Data processing: software development – installation – and managem – Software program development tool – Programming language
Reexamination Certificate
2002-04-23
2004-05-04
Dam, Tuan (Department: 2122)
Data processing: software development, installation, and managem
Software program development tool
Programming language
C717S114000, C717S149000, C717S150000
Reexamination Certificate
active
06732354
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates, in general, to software and code languages used in programming hardware circuits, and more specifically, to a method, system, and language command or statement structure for defining adaptive computational units in reconfigurable integrated circuitry.
BACKGROUND OF THE INVENTION
The first related application discloses a new form or type of integrated circuitry which effectively and efficiently combines and maximizes the various advantages of processors, application specific integrated circuits (“ASICs”), and field programmable gate arrays (“FPGAs”), while minimizing potential disadvantages. The first related application illustrates a new form or type of integrated circuit (“IC”), referred to as an adaptive computing engine (“ACE”), which provides the programming flexibility of a processor, the post-fabrication flexibility of FPGAs, and the high speed and high utilization factors of an ASIC. This ACE integrated circuitry is readily reconfigurable, is capable of having corresponding, multiple modes of operation, and further minimizes power consumption while increasing performance, with particular suitability for low power applications, such as for use in hand-held and other battery-powered devices.
Configuration information (or, equivalently, adaptation information) is required to generate, in advance or in real-time (or potentially at a slower rate), the adaptations (configurations and reconfigurations) which provide and create one or more operating modes for the ACE circuit, such as wireless communication, radio reception, personal digital assistance (“PDA”), MP3 music playing, or any other desired functions.
The second related application discloses a preferred system embodiment that includes an ACE integrated circuit coupled with one or more sets of configuration information. This configuration (adaptation) information is required to generate, in advance or in real-time (or potentially at a slower rate), the configurations and reconfigurations which provide and create one or more operating modes for the ACE circuit, such as wireless communication, radio reception, personal digital assistance (“PDA”), MP3 or MP4 music playing, or any other desired functions. Various methods, apparatuses and systems are also illustrated in the second related application for generating and providing configuration information for an ACE integrated circuit, for determining ACE reconfiguration capacity or capability, for providing secure and authorized configurations, and for providing appropriate monitoring of configuration and content usage.
As disclosed in the first and second related applications, the adaptive computing engine (“ACE”) circuit of the present invention, for adaptive or reconfigurable computing, includes a plurality of differing, heterogeneous computational elements coupled to an interconnection network (rather than the same, homogeneous repeating and arrayed units of FPGAs). 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, synchronization, queuing, sampling, configuration, reconfiguration, control, input, output, routing, and field programmability. In response to configuration information, the interconnection network is operative, in advance, in real-time or potentially slower, 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. In turn, this configuration and reconfiguration of heterogeneous computational elements, forming various computational units and adaptive matrices, generates the selected, higher-level operating mode of the ACE integrated circuit, for the performance of a wide variety of tasks.
This adaptability or reconfigurability (with adaptation and configuration used interchangeably and equivalently herein) of the ACE circuitry is based upon, among other things, determining the optimal type, number, and sequence of computational elements required to perform a given task. As indicated above, such adaptation or configuration, as used herein, refers to changing or modifying ACE functionality, from one functional mode to another, in general, for performing a task within a specific operating mode, or for changing operating modes.
The algorithm of the task, preferably, is expressed through “data flow graphs” (“DFGs”), which schematically depict inputs, outputs and the computational elements needed for a given operation. Software engineers frequently use data flow graphs to guide the programming of the algorithms, particularly for digital signal processing (“DSP”) applications. Such DFGs typically have one of two forms, either of which are applicable to the present invention: (1) representing the flow of data through a system where data streams from one module (e.g., a filter) to another module; and (2) representing a computation as a combinational flow of data through a set of operators from inputs to outputs.
A dilemma arises when developing programs for adaptive or reconfigurable computing applications, as currently there are not any adequate or sufficient methodologies or programming languages expressly designed for such adaptive computing, other than the present invention. High-level programming languages, such as C++ or Java, are widely used, well known, and easily maintainable. The languages were developed to accommodate a variety of applications, many of which are platform-independent, but all of which are fundamentally based upon compiling a sequence of instructions ultimately fed into processor, microprocessor, or DSP. The program code is designed to run sequentially, generally in response to a user-initiated event. However the languages have limited capabilities of expressing the concurrency of computing operations, and other features, which may be significant in adaptive computing applications.
Assembly languages, at the other extreme, tightly control data flow through hardware elements such as the logic gates, registers and random access memory (RAM) of a specific processor, and efficiently direct resource usage. By their very nature, however, assembly languages are extremely verbose and detailed, requiring the programmer to specify exactly when and where every operation is to be performed. Consequently, programming in an assembly language is extraordinarily labor-intensive, expensive, and difficult to learn. In addition, as languages designed specifically for programming a processor (i.e., fixed processor architecture), assembly languages have limited, if any, applicability to or utility for adaptive computing applications.
In between these extremes, and also very different than a high-level language, are hardware description languages (HDLs), that allow a designer to specify the behavior of a hardware system as a collection of components described at the structural or behavioral level. These languages may allow explicit parallelism, but require the designer to manage such parallelism in great detail. In addition, like assembly languages, HDLs require the programmer to specify exactly when and where every operation is to be performed.
As a consequence, a need remains for a method and system of providing programmability of adaptive computing architectures. A need also remains for a comparatively high-level language that is syntactically similar to widely used and well known languages like C++, for ready acceptance within the engineering and computing fields, but that also contains specialized constructs for an adaptive computing environment and for maximizing the performance of an ACE integrated circuit or other adaptive computing architecture.
SUMMARY OF THE INVENTION
The present invention is a system, tangible medium storing computer re
Ebeling W. H. Carl
Hogenauer Eugene B.
Dam Tuan
Dykema Gossett PLLC
Gamburd Nancy R.
QuickSilver Technology, Inc.
Rutten J. Derek
LandOfFree
Method, system and software for programming reconfigurable... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method, system and software for programming reconfigurable..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method, system and software for programming reconfigurable... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3195512