DIFFUSION OF SOFTWARE INNOVATION : A PETRI NET THEORY PERSPECTIVE

Abstract

MPSOC환경은 하드웨어적, 소프트웨어적으로 다양한 발전을 하여왔고 현재에도 산업 및 학계에서 다양한 연구가 진행되고 있다. 그에 따른 다방면에서의 발전적 접근법이 나오게 되었고 현재에도 다양한 방법론을 적용하여 진행되고 있다. 본 연구에서는 소프트웨어적인 측면을 주 연구대상으로 하였고 특히 자체적인 분류에 따른 Data, Tasks, Data flow모델을 선별하였고 그중 CUDA와 HOPES를 경험한 대상으로 PETRI NET을 활용 그들의 숙련도를 확인하는 과정을 담고 있다. 그에 따라 각 영역의 숙련정도, 서로 다른 모델에 대한 이해도를 실험을 통해 검증하였고 나아가 합리적이 연구 방향을 제시 할 것을 목표로 하고 있다. PETRI NET은 TASKS중심의 모형과 DATA중심의 병렬프로그래밍의 설명에 용이한 모델로서 특이 동시성과 병렬성을 설명하는데 탁월한 모형을 제시 할 수 있었고 이를 바탕으로 실질 실험대상자들에게 PETRI NET에 관한 4시간의 선행 학습을 주도 후 실험을 실시, 객관적이고 다양한 결과를 얻을 수 있었다. 이를 바탕으로 각 영역에서의 숙련자들이 TASKS중심 혹은 DATA중심의 모형을 상호 얼마나 이해하는 지를 판단 할 수 있었고 그 깊이가 주는 영향에 대해 설명할 수 있는 기본 자료를 재공해 준다는 것을 확인하였다.|Hardware and software field are developed by Environment of MPSOC. also it is still working with economic world and academic world. that means We believe the major cause for this state of affairs is that most parallel programming environments focus on how concurrency is implemented rather than on how concurrency is exploited in a program design. In other words, bringing parallel computing to a broader audience requires solving the problem at the algorithm design level. This study focus on software side and try to classify from parallel programming design world. it can be divided by three ? Data, Tasks, Data flow model. then we used PETRI NET to CUDA and HOPES programmer, how much they understand parallel programming for each side. we focus on two side frist one is what is different between their experience. PETRI NET is easy to descript parallel program or parallel design pattern for Task, Data, and hybird. so this research can explain how they know and how much they know about parallel programming.; Hardware and software field are developed by Environment of MPSOC. also it is still working with economic world and academic world. that means We believe the major cause for this state of affairs is that most parallel programming environments focus on how concurrency is implemented rather than on how concurrency is exploited in a program design. In other words, bringing parallel computing to a broader audience requires solving the problem at the algorithm design level. This study focus on software side and try to classify from parallel programming design world. it can be divided by three ? Data, Tasks, Data flow model. then we used PETRI NET to CUDA and HOPES programmer, how much they understand parallel programming for each side. we focus on two side frist one is what is different between their experience. PETRI NET is easy to descript parallel program or parallel design pattern for Task, Data, and hybird. so this research can explain how they know and how much they know about parallel programming.