The effect of network total order, broadcast, and remote-write capability on network-based shared memory computing

IEEE High-Performance Computer Architecture Symposium Proceedings

Volumn , Issue , 2000, Pages 265-276

  Stets, Robert ^a   Dwarkadas, Sandhya ^b   Kontothanassis, Leonidas ^a   Rencuzogullari, Umit ^b   Scott, Michael L ^b  

^a HEWLETT PACKARD COMPANY   (United States)

^b University of Rochester   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER NETWORKS; DATA STORAGE EQUIPMENT; NETWORK PROTOCOLS; PACKET NETWORKS;

REMOTE WRITE CAPABILITY; SOFTWARE DISTRIBUTED SHARED MEMORY; SYSTEM AREA NETWORKS;

DISTRIBUTED COMPUTER SYSTEMS;

EID: 0034581381     PISSN: 15300897     EISSN: None     Source Type: Journal    
DOI: 10.1109/HPCA.2000.824356     Document Type: Article

References (31)

1. A unified formulation of four shared-memory models
2. TreadMarks: Shared memory computing on networks of workstations
3. Software DSM protocols that adapt between single writer and multiple writer
4. Using network interface support to avoid asynchronous protocol processing in shared virtual memory systems
5. Virtual memory mapped network interface for the SHRIMP multicomputer
6. An implementation of the Hamlyn sender-managed interface architecture
7. UTLB: A mechanism for address translation on network interfaces
8. Adaptive cache coherency for detecting migratory shared data
9. Parallel programming in split-C
10. The virtual interface architecture
11. Parallelization of general linkage analysis problems
12. Comparative evaluation of fine- and coarse-grain approaches for software distributed shared memory
13. U-Net: A user-level network interface for parallel and distributed computing
14. SoftFLASH: Analyzing the performance of clustered distributed virtual shared memory
15. Memory channel: An optimized cluster interconnect
16. ServerNet SAN I/O architecture
17. Lazy release consistency for software distributed shared memory
18. VM-based shared memory on low-latency, remote-memory-access networks
19. The SGI origin: A ccNUMA highly scalable server
20. Using simple page placement policies to reduce the cost of cache fills in coherent shared-memory systems
21. Efficiently adapting to sharing patterns in software DSMs
22. Homebased SVM protocols for SMP clusters: Design and performance
23. Towards transparent and efficient software distributed shared memory
24. Fine-grain software distributed shared memory on SMP clusters
25. SPLASH: Stanford parallel applications for shared-memory
26. Using multicast and multithreading to reduce communication in software DSM systems
27. An adaptive cache coherence protocol optimized for migratory sharing
28. Cashmere-2L: Software coherent shared memory on a clustered remote-write network
29. Operating system support for improving data locality on CC-NUMA compute servers
30. Incorporating memory management into user-level network interfaces
31. Methodological considerations and characterization of the SPLASH-2 parallel application suite