If software is king for systems-on-silicon, what's new in compilers?

Abstract

While software is already a significant component in today's system-on-silicon, it is expected to greatly dominate future generations of systems-on-silicon that will contain several (possibly heterogeneous) programmable processors, as well as reconfigurable hardware blocks and large amounts of on-chip memory. In this context, one could argue that the problems for compiler designers haven't changed at all, since the basic issues all boil down to the traditional challenges of: 1) coarse-grain parallelism extraction for the multiple processors on chip, 2) instruction level parallelism exploitation for individual processors, and 3) retargetable code generation for versions of the on-chip processors. This paper summarizes the positions of the panelists who presented their views on the new challenges in compilers for future systems-on-silicon, and who debated these issues at ICCD '97.