Performance analysis of embedded media applications in newer ARM architectures

As more and more applications require audio, video and communication processing capabilities, the requirements placed on embedded processors used in portable devices and edge-client devices have become more computation and bandwidth intensive. Both RISC micro processors and DSPs have served these applications. While RISC processors are traditionally designed to enable efficient asynchronous control flow, DSPs are designed to perform well for synchronous, constant-rate data flow. Because so many embedded applications have intense requirements for both control and media processing, engineers have typically turned to inelegantly grafting DSPs and microprocessors together in one form or another. Together, the respective functional aspects of RISC processors and DSPs unite as the perfect processing engine for a wide variety of multimedia applications and products. ARM version 6 processors have incorporated SIMD instructions for signal processing functionality and some media extension instructions to support multimedia applications. This paper presents a comprehensive evaluation of the execution characteristics of multimedia applications on SIMD and DSP enhanced ARM v6 processors and the detection of bottlenecks in the execution of multimedia applications on ARM v6 processors.