Summary of the Invention

 However, the confluence of all three of the established major trends summarized above -- supercomputer-like personal computers, the spread of parallel processing using personal computer microprocessors (particularly massively parallel processing), and the enormous increase in network communications bandwidth -- has made possible a surprising solution to the hugely excessive idleness problem of personal computers (and to the problematic possible end of Moore's Law), with very high potential economic savings once the basic infrastructure connecting personal computers with optical fiber is in place in the relatively near future.

 The solution is use those mostly idle PC's (or their equivalents or successors) to build a parallel or massively parallel processing computer or computers utilizing a very large network like the Internet or, more specifically, like the World Wide Web (WWW), or their equivalents or eventual successors like the MetaInternet (and including Internet II and the Next Generation Internet, which are under development now and which will utilize much broader bandwidth and will coexist with the Internet, the structure of which is in ever constant hardware and software upgrade and including the SuperInternet based on essentially all optical fiber transmission) with extremely broad bandwidth connections and virtually unlimited data transmission speed.

 The prime characteristic of the Internet is of course the very large number of computers of all sorts already linked to it, with the future potential for effectively universal connection; it is a network of networks of computers that provides nearly unrestricted access (other than cost) worldwide. The currently existing and soon-to-be widely available very broad bandwidth of network communications is used to link personal computers externally in a manner at least equivalent, and probably much faster, to the faster internal system buses of the personal computers, so that no external processing constraint will be imposed on linked personal computers by data input or output, or throughput; the speed of the microprocessor itself and the internal connections or buses of the PC are the only processing constraint of the system.

 This makes efficient external parallel processing (and multitasking) possible, including massively parallel processing, in a manner paralleling more conventional internal parallel processing, call superscalar processing.

 In one preferred embodiment, the World Wide Web (or its equivalents or successors) is transformed into a huge virtual massively parallel processing computer or computers, with potential through its established hyperlinks connections to operate in a manner at least somewhat like a neural network or neural networks, since the speed of transmission in the broadband linkages is so great that any linkage between two microprocessors is virtually equivalent to direct, physically close connections between those microprocessors.

 With further development, digital signal processor-type microprocessors and/or analogue microprocessors may be particularly advantageous for this approach, either alone or in conjunction with conventional microprocessors and/or those new microprocessors described later in this application. Networks with WWW-type hyperlinks incorporating digital signal processor-type microprocessor (or successors or equivalents) could operate separately from networks of conventional microprocessors (or successors or equivalents) or with one or more connections between such differing networks or with relatively complete integration between such differing networks. Simultaneous operation across the same network connection structure should be possible, employing non-interfering transmission links.

 Such extremely broad bandwidth networks of computers enable every PC within the network to be fully utilized or nearly so. Because of the extraordinary extent to which existing PC's are currently idle, at optimal performance this new system potentially results in a thousand-fold increase in computer power available to each and every PC user (and any other user); and, on demand, almost any desired level of increased power, limited mostly by the increased cost, which however is relatively far less than possible from any other conceivable computer network configuration. This revolutionary increase is on top of the extremely rapid, but evolutionary increases already occurring in the computer/network industry discussed above.

 The metacomputing hardware and software means of the MetaInternet provides performance increases that is likely to at least double every eighteen months based on the doubling of personal computers shared in a typical parallel processing operation by a standard PC user, starting first with at least 2 PC's, then about 4, about 8, about 16, about 32, about 64, about 128, about 256, and about 512, for example. After about fifteen years, for example, it is anticipated that each standard PC user will likely be able to use a maximum of about 1024 personal computers for parallel processing or any other shared computing use, while generally using the Internet or its successors like the MetaInternet for free. At the other end of the performance spectrum, supercomputers experience a similar performance increase generally, but ultimately the performance increase is limited primarily by cost of adding network linkages to available PC's, so there is definite potential for a huge leap in supercomputer performance.

 Network computer systems as described above offer almost limitless flexibility due to the abundant supply of heretofore idle connected microprocessors. This advantage allows "tightly coupled" computing problems (which normally are difficult to process in parallel) to be solved without knowing in advance (as is now necessary in relatively massively parallel processing) how many processors are available, what they are and their connection characteristics. A minimum number of equivalent processors (with equivalent other specs) are easily found nearby in a massive network like the Internet and assigned within the network from those multitudes available nearby. Moreover, the number of microprocessors used are almost completely flexible, depending on the complexity of the problem, and limited only by cost.  The existing problem of time delay is solved largely by the widespread introduction of broad bandwidth connections between computers processing in parallel.

 The state of the known art relating to this application is summarized in The Grid: Blueprint for a New Computing Infrastructure, edited by Ian Foster and Carl Kesselman, and published by Morgan Kaufman Publishers, Inc. in 1998. The state of the known art relating to this application is also summarized in: Scalable Parallel Computing by Kai Hwang and Zhiwei Xu, published by WCB McGraw-Hill in 1998; Parallel Programming by Barry Wilkinson and Michael Allen, published by Prentice Hall in 1998; Computer Architecture: A Quantitative Approach (2nd Edition) by David Patterson and John Hennessy, published by Morgan Kaufmann in 1996; Parallel Computer Architecture by David Culler and Jaswinder Singh, published by Morgan Kaufman in 1998; and Computer Organization and Design by John Hennessy and David Patterson, published by Morgan Kaufman in 1998.

[GloNetComp] [Who We Are] [PCT Applications] [US Patents] [In Depth]

Friday, February 16, 2001