Compilers are crucial software tools that usually convert programs in high-level languages into machine code. A compiler provides hundreds of optimizations to improve the performance of the compiled code, which are controlled by enabled or disabled optimization flags. However, the vast number of combinations of these flags makes it extremely challenging to select the desired settings for compiler optimization flags (i.e., an optimization sequence) for a given target program. In the literature, many auto-tuning techniques have been proposed to select a desired optimization sequence via different strategies across the entire optimization space. However, due to the huge optimization space, these techniques commonly suffer from the widely-recognized efficiency problem. To address this problem, in this paper, we propose a preference-driven selection approach PDCAT, which reduces the search space of optimization sequences through the following three components. In particular, PDCAT first identifies combined optimizations based on compiler documentation to exclude the optimization sequences violating the combined constraints, and then categorizes the optimizations into a common optimization set (whose optimization flags are fixed) and an exploration set containing the remaining optimizations. Finally, within the search process, PDCAT assigns distinct enable probabilities to the explored optimization flags and finally selects a desired optimization sequence. The former two components reduce the search space by removing invalid optimization sequences and fixing some optimization flags, whereas the latter performs a biased search in the search space. To evaluate the performance of the proposed approach PDCAT, we conduct an extensive experimental study on the latest version of the compiler GCC with two widely used benchmarks cBench and PolyBench. The results show that PDCAT significantly outperforms the four compared techniques, including the state-of-art technique SRTuner. Moreover, each component of PDCAT not only contributes to its performance but also improves the acceleration performance of compared techniques.
Wed 25 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
11:00 - 12:30 | CompilerResearch Papers / Journal First / Ideas, Visions and Reflections at Cosmos 3C Chair(s): Na Meng Virginia Tech | ||
11:00 20mTalk | De-duplicating Silent Compiler Bugs via Deep Semantic Representation Research Papers Junjie Chen Tianjin University, Xingyu Fan Tianjin University, Chen Yang Tianjin University, Shuang Liu Renmin University of China, Jun Sun Singapore Management University DOI | ||
11:20 20mTalk | DiSCo: Towards Decompiling EVM Bytecode to Source Code using Large Language Models Research Papers Xing Su National Key Lab for Novel Software Technology, Nanjing University, China, Hanzhong Liang National Key Lab for Novel Software Technology, Nanjing University, China, Hao Wu , Ben Niu State Key Laboratory of Information Security, Institute of Information Engineering, China, Fengyuan Xu National Key Lab for Novel Software Technology, Nanjing University, China, Sheng Zhong National Key Lab for Novel Software Technology, Nanjing University, China DOI | ||
11:40 20mTalk | Compiler Autotuning through Multiple Phase Learning Journal First | ||
12:00 20mTalk | PDCAT: Preference-Driven Compiler Auto-Tuning Research Papers Mingxuan Zhu Peking University, Zeyu Sun Institute of Software, Chinese Academy of Sciences, Dan Hao Peking University DOI | ||
12:20 10mTalk | Compiler Optimization Testing Based on Optimization-Guided Equivalence Transformations Ideas, Visions and Reflections Jingwen Wu Shandong University, Jiajing Zheng Shandong University, Zhenyu Yang Shandong University, Zhongxing Yu Shandong University |
Cosmos 3C is the third room in the Cosmos 3 wing.
When facing the main Cosmos Hall, access to the Cosmos 3 wing is on the left, close to the stairs. The area is accessed through a large door with the number “3”, which will stay open during the event.