Regression verification is an approach complementing regression testing with formal verification. The goal is to formally prove that two versions of a program behave either equally or differently in a precisely specif...
详细信息
Regression verification is an approach complementing regression testing with formal verification. The goal is to formally prove that two versions of a program behave either equally or differently in a precisely specified way. In this paper, we present a novel automated approach for regression verification that reduces the equivalence of two related imperative pointer programs to constrained Horn clauses over uninterpreted predicates. Subsequently, state-of-the-art SMT solvers are used to solve the clauses. We have implemented the approach, and our experiments show that non-trivial programs with integer and pointer arithmetic can now be proved equivalent without further user input.
Existing pattern-based compiler technology is unable to effectively exploit the full potential of SIMD architectures. We present a new program synthesis based technique for auto-vectorizing performance critical innerm...
详细信息
Existing pattern-based compiler technology is unable to effectively exploit the full potential of SIMD architectures. We present a new program synthesis based technique for auto-vectorizing performance critical innermost loops. Our synthesis technique is applicable to a wide range of loops, consistently produces performant SIMD code, and generates correctness proofs for the output code. The synthesis technique, which leverages existing work on relationalverification methods, is a novel combination of deductive loop restructuring, synthesis condition generation and a new inductive synthesis algorithm for producing loop-free code fragments. The inductive synthesis algorithm wraps an optimized depth-first exploration of code sequences inside a CEGIS loop. Our technique is able to quickly produce SIMD implementations (up to 9 instructions in 0.12 seconds) for a wide range of fundamental looping structures. The resulting SIMD implementations outperform the original loops by 2.0 x -3.7 x.
暂无评论