Designing Non-blocking Allreduce with Collective Offload on InfiniBand Clusters: A Case Study with Conjugate Gradient Solvers
- Research Organization:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 1114691
- Report Number(s):
- LLNL-CONF-502793
- Resource Relation:
- Conference: Presented at: IEEE IPDPS 2012, Shanghai, China, May 21 - May 25, 2012
- Country of Publication:
- United States
- Language:
- English
Similar Records
Designing Topology-Aware Collective Communication Algorithms for Large Scale InfiniBand Clusters: Case Studies with Scatter and Gather
ConnectX-2 InfiniBand Management Queues: First Investigation of the New Support for Network Offloaded Collective Operations
GPU-Centric Communication on NVIDIA GPU Clusters with InfiniBand: A Case Study with OpenSHMEM
Conference
·
Thu Apr 01 00:00:00 EDT 2010
·
OSTI ID:1114691
+1 more
ConnectX-2 InfiniBand Management Queues: First Investigation of the New Support for Network Offloaded Collective Operations
Conference
·
Fri Jan 01 00:00:00 EST 2010
·
OSTI ID:1114691
+7 more
GPU-Centric Communication on NVIDIA GPU Clusters with InfiniBand: A Case Study with OpenSHMEM
Conference
·
Fri Dec 01 00:00:00 EST 2017
·
OSTI ID:1114691
+3 more