Definition
NUMA is the acronym for Non-Uniform Memory Access. A NUMA cache is a cache memory in which the access time is not uniform but depends on the position of the referred block inside the cache. Among NUMA caches, it possible to distinguish: (1) the NUCA (Non-Uniform Cache Access) architectures, in which the memory space is deeply sub-banked, and the access latency depends on which sub-bank is accessed; and (2) the shared and distributed cache of a tiled Chip Multiprocessor (CMP), in which the latency depends on which cache slice has to be accessed.
Discussion
Introduction
For the past decades, microprocessors’ overall performance has been improved thanks to the continuous reduction of transistor size obtained in silicon fabrication technology. This scaling contributed in both (1) allowing designers to put on a chip more and more transistors, and thus to implement on the same die more and more complex microarchitectures, up to...
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Bibliography
Matzke D (1997) Will physical scalability sabotage performance gains? IEEE Comput 30(9):37–39
Kim C, Burger D, Keckler SW (2003) Non uniform cache architectures for wire-delay dominated on-chip caches. IEEE Micro 23(6):99–107
Chisti Z, Powell MD, Vijaykumar TN (2003) Distance associativity for high-performance energy-efficient non-uniform cache architectures. Proc. 36th int. symp. on microarchitecture. San Diego, CA, pp 55–66
Huh J, Kim C, Shafi H, Zhang L, Bourger D, Keckler SW (2005) A NUCA substrate for flexible CMP cache sharing. Proc. of the 19th int. conf. on supercomputing. Cambridge, MA, pp 20–22
Beckmann BM, Wood DA (2003) Managing wire delay in large chip-multiprocessors caches. Proc. of 37th int. symp. on microarchitecture. San Diego, CA, pp 55–66
Foglia P, Mangano D, Prete CA (2005) A cache design for high performance embedded systems. J Embedded Comput 1(4): 587–598
Foglia P, Mangano D, Prete CA (2005) A NUCA model for embedded systems cache design. IEEE 2005 workshop on embedded systems for real-time multimedia (ESTIMEDIA). New York Metropolitan Area, USA, pp 41–46
Chisti Z, Powell MD, Vijaykumar TN (2005) Optimizing replication, communication, and capacity allocation in CMPs. Proc. of the 32nd int. symp. on computer architecture. Madison
Foglia P, Panicucci F, Prete CA, Solinas M (2009) An evaluation of behaviors of S-NUCA CMPs running scientific workload. Proc. of the 12th euromicro conference on digital system design (DSD). Patras, Greece, pp 26–33
Foglia P, Panicucci F, Prete CA, Solinas M (2009) Analysis of performance dependencies in NUCA-based CMP systems. Proc. of the 21st international symposium on computer architecture and high performance computing (SBAC-PAD), Sao Paulo
Hardavellas N, Ferdman M, Falsafi B, Ailamaki A (2009) Reactive NUCA: near-optimal block placement and replication in distributed caches. Proc. of the 36th international symposium on computer architecture (ISCA-09). Austin, pp 184–195
Merino J, Puente V, Prieto P, Gregorio JÁ (2008) SP-NUCA: a cost effective dynamic non-uniform cache architecture. ACM SIGARCH Computer Architecture News 36(2):64–71, New York
Hammoud M, Cho S, Melhem R (2009) ACM: an efficient approach for managing shared caches in chip multiprocessors. Proc. 4th int. conf. on high performance embedded architectures and compilers (HiPEAC-09). Paphos, Cyprus, pp 355–372
Bardine A, Foglia P, Gabrielli G, Prete CA (2007) Analysis of static and dynamic energy consumption in NUCA caches: initial results. Proc. of the MEDEA 2007 workshop. Brasov, Romania, pp 105–112
Bardine A, Comparetti M, Foglia P, Gabrielli G, Prete CA (2010) Way-adaptable D-Nuca caches. International Journals of High Performance Systems Architecture 2(3/4):215–228
Bartolini S, Foglia P, Prete CA, Solinas M (2010) Feedback driven restructuring of multi-threaded applications for NUCA cache performance in CMPs. 22nd international symposium on computer architecture and high performance computing. Petropolis, Brazil
Bardine A, Comparetti M, Foglia P, Gabrielli G, Prete CA (2009) Impact of on-chip network parameters on NUCA cache performance. IET Computers & Digital Techniques 3(5):501–512
Foglia P, Monni G, Prete CA, Solinas M (2010) Re-Nuca: boosting CMP performances through block replication. In: 13th EUROMICRO conference on digital system design, architectures, methods and tools (DSD2010), Lille, 1–3 Sep 2010. IEEE CS, Los Alamitos, pp 199–206. ISBN: 978-0-7695-4171-6
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
Bardine, A., Foglia, P., Prete, C.A., Solinas, M. (2011). NUMA Caches. In: Padua, D. (eds) Encyclopedia of Parallel Computing. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-09766-4_16
Download citation
DOI: https://doi.org/10.1007/978-0-387-09766-4_16
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-09765-7
Online ISBN: 978-0-387-09766-4
eBook Packages: Computer ScienceReference Module Computer Science and Engineering