Title :
Performance analysis of enhanced fine-grain multithreaded distributed-memory systems
Author_Institution :
Dept. of Comput. Sci., Memorial Univ. of Newfoundland, St. John´´s, Nfld., Canada
Abstract :
In fine-grain multithreading, the thread changes in each processor cycle, consecutive instructions are thus issued from different threads, and no data dependencies stall the pipeline. Enhanced fine-grain multithreading maintains a number of additional threads which are used to replace an active thread when it initiates a long-latency operation. Performance improvements due to enhanced multithreading are studied by analyzing a timed Petri net model of a fine-grain multithreaded architecture at the instruction execution level
Keywords :
Petri nets; discrete event simulation; distributed memory systems; multi-threading; performance evaluation; pipeline processing; active thread; consecutive instructions; fine-grain multithreaded architecture; fine-grain multithreaded distributed-memory systems; fine-grain multithreading; instruction execution level; long-latency operation; performance analysis; processor cycle; timed Petri net model; Analytical models; Computer science; Delay; Microprocessors; Multithreading; Performance analysis; Petri nets; Pipelines; Switches; Yarn;
Conference_Titel :
Systems, Man, and Cybernetics, 2001 IEEE International Conference on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-7087-2
DOI :
10.1109/ICSMC.2001.973067
