ACM Home Page
Please provide us with feedback. Feedback
Compiler-optimized usage of partitioned memories
Full text PdfPdf (412 KB)
Source ACM International Conference Proceeding Series; Vol. 68 archive
Proceedings of the 3rd workshop on Memory performance issues: in conjunction with the 31st international symposium on computer architecture table of contents
Munich, Germany
Pages: 114 - 120  
Year of Publication: 2004
ISBN:1-59593-040-X
Authors
Lars Wehmeyer  Univ. of Dortmund, Germany
Urs Helmig  Univ. of Dortmund, Germany
Peter Marwedel  Univ. of Dortmund, Germany
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 3,   Downloads (12 Months): 20,   Citation Count: 8
Additional Information:

abstract   references   cited by   collaborative colleagues  

Tools and Actions: Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1054943.1054959
What is a DOI?

ABSTRACT

In order to meet the requirements concerning both performance and energy consumption in embedded systems, new memory architectures are being introduced. Beside the well-known use of caches in the memory hierarchy, processor cores today also include small onchip memories called scratchpad memories whose usage is not controlled by hardware, but rather by the programmer or the compiler. Techniques for utilization of these scratchpads have been known for some time. Some new processors provide more than one scratchpad, making it necessary to enhance the workflow such that this complex memory architecture can be efficiently utilized. In this work, we present an energy model and an ILP formulation to optimally assign memory objects to different partitions of scratchpad memories at compile time, achieving energy savings of up to 22% compared to previous approaches.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
L. Eggermont. Embedded Systems Roadmap. Technical report, STW, http://www.stw.nl/progress/ESroadmap/index.html, 2002.
 
2
H. De Man. Keynote session at DATE'02. http://www.date-conference.com/conference/keynotes/index.htm, 2002.
 
3
P. Machanik. Approaches to Addressing the Memory Wall. Technical Report, November, Univ. Brisban, 2002.
 
4
S. Wilton and N. Jouppi. CACTI: An enhanced access and cycle time model. Int. Journal on Solid State Circuits, 31(5):677--688, 1996.
5
 
6
 
7
8
9
10
11
 
12
ARM Ltd. ARM7TDMI Technical Reference Manual, Ref: DDI0029G. Available from http://www.arm.com, 2001.
 
13
S. Steinke, M. Knauer, L. Wehmeyer, and P. Marwedel. An Accurate and Fine Grain Instruction-Level Energy Model Supporting Optimizations. In Proceedings of the International Workshop - Power and Timing Modeling, Optimization and Simulation, Yverdon-les-bains, Switzerland, September 2001.
 
14
Lars Wehmeyer, Stefan Steinke, encc Compiler. Information available from: http://ls12-www.cs.uni-dortmund.de/research/encc, 2004.
 
15
ARM Inc. ARM Documentation - ARM Processor Cores. Available from: http://www.arm.com/documentation/ARM Processor_Cores/index.html, 2004.
 
16
Oki. Oki Global Homepage, http://www.oki.com, 2004.
 
17
Samsung. Samsung's Digital World. http://www.samsung.com, 2004.
 
18
Atmel Corporation. Atmel Corporation Homepage. http://www.atmel.com, 2004.
 
19
ILOG. CPLEX. http://www.ilog.com/products/cplex.
 
20
Manish Verma, Stefan Steinke, and Peter Marwedel. Data Partitioning for Maximal Scratchpad Usage. In Proceedings of the Asia and South Pacific Design Automation Conference, page 77, January 2003.

CITED BY  8
Collaborative Colleagues:
Lars Wehmeyer: colleagues
Urs Helmig: colleagues
Peter Marwedel: colleagues