Thinking Machines Corporation

Karl P Sims

W Daniel Hillis

Brewster A Kahle

Clifford A Lasser

Guy Lewis Steele, Jr

Tomaso A Poggio

Howard L Resnikoff

James B Salem

Guy Blelloch

Abhiram Ranade

Michael Drumbeller

A computer object processing system for, during selected iterations, generating an object, such as an expression defining an image. During an initial iteration, a predetermined number of seed objects are generated, each seed object defining an object for the initial iteration. During each successive iteration, a predetermined number of mutated objects are generated (i) in response to an operator selected one of the seed objects during the initial iteration and (ii) in response to a an operator selected object during each iteration after the initial iteration. During each iteration one of the seed objects or one of the mutated objects is selected for use in generating a mutated object during a subsequent iteration.

Computer system and method for generating and mutating objects by

A system processes directed graphs, each directed graph comprising a plurality of nodes interconnected by arrows defining a relationship among the nodes, each node defining a selected attribute. The system comprises an initial population means, a subsequent generation population generating means, and a competition simulation means. The initial population means provides an initial population of directed graphs that comprises an initial current generation during an initial iteration. The subsequent generation population generating means generates, in response to selected ones of the directed graphs in each of a plurality of current generations, modified directed graphs for use generation during a subsequent iteration. The competition simulation means performs a processing operation in connection with attributes of the nodes of the graphs to simulate a competition among the current generation of directed graphs in connection with a selected goal, to develop the ranking information for use by the subsequent generation population generating means. The operations of the initial population means, the subsequent generation population generating means and the competition simulation means are controlled through a series of iterations. In the successive iterations, the performance of the graphs in response to the selected goal is anticipated to improve, since the population of graphs for each iteration is based on the graphs determined to have the best fitness during the previous iteration.

System and method for creating and evolving directed graphs

A virtual processor mechanism and specific techniques and instructions for utilizing such virtual processor mechanism within an SIMD computer having numerous processors, and each physical processor having dedicated memory associated therewith. Each physical processor is used to simulate multiple 'virtual' processors, with each physical processor simulating the same number of virtual processors. The memory of each physical processor is divided into n regions of equal size, each such region being allocated to one virtual processor, where n is the number of virtual processors simulated by each physical processor. Whenever an instruction is processed, each physical processor is time-sliced among the virtual memory regions, performing the operation first as one virtual processor, then another, until the operation has been performed for all virtual processors. Physical processors are switched among the virtual processors in a completely regular, predictable, deterministic fashion. The virtual processor mechanism switches among virtual processors within instructions, so that at the completion of each instruction, it has been executed on behalf of all virtual processors. A number of instructions are shown for execution using these virtual processor techniques.

Virtual processor techniques in a SIMD multiprocessor array

A method is described for simulating additional processors in a SIMD computer by dividing the memory associated with each processor into a plurality of sub-memories and then operating on each sub-memory in succession as if it were associated with a separate processor. Thus, a first instruction or set of instructions is applied to all the processors of the array to cause at least some processors to process data stored at a first location or locations in the first sub-memory. Thereafter, the same first instruction or set of instructions is applied to all the processors of the array to cause at least some processors to process data stored at the same first location in a second sub-memory. And so forth for each of the sub-memories. By operating a SIMD computer in this fashion, it is possible in effect to vary the number of processors in the array so as to provide the number of processors required for a problem.

Method of simulating additional processors in a SIMD parallel processor

A sensing device for generating an output signal corresponding to an input signal which comprises a substrate, an array of sensor elements for receiving the input signal and transfer members located on the surface of the substrate and interposed between the sensor elements. The sensor elements have their barycenters distributed on the surface of the substrate in a random non-periodic pattern. The transfer members are coupled to the sensor elements and generate the output signal. The sensing device is incorporated in an apparatus which generates an output signal from an input image wherein the output signal is substantially free of detectable aliases. The apparatus includes an image pick-up device for viewing the input image and transmitting radiation to the image sensing device, an analog-to-digital converter for converting the analog signal from a sensing device to a digital signal, a position encoder, an interpolator and a memory means for storing the output of the interpolator. The position encoder is provided with a plurality of storage addresses for storing digital signals each having a value corresponding to the intensity of the radiation incident on a corresponding sensor element, and the interpolator generates a plurality of signals corresponding to intensity values intermediate to those stored in the storage addresses of the position encoder.

Growing community of inventors

Somerville, MA, United States of America

Karl P Sims