Microthread

Microthreads are functions that may run in <a href="/facts/Parallel_computing/nQzcpzQt">parallel</a> to gain increased performance in <a href="/facts/Microprocessor/Fx9CaQht">microprocessors</a>. They provide an execution model that uses a few additional <a href="/facts/CPU_instructions/bgdQ1Fxf">instructions</a> in a conventional processor to break code down into fragments that execute simultaneously. Dependencies are managed by making <a href="/facts/Processor_registers/32RvbUdz">registers</a> in the microprocessors executing the code synchronising, so one microthread will wait for another to produce data. 
This is a form of <a href="/facts/Dataflow/jea04eH2">dataflow</a>. This model can be applied to an existing <a href="/facts/Instruction_set_architecture/8p8vwUeE">instruction set architecture</a> incrementally by providing just five new instructions to implement concurrency controls. A set of microthreads is a static partition of a basic block into <a href="/facts/Concurrent_processing/Q4acPNMv">concurrently</a> executing fragments, which execute on a single processor and share a microcontext. An iterator over a set provides a dynamic and <a href="/facts/Parametric_family/YoEWw0I8">parametric family</a> of microthreads. Iterators capture loop concurrency and can be scheduled to different processors. An iterator over a set is created dynamically and is called a family of microthreads. This is the mechanism that allows the model to generate concurrency, which can be run on multiple processors or functional units.

Microthread open-in-new

Microthread