Data flow algorithms for processors with vector extensions: Handling actors with internal state

• Published in: 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP) pp. 20 - 24
• Main Authors: Barford, Lee, Bhattacharyya, Shuvra S., Yanzhou Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2014
• Subjects: data flow computing; digital signal processing; Graphics processing units; Indexes; Kernel; parallel algorithms; Signal processing; Signal processing algorithms; vector processors; Vectors
• DOI: 10.1109/GlobalSIP.2014.7032070

Full use of the parallel computation capabilities of present and expected CPUs and CPUs require use of vector extensions. Yet many actors in data flow systems for digital signal processing have internal state (or, equivalently, an edge that loops from the actor back to itself) that impose serial dependencies between actor invocations that make vectorizing across actor invocations impossible. Ideally, issues of inter-thread coordination required by serial data dependencies should be handled by code written by parallel programming experts that is separate from code specifying signal processing operations. The purpose of this paper is to present one approach for so doing in the case of actors that maintain state. We propose a methodology for using the parallel scan (also known as prefix sum) pattern to create algorithms for multiple simultaneous invocations of such an actor that results in vectorizable code. Two examples of applying this methodology are given: (1) infinite impulse response filters and (2) finite state machines. The correctness and performance of the resulting IIR filters are studied.