Active messages
Thorsten von Eicken, David Culler, Seth Copen Goldstein et al. · Proceedings - International Symposium on Computer Architecture/Proceedings · 1992
The design challenge for large-scale multiprocessors is (1) to minimize communication overhead, (2) allow communication to overlap computation, and (3) coordinate the two without sacrificing processor cost/performance. We show that existing message passing multiprocessors have unnecessarily high communication costs. Research prototypes of message driven machines demonstrate low communication overhead, but poor processor cost/performance. We introduce a simple communication mechanism, Active Messages, show that it is intrinsic to both architectures, allows cost effective use of the hardware, and offers tremendous flexibility. Implementations on nCUBE/2 and CM-5 are described and evaluated using a split-phase shared-memory extension to C, Split-C. We further show that active messages are sufficient to implement the dynamically scheduled languages for which message driven machines were designed. With this mechanism, latency tolerance becomes a programming/compiling concern. Hardware support for active messages is desirable and we outline a range of enhancements to mainstream processors.
Cited by 1,393 works. doi:10.1145/139669.140382
Authors
References
- Remote procedure call
- MULTILISP: a language for concurrent symbolic computation
- Performance of various computers using standard linear equations software
- Fine-grain parallelism with minimal hardware support: a compiler-controlled threaded abstract machine
- Lightweight remote procedure call
- The J-Machine: A Fine Grain Concurrent Computer
- Two fundamental issues in multiprocessing
- Architecture of a message-driven processor
- Implementation of a General-Purpose Dataflow Multiprocessor
- Monsoon