Sensitivity of parallel applications to large differences in bandwidth and latency in two-layer interconnects

Future Generation Computer Systems

Volumn 17, Issue 6, 2001, Pages 769-782

  Plaat, Aske ^a   Bal, Henri E ^a   Hofman, Rutger F H ^a   Kielmann, Thilo ^a  

^a VU UNIVERSITY AMSTERDAM   (Netherlands)

Author keywords

Application sensitivity; Cluster computing; Orca; Wide area networks

Indexed keywords

BANDWIDTH; CONGESTION CONTROL (COMMUNICATION); DATA STRUCTURES; HIERARCHICAL SYSTEMS; INTERCONNECTION NETWORKS; SENSITIVITY ANALYSIS; TELECOMMUNICATION TRAFFIC; WIDE AREA NETWORKS;

REMOTE MEMORY ACCESS; TWO-LAYER INTERCONNECTS;

PARALLEL PROCESSING SYSTEMS;

EID: 0035312547     PISSN: 0167739X     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-739X(00)00103-5     Document Type: Article

References (41)

1. Parallel retrograde analysis on a distributed system
2. Performance evaluation of the Orca shared object system
3. Optimizing parallel applications for wide area clusters
4. User-level network interface protocols
5. Highly portable and efficient implementations of parallel adaptive n-body methods
6. Myrinet: A gigabit-per-second local area network
7. Techniques for reducing consistency-related communication in distributed shared memory system
8. Implementing an irregular application on a distributed memory multiprocessor
9. Where is time spent in message-passing and shared-memory programs
10. The sensitivity of communication mechanisms to bandwidth and latency
11. Software versus hardware shared-memory implementation: A case study
12. SoftFLASH: Analyzing the performance of clustered distributed virtual shared memory
13. Globus: A metacomputing infrastructure toolkit
14. Scalable parallel formulations of the Barnes-Hut algorithm for n-body simulations
15. The legion vision of a worldwide virtual computer
16. A high-performance, portable implementation of the MPI message passing interface standard
17. Reducing false sharing on shared memory multiprocessors through compile-time data transformations
18. Application restructuring and performance portability on shared virtual memory and hardware-coherent multiprocessors
19. A methodology and an evaluation of the SGI origin2000
20. Crl: High-performance all-software distributed shared memory
21. MagPIe: MPIs collective communication operations for clustered wide area systems
22. VM-based shared memory on low-latency, remote-memory-access networks
23. The SGI origin: A ccNUMA highly scalable server
24. Multi-protocol active messages on a cluster of SMPs
25. An efficient implementation of Java's remote method invocation
26. MPI: A message passing interface standard
27. High performance messaging on workstations: Illinois fast messages (FM) for Myrinet
28. Parallel n-body simulation on a large-scale homogeneous distributed system
29. Fine-grain software distributed shared memory on SMP clusters
30. The enterprise model for developing distributed applications
31. Load balancing and data locality in adaptive hierarchical n-body methods: Barnes-Hut, fast multipole and radiosity
32. SPLASH: Stanford parallel applications for shared memory
33. Flexible use of memory for replication/migration in cache-coherent DSM multiprocessors
34. Cashmere-2L: Software coherent shared memory on a clustered remote-write network
35. Towards efficiency and portability: Programming with the BSP model
36. A bridging model for parallel computation
37. Wide area parallel computing in Java
38. A parallel hashed oct-tree n-body algorithm
39. The Splash-2 programs: Characterization and methodological considerations
40. MGS: A multigrain shared memory system