A Low-Cost and High-Performance Embedded System Architecture and an Evaluation Methodology

A reduced interface and high performance embedded system architecture (MSBUS) is proposed in this paper. The control bus is low-cost and low-power, whereas the data bus is high-bandwidth and high-speed especially. In addition, a Universal Verification Methodology (UVM)-based performance evaluation methodology is proposed to estimate the hardware structures. In order to evaluate the bus performance, AHB, AXI and MSBUS DMA are implemented as a case study. The experimental results show that MSBUS DMA uses the least hardware resources, reduces energy consumption to a half of AHB and AXI in the block transfer mode, and achieves 3.3 times and 1.6 times valid bandwidth of AHB and AXI respectively. Moreover, the proposed evaluation methodology is effectively used with sufficient accuracy.

[1]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[2]  Hyuk-Jae Lee,et al.  Wire Optimization for Multimedia SoC and SiP Designs , 2008, IEEE Transactions on Circuits and Systems I: Regular Papers.

[3]  Soo-Ik Chae,et al.  Constrained-random bitstream generation for H.264/AVC decoder conformance test , 2010, IEEE Transactions on Consumer Electronics.

[4]  Jing Cao,et al.  A Markov Performance Model for Buffered Protocol Design , 2011, 2011 IEEE Computer Society Annual Symposium on VLSI.

[5]  Kyoung-Rok Cho,et al.  Modeling and analysis of the system bus latency on the SoC platform , 2006, SLIP '06.

[6]  Younghyun Kim,et al.  System-level power estimation using an on-chip bus performance monitoring unit , 2008, ICCAD 2008.

[7]  Dimitrios Soudris,et al.  FILESPPA: Fast Instruction Level Embedded System Power and Performance Analyzer , 2011, Microprocess. Microsystems.

[8]  José L. Núñez-Yáñez,et al.  Enabling accurate modeling of power and energy consumption in an ARM-based System-on-Chip , 2013, Microprocess. Microsystems.

[9]  Jihong Kim,et al.  Broadcast filtering: Snoop energy reduction in shared bus-based low-power MPSoCs , 2009, J. Syst. Archit..

[10]  Eduard Cerny,et al.  Verification Methodology Manual for SystemVerilog , 2005 .

[11]  Sandeep K. Shukla,et al.  High Level Power Estimation Models for FPGAs , 2011, 2011 IEEE Computer Society Annual Symposium on VLSI.

[12]  Fernando Gehm Moraes,et al.  NoC Power Estimation at the RTL Abstraction Level , 2008, 2008 IEEE Computer Society Annual Symposium on VLSI.

[13]  Naehyuck Chang,et al.  System-Level Online Power Estimation Using an On-Chip Bus Performance Monitoring Unit , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[14]  Wei Song,et al.  Real-energy: A new framework and a case study to evaluate power-aware real-time scheduling algorithms , 2010, 2010 ACM/IEEE International Symposium on Low-Power Electronics and Design (ISLPED).

[15]  Harry D. Foster,et al.  Assertion-Based Design , 2010 .

[16]  Vineet Sahula,et al.  Stochastic Automata Network Based Approach for Performance Evaluation of Network-on-Chip Communication Architecture , 2010, 2010 IEEE Computer Society Annual Symposium on VLSI.