MICROTASKING, MACROTASKING, AND AUTOTASKING FOR STRUCTURAL OPTIMIZATION

Various multitasking approaches are investigated for optimization of large space structures. Judicious combination of microtasking, macrotasking, and autotasking is explored with the goal of achieving a vectorized and multitasked algorithm for optimization of a large structure with maximum speedup performance. Speedup results are presented and compared for three space truss structures, with 526, 1,046, and 3,126 members. The processing time required for optimization of large structures increases exponentially with the size of the structure (number of design variables). Example 3 of this paper has 3,126 members and 2,226 displacement degrees of freedom. Development of efficient concurrent algorithms utilizing the unique architecture and capabilities of high-performance computers results in substantial reduction in the overall execution time.