This paper focuses on the resource sharing problem when performing high-level synthesis. It argues that the conventionally accepted synthesis flow when resource sharing is done after scheduling is sub-optimal because it cannot account for timing penalties from resource merging. The paper describes a competitive approach when resource sharing and scheduling are performed simultaneously. It provides a quantitative evaluation of both approaches and shows that performing sharing during scheduling wins over the conventional approach in terms of quality of results.

This paper proposes an enhanced scheduling approach for high-level synthesis, which relies on a multi-cycle behavioral timing analysis step that is performed before and during scheduling. The goal of this analysis is to accurately evaluate the criticality of operations and determine the most suitable candidate resources to implement them. The efficiency of the approach is confirmed by testing it on industrial examples, where it achieves, on average, 9% area savings after logic synthesis.

This paper describes an approach to pipelining in high-level synthesis that modifies the control/data flow graph before and after scheduling. This enables the direct re-use of a pre-existing, timing- and area-aware non-pipelined simultaneous scheduler and binder. Such an approach ensures that the RTL output can be synthesized within the given timing and area constraints. Results from real industrial designs show the effectiveness of this approach in improving Pareto optimality with respect to area, delay and power.

The widespread acceptance of High-level synthesis as a mainstream tool mostly depends on its tight integration with the following RTL-to-GDSII design flow. A key aspect is the handling of so-called Engineering Change Orders (ECOs), i.e. minor changes required to fix small functional bugs or meet performance requirements late in the design cycle. Traditional high-level synthesis has attempted to optimize at best the output logic. However, in the ECO scenario the goal is to implement the required change with as few modifications as possible to the RTL, logic netlist, placed netlist and layout. In this paper we show how, by judiciously changing the internal databases used by the tool to match as much as possible the original design, one can achieve minimal impact and implement ECOs in truly incremental mode, while full-blow re-synthesis would lead to massive unnecessary downstream changes. The tool essentially matches source constructs between the original and the ECO design, and copies as many synthesis decisions as possible from the original design to the ECO design.

Hardware synthesis is the process by which system-level, Register Transfer (RT)-level, or behavioral descriptions can be turned into real implementations, in terms of logic gates. Scheduling is one of the most time-consuming steps in the overall design flow, and may become much more complex when performing hardware synthesis from high-level specifications. Exploiting a single scheduling strategy on very large designs is often reductive and potentially inadequate. Furthermore, finding the “best” single candidate among all possible scheduling algorithms is practically infeasible. In this article we introduce a hybrid scheduling approach that is a preliminary step towards a comprehensive solution not yet provided by industrial or by academic solutions. Our method relies on an abstract symbolic representation of data flow nodes (operations) bound to control flow paths: it produces a more realistic lower bound during the prescheduling resource estimation step and speeds up slower but accurate heuristic scheduling techniques, thus achieving a globally improved result.

Asynchronous implementation techniques, which measure logic delays at runtime and activate registers accordingly, are inherently more robust than their synchronous counterparts, which estimate worst case delays at design time and constrain the clock cycle accordingly. Desynchronization is a new paradigm to automate the design of asynchronous circuits from synchronous specifications, thus, permitting widespread adoption of asynchronicity without requiring special design skills or tools. In this paper, different protocols for desynchronization are first studied, and their correctness is formally proven using techniques originally developed for distributed deployment of synchronous language specifications. A taxonomy of existing protocols for asynchronous latch controllers, covering, in particular, the four-phase handshake protocols devised in the literature for micropipelines, is also provided. A new controller that exhibits provably maximal concurrency is then proposed, and the performance of desynchronized circuits is analyzed with respect to the original synchronous optimized implementation. Finally, this paper proves the feasibility and effectiveness of the proposed approach by showing its application to a set of real designs, including a complete implementation of the DLX microprocessor architecture

We describe a system as a set of communicating concurrent programs. Quasi-static scheduling compiles the concurrent programs into a sequential one. It uses a Petri net as an intermediate model of the system. However, Petri nets generated from many interesting applications are not schedulable. In this paper, we show the underlying mechanism which causes unschedulability in terms of the structure of a Petri net. We introduce a Petri net structural property and prove unschedulability if the property holds. We propose a linear programming based algorithm to check the property, and prove the algorithm is valid. Our approach prove unschedulability typically within a second for Petri nets generated from industrial JPEG and MPEG codecs, while the scheduler fails to terminate within 24 hours.

