Optimizing compilers rely on peephole optimizations to simplify combinations of instructions and remove redundant instructions. Typically, a new peephole optimization is added when a compiler developer notices an optimization opportunity---a collection of dependent instructions that can be improved---and manually derives a more general rewrite rule that optimizes not only the original code, but also other, similar collections of instructions. In this paper, we present Hydra, a tool that automates the process of generalizing peephole optimizations using a collection of techniques centered on program synthesis. One of the most important problems we have solved is finding a version of each optimization that is independent of the bitwidths of the optimization's inputs (when this version exists). We show that Hydra can generalize 75% of the ungeneralized missed peephole optimizations that LLVM developers have posted to the LLVM project's issue tracker. All of Hydra's generalized peephole optimizations have been formally verified, and furthermore we can automatically turn them into C++ code that is suitable for inclusion in an LLVM pass.

Superoptimization is a compilation strategy that uses search to improve code quality, rather than relying on a canned sequence of transformations, as traditional optimizing compilers do. This search can be seen as a program synthesis problem: from unoptimized code serving as a specification, the synthesis procedure attempts to create a more efficient implementation. An important family of synthesis algorithms works by enumerating candidates and then successively checking if each refines the specification, using an SMT solver. The contribution of this paper is a pruning technique which reduces the enumerative search space using fast dataflow-based techniques to discard synthesis candidates that contain symbolic constants and uninstantiated instructions. We demonstrate the effectiveness of this technique by improving the runtime of an enumerative synthesis procedure in the Souper superoptimizer for the LLVM intermediate representation. The techniques presented in this paper eliminate 65% of the solver calls made by Souper, making it 2.32x faster (14.54 hours vs 33.76 hours baseline, on a large multicore) at solving all 269,113 synthesis problems that Souper encounters when optimizing the C and C++ programs from SPEC CPU 2017.