摘要:
A computing system for implementing at least one electronic circuit with gain comprises at least one two-dimensional molecular switch array. The molecular switch array is formed by assembling two or more crossed planes of wires into a configuration of devices. Each device comprises a junction formed by a pair of crossed wires and at least one connector species that connects the pair of crossed wires in the junction. The junction has a functional dimension in nanometers, and includes a switching capability provided by both (1) one or more connector species and the pair of crossed wires and (2) a configurable nano-scale wire transistor having a first state that functions as a transistor and a second state that functions as a conducting semiconductor wire. Specific connections are made to interconnect the devices and connect the devices to two structures that provide high and low voltages.
摘要:
A method for implementing an artificial neural network includes connecting a plurality of receiving neurons to a plurality of transmitting neurons through memristive synapses. Each memristive synapse has a weight which is initialized into a conductive state. A binary input vector is presented through the memristive synapses to the plurality of receiving neurons and the state of one or more of the memristive synapses modified based on the binary input vector.
摘要:
The present invention is directed toward a system for forming miter joints including a miter saw and an angle gauge. The miter saw includes a platform with a kerf slot and a pair of arcuate slots. Each arcuate slot includes an associated rail located on the underside of the platform. A fence is coupled to each of the rails such that the fence may be pivoted with respect to the platform. The angle measurement tool is a one-handed tool including spring loaded paddles that measure the angle between intersecting surfaces. The angle measurement tool connects to the miter saw to permit the transfer of the measured angle to the fences.
摘要:
A method for implementing an artificial neural network includes connecting a plurality of receiving neurons to a plurality of transmitting neurons through memristive synapses (705). Each memristive synapse has a weight which is initialized into a conductive state (715). A binary input vector is presented through the memristive synapses to the plurality of receiving neurons (735) and the state of one or more of the memristive synapses modified based on the binary input vector (760).
摘要:
Various embodiments of the present invention are directed to photonic-interconnection-based compute clusters that provide high-speed, high-bandwidth interconnections between compute cluster nodes. In one embodiment of the present invention, the compute cluster includes a photonic interconnection having one or more optical transmission paths for transmitting independent frequency channels within an optical signal to each node in a set of nodes. The compute cluster includes one or more photonic-interconnection-based writers, each writer associated with a particular node, and each writer encoding information generated by the node into one of the independent frequency channels. A switch fabric directs the information encoded in the independent frequency channels to one or more nodes in the compute cluster. The compute cluster also includes one or more photonic-interconnection-based readers, each reader associated with a particular node, and each reader extracting the information encoded in the independent frequency channels directed to the node for processing.
摘要:
Methods for inputting a data-value pattern into a nanowire crossbar, for inputting a data-value pattern into a nanowire crossbar that support computer instructions stored in a computer-readable medium, and for distributing a received data value to each of a set of nanowires that support control logic implemented in logic circuits are provided. First and second nanoscale shift registers are employed, the first having output signal lines that form or interconnect with a first parallel set of nanowire-crossbar nanowires and the second having output signal lines that form or interconnect with a second parallel set of nanowire-crossbar nanowires. A first pattern of values is stored in the first shift register and a second pattern of values is stored in the second shift register using voltage signals below the WRITE voltage for junctions of the crossbar. Voltage signals greater than or equal to the WRITE threshold are applied for junctions of the crossbar to write the pattern of data values into the crossbar.
摘要:
A computing arrangement including a processor and programmable logic. In various embodiments, the arrangement includes an instruction processing circuit coupled to a programmable logic circuit, and a memory arrangement coupled to the instruction processing circuit and to the programmable logic circuit. The instruction processing circuit executes instructions of a native instruction set, and the programmable logic is configured to dynamically translate input instructions to translated instructions of the native instruction set. The translated instructions are stored in a translation cache in the memory arrangement, and the translation cache is managed by the programmable logic. The programmable logic then provides the translated instructions to the instruction processing circuit for execution.
摘要:
In one embodiment of the present invention, a nanoscale latch is implemented by interconnecting an enable line, two control lines, and a pull-down line, when needed, to a signal line carrying encoded binary values to be latched and subsequently output. The enable line is interconnected with the signal line through a field-effect-transistor-like nanoscale junction. Both control lines are interconnected with the signal line through asymmetric-switch nanoscale junctions of like polarities. The pull-down line, when needed, is interconnected with the signal line through a resistive nanoscale junction. Inputting a sequence of signals to the enable and control lines allows a value input from the signal line to be stored and subsequently output to the signal line. In various additional embodiments, an array of nanoscale latches can be implemented by overlaying enable and control lines, and a pull-down line when needed, over a set of parallel nanowires.
摘要:
Various embodiments of the present invention are directed to demultiplexers that include tunneling resistor nanowire junctions, and to nanowire addressing methods for reliably addressing nanowire signal lines in nanoscale and mixed-scale demultiplexers. In one embodiment of the present invention, an encoder-demultiplexer comprises a number of input signal lines and an encoder that generates an n-bit-constant-weight-code code-word internal address for each different input address received on the input signal lines. The encoder-demultiplexer includes n microscale signal lines on which an n-bit-constant-weight-code code-word internal address is output by the encoder, where each microscale signal line carries one bit of the n-bit-constant-weight-code code-word internal address. The encoder-demultiplexer also includes a number of encoder-demultiplexer-addressed nanowire signal lines interconnected with the n microscale signal lines via tunneling resistor junctions, the encoder-demultiplexer-addressed nanowire signal lines each associated with an n-bit-constant-weight-code code-word internal address.