Profiling and optimization of variable step size algorithm used for adaptive noise cancellation

This paper proposes profiling and optimization of Variable Step Size (VSS) algorithm for adaptive noise cancellation by implementing the algorithm in DSP Processor TMS320C6713. The implementation of VSS algorithm in DSK (DSP Starter Kit) includes optimization of algorithms using various optimization techniques via profiling. Code Compose Studio (CCS an Integrated Development Environment for TMS320C6713) has been used for profiling and optimization. This paper presents different ways to reduce the computation complexity using different optimization algorithms. The code has been implemented using C language. The types of optimization used are code optimization and compiler optimization. By using the various optimization techniques for C code 25-30% reduction in Millions Instruction per Seconds (MIPS) has been obtained successfully. The optimized algorithm founds its application in speech and audio signal processing to remove noises from signal.