The present invention concerns a new category of integrated circuitry and a new methodology for adaptive or reconfigurable computing. The preferred IC embodiment includes a plurality of heterogeneous computational elements coupled to an interconnection network. The plurality of heterogeneous computational elements include corresponding computational elements having fixed and differing architectures, such as fixed architectures for different functions such as memory, addition, multiplication, complex multiplication, subtraction, configuration, reconfiguration, control, input, output, and field programmability. In response to configuration information, the interconnection network is operative in real-time to configure and reconfigure the plurality of heterogeneous computational elements for a plurality of different functional modes, including linear algorithmic operations, non-linear algorithmic operations, finite state machine operations, memory operations, and bit-level manipulations. The various fixed architectures are selected to comparatively minimize power consumption and increase performance of the adaptive computing integrated circuit, particularly suitable for mobile, hand-held or other battery-powered computing applications.

Adaptive integrated circuitry with heterogeneous and reconfigurable matrices of diverse and adaptive computational units having fixed, application specific computational elements

An apparatus includes an FPGA, which includes a first FPGA tile including a plurality of FGs, a first, second, and third set of routing conductors, and a plurality of IGs. The FGs are arranged in rows and columns with each FG being configured to receive tertiary and 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 FPGA tile, and provide input signals to the third set of input ports of the FGs. The IGs surround the FGs such that one IG is positioned at each end of each row and column. Each IG is coupled to the third set of routing conductors and configured to transfer signals from the third set of routing conductors to outside the first FPGA tile.

Tileable field-programmable gate array architecture

The present invention concerns configuration of a new category of integrated circuitry for adaptive computing. The various embodiments provide an executable information module for an adaptive computing engine (ACE) integrated circuit and may include configuration information, operand data, and may also include routing and power control information. The ACE IC comprises a plurality of heterogeneous computational elements coupled to an interconnection network. The plurality of heterogeneous computational elements include corresponding computational elements having fixed and differing architectures, such as fixed architectures for different functions such as memory, addition, multiplication, complex multiplication, subtraction, configuration, reconfiguration, control, input, output, and field programmability. In response to configuration information, the interconnection network is operative to configure the plurality of heterogeneous computational elements for a plurality of different functional modes.

Apparatus, method, system and executable module for configuration and operation of adaptive integrated circuitry having fixed, application specific computational elements

This paper introduces a new field-programmable architecture that is targeted at compute-intensive applications. These applications are important because of their use in the expanding multi-media markets in signal and data processing. We explain the design methodology, layout and implementation of the new architecture. A synthesis method has also been developed with which we have mapped several circuits to the new architecture. In this paper, we show that the invented architecture is more area-efficient than traditional FPGAs by a factor of more than 2.5 times.

Computational field programmable architecture

One or more columns of multi-function tiles are positioned between CLB tiles of the FPGA array. Each multi-function tile includes multiple function elements that share routing resources. In one embodiment, a multi-function tile includes a configurable, dual-ported RAM and a multiplier that share routing resources of the multi-function tile. The RAM includes first and second input ports coupled to first and second input data buses, respectively, and includes first and second output ports coupled to first and second output data buses, respectively. The multiplier includes first and second operand ports coupled to receive operands from the first and second input data buses, and in response thereto provides a product. In one embodiment, the most significant bits (MSBs) of the product are selectively provided to the first output data bus using bus multiplexer logic, and the least significant bits (LSBs) of the product are selectively provided to the second output data bus using bus multiplexer logic.

Method and apparatus for incorporating a multiplier into an FPGA

An improved, scalable CPLD device has a two-tiered hierarchical switch construct comprised of a Global Switch Matrix (GSM) and an even number of Segment Switch Matrices (SSM's) An even number of Super Logic Blocks (SLB's) are coupled to each SSM Each SSM and its SLB's define a segment that couples to the GSM Each SLB has a relatively large number of inputs (at least 80) and can generate product term signals (PT's) that are products of independent input terms provided from the SSM to the SLB inputs Some of the product terms generated within each SLB are dedicated to SLB-local controls Each SLB has at least 32 macrocells and at least 16 I/O pads which feedback to both to the local SSM and the global GSM 100 % intra-segment connectivity is assured within each segment so that each segment can function as an independent, mini-CPLD Each SSM has additional lines, dedicated for inter-segment (global) communications The large number of parallel inputs to each SLB ease implementation of 64-bit wide designs Symmetry within the design of each segment allow for more finely-granulated implementations such as for 32 or 16-bit wide designs

