A Multi-GPU Framework for In-Memory Text Data Analytics

A performance comparison of in-memory Virtual Desktop Environment

“…In [8], the authors try to tackle big-data analysis problem by combining parallel computing with in-memory technique. Their framework utilizes the parallel processing power of multiple graphics-processing-units (GPU), and performs inmemory text data analysis with their custom architecture.…”

Local Concurrency in Text Block Search Tasks

“…Therefore, they were developed mainly to solve particular tasks and the problem of sorting and search was regarded primarily in terms of common algorithm parallelizing principles realization in respect to data bulk. The situation changed "at the cusp of centuries" with the emergence of multicore processors and mass use of network computation structures [4,5]: limited (relatively small) data arrays processing with general-purpose computers prior use has gained relevancy. It is quite clear that limited data arrays and general-purpose computers of the early XXIst century are almost like big data and back-end processors of the late XXth century.…”

“…The tasks of the given type cover, in particular, the major part of the subject of man-machine interaction. One of the dominant paradigms (not the only one [5]) in this field is the research and reproduction of the structure and functions of the human intellect [9]. At every certain moment of their practical activity, an individual operates effectively with a limited small number of notions [10,11].…”