Interprocessor invocation on a NUMA multiprocessor. Technical report
On a distributed shared memory machine, the problem of minimizing accesses to remote memory modules is crucial for obtaining high performance. We describe an object-based, parallel programming system called OSMIUM to support experiments with mechanisms for performing invocations on remote objects. The mechanisms we have studied include: non-cached access to remote memory, data migration, and function-shipping using an interprocessor invocation protocol (IIP). Our analyses and experiments indicate that IIP competes well with the alternatives, especially when the structure of user programs requires synchronized access to data structures. While these results are obtained on a NUMA multiprocessor, they are also applicable to systems that use hardware cache coherency techniques.
- Research Organization:
- Rochester Univ., NY (USA). Dept. of Computer Science
- OSTI ID:
- 5971577
- Report Number(s):
- AD-A-228930/4/XAB; TR-356; CNN: N00014-82-K-0193; NSF-CDA88-22724
- Country of Publication:
- United States
- Language:
- English
Similar Records
Analysis of cache invalidation patterns in multiprocessors
Lockup-free caches in high-performance multiprocessors
Related Subjects
ARRAY PROCESSORS
ALGORITHMS
COMPUTERS
DATA-FLOW PROCESSING
DISTRIBUTED DATA PROCESSING
MIGRATION
PARALLEL PROCESSING
PROGRAMMING
PROGRESS REPORT
TASK SCHEDULING
DATA PROCESSING
DOCUMENT TYPES
MATHEMATICAL LOGIC
PROCESSING
990200* - Mathematics & Computers