Integrated scheduling and register assignment for VLIW-DSP architectures
Authors:
- B. WessBWB. Wess
- 13 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 339-343
Abstract
This paper describes code generation techniques for VLIW-DSP architectures. We focus on architectures with heterogeneous functional units and heterogeneous register sets. When generating code, scheduling and register allocation/assignment are typically done in separate steps. This is due to the fact that these tasks are complex combinatorial optimization problems particularly in case of irregular data-paths. However, these phases are strongly interdependent and therefore traditional approaches are often suboptimal. This paper proposes a new technique to integrate scheduling and register assignment. Our approach ensures that only schedules are produced for which a register assignment is guaranteed to exist. This is achieved by mapping the register set of the architecture onto a set of virtual resources. The concept of virtual resources provides a powerful methodology to easily check whether a register assignment for a specific schedule exists without the necessity to generate one. This allows to apply any schedule generation or optimization strategy and register assignment to be done only for the optimized final schedule for which a solution is known to exist.Keywords
This publication has 9 references indexed in Scilit:
- Constraint analysis for code generationACM Transactions on Design Automation of Electronic Systems, 2000
- Code generation of nested loops for DSP processors with heterogeneous registers and structural pipeliningACM Transactions on Design Automation of Electronic Systems, 1999
- Operation scheduling for parallel functional units using genetic algorithms1999
- Improvements to graph coloring register allocationACM Transactions on Programming Languages and Systems, 1994
- Register allocation with instruction scheduling1993
- Register allocation via hierarchical graph coloring1991
- Register allocation by priority-based coloringACM SIGPLAN Notices, 1984
- Register allocation & spilling via graph coloringACM SIGPLAN Notices, 1982
- Local Microcode Compaction TechniquesACM Computing Surveys, 1980