This paper presents a new approach for improving performance of instruction cache based systems. The idea is to prevent cache misses caused when different segments of code which are executed in the same loop are mapped onto the same cache area. The new approach uses static information only and does not rely on any special hardware mechanisms such as support… (More)
It is shown that an algebraic implementation of "LET" statements may be useful in producing comprehensible outputs. The suggested algorithm is based on solving large set of linear equations over a field.
An adaptive run time scheduling approach to parallel algebraic computation is suggested. Study of a toy example, the factorial function, illustrates the need for such an approach on an asynchronous multiprocessing system. The example is run in several parallelized variants on two distinct implementations of ALDES/SAC2 on a Sequent Symmetry computer.