Stochastic program optimization
Stochastic program optimization
复制标题
随机程序优化
DOI：
10.1145/2863701
复制
发表时间：
2016
影响因子：
22.7
通讯作者：
A. Aiken
中科院分区：
文献类型：
--
作者：
Eric Schkufza;Rahul Sharma;A. Aiken
在高性能计算中，对无环，固定点组件代码序列的简短序列的优化是一个重要的问题。但是，转型正确性和绩效提高的竞争限制通常会迫使特殊目的编译器产生次优码。我们表明，通过将这些约束作为成本函数中的术语编码，并使用马尔可夫链蒙特卡洛采样器快速探索所有可能的代码序列的空间，我们能够生成给定目标代码序列的积极优化版本。从11VM -O0编制的二进制文件开始，我们能够生成可证明的正确的代码序列，这些序列匹配或胜过QCC -O3，ICC -O3产生的代码，在某些情况下，专家手写组件。
The optimization of short sequences of loop-free, fixed-point assembly code sequences is an important problem in high-performance computing. However, the competing constraints of transformation correctness and performance improvement often force even special purpose compilers to produce sub-optimal code. We show that by encoding these constraints as terms in a cost function, and using a Markov Chain Monte Carlo sampler to rapidly explore the space of all possible code sequences, we are able to generate aggressively optimized versions of a given target code sequence. Beginning from binaries compiled by 11vm --O0, we are able to produce provably correct code sequences that either match or outperform the code produced by qcc --O3, icc --O3, and in some cases expert handwritten assembly.