Cluster'11), Aust
in, TX, Sep. 2011
- Jaehwan Lee, Pete Keleher and Alan Sussman, "Decentralized Resource Management for Multi-core Desktop Grids", IEEE 24th 2010 International Parallel & Distributed Processing Symposium (IPDPS'10), Atlanta, GA, April 2010
- Jaehwan Lee, Pete Keleher and Alan Sussman, "Decentralized Dynamic Scheduling across Heterogeneous Multi-core Desktop Grids", IEEE 19th International Heterogeneity in Computing Workshop (HCW'10) in conjunction with IPDPS 2010, Atlanta, GA, April 2010
|
Fig.1. How to represent dynamic resource status in P2P Grid for multi-core
|
Fig.2. Dynamic Load Balancing under Multiple Resource Constraints
|
Fig.3. Efficient Communication Scheme in P2P Grids for Heterogeneous Nodes
|
|
|
|