基于软硬件协同设计的解释器指令分派方法 |
| |
引用本文: | 傅杰,靳国杰,章隆兵,王剑.基于软硬件协同设计的解释器指令分派方法[J].高技术通讯,2016(3):226-234. |
| |
作者姓名: | 傅杰 靳国杰 章隆兵 王剑 |
| |
作者单位: | 1. 中国科学院大学 北京100049; 计算机系统结构国家重点实验室 北京100190; 中国科学院计算技术研究所 北京100190;2. 龙芯中科技术有限公司 北京100095;3. 计算机系统结构国家重点实验室 北京100190; 中国科学院计算技术研究所 北京100190 |
| |
基金项目: | 国家“核高基”科技重大专项课题(2009ZX01028-002-003,2009ZX01029-001-003,2010ZX01036-001-002,2012ZX01029-001-002-002,2014ZX01020201,2014ZX01030101),国家自然科学基金(61221062,61133004,61173001,6123009,61222204,61432016),863计划(2012AA010901,2013AA014301)资助项目。 |
| |
摘 要: | 为了降低指令分派造成的运行开销以提高解释器的性能,提出了一种采用软硬件协同设计的解释器指令分派方法。其核心思想是在软件层面通过对指令分派表进行优化以消除了代价较高的地址常量加载操作,在硬件层面通过扩展处理器的访存指令进一步实现基于硬件支持的访存加速。软硬件协同设计可以最大限度地降低由指令分派引入的运行时开销,从而提升解释执行的效率。试验结果表明,该方法能够显著提升解释器的性能。对于SPECjvm98和Da Capo测试集,解释器总体性能提升了11.5%,且单项性能的最大提升幅度高达15.4%。该方法通用性强,实现代价低,适用于现代主流处理器平台上高性能解释器的设计和优化。
|
关 键 词: | 解释器 指令分派 软硬件协同设计 虚拟机 优化 |
An instruction dispatch approach using hardware-software co-design for interpreters |
| |
Abstract: | To reduce the overhead caused by instruction dispatch to improve the performance of interpreters , an instruc-tion dispatch approach based on hardware and software co-design is proposed .Its main idea is to eliminate the ex-pensive operation of constant address loading by optimizing the instruction dispatch table in the aspect of sofware , and to acceleratethe speed of memory access under the support of hardware by enhancing the processor ’ s instruction set in the aspect of hardware .The hardware-software co-design can minimize the runtime overhead of instruction dispatch , thus improving the performance of interpreters .The experimental results showed that the proposed ap-proach significantly improved the performance of interpreters .For benchmarks of SPECjvm 98 and DaCapo , the overall performance of interpreters was improved by 11.5%, and the highest performance boost was up to 15.4%. The approach is highly versatile , easy to implement and can be applied to the design and implementation of high performance interpreters on mainstream processors . |
| |
Keywords: | interpreter instruction dispatch hardware and software co-design virtual machine optimization |
本文献已被 CNKI 万方数据 等数据库收录! |
|