A fast algorithm for scheduling instructions with deadline constraints on RISC machines

Abstract

We present a fast algorithm for scheduling UET (Unit Execution Time) instructions with deadline constraints in a basic block on RISC machines with multiple processors. Unlike Palem and Simon's algorithm, our algorithm allows latency of 1/sub ij/=-1 which denotes that instruction v/sub j/ cannot be started before v/sub i/. The time complexity of our algorithm is O(ne+nd), where n is the number of instructions, e is the number of edges in the precedence graph and d is the maximum latency. Our algorithm is guaranteed to compute a feasible schedule whenever one exists in the following special cases: 1) Arbitrary precedence constraints, latencies in {0, 1} and one processor. In this special case, our algorithm improves the existing fastest algorithm from O(ne+e'log n) to O(min{ne, n/sup 2.376}/), where e' is the number of edges in the transitively closed precedence graph. 2) Arbitrary precedence constraints, latencies in {-1, 0} and two processors. In the special case where all latencies are 0, our algorithm degenerates to Garey and Johnson's two processor algorithm. 3) Special precedence constraints in the form of monotone interval graph, arbitrary latencies in {-1, 0, 1, /spl middot//spl middot//spl middot/, d} and multiple processors. 4) Special precedence constraints in the form of in-forest, equal latencies and multiple processors. In the above special cases, if no feasible schedule exists, our algorithm will compute a schedule with minimum lateness. Moreover, by setting all deadlines to a sufficiently large integer, our algorithm will compute a schedule with minimum length in all the above special cases and the special case of out-forest, equal latencies and multiple processors.