We discuss a new synthesis flow, which offers the ability to do easy delay testing almost free in terms of its impact on speed and area compared to corresponding implementations with standard cells. The methodology uses matched delays in pre-charged PLAs and bundled routing to produce a completion signal, which is guaranteed to lie on all critical paths. We give a nondelay testing method for ensuring matched delays are correct, i.e. that all completion signals arrive after their corresponding data signals. The design margins of the matched delays can be small since they are internal to the PLAs, which are regular structures and therefore more predictable.

A reactive system must process inputs from the environment at the speed and with the delay dictated by the environment. The synthesis of reactive software from a modular concurrent specification model generates a set of concurrent tasks coordinated by an operating system. This paper presents a synthesis approach for reactive software that is aimed at minimizing the overhead introduced by the operating system and the interaction among the concurrent tasks. A formal model based on Petri nets is used to synthesize the tasks and verify the correctness of their composition. A practical application of the approach is illustrated by means of a real-life industrial example, which shows the significant impact of the approach on the performance of the system.

Noise affects circuit operation by varying circuit delays and causing latches to capture incorrect values. Conventional noise analysis techniques can detect some of such noise faults, but accurate analysis requires a careful examination of timing and functional properties of the circuit. In this paper, a method of characterizing correlation of signal transitions in nets by considering in a unified way both timing and functionality of the signals is proposed. An analysis procedure to eliminate noise faults that cannot actually happen when such correlations are considered is described. The timed-Boolean logic is used to characterize signal transitions in a time interval, and correlations are checked by solving Boolean satisfiability (SAT) between aggressor and victim transitions under the min-max delay model for gates. The method is applicable for checking noise faults at a single net, on a path, or in a cone of logic. The proposed technique is scalable as it keeps the size of Boolean formulation linear to the size of the modeled circuit. It has been applied on a set of large circuits, eliminating up to 50% of noise delay faults reported by a conventional noise-analysis method.

The desynchronization approach combines a traditional synchronous specification style with a robust asynchronous implementation model. The main contribution of this paper is the description of two optimizations that decrease the overhead of desynchronization. First, we investigate the use of clustering to vary the granularity of desynchronization. Second, by applying temporal analysis on a formal execution model of the desynchronized design, we uncover significant amounts of timing slack. These methods are successfully applied to industrial RTL designs.

This paper presents a methodology to derive asynchronous circuits from optimized synchronous circuits by replacing the clock distribution tree by a handshaking network. A case study shows the applicability of the method and the potential benefits of de-synchronizing synchronous circuits.

Noise affects circuit operation by increasing gate delays and causing latches to capture incorrect values. Noise analysis techniques can detect some of such noise faults, but accurate analysis requires a careful examination of timing and functional properties of the circuit. This paper proposes a method to check the "true" noise impact on path delay. It uses four-variable Boolean logic to characterize signal transitions in a time interval, and formulates Boolean satisfiability between aggressors and a victim under the min-max delay model for gates. The proposed technique is scalable as it keeps the size of Boolean formulation linear to the size of the modeled circuit. By applying it to a set of large circuits, it has eliminated up to 50% of noise delay faults reported by conventional noise analysis method.

This paper proposes a technique for creating a combinational logic network with an output that signals when all other outputs have stabilized. The method is based on dual-rail encoding, and guarantees low timing overhead and reasonable area and power overhead. We discuss various scenarios in which completion detection can be used to measure the delay of a synchronous circuit at fabrication time or at run time, and of an asynchronous circuit at run time. We conclude by showing, on a large set of benchmarks, the effectiveness of the proposed technique.

Noise a#ects circuit operation by increasing gate delays and causing latches to capture incorrect values. This paper proposes a method of characterizing correlation of signal transitions in multiple nets by considering both timing and functionality of the signals, and uses it in an analysis procedure to eliminate noise faults that cannot actually happen when such correlations are considered. It uses four-variable Boolean logic to characterize signal transitions in a time interval, and formulates Boolean satisfiability between aggressors and a victim under the min-max delay model for gates. The technique has been successfully applied to commercial ASIC designs and has eliminated up to 35% of delay noise faults reported by a state-of-the-art noise analysis tool.

