QCD support for Multi-Threads
QMT is a software library providing OpenMP like fork-join multi-thread APIs. The current implementation works on i386 and x86-64 using pthread and other optimizations.
There is a paper published in the Proceedings of 9th International Conference on High Performance Computing in Asia Pacific Region (HPC-Asia 2007) that describes the implementation of the barriers, a later paper that describes the performance on the AMD quad-core processors, and a recent talk on the implementation as well.