This paper characterizes selected workloads of multimedia applications on current superscalar architectures, and then it characterizes the same workloads on Intel® Hyper-Threading Technology. The workloads, including video encoding, decoding, and watermark detection, are optimized for the Intel® Pentium® 4 processor. One of the workloads is even commercially available and it performs best on the Pentium 4 processor. Nonetheless, due to the inherently sequential constitution of the algorithms, most of the modules in these well-optimized workloads cannot fully utilize all the execution units available in the microprocessor. Some of the modules are memory-bounded, while some are computation-bounded. Therefore, Hyper-Threading Technology is a promising architecture feature that allows more CPU resources to be used at a given moment.

Our goal, in this paper, is to better explain the performance improvements that are possible in multimedia applications using Hyper-Threading Technology. Our initial studies show that there are many unexplored issues in algorithms and applications for Hyper-Threading Technology. In particular, there are many techniques to develop better software for multithreading systems. We demonstrate different task partition/scheduling schemes and discuss their trade-offs so that a reader can understand how to develop efficient applications on processors with Hyper-Threading Technology.

Intel and Pentium are registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries.