Parallel virtualized memory translation with nested elastic cuckoo page tables

Parallel virtualized memory translation with nested elastic cuckoo page tables
复制标题

使用嵌套弹性布谷鸟页表进行并行虚拟化内存转换

DOI:
10.1145/3503222.3507720
复制
发表时间:
2022
期刊:
Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
影响因子:
--
通讯作者:
Torrellas, Josep
Torrellas, Josep
中科院分区:
--
文献类型:
--
作者:
Stojkovic, Jovan;Skarlatos, Dimitrios;Kokolis, Apostolos;Xu, Tianyin;Torrellas, Josep

文献摘要

参考文献

被引文献

相似文献

嵌套或虚拟化地址转换缓慢的主要原因是当前系统将页表组织在以顺序方式访问的多级树中。嵌套翻译可能需要多达二十四次连续存储器访问。为了解决这个问题,本文提出了第一个支持并行嵌套地址转换的页表设计。该设计基于对来宾和主机使用散列页表 (HPT)。然而,直接将本机 HPT 设计扩展到嵌套环境会带来较小的收益。相反,我们的设计解决了嵌套环境中出现的一系列新挑战。我们的方案消除了嵌套转换的潜在二十四个连续步骤中的所有步骤,只保留了三​​个步骤,同时明智地限制发出的并行内存访问的数量,以避免过度消耗缓存带宽。因此,与传统的嵌套基数表相比,我们的设计将一组应用程序的执行速度平均提高了 1.19 倍(对于 4KB 页)和 1.24 倍(使用大页时)。此外,我们还展示了从当前嵌套基数页表到我们的设计的迁移路径。
A major reason why nested or virtualized address translations are slow is because current systems organize page tables in a multi-level tree that is accessed in a sequential manner. A nested translation may potentially require up to twenty-four sequential memory accesses. To address this problem, this paper presents the first page table design that supportsparallelnested address translation. The design is based on using hashed page tables (HPTs) for both guest and host. However, directly extending a native HPT design to a nested environment leads to minor gains. Instead, our design solves a new set of challenges that appear in nested environments. Our scheme eliminates all but three of the potentially twenty-four sequential steps of a nested translation—while judiciously limiting the number of parallel memory accesses issued to avoid over-consuming cache bandwidth. As a result, compared to conventional nested radix tables, our design speeds-up the execution of a set of applications by an average of 1.19x (for 4KB pages) and 1.24x (when huge pages are used). In addition, we also show a migration path from current nested radix page tables to our design.
Linux / ia 64 项目:内核设计和状态更新
DOI: --
发表时间: 2000
期刊:
影响因子: --
作者:
S. Eranian;D. Mosberger
通讯作者: D. Mosberger
DOI: 10.1109/micro50266.2020.00023
发表时间: 2020-10
期刊: 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)
影响因子: --
作者:
Samira Mirbagher Ajorpaz;Elba Garza;Gilles A. Pokam;Daniel A. Jiménez
通讯作者: Samira Mirbagher Ajorpaz;Elba Garza;Gilles A. Pokam;Daniel A. Jiménez
IBM POWER9系统软件
DOI: --
发表时间: 2018
影响因子: 1.3
作者:
Joefon Jann;P. Mackerras;J. Ludden;M. Gschwind;Wade Ouren;S. Jacobs;B. F. Veale;D. Edelsohn
通讯作者: D. Edelsohn
Powerpc 微处理器系列:编程环境
DOI: --
发表时间: 1994
期刊:
影响因子: --
作者:
A. Cozzolino
通讯作者: A. Cozzolino
坚持 TLB 预取:一项应用程序驱动的研究
DOI: 10.1109/isca.2002.1003578
发表时间: 2002
期刊: Proceedings 29th Annual International Symposium on Computer Architecture
影响因子: --
作者:
G. Kandiraju;A. Sivasubramaniam
通讯作者: A. Sivasubramaniam