Automatic self-allocating threads (ASAT) on an SGI Challenge

Automatic self allocating threads (ASAT) is proposed as a way to balance the number of active threads across a shared-memory multiprocessing system. Our approach is significant in that it is designed for a system running multiple jobs, and it considers the load of all running jobs in its thread allocation. In addition, the overhead of ASAT is sufficiently small so that the run times of all jobs improve when it is in use. We consider the application of ASAT for improving the scheduling of threads on an SGI Challenge. We demonstrate how the number of threads of an ASAT job adjusts to the overall system load to maintain thread balance and improve system throughput.