arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.05076cs.PLcs.CY
收藏

字节码解释器的 CHERI 性能增强

CHERI Performance Enhancement for a Bytecode Interpreter

Duncan Lowther, Dejice Jacob, Jeremy Singer

AI总结:

本文探讨了将 MicroPython 字节码解释器移植到 Arm Morello 平台时的性能下降问题,通过修复隐式指针大小预设,将基准测试减速比从 5 倍降至 1.7 倍,显著提升了 CHERI 平台的执行效率。

摘要:

在将 MicroPython 字节码解释器移植到基于 CHERI 的 Arm Morello 平台期间,我们遇到了许多严重的性能下降问题。本文详细探讨了其中几个性能问题,针对每种情况,我们分析了问题原因、修复方法,以及在一组标准 Python 基准测试下解释器相应的性能提升。尽管我们认识到 Morello 是 CHERI 概念的原型物理实例,但我们表明,消除由于 CHERI capabilities(128 位)相对于原生指针(通常 64 位)尺寸更大而引发的某些软件诱导的运行时开销是可行的。在我们的案例中,相对于 AArch64 非 capability 执行,我们将几何平均基准测试的减速比从优化前的 5 倍降至优化后的 1.7 倍。最坏情况下的减速比得到显著改善,从优化前的 100 倍提升至优化后的 2 倍。关键洞察是,隐式指针大小预设遍布于系统代码中;以往 CHERI 移植项目强调指针大小假设引发的编译时和执行时错误,而我们则侧重于此类假设对性能的影响。

英文摘要:

During our port of the MicroPython bytecode interpreter to the CHERI-based Arm Morello platform, we encountered a number of serious performance degradations. This paper explores several of these performance issues in detail, in each case we characterize the cause of the problem, the fix, and the corresponding interpreter performance improvement over a set of standard Python benchmarks. While we recognize that Morello is a prototypical physical instantiation of the CHERI concept, we show that it is possible to eliminate certain kinds of software-induced runtime overhead that occur due to the larger size of CHERI capabilities (128 bits) relative to native pointers (generally 64 bits). In our case, we reduce a geometric mean benchmark slowdown from 5x (before optimization) to 1.7x (after optimization) relative to AArch64, non-capability, execution. The worst-case slowdowns are greatly improved, from 100x (before optimization) to 2x (after optimization). The key insight is that implicit pointer size presuppositions pervade systems code; whereas previous CHERI porting projects highlighted compile-time and execution-time errors exposed by pointer size assumptions, we instead focus on the performance implications of such assumptions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