Cognitive Computing is a new and quickly advancing technology. In the last decade Cognitive Computing has been used to assist researchers in their endeavors in many different scientific fields such as Health & med...
详细信息
Cognitive Computing is a new and quickly advancing technology. In the last decade Cognitive Computing has been used to assist researchers in their endeavors in many different scientific fields such as Health & medicine, Education, Marketing, Psychology and Financial Services. On the other hand, parallelprogramming is a more complex concept than sequential programming. The additional complexity of parallelprogramming is introduced by its nature that requires implementations of more complex algorithms and it introduces additional concepts to the developers, namely the communication between the processes (Distributed memory systems) that execute the parallel program and their synchronization (Share memory systems). As a result of this additional complexity, a lot of novice developers are reserved in their attempts to implement parallel programs. The objective of this research project was to investigate whether we can assist parallelprogramming process through cognitive computing solutions. In order to achieve our objective, the MPI Assistant, a Q&A system has been developed and a case study has been carried out to determine our application's efficiency in our attempt to assist parallelprogramming developers. The case study showed that our MPI Assistant system indeed helped developers reduce the time they spend to develop their solutions, but not improve the quality of the program or its efficiency as these improvements require features that are out of this research project's scope. However, the case study had limited number of participants, which may affect our results' reliability. As a next step in our attempt to determine if cognitive computing technologies are able to assist developers in their parallelprogramming development, we moved to investigate if cognitive solutions can extract better and more complete responses compared to our manually-created responses that we created for the MPI Assistant. We have experimented with 2 different approaches to the probl
暂无评论