A schedule control program that is capable of allocating threads to CPUs so as to effectively use caches. When a thread is executed, the execution start time and the CPU number of a CPU that executes the thread are stored. When an interrupted thread is re-allocated to a CPU to execute it next, an elapsed time t counted from the execution start time is calculated. Time parameters are set to caches that are used by the CPUs in such a way that the higher the level of a cache, the larger time parameter is set. If the elapsed time t is smaller than a time parameter set to an n-level (where n is a natural number of 2 or greater) cache and is equal to or larger than a time parameter set to an (n-1)-level cache, the thread is allocated to a CPU with the lowest load among the CPUs sharing the n-level cache with the last execution CPU.