Acceleration of high dynamic range imaging pipeline based on multi-threading and SIMD technologies

In this paper we present a holistic approach to CPU based acceleration of the high dynamic range imaging (HDRI) pipeline. The high dynamic range representation can encode images regardless of the technology used to create and display them, with the accuracy that is only constrained by the limitations of the human eye and not a particular output medium. Unfortunately, the increase in accuracy causes significant computational overhead and effective hardware acceleration is needed to ensure a utility value of HDRI applications. In this work we propose a novel architecture of the HDRI pipeline based on CPU SIMD and multi-threading technologies. We discuss the impact on processing speed caused by vectorization and parallelization of individual image processing operations. A commercial application of the new HDRI pipeline is described together with evaluation of achieved image processing speed-up.