Filters








23 Hits in 2.7 sec

The Impulse memory controller

Lixin Zhang, Zhen Fang, M. Parker, B.K. Mathew, L. Schaelicke, J.B. Carter, W.C. Hsieh, S.A. McKee
2001 IEEE transactions on computers  
Alternatively, Impulse can be used by the OS for dynamic superpage creation; the best policy for creating superpages using Impulse outperforms previously known superpage creation policies.  ...  Applications can use this level of indirection to remap their data structures in memory.  ...  Using superpages makes more efficient use of a TLB, but the physical pages that back a superpage must be contiguous and properly aligned.  ... 
doi:10.1109/12.966490 fatcat:aorvqc2pm5erbotcexbgbpks4i

Architectural and Operating System Support for Virtual Memory

Abhishek Bhattacharjee, Daniel Lustig
2017 Synthesis Lectures on Computer Architecture  
Eight years ago, our advisor, Margaret Martonosi, started us down this research path. We thank her for her support in pursuing our research endeavors.  ...  Thank you also to Trey Cain, Derek Hower, Lisa Hsu, Aamer Jaleel, Yatin Manerkar, Michael Pellauer, and Caroline Trippel for the countless helpful discussions about virtual memory and memory system behavior  ...  IMPROVING TLB REACH We begin by discussing hardware approaches to improve TLB reach. By TLB reach, we mean the effective capacity that a TLB offers.  ... 
doi:10.2200/s00795ed1v01y201708cac042 fatcat:4re5afn53jhu7ezxwtb25ja3ca

The Synonym Lookaside Buffer: A Solution to the Synonym Problem in Virtual Caches

Xiaogang Qiu, M. Dubois
2008 IEEE transactions on computers  
The major idea is the replacement of the on-chip TLB by a synonym lookaside buffer (SLB).  ...  This paper introduces new ideas to enable the use of virtual addresses in the cache hierarchy, thus removing the TLB from the critical path of the processor core.  ...  Impulse [28] attempts to increase TLB coverage by backing up superpages with shadow physical memory.  ... 
doi:10.1109/tc.2008.108 fatcat:c6lyqm76njblhbqtukzfmsmtfq

Architectural support for shadow memory in multiprocessors

Vijay Nagarajan, Rajiv Gupta
2009 Proceedings of the 2009 ACM SIGPLAN/SIGOPS international conference on Virtual execution environments - VEE '09  
by the application and associated shadow memory pages) is proposed.  ...  By coupling the coherency of shadow memory with the coherency of the main memory, we ensure that the shadow memory instructions execute atomically with their corresponding original memory instructions.  ...  We would like to thank the anonymous reviewers for providing useful comments to improve the paper.  ... 
doi:10.1145/1508293.1508295 dblp:conf/vee/NagarajanG09 fatcat:zangprimynfpxkubvvmebqutyu

A Survey of Non-Volatile Main Memory Technologies: State-of-the-Arts, Practices, and Future Directions [article]

Haikun Liu, Di Chen, Hai Jin, Xiaofei Liao, Bingsheng He, Kan Hu, Yu Zhang
2020 arXiv   pre-print
Non-Volatile Main Memories (NVMMs) have recently emerged as promising technologies for future memory systems.  ...  NVMMs have become a competitive alternative of Dynamic Random Access Memory (DRAM), and will fundamentally change the landscape of memory systems.  ...  Acknowledgments This work is supported jointly by National Natural  ... 
arXiv:2010.04406v1 fatcat:jna5pb7lizhvllmhfle4yikife

Runtime monitoring on multicores via OASES

Vijay Nagarajan, Rajiv Gupta
2009 ACM SIGOPS Operating Systems Review  
A combination of operating system support (in the form of coupled allocation of memory pages used by the application and associated shadow memory pages) and architectural support (in the form of ISA support  ...  By exposing the cache events to the software, we ensure in software that the shadow memory instructions execute atomically with their corresponding original memory instructions.  ...  We also thank the reviewers for providing useful comments to improve the paper.  ... 
doi:10.1145/1531793.1531798 fatcat:5zm45ahumjcuff3ka435mvv3fi

A First Look at RISC-V Virtualization from an Embedded Systems Perspective [article]

Bruno Sá, José Martins, Sandro Pinto
2021 arXiv   pre-print
Our hardware implementation was opensourced and is currently in use by the RISC-V community towards the ratification of the H-extension specification.  ...  This work has also been supported by FCT within the PhD Scholarship Project Scope: SFRH/BD/138660/2018.  ...  ACKNOWLEDGMENT This work has been supported by FCT -Fundac ¸ão para a Ciência e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020.  ... 
arXiv:2103.14951v2 fatcat:ib52qw4swvaidffp6a7llb5slu

A lifetime optimal algorithm for speculative PRE

Jingling Xue, Qiong Cai
2006 ACM Transactions on Architecture and Code Optimization (TACO)  
Each of both benefits has contributed to the performance improvements in benchmark programs at the costs of only small compile-time and code-size increases in some benchmarks.  ...  This work is partially supported by an ARC grant DP0452623.  ...  Effects of TLB. While it is hard to increase cache sizes to reduce cache misses, some systems use superpages to increase the effective TLB reach without increasing TLB size.  ... 
doi:10.1145/1138035.1138036 fatcat:6jxnqgxw6vbzpoefpqlt56pacm

