摘要:
A technique determines whether configured logical bandwidth allotments for logical channels are supported by maximum available physical bandwidths of physical channels assigned to those logical channels. The technique establishes a bandwidth-constraint directed acyclic graph (DAG) or “BCD” based on novel relationship rules between vertexes of the BCD that represent logical channels or unions of logical channels as well as the underlying physical channels and their maximum available bandwidth constraints. Once the BCD is established, the vertexes of the BCD may be traversed (e.g., from in-neighbor vertexes to out-neighbor vertexes) to determine whether their constraints are met.
摘要:
A method of compressing an original dynamic range of an original image, includes a first step of obtaining a reduced image corresponding to the original image by performing quantization and downsampling on the original image that has been input; a second step of calculating a look-up table based on the reduced image, wherein the look-up table indicates a mapping relationship between the original dynamic range of the original image and a dynamic range of a medium; and a third step of mapping each of the pixels in the original image from the original dynamic range of the original image onto the dynamic range of the medium based on the look-up table.
摘要:
A computed tomography system having a fixed X-ray source [10] for producing a fan beam [20], a fixed digital detector [12] and a manipulator [14] for holding and rotating an object [16] to be inspected. Left and right projections of the rotated object on the fixed digital detector are used to determine a central ray, reconstruction of an image of the object being based on the central ray position. A corresponding method and apparatus are also disclosed.
摘要:
An apparatus includes a field-programmable gate array (FPGA). The FPGA includes a first FPGA tile, and the first FPGA tile includes a plurality of functional groups (FGs), a regular routing structure, and a plurality of interface groups (IGs). The plurality of FGs are arranged in rows and columns with each of the FGs being configured to receive regular input signals, perform a logic operation, and generate regular output signals. The regular routing structure is coupled to the FGs and configured to receive the regular output signals, route signals within the first FPGA tile, and provide the regular input signals to the FGs. The routability of the regular routing structure is maximized by depositing switches according to designators. This novel designation method provides the same routability with approximately half the switches. Thus, further reduction in routing area is achieved. The plurality of IGs surround the plurality of FGs such that one IG is positioned at each end of each row and column. Each of the IGs is coupled to the regular routing structure and configured to transfer signals from the regular routing structure to outside of the first FPGA tile.
摘要:
The invention relates to an inter-tile buffering system for a field programmable gate array. The field programmable gate array is comprised of the following. A plurality of field programmable gate array tiles are arranged in an array of rows and columns. Each of said field programmable gate array tiles comprises a plurality of functional groups and a plurality of interface groups, and a primary routing structure. The primary routing structure is coupled to said functional groups and interface groups and is configured to receive primary output signals, route primary output signals within said at least one field programmable gate array tile, and provide primary input signals to said functional groups and interface groups. Each functional group is configured to receive primary input signals, perform a logic operation, and generate primary output signals. Each interface group is configured to transfer signals from said primary routing structure to outside of said at least one field programmable gate array tile, and includes a plurality of input multiplexers configured to select signals received from outside of said at least one field programmable gate array tile and provide signals to the primary routing structure inside said at least one field programmable gate array tile. Said primary routing structure comprises a horizontal bus and a vertical bus. A horizontal buffer is located between each column of field programmable gate array tiles and is coupled to the primary routing structure. A vertical buffer is located between each row of field programmable gate array tiles and is coupled to the primary routing structure.
摘要:
An apparatus includes a field-programmable gate array (FPGA). The FPGA includes a first FPGA tile, and the first FPGA tile includes a plurality of functional groups (FGs), a third set of routing conductors, in addition to a first set of routing conductors and a second set of routing conductors and a plurality of interface groups (IGs). The plurality of FGs are arranged in rows and columns with each of the FGs being configured to receive tertiary input signals as well as regular input signals, perform a logic operation, and generate regular output signals. The third set of routing conductors is coupled to the first set of output ports of the FGs and configured to receive signals, route signals within the first FPGA tile, and provide input signals to the third set of input ports of the FGs. The plurality of IGs surround the plurality of FGs such that one IG is positioned at each end of each row and column. Each of the IGs is coupled to the third set of routing conductors and configured to transfer signals from the third set of routing conductors to outside of the first FPGA tile.
摘要:
A field-programmable gate array (FPGA), comprising: a first FPGA tile, the first FPGA tile comprising a plurality of functional groups (FGs), a regular routing structure, and a plurality of interface groups (IGs). The plurality of FGs are arranged in rows and columns with each of the FGs being configured to receive regular input signals, perform a logic operation, and generate regular output signals. The regular routing structure is coupled to the FGs and configured to receive the regular output signals, route signals within the first FPGA tile, and provide the regular input signals to the FGs. The plurality of IGs surround the plurality of FGs such that one IG is positioned at each end of each row and column. Each of the IGs is coupled to the regular routing structure and configured to transfer signals from the regular routing structure to outside of the first FPGA tile. The first FPGA tile also comprising a secondary routing structure independent of the regular routing structure, coupled to each of the IGs, configured to transfer signals from said first FPGA tile to at least one other FPGA tile. The disclosed apparatus also provides for a routing structure between IGs and RAM blocks. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understand that it will not be used to interpret or limit the scope or meaning of the claims.
摘要:
A resistive floating electrode device (RFED) provides a logic cell or non-volatile storage or dynamic or static random access memory on an extremely compact matrix with individual cells scalable to the minimum available lithographic feature size regime by providing atomic switches connected in anti-parallel relationship, preferably with a common inert electrode. Programming is facilitated by limiting current to a compliance current level in order to maintain an OB state from which the cell can be written to either the 0 or 1 state. A perfecting feature of the invention provides for selective operation of a cell as a diode or in a volatile or non-volatile storage mode within the same memory array. A series connection of three or more RFEDs in accordance with the invention having different ON state currents, OFF state currents and reset currents can be used as adaptive, neural or chaotic logic cells.
摘要:
A method and an apparatus for detecting a continuous road partition with a height that includes obtaining disparity maps having the continuous road partition, and U-disparity maps corresponding to the disparity maps; obtaining an intermediate detection result of the continuous road partition detected from the U-disparity maps of first N frames; and detecting the continuous road partition from the U-disparity map of a current frame, based on the obtained intermediate detection result.