完整後設資料紀錄
DC 欄位語言
dc.contributor.authorHsu, Chun-Chenen_US
dc.contributor.authorLiu, Pangfengen_US
dc.contributor.authorWu, Jan-Janen_US
dc.contributor.authorYew, Pen-Chungen_US
dc.contributor.authorHong, Ding-Yongen_US
dc.contributor.authorHsu, Wei-Chungen_US
dc.contributor.authorWang, Chien-Minen_US
dc.date.accessioned2014-12-08T15:32:35Z-
dc.date.available2014-12-08T15:32:35Z-
dc.date.issued2013-07-01en_US
dc.identifier.issn0362-1340en_US
dc.identifier.urihttp://dx.doi.org/10.1145/2517326.2451519en_US
dc.identifier.urihttp://hdl.handle.net/11536/22804-
dc.description.abstractMost dynamic binary translators (DBT) and optimizers (DBO) target binary traces, i.e. frequently executed paths, as code regions to be translated and optimized. Code region formation is the most important first step in all DBTs and DBOs. The quality of the dynamically formed code regions determines the extent and the types of optimization opportunities that can be exposed to DBTs and DBOs, and thus, determines the ultimate quality of the final optimized code. The Next-Executing-Tail (NET) trace formation method used in HP Dynamo is an early example of such techniques. Many existing trace formation schemes are variants of NET. They work very well for most binary traces, but they also suffer a major problem: the formed traces may contain a large number of early exits that could be branched out during the execution. If this happens frequently, the program execution will spend more time in the slow binary interpreter or in the unoptimized code regions than in the optimized traces in code cache. The benefit of the trace optimization is thus lost. Traces/regions with frequently taken early-exits are called delinquent traces/regions. Our empirical study shows that at least 8 of the 12 SPEC CPU2006 integer benchmarks have delinquent traces. In this paper, we propose a light-weight region formation technique called Early-Exit Guided Region Formation (EEG) to improve the quality of the formed traces/regions. It iteratively identifies and merges delinquent regions into larger code regions. We have implemented our EEG algorithm in two LLVM-based multi-threaded DBTs targeting ARM and IA32 instruction set architecture (ISA), respectively. Using SPEC CPU2006 benchmark suite with reference inputs, our results show that compared to an NET-variant currently used in QEMU, a state-of-the-art retargetable DBT, EEG can achieve a significant performance improvement of up to 72% (27% on average), and to 49% (23% on average) for IA32 and ARM, respectively.en_US
dc.language.isoen_USen_US
dc.subjectDesignen_US
dc.subjectPerformanceen_US
dc.subjectDynamic Binary Translationen_US
dc.subjectTrace-Based JIT Compilationen_US
dc.subjectVirtual Machineen_US
dc.subjectHardware-based Performance Monitoringen_US
dc.subjectHot Region Formationen_US
dc.titleImproving Dynamic Binary Optimization Through Early-Exit Guided Code Region Formationen_US
dc.typeArticleen_US
dc.identifier.doi10.1145/2517326.2451519en_US
dc.identifier.journalACM SIGPLAN NOTICESen_US
dc.citation.volume48en_US
dc.citation.issue7en_US
dc.citation.spage23en_US
dc.citation.epage32en_US
dc.contributor.department交大名義發表zh_TW
dc.contributor.departmentNational Chiao Tung Universityen_US
dc.identifier.wosnumberWOS:000324470900003-
dc.citation.woscount0-
顯示於類別:期刊論文


文件中的檔案:

  1. 000324470900003.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。