Reevaluating online superpage promotion with hardware support

Zhen Fang, Lixin Zhang, J.B. Carter, W.C. Hsieh, S.A. McKee
Proceedings HPCA Seventh International Symposium on High-Performance Computer Architecture  
This bottleneck can be mitigated by the use of superpages, multiple adjacent virtual memory pages that can be mapped with a single TLB entry, that extend TLB reach without significantly increasing size  ...  This study extends previous work by using execution-driven simulation to compare creating superpages via copying with remapping pages within the memory controller, and by examining how the tradeoffs change  ...  Using superpages makes more efficient use of a TLB, but the physical pages that back a superpage must be contiguous and properly This effort was sponsored in part by the Defense Advanced Research Projects  ... 
doi:10.1109/hpca.2001.903252 dblp:conf/hpca/FangZCHM01 fatcat:mmhbrkvzxzeabpuh22euwtqe7e

Simple DRAM and Virtual Memory Abstractions to Enable Highly Efficient Memory Systems [article]

Vivek Seshadri
2016 arXiv   pre-print
We show that this extension is powerful by demonstrating its benefits on a number of applications. Second, we show that DRAM can be used to perform more complex operations than just store data.  ...  For these access patterns, GS-DRAM achieves near-ideal bandwidth and cache utilization, without increasing the latency of fetching data from memory.  ...  The primary benefit of using superpages is to increase TLB reach and thereby reduce overall TLB misses. However, we observe that superpages are ineffective for reducing memory redundancy.  ... 
arXiv:1605.06483v1 fatcat:5pa4zmkbdzgulim2jsqjkry3pu

Xen and the art of virtualization

Paul Barham, Boris Dragovic, Keir Fraser, Steven Hand, Tim Harris, Alex Ho, Rolf Neugebauer
2003 Proceedings of the nineteenth ACM symposium on Operating systems principles - SOSP '03  
Numerous systems have been designed which use virtualization to subdivide the ample resources of a modern computer. Some require specialized hardware, or cannot support commodity operating systems.  ...  This is achieved by providing an idealized virtual machine abstraction to which operating systems such as Linux, BSD and Windows XP, can be ported with minimal effort.  ...  Acknowledgments This work is supported by ESPRC Grant GR/S01894/01 and by Microsoft. We would like to thank Evangelos Kotsovinos, Anil Madhavapeddy, Russ Ross and James Scott for their contributions.  ... 
doi:10.1145/945461.945462 fatcat:7hm3vlf3szhije46eqm6cl3iu4

Improving the reliability of commodity operating systems

Michael M. Swift, Brian N. Bershad, Henry M. Levy
2003 Proceedings of the nineteenth ACM symposium on Operating systems principles - SOSP '03  
Nooks also tracks a driver's use of kernel resources to facilitate automatic cleanup during recovery.  ...  We demonstrate this by isolating a kernel-mode file system and an in-kernel Internet service.  ...  This suggests that optimizations to reduce the number of TLB misses, such as superpages, may be important in future versions of the system.  ... 
doi:10.1145/945465.945466 fatcat:s3mtk5zegzhlph7smb4ti2httq

Improving the reliability of commodity operating systems

Michael M. Swift, Brian N. Bershad, Henry M. Levy
2003 Proceedings of the nineteenth ACM symposium on Operating systems principles - SOSP '03  
Nooks also tracks a driver's use of kernel resources to facilitate automatic cleanup during recovery.  ...  We demonstrate this by isolating a kernel-mode file system and an in-kernel Internet service.  ...  This suggests that optimizations to reduce the number of TLB misses, such as superpages, may be important in future versions of the system.  ... 
doi:10.1145/945445.945466 dblp:conf/sosp/SwiftBL03 fatcat:a6c2wwotb5crlf5q5jm25vdy6e

Improving the reliability of commodity operating systems

Michael M. Swift, Brian N. Bershad, Henry M. Levy
2003 ACM SIGOPS Operating Systems Review  
Nooks also tracks a driver's use of kernel resources to facilitate automatic cleanup during recovery.  ...  We demonstrate this by isolating a kernel-mode file system and an in-kernel Internet service.  ...  This suggests that optimizations to reduce the number of TLB misses, such as superpages, may be important in future versions of the system.  ... 
doi:10.1145/1165389.945466 fatcat:6leoyuwd2bd2dgebv46zigis5a

Improving the reliability of commodity operating systems

Michael M. Swift, Brian N. Bershad, Henry M. Levy
2005 ACM Transactions on Computer Systems  
Nooks also tracks a driver's use of kernel resources to facilitate automatic cleanup during recovery.  ...  We demonstrate this by isolating a kernel-mode file system and an in-kernel Internet service.  ...  This suggests that optimizations to reduce the number of TLB misses, such as superpages, may be important in future versions of the system.  ... 
doi:10.1145/1047915.1047919 fatcat:lqb4fziluvhkjdvtdhhl75u66a
« Previous Showing results 1 — 15 out of 23 results