Code reordering and speculation support for dynamic optimization systems

For dynamic optimization systems, success is limited by two difficult problems arising from instruction reordering. Following optimization within and across basic block boundaries, both the ordering of exceptions and the observed processor register contents at each exception point must be consistent with the original code. While compilers traditionally utilize global data-flow analysis to determine which registers require preservation, this analysis is often infeasible in dynamic optimization systems due to both strict time/space constraints and incomplete code discovery. This paper presents an approach called Precise Speculation that addresses these problems. The proposed mechanism is a component of our vision for Run-time Optimization ARchitecture, or ROAR, to support aggressive dynamic optimization of programs. It utilizes a hardware mechanism to automatically recover the precise register states when a deferred exception is reported, utilizing the original unoptimized code to perform all recovery. We observe that Precise Speculation enables a dynamic optimization system to achieve a large performance gain over aggressively optimized base code, while preserving precise exceptions. For an 8-issue EPIC processor, the dynamic optimizer achieves between 3.6% and 57% speedup over a full-strength optimizing compiler that employs profile-guided optimization.