ACM Home Page
Please provide us with feedback. Feedback
Cycle-approximate retargetable performance estimation at the transaction level
Full text PdfPdf (610 KB)
Source Design, Automation, and Test in Europe archive
Proceedings of the conference on Design, automation and test in Europe table of contents
Munich, Germany
SESSION: Transaction-level modelling (TLM) table of contents
Pages 3-8  
Year of Publication: 2008
ISBN:978-3-9810801-3-1
Authors
Yonghyun Hwang  University of California, Irvine
Samar Abdi  University of California, Irvine
Daniel Gajski  University of California, Irvine
Sponsors
: IEEE Council on Electronic Design Automation (CEDA)
EDAA : European Design Automation Association
: The EDA Consortium
SIGDA: ACM Special Interest Group on Design Automation
RAS : RAS
: The IEEE Computer Society TTTC
: ECSI
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 17,   Downloads (12 Months): 98,   Citation Count: 4
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1403375.1403380
What is a DOI?

ABSTRACT

This paper presents a novel cycle-approximate performance estimation technique for automatically generated transaction level models (TLMs) for heterogeneous multi-core designs. The inputs are application C processes and their mapping to processing units in the platform. The processing unit model consists of pipelined datapath, memory hierarchy and branch delay model. Using the processing unit model, the basic blocks in the C processes are analyzed and annotated with estimated delays. This is followed by a code generation phase where delay-annotated C code is generated and linked with a SystemC wrapper consisting of inter-process communication channels. The generated TLM is compiled and executed natively on the host machine. Our key contribution is that the estimation technique is close to cycle-accurate, it can be applied to any multi-core platform and it produces high-speed native compiled TLMs. For experiments, timed TLMs for industrial scale designs such as MP3 decoder were automatically generated for 4 heterogeneous multi-processor platforms with up to 5 PEs under 1 minute. Each TLM simulated under 1 second, compared to 3--4 hrs of instruction set simulation (ISS) and 15--18 hrs of RTL simulation. Comparison to on-board measurement showed only 8% error on average in estimated number of cycles.


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
2
3
4
 
5
M.-K. Chung, S. Na, and C.-M. Kyung. System-Level Performance Analysis of Embedded System using Behavioral C/C++ model. In VLSI-TSA-DAT, Hsinchu, Taiwan, April 2005.
 
6
ESE: Embedded Systems Environment. "http://www.cecs.uci.edu/ese".
 
7
FastVeri (SystemC-based High-Speed Simulator) Product. "http://www.interdesigntech.co.jp/english/fastveri/".
 
8
9
10
 
11
LLVM(Low Level Virtual Machine) Compiler Infrastructure Project. "http://www.llvm.org".
12
 
13
VaST: Virtual System Prototype Technologies. "http://www.vastsystems.com/solutions-architecture-systems.html".
 
14
Xilinx. Embedded System Tools Reference Manual. 2005.
 
15
Xilinx. MicroBlaze Processor Reference Manual. 2007.
 
16
L. Yu, S. Abdi, and D. Gajski. Transaction level platform modeling in systemc for multi-processor designs. Technical Report CECS-TR-07-01, January 2007.


Collaborative Colleagues:
Yonghyun Hwang: colleagues
Samar Abdi: colleagues
Daniel Gajski: colleagues