ON BALANCING SORTING ON A LINEAR-ARRAY

The processing rate of a parallel computing system is usually restricted by its slower I/O. An important measure to speed up the processing is to make the I/O time equal the computing time by employing local memories in the processors, thus achieving balanced computation. A balanced system makes neither the computation bandwidth, the I/O bandwidth, nor the memory size excessive. We present a balanced parallel algorithm to sort a sequence of items on a linear array of processors. The length of the sequence may be small to arbitrarily large. For a short sequence, the output of the sorted sequence begins at the step following the last input of the whole sequence. For an arbitrarily long sequence, the time complexity is optimal under realistic hardware conditions. A variation of the algorithm is also introduced. Both algorithms require far less local memory than that required by a different approach of balanced computation. Any number of balanced processors can be connected to deliver more computing power without increasing the memory size of each processor.