In this paper we describe a technology mapping technique based on the logical effort theory [13]. First, we appropriately characterize a given standard cell library and extract from it a set of cell classes. Each cell-class is assigned a constant-delay model and corresponding load-bounds, which define the conditions of the delay model's validity. Next, we perform technology mapping using the classes determined in the first step. We propose several effective area-optimization heuristics which allow us to apply our algorithm directly to general graphs. Experimental results show that our gain-based mapping algorithm achieves reduced delay with less area, compared to the mapper in SIS [15]. By adjusting the constant delay model associated with each class, we determine the area-delay trade-off curve. We achieve the best area-delay trade-off using a design-specific constant delay models.

The roadblock to wide acceptance of asynchronous methodology is poor CAD support. Current asynchronous design tools require a significant re-education of designers, and their features are far behind synchronous commercial tools. This paper considers a particular subclass of asynchronous circuits (Null Convention Logic or NCL) and suggests a design flow that is based entirely on commercial CAD tools. This new design flow shows a significant area improvement over known flows based on NCL.

This paper presents a design flow for timed asynchronous circuits. It introduces lazy transitions systems as a new computational model to represent the timing information required for synthesis. The notion of laziness explicitly distinguishes between the enabling and the firing of an event in a transition system. Lazy transition systems can be effectively used to model the behavior of asynchronous circuits in which relative timing assumptions can be made on the occurrence of events. These assumptions can be derived from the information known a priori about the delay of the environment and the timing characteristics of the gates that will implement the circuit. The paper presents the necessary conditions to generate circuits and a synthesis algorithm that exploits the timing assumptions for optimization. It also proposes a method for back-annotation that derives a set of sufficient timing constraints that guarantee the correctness of the circuit.

The problem of optimal software synthesis for concurrent processes to be implemented on a single processor is addressed. The approach calls for the representation of the concurrent processes with Petri nets that give a theoretical foundation for the scheduling algorithm that sequentializes the concurrent processes and for the code generation step. The approach maximizes the amount of static scheduling to reduce the need of context switch and operating system intervention. Experimental results show the potential of our method to reduce software design time and errors.

A method for automating the synthesis of asynchronous control circuits from high level (CSP-like) and/or partial STG (involving only functionally critical events) specifications is presented.The method solves two key subtasks in this new, more flexible, design flow: handshake expansion, i.e. inserting reset events with maximum concurrency, and event reshuffling under interface and concurrency constraints, by means of concurrency reduction.In doing so, the algorithm optimizes the circuit both for size and performance.Experimental results show a significant increase in the solution space explored when compared to existing CSP-based or STG-based synthesis tools.

Deep submicron technology calls for new design techniques, in which wire and gate delays are accounted to have equal or nearly equal effect on circuit behaviour. Asynchronous speed-independent (SI) circuits, whose behaviour is only robust to gate delay variations, may be too optimistic. On the other hand, building circuits totally delay-insensitive (DI), for both gates and wires, is impractical. The paper presents an approach for automated synthesis of globally DI and locally SI circuits. It is based on order relaxation, a simple graphical transformation of a circuit's behavioural specification, for which the Signal Transition Graph, an interpreted Petri net, is used. The method is successfully tested on a set of benchmarks and a realistic design example. It proves effective showing average cost of DI interfacing at about 40% for area and 20% for speed.

Logic decomposition is a well-known problem in logic synthesis, but it poses new challenges when targeted to speed-independent circuits. The decomposition of a gate into smaller gates must preserve not only the functional correctness of a circuit but also speed independence, i.e., hazard freedom under unbounded gate delays. This paper presents a new method for logic decomposition of speed-independent circuits that solves the problem in two major steps: (1) logic decomposition of complex gates and (2) insertion of new signals that preserve hazard freedom. The method is shown to be more general than previous approaches and its effectiveness is evaluated by experiments on a set of benchmarks.

