I'm not sure if this is the appropriate forum for asking the following question. Please guide me to the right forum.
I am trying to understand the algorithms used by kernels(such as Integer Sort) in NAS parallel benchmarks. I could not find any source online that explained the algorithms used by the kernels. I could try to infer the algorithms from the code, but that would be really messy. The algorithms are not explained in the paper published by the authors of the benchmark either.
Please point me to some tutorials/documents describing these algorithms. Thanks
