Parallelizing Wavelet Transformation with a Reduction Style Framework

There is an increasing trend towards parallel processing and data processing using cloud environments. Simple APIs for expressing parallelism, such as map-reduce, are popular in cloud environments, but their expressibility is generally considered limited. This paper focuses on how a signal processing algorithm, wavelet transform, can be parallelized in a cloud environment comprising a cluster of multi-cores using a reduction-based framework. Particularly, we use a framework, FREERIDE, which has many similarities with map-reduce, but its API involves an explicit reduction object. We show how all communication in this algorithm can be managed using a reduction object. Besides programming with a simpler model, we also achieve good parallel efficiency, with a speedup of up to 42 on 64 cores.