Multithreading (computer architecture): Difference between revisions

Revision as of 18:17, 7 April 2007

Revision as of 18:22, 7 April 2007

Line 67:

For example:

# in cycleCycle i, it executes an instruction from thread A is issued

# in cycleCycle i+1, it executes an instruction from thread B is issued

# in cycleCycle i+2, it executes an instruction from thread C is issued

# andAnd so on for every cycle.

The purpose of this type of multithreading is to remove all data dependency stalls from the execution pipeline.

Conceptually, it is similiar to [[preemption (computing)|pre-exemptive]] multi-tasking used in operating systems. One can

make the analogy that the time-slice given to each active thread is one CPU cycle.

====Terminology====