skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Portable SHMEMCache: A High-Performance Key-Value Store on OpenSHMEM and MPI

Conference · · OPENSHMEM AND RELATED TECHNOLOGIES: BIG COMPUTE AND BIG DATA CONVERGENCE, OPENSHMEM 2017
 [1];  [2];  [2];  [1]
  1. Florida State Univ., Tallahassee, FL (United States)
  2. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
+ Show Author Affiliations

The integration of Big Data frameworks and HPC capabilities has drawn enormous interests in recent years. SHMEMCache is a distributed key-value store built on the OpenSHMEM global address space. It has solved several practical issues in leveraging OpenSHMEM’s one-sided operations for a distributed key-value store and providing efficient key-value operations on both commodity machines and supercomputers. However, being based solely on OpenSHMEM, SHMEMCache cannot leverage one-sided operations from a variety of software packages. This results in several limitations for SHMEMCache. First, we cannot make SHMEMCache available to a wider range of platforms. Second, an opportunity for potential performance improvement is missed. Third, there is a lack of deep understanding about how different one-sided operations can fit in with SHMEMCache and other distributed key-values in general. For example, the one-sided operations in OpenSHMEM and MPI have many differences in their interfaces, memory semantics and synchronization methods, all of which can have distinct implications and also increase the complexity in supporting both OpenSHMEM and MPI for SHMEMCache. Therefore, we have taken on an effort on leveraging different one-sided operations for SHMEMCache and proposed a design of portable SHMEMCache. Based on this new framework, we have supported both OpenSHMEM and MPI for SHMEMCache. We have also conducted an extensive set of experiments to compare the performance of the two versions on both commodity machines and the Titan supercomputer.

Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF); UT-Battelle LLC/ORNL, Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
DOE Contract Number:
AC05-00OR22725
OSTI ID:
1567475
Journal Information:
OPENSHMEM AND RELATED TECHNOLOGIES: BIG COMPUTE AND BIG DATA CONVERGENCE, OPENSHMEM 2017, Vol. 10679; Conference: OpenSHMEM 2017: OpenSHMEM and Related Technologies. Big Compute and Big Data Convergence, Annapolis, Maryland, August 7-9, 2017.
Country of Publication:
United States
Language:
English

References (19)

Providing a cloud network infrastructure on a supercomputer
  • Appavoo, Jonathan; Waterland, Amos; Da Silva, Dilma
  • Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing - HPDC '10 https://doi.org/10.1145/1851476.1851534
conference January 2010
Introducing OpenSHMEM: SHMEM for the PGAS community conference January 2010
Fast and general distributed transactions using RDMA and HTM conference January 2016
Benchmarking cloud serving systems with YCSB conference January 2010
An implementation and evaluation of the MPI 3.0 one-sided communication interface: MPI 3.0 RMA IMPLEMENTATION AND EVALUATION journal January 2016
No compromises: distributed transactions with consistency, availability, and performance conference January 2015
High-Performance Key-Value Store on OpenSHMEM
  • Fu, Huansong; Venkata, Manjunath Gorentla; Choudhury, Ahana Roy
  • 2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID) https://doi.org/10.1109/CCGRID.2017.49
conference May 2017
Implementing OpenSHMEM Using MPI-3 One-Sided Communication book January 2014
High-Performance Design of HBase with RDMA over InfiniBand
  • Huang, Jian; Ouyang, Xiangyong; Jose, Jithin
  • 2012 IEEE International Symposium on Parallel & Distributed Processing (IPDPS), 2012 IEEE 26th International Parallel and Distributed Processing Symposium https://doi.org/10.1109/IPDPS.2012.74
conference May 2012
High performance MPI-2 one-sided communication over infinilband conference January 2004
Scalable Memcached Design for InfiniBand Clusters Using Hybrid Transports
  • Jose, Jithin; Subramoni, Hari; Kandalla, Krishna
  • 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012) https://doi.org/10.1109/CCGrid.2012.141
conference May 2012
Memcached Design on High Performance RDMA Capable Interconnects conference September 2011
High Performance RDMA-Based MPI Implementation over InfiniBand journal June 2004
Advances, Applications and Performance of the Global Arrays Shared Memory Programming Toolkit journal May 2006
Co-array Fortran for parallel programming journal August 1998
High-Performance Hybrid Key-Value Store on Modern Clusters with RDMA Interconnects and SSDs: Non-blocking Extensions, Designs, and Benefits conference May 2016
Infiniband scalability in Open MPI conference January 2006
Hadoop acceleration through network levitated merge
  • Wang, Yandong; Que, Xinyu; Yu, Weikuan
  • Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '11 https://doi.org/10.1145/2063384.2063461
conference January 2011
HydraDB: a resilient RDMA-driven key-value middleware for in-memory cluster computing
  • Wang, Yandong; Zhang, Li; Tan, Jian
  • Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '15 https://doi.org/10.1145/2807591.2807614
conference January 2015

Similar Records

High-Performance Key-Value Store on OpenSHMEM
Conference · Mon May 01 00:00:00 EDT 2017 · OSTI ID:1567475
+2 more
OpenSHMEM over MPI-3
Software · Wed Feb 26 00:00:00 EST 2014 · OSTI ID:1567475
Accelerating k-NN Algorithm with Hybrid MPI and OpenSHMEM
Conference · Wed Aug 05 00:00:00 EDT 2015 · OSTI ID:1567475
+3 more

Related Subjects

Computer Science