The Need for Modern Computing Paradigm: Science Applied to Computing

Abstract

More than hundred years ago the 'classic physics' was it in its full power, with just a few unexplained phenomena; which however led to a revolution and the development of the 'modern physics'. Today the computing is in a similar position: computing is a sound success story, with exponentially growing utilization, but with a growing number of difficulties and unexpected issues as moving towards extreme utilization conditions. In physics studying the nature under extreme conditions has lead to the understanding of the relativistic and quantal behavior. Quite similarly in computing some phenomena, acquired in connection with extreme (computing) conditions, cannot be understood based on of the 'classic computing paradigm'. The paper draws the attention that under extreme conditions qualitatively different behaviors may be encountered in both classic and world, and pinpointing that certain, formerly unnoticed or neglected aspects enable to explain new phenomena as well as to enhance computing features. Moreover,an idea of modern computing paradigm implementation is proposed.

Finally, how many efficiencies the supercomputers have?

“…No surprise that all payload performance diagram lines runs into saturation, even the 'FP0' and 'Science' ones. As discussed in detals in [4], the behavior of the computing system under extreme conditions shows surprising parallels with the behavior of natural objects. The example shown in Table 1 and Figure 4 parallel the nonlinearity of speed addition in modern physics with the performance addition in modern computing.…”

“…In section 4 the form of the correction for adding performances, stemming out from Amdahl's law, enables to introduce an interesting parallel with the correction term introduced by the relativistic physics for adding speeds. Interestingly enough, under extreme conditions, the technical objects of computing show up a series of similar behavior (for more details see [4]) to that of natural objects.…”

“…actually increases the execution time rather than reducing it" [3]. The parallelized sequential processing has different rules of game [3], [4]: the performance gain ("the speedup") has its inherent bounds [5].…”

“…Akin to as the laws of science limit the performance of the single-thread processors [6], the commonly used computing paradigm (and its technical implementation) limits the performance of supercomputers [4]. On one side, experts expected the performance 1 to achieve the magic 1 Eflops around year 2020, see Figure 1 in [7] 2 .…”

On the Spatiotemporal Behavior in Biology-Mimicking Computing Systems

“…There are many analogies between science and computing [18], among others, how they handle time. Both classic science and classic computing assume instant (infinitely quick) interaction between its objects.…”