SCALABLE ARCHITECTURE FOR HIGH DENSITY CPLD's HAVING TWO-LEVEL HIERARCHY OF ROUTING RESOURCES

Field programmable gate arrays (FPGA's) may be structured in accordance with the disclosure to have a hierarchical general interconnect architecture in which: (1) reliance on single-length general interconnect lines is avoided; (2) the next greater length of general interconnect line is at least double-reach length (triple span); and (3) yet greater lengths of general interconnect line (eg, Deca-Reach Length, or 11-span) can feed signals into logic blocks indirectly through switching resources of the shorter length, general interconnect line rather than feeding such signals directly into the logic blocks through their own respective switching resources Additionally, the yet greater lengths of general interconnect line (eg, Deca-Reach Length) have a fewer number of signal tap points on them than the number of logic blocks spanned by such longer ones of the general interconnect lines Navigation limiting rules may be established to reduce the number of drive buffers needed for driving signals onto the longer ones of the general interconnect lines In one embodiment, there are no drive buffers for middle tap points of the longer ones of the general interconnect lines

Hierarchical general interconnect architecture for high density fpga's

Structures and techniques are provided for allowing one or more of the following actions to occur within a Complex Programmable Logic Device (CPLD): (1) Elective use of a fast, allocator-bypassing path (e.g., a fast 5-PT path) in combination with in-block simple or super-allocation; (2) Elective use of an OSM-bypassing path for signals that do not need pin-consistency; (3) Automatic re-routing of output enable signals that corresponding to output signals which are re-routed for pin-consistency purposes; (4) Global distribution of globally-usable output enable signals; (5) Elective use of two-stage steering to develop complex sum-of-clusters terms where fast path or simple allocation will not be sufficient; and (6) Use of unidirectional super-allocation with stage- 2 wrap-around in designs having about 24 or less macrocell units per logic block. Techniques are provided for concentrating the development of complex function signals (e.g., ≧80 PT's) within singular logic blocks so that the development of such complex function signals does not consume inter-block interconnect resources. One CPLD configuring method includes the machine-implemented steps-of first identifying middle-complexity functions that are achievable by combined simple or super-allocation based development in one logic block and fast-path completion in the same or a second logic block; and configuring the CPLD to realize one or more of the functions identified in the first identification step by simple or super-allocation based development in one logic block and fast-path completion in the same or a second logic block.

Enhanced CPLD macrocell module having selectable bypass of steering-based resource allocation and methods of use

A Variable Grain Architecture (VGA) is used for synthesizing from primitive building elements (CBE's) an appropriate amount of dynamic multiplexing capability for each given task. Unused ones of such Configurable Building Elements (CBE's) are reconfigured to carry out further logic functions in place of the dynamic multiplexing functions. Each CBE may be programmably configured to provide no more than a 2-to-1 dynamic multiplexer (2:1 DyMUX). The dynamically-selectable output of such a synthesized 2:1 DyMUX may then be output onto a shared interconnect line. Pairs of CBE's may be synthetically combined to efficiently define 4:1 DyMUX's with each such 4:1 multiplexer occupying a Configurable Building Block (CBB) structure. Pairs of CBB's may be synthetically combined to efficiently define 8:1 DyMUX's with each such synthesized 8:1 multiplexer occupying a vertically or horizontally-extending leg portion of an L-shaped, VGB structure (Variable Grain Block). The so-configured leg portion of the VGB may then output the signal selected by its 8:1 DyMUX onto a shared interconnect line that is drivable by the VGB leg. Pairs or quartets of VGB's may be synthetically combined to efficiently define higher order, N:1 DyMUX's.

Methods for configuring FPGA's having variable grain components for providing time-shared access to interconnect resources

Field programmable gate arrays (FPGA's) may be structured in accordance with the disclosure to have a register-intensive architecture that provides, for each of plural function-spawning LookUp Tables (e.g. a 4-input, base LUT's) within a logic block, a plurality of in-block accessible registers. A register-feeding multiplexer means may be provided for allowing each of the plural registers to equivalently capture and store a result signal output by the corresponding, base LUT of the plural registers. Registerable, primary and secondary feedthroughs may be provided for each base LUT so that locally-acquired input signals of the LUT may be fed-through to the corresponding, in-block registers for register-recovery purposes without fully consuming (wasting) the lookup resources of the associated, base LUT. A multi-stage, input switch matrix (ISM) may be further provided for acquiring and routing input signals from adjacent, block-interconnect lines (AIL's) and/or block-intra-connect lines (e.g., FB's) to the base LUT's and/or their respective, registerable feedthroughs. Techniques are disclosed for utilizing the many in-block registers and/or the registerable feedthroughs and/or the multi-stage ISM's for efficiently implementing various circuit designs by appropriately configuring such register-intensive FPGA's.

FPGA with register-intensive architecture

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Om P. Agrawal

Author Tools

Chat about Author