Massively parallel processors

Kirk, D.B., Hwu, W.W. Programming Massively Parallel Processors, Morgan Kaufmann Publishers, Burlington, 2010. 

Chemical Network Problems Solved on NASA/Goddard s Massively Parallel Processor (MPP) Computer Symbolic Computation and Chemical Engineering Model Development An Overall Strategy for the Systematic Synthesis and Optimization of Large-Scale Chemical Processing Systems Synthesis of Solids Processing (Heuristics Selection)... 

The Tianhe-IA, a massively parallel processor at the National Supercomputing Center in Tianjin, China, was officially timed hy the TOP500 as the world s fastest computer... 

Kirk, David, and Wen-mei W. Hwu. Programming Massively Parallel Processors A Hands-On Approach. Burlington, Mass. Morgan Kaufinann, 2010. A useful text describing the methods used for CPU and... 

GPU programming used in modem massively parallel processors. 

MPP systems, where MPP stands for massively parallel processors, can be of both the shared-memory type and the distributed-memory type. In both of these types, one is confronted with the problem of how to deliver the data from the memory to the processors. An interconnection network is needed that connects the memory or memories, in the case of a distributed memory machine, to the processors. Through the years many types of networks have been devised. Figure 4 shows some types of networks used in present-day MPP systems. 

The massively parallel approach adopted in the Connection Machine has been termed data parallel. Whereas a uniprocessor must sequentially step through large amounts of data, a data parallel machine moves processors to the data. Aggregate memory to processor bandwidth in the Connection Machine is more than 700 megabytes per second. 

Haykin [22] offers a dehnition based on Aleksander and Morton [19] A neural network is a massively parallel distrihuted processor that has a natural propensity for storing experienhal knowledge and making it available for use. It resembles the brain in two respects ... 

Massively parallel (multiple instruction, multiple data) computers with tens or hundreds of processors are not readily accessible to the majority of quantum chemists at the present time. However the cost of currently available hypercube machines with tens of processors (each with about the power of a VAX) is comparable to that of superminis but with up to a hundred times the power. For applications of the type discussed above the performance of a machine with as few as 32 or 64 processors would be comparable to (or perhaps even exceed) that of a single processor supercomputer. Although computer requirements currently limit QMC applications (even with effective potentials) the proliferation of inexpensive massively parallel machines could conceivably make the application of relativistic effective potentials with C C quite competitive with more conventional electronic structure techniques. 

Much of the pioneering work in applying parallel processing to large problems in computational chemistry is due to Enrico Clementi and coworkers, and the development of the LCAP parallel processing systems (see Ref. 90 and the numerous references therein). The LCAP (loosely coupled array of processors) project commenced in 1983, with the stated aim of coupling readily available commercial processors to form a system that is not massively parallel, but rather is modular and can be expanded to match the degree of parallelism that a set of applications can support. 

Large numbers of cheap processors arranged in grids can be an effective way to achieve massive parallelism and high throughput, provided the workflow system is able to orchestrate tasks appropriately between these processors. 

---