We present combined temporal partitioning and design space exploration techniques for synthesizing behavioral specifications for run-time reconfigurable processors. Design space exploration involves selecting a design...
详细信息
We present combined temporal partitioning and design space exploration techniques for synthesizing behavioral specifications for run-time reconfigurable processors. Design space exploration involves selecting a design point for each task from a set of design points for that task to achieve latency minimization of partitioned solutions. We present an iterative search procedure that uses a core ILP (integer linear programming) technique, to obtain constraint satisfying solutions. The search procedure explores different regions of the design space while accomplishing combined partitioning and design space exploration. A case study of the DCT (discrete cosine transform) demonstrates the effectiveness of our approach.
The main objectives of built-in self test (BIST) are the design of test pattern generator circuits which achieve the highest fault coverage, require the shortest sequence of test vectors and utilize the minimum circui...
详细信息
The main objectives of built-in self test (BIST) are the design of test pattern generator circuits which achieve the highest fault coverage, require the shortest sequence of test vectors and utilize the minimum circuit area. This paper targets the problem of generating test patterns for stuck-at faults that induce compatibility relations between the primary inputs of the circuit under test. These compatibility relations can be used for designing counter-based test generator circuits with a reduced number of bits, thus requiring smaller testing time and smaller area. The proposed solution is based on an integer linear programming (ILP) formulation that builds on existing propositional satisfiability (SAT) models for test pattern generation. An ATPG tool for minimum test pattern generation for width compression (MTP-C) is described, which illustrates the practical applicability of our approach for a wide range of benchmark circuits.
Exploring lower bound of scheduling is an important problem in high-level synthesis, In this paper, we address the problem of computing lower bound on the general minimal resource interval scheduling problem, called n...
详细信息
Exploring lower bound of scheduling is an important problem in high-level synthesis, In this paper, we address the problem of computing lower bound on the general minimal resource interval scheduling problem, called n-n-MRIS, in which arbitrary component selections are allowed in stead of the traditional unicomponent selection. The problem of n-n-MRIS is proved to be strongly NP hard. An efficient ILP model and a surrogate relaxation technique are proposed to produce a lower bound for the n-n-MRIS problem.
In order to extract high levels of performance from modern parallel architectures, the effective management of deep memory hierarchies is very important. While architectural advances in caches help in better utilizati...
详细信息
In order to extract high levels of performance from modern parallel architectures, the effective management of deep memory hierarchies is very important. While architectural advances in caches help in better utilization of the memory hierarchy, compiler-directed locality enhancement techniques are also important. In this paper we propose a locality improvement technique that uses data space (array layout) transformations in contrast to most of the previous work based on iteration space (loop) transformations. In other words, rather than changing the order of loop iterations, our technique modifies the memory layouts of multi-dimensional arrays. In comparison with previous work on data transformations it brings two novelties. First, we formulate the problem on a special graph structure called the layout graph (LG) and use integer linear programming (ILP) methods to determine optimal layouts. Second, in addition to static layout detection, our approach also enables the compiler to determine optimal dynamic layouts; that is, the layouts that can be changed across loop nest boundaries. We believe that this is the first attempt to determine optimal dynamic memory layouts. We also present preliminary experimental results on the SGI Origin 2000 distributed shared memory multiprocessor. Our results so far are encouraging and indicate that the additional compilation time taken by the solver is tolerable.
An automatic placement system with emphasis on technology independent methodology and device matching consideration for analog layout design is presented. A novel optimization approach based on circuit partitioning, s...
详细信息
ISBN:
(纸本)078035012X
An automatic placement system with emphasis on technology independent methodology and device matching consideration for analog layout design is presented. A novel optimization approach based on circuit partitioning, simulated annealing and a branch-and-bound algorithm is proposed to solve the placement problem. The move set used to generate perturbations for annealing is capable of arriving at any topological placement. The branch-and-bound is modified to take circuit performance into consideration. Results of two silicon proven designs generated by the system demonstrate an 8X cycle time reduction as compared to a manual approach.
By using fuzzy linearprogramming (FLIP), tolerance intervals are used for calculating the availability of capital at each point in time. The main advantage, compared to the non-fuzzy problem formulation, is the fact ...
详细信息
By using fuzzy linearprogramming (FLIP), tolerance intervals are used for calculating the availability of capital at each point in time. The main advantage, compared to the non-fuzzy problem formulation, is the fact that the decision maker is not forced into a precise formulation for mathematical reasons. linear membership functions which monotonically increase or decrease in the tolerance interval are used because they can be handled quite easily. A numeric example is given.
Area and test time are two major overheads encountered during data path synthesis for BIST. This paper presents an attempt towards testability enhancement in data path BIST synthesis by considering two factors simulta...
详细信息
ISBN:
(纸本)0769501044
Area and test time are two major overheads encountered during data path synthesis for BIST. This paper presents an attempt towards testability enhancement in data path BIST synthesis by considering two factors simultaneously. It is achieved by incorporating two testability constraints in data path synthesis. Experimental results are presented to demonstrate the effectiveness of the proposed (data path) BIST synthesis approach.
Predicting the worst case execution time (WCET) of a real time program is a challenging task. Though much progress has been made in obtaining tighter timing predictions by using techniques that model the architectural...
详细信息
Predicting the worst case execution time (WCET) of a real time program is a challenging task. Though much progress has been made in obtaining tighter timing predictions by using techniques that model the architectural features of a machine, significant overestimations of WCET can still occur. Even with perfect architectural modeling, dependencies on data values can constrain the outcome of conditional branches and the corresponding set of paths that can be taken in a program. While value-dependent constraint information has been used in the past by some timing analyzers, it has typically been specified manually, which is both tedious and error prone. The paper describes efficient techniques for automatically detecting value-dependent constraints by a compiler and automatically exploiting these constraints within a timing analyzer. The result is tighter timing analysis predictions without requiring additional interaction with a user.
In this paper, we present a new method for the built-in self-testable data path synthesis based on integer linear programming (ILP). Our method performs system register assignment, built-in self-test (BIST) register a...
详细信息
ISBN:
(纸本)1581130929
In this paper, we present a new method for the built-in self-testable data path synthesis based on integer linear programming (ILP). Our method performs system register assignment, built-in self-test (BIST) register assignment, and interconnection assignment concurrently to yield optimal designs. Our experimental results show that our method successfully synthesizes BIST circuits for all six circuits experimented on. All the BIST circuits are better in area overhead than those generated by existing high-level BIST synthesis methods.
We present an automated temporal partitioning and loop transformation approach for developing dynamically reconfigurable designs starting from behavior level specifications. An integer linear programming (ILP) model i...
详细信息
We present an automated temporal partitioning and loop transformation approach for developing dynamically reconfigurable designs starting from behavior level specifications. An integer linear programming (ILP) model is formulated to achieve near-optimal latency designs. We, also present a loop restructuring method to achieve maximum throughput for a class of DSP applications. This restructuring transformation is performed on the temporally partitioned behavior and results in near-optimization of throughput. We discuss efficient memory mapping and address generation techniques for the synthesis of reconfigurable designs. A case study on the Joint Photographic Experts Group (JPEG) image compression algorithm demonstrates the effectiveness of our approach.
暂无评论