This paper presents a new technique for decomposition and technology mapping of speed-independent circuits. An initial circuit implementation is obtained in the form of a netlist of complex gates, which may not be available in the design library. The proposed method iteratively performs Boolean decomposition of each such gate F into a two-input combinational or sequential gate G available in the library and two gates H/sub 1/ and H/sub 2/ simpler than F, while preserving the original behavior and speed-independence of the circuit. To extract functions for H/sub 1/ and H/sub 2/ the method uses Boolean relations as opposed to the less powerful algebraic factorization approach used in previous methods. After logic decomposition, the overall library matching and optimization is carried out. Logic resynthesis, performed after speed-independent signal insertion for H/sub 1/ and H/sub 2/, allows for sharing of decomposed logic. Overall, this method is more general than the existing techniques based on restricted decomposition architectures, and thereby leads to better results in technology mapping.

Interfaces, by nature, are often asynchronous since they serve for connecting multiple distributed mod ules/agents without common clock. However, the most recent developments in the the ory of asynchronous design in the areas of specifications, mo dels, analysis, verification, synthesis, technology mapping, timing optimization and performanc e analysis are not widely known and r arely accepted by industry.

This paper introduces bzy Transitions Systems &zTSs).The notion of laziness exDlicitlv distinguishes behveen the enabling and the firing of an e;ent in"a transition system.LzTSS can be effectively used to model the behavior of asynchronous circuits in whicfi relative timing assumptions cm-be made on the occurrence of events.These assumptions can be derived from the information known a priori about fie de]ay of fie environment and the timing characteristics of the gates that will implement the circuit.The paper presents necessary conditions to synthesize circuits with a correct behavior under the given timing assumr3tions.Preliminary results show that significant area and performance improvements can be obtained by exploiting the extra "don't care" space implicitly provided by the Iazmess of the events.

Asynchronous circuits operate correctly only under timing assumptions. Hence testing those circuits for delay faults is crucial. Previous work has shown that full-scan delay-fault testing of asynchronous circuits is feasible. In this work, we tackle the problem of partial-scan testing, which requires test-pattern generation on a sequential circuit. We show how this problem can be effectively reduced to a classical problem of stuck-at test-pattern generation for a related combinational circuit. The reduction is done in three steps. The first step reduces testing of an asynchronous sequential circuit, by using a partial-scan approach, to testing an object called an asynchronous net, in which feedback is allowed only inside asynchronous memory elements. We then decompose the problem of testing asynchronous nets into that of initializing memory elements (the second step), followed by robust path delay fault testing (the third step). We provide effective procedures to solve both the initialization and the test-pattern generation problem. The technique is complete, automated, and requires only partial scan of some memory element outputs.

This paper develops a theoretical framework for the hazard-free gate-level implementation of speed-independent circuits specified by event-based models, such as signal transition graphs (for processes with AND causality and input choice) or their extension, called change diagrams (which allow OR-causality). It presents sufficient conditions, called the generalized monotonous cover requirements, for a hazard-free circuit to be built within a standard implementation structure. This structure consists of two-level simple-gate combinational logic and a row of latches, either a C-element or an RS-latch. A set of semantic-preserving transformations is defined that can be applied to an original behavioral description of the circuit so as to produce its specification in the form that satisfies the monotonous cover requirement. The transformations are applied at the event-based representation level (to avoid state explosion) and proved to be effective. The main result of the paper is therefore twofold: 1) the proof that any speed-independent behavior can be implemented at the gate level without hazards and 2) an efficient method for constructing such an implementation. Experimental results show that the proposed method compares very favorably, in area and performance, to the previously known techniques.

Asynchronous circuits can be modeled as concurrent systems in which events are interpreted as signal transitions. The synthesis of concurrent systems implies the analysis of a vast state space that often requires computationally expensive methods. This work presents new methods for the synthesis of speed-independent circuits from a new perspective, overcoming both the analysis and computation complexity bottlenecks. The circuits are specified by free-choice signal transition graphs (STGs), a subclass of interpreted Petri nets. The synthesis approach is divided into the following steps: correctness, binary coding, implementability conditions, and logic synthesis. Each step is efficiently implemented by applying a set of structural techniques that analyze STGs without explicitly enumerating the underlying state space. Experimental results show that circuits can be generated from specifications that exceed in several orders of magnitude the largest STGs ever synthesized-with over 10/sup 27/ states. Computation times are also dramatically reduced. Nevertheless, the quality of results does not suffer from the use of structural techniques.

