EE464 Senior Design Project - Design and Measurement of Low-Power Software on DSPs

Portable computing demands minimizing power dissipation due to a limited power supply and a cooling mechanism. Lowering supply voltage and minimizing hardware area are used for low power hardware. Changing instruction order and reducing the number of operations are used for low-power software. One of recent low-power software method is data wordlength reduction. Data wordlength reduction methods reduce the power consumption while not changing any hardware. The reduction methods can adaptively change data wordlength according to demand of power minimization and robust computation.

The project would involve the design of the low-power software based on data wordlength reduction method and measurement of the software power consumption on digital signal processors. The senior project team would work closely with a graduate student who is conducting research in this area.

Related courses: EE 313, EE 345S

References:

• V. Tiwari, S. Malik, and A. Wolfe, "Power analysis of embedded software: A first step towards software power minimization," in Proc. IEEE Int. Conf. on Computer-Aided Design , San Jose, CA, Nov. 1994, pp. 429-435.
• M. T. Lee, V. Tiwari, S. Malik, and M. Fujita, "Power analysis and minimization techniques for embedded DSP software," IEEE Transactions on VLSI Systems, vol. 5, pp. 123-135, 1997.
• Behrooz Parhami, Computer Arithmetic algorithm and hardware designs, Oxford University Press, 2000.

Graduate Student Contact: Mr. Kyungtae Han (khan@ece.utexas.edu)

Faculty Contact: Prof. Brian L. Evans (bevans@ece.utexas.edu)