Leveraging cache coherence in active memory systems

Proceedings of the International Conference on Supercomputing

Volumn , Issue , 2002, Pages 2-13

  Kim, Daehyun ^a   Chaudhuri, Mainak ^a   Heinrich, Mark ^a  

^a Cornell University ^*  (United States)

Author keywords

Active Memory; Address Re mapping; Cache Coherence

Indexed keywords

COMPUTER SIMULATION; DATA STORAGE EQUIPMENT; PARALLEL PROCESSING SYSTEMS; PROBLEM SOLVING;

CACHE COHERENCE;

CACHE MEMORY;

EID: 0036375919     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/514191.514196     Document Type: Conference Paper

References (37)

1. Software caching and computation migration in olden
2. Impulse: Building a smarter memory controller
3. FFTW: An adaptive software architecture for the FFT
4. Architectural support for parallel reductions in scalable shared-memory multiprocessors
5. Architecture and design of alphaserver GS320
6. FLASH vs. (simulated) FLASH: Closing the simulation loop
7. Differential FCM: Increasing value prediction accuracy by improving table usage efficiency
8. Mapping irregular applications to DIVA, a PIM-based data-intensive architecture
9. The performance impact of flexibility in the stanford FLASH multiprocessor
10. Active memory clusters: Efficient multiprocessing on commodity clusters
11. FlexRAM: Toward an advanced intelligent memory system
12. Cache coherence in intelligent memory systems
13. The stanford FLASH multiprocessor
14. Memory sharing predictor: The key to a speculative coherent DSM
15. The SGI origin: A ccNUMA highly scalable server
16. Memory forwarding: Enabling aggressive layout optimizations by guaranteeing the safety of data relocation
17. A case for asynchronous active memories
18. Algorithmic foundation for a parallel vector access memory system
19. Using prediction to accelerate coherence protocols
20. High-throughput coherence controllers
21. The S3.mp scalable shared memory multiprocessor
22. Active pages: A computation model for intelligent memory
23. Missing the memory wall: The case for processor/memory integration
24. The predictability of data values
25. Design of the 21174 memory controller for DIGITAL personal workstations
26. Adaptatively mapping code in an intelligent memory architecture
27. Toward a cost-effective DSM organization that exploits processor-memory integration
28. The SPLASH-2 programs: Characterization and methodological considerations
29. Memory system support for dynamic cacheline assembly
30. Pointer-based prefetching within the impulse adaptable memory controller: Initial results