Presents a new technique for the decomposition and technology mapping of speed-independent circuits. An initial circuit implementation is obtained in the form of a netlist of complex gates, which may not be available in the design library. The proposed method iteratively performs Boolean decomposition of each such gate F into a two-input combinational or sequential gate G, which is available in the library, and two gates H/sub 1/ and H/sub 2/, which are simpler than F, while preserving the original behavior and speed-independence of the circuit. To extract functions for H/sub 1/ and H/sub 2/, the method uses Boolean relations, as opposed to the less powerful algebraic factorization approach used in previous methods. After logic decomposition, overall library matching and optimization is carried out. Logic resynthesis, performed after speed-independent signal insertion for H/sub 1/ and H/sub 2/, allows for the sharing of decomposed logic. Overall, this method is more general than existing techniques based on restricted decomposition architectures, and thereby leads to better results in technology mapping.

Asynchronous circuits operate correctly only under timing assumptions. Hence testing those circuits for delay faults is crucial. The paper describes a three step method to detect possible delay faults in a sequential asynchronous circuit. The delays that are to be tested must be provided by the synthesis system. By using this information a set of paths in the circuit that must be tested is identified (step 1). For these paths the circuit is made acyclic by inserting at least one scan latch in every cycle (step 2). Then test patterns are generated for these paths (step 3). These test patterns consist of setup and initialization vectors and the final test vector. We provide effective procedures to solve both the initialization and the test pattern generation problem. The latter problem is solved by reduction to a classical problem of stuck-at test pattern generation for a related combinational circuit. Finally, a heuristic is proposed to determine which state variables must become part of a scan chain, or for which input variables the positive and negative phase must be driven independently in test mode. Experimental results shows that a high level of path delay fault testability can be achieved with partial scan.

State assignment problems still need satisfactory solutions to make asynchronous circuit synthesis more practical. A well-known example of such a problem is that of complete state coding (CSC), which happens when a pair of different states in a specification has the same binary encoding. A standard way to approach state coding conflicts is to insert new state signals into the original specification in such a way that the original behavior remains intact. This paper proposes a method which improves over existing approaches by coupling generality, optimality, and efficiency. The method is based on the use of a class of "ground objects", called regions, that play the role of a bridge between state-based specifications (transition systems, TS's) and event-based specifications (signal transition graphs, STG's), We need to deal with both types of specification because designers usually prefer a timing diagram-like notation, such as STG, while optimization and cost analysis work better at the state level. A region in a transition system is a set of states that corresponds to a place in an STG (or the underlying Petri net). Regions are tightly connected with a set of properties that are to be preserved across the state encoding process, namely, 1) trace equivalence between the original and the encoded specification, and 2) implementability as a speed-independent circuit. We will build on a theoretical body of work that has shown the significance of regions for such property-preserving transformations, and describe a set of algorithms aimed at efficiently solving the encoding problem. The algorithms have been implemented in a software tool called petrify. Unlike many existing tools, petrify represents the encoded specification as an STG. This significantly improves the readability of the result (compared to a state-based description in which concurrency is represented implicitly by interleaving), and allows the designer to be more closely involved in the synthesis process. The efficiency of the method is demonstrated on a number of "difficult" examples.

This paper proposes a state encoding method for asynchronous circuits based on the theory of regions. A region in a Transition System is a set of states that “behave uniformly” with respect to a given transition (value change of an observable signal), and is analogue to a place in a Petri net. Regions are tightly connected with a set of properties that must be preserved across the state encoding process, namely: (1) trace equivalence between the original and the encoded specification, and (2) implementability as a speed-independent circuit. We build on a theoretical body of work that has shown the significance of regions for such property-preserving transformations, and describe a set of algorithms aimed at efficiently solving the encoding problem. The algorithms have been implemented in a software tool called petrify. Unlike many existing tools, petrify represents the encoded specification as an STG, and thus allows the designer to be more closely involved in the synthesis process. The efficiency of the method is demonstrated on a number of “difficult” examples.

No abstract available.

Existing methods for synthesis of speedindependent circuits under unbounded delay model have difficulties in combining the generality of formal approach with the practicality of the implementation architectures used at the logic level.This paper presents a characteristic property of the state graph specification, called Monotonous Cover requirement, implying its hazard-free implementation within the standard structure of a two-level SOP logic and a row of latches.The overall synthesis procedure ensures satisfiability of this condition by applying the generalised state assignment approach.