Carl Björkman
Michel Cupurdija
In recent years parallel computing has become increasingly important. In a regular PC today lies often a FLOPS-capacity surpassing the capacity of a single core in the CPU by far.
OpenCL is a standardized framework that allows the programmer to write code able to execute on any computational unit having supporting drivers.
This thesis examines the framework by an implementation doing exhaustive searches in order to find solutions to instances of the NP-complete problem of verbal arithmetic.
The results imply that this kind of computation is unsuited for processing units without efficient support for random access, but on the other hand showing excellent performance on the ones that do.