A system and method for verifying the correct behavior of instruction and data fetches and the order of instruction and data fetch resource modifications by a speculative and or out-of-order computer architecture under test is presented. An architectural model which models the high-level architectural requirements of the computer architecture under test, including instruction fetch resources and data fetch resources, executes test stimuli instructions in natural program order. A behavioral model, which models the high-level architectural requirements of the computer architecture, including instruction fetch resources and data fetch resources, executes the same test stimuli instructions, but according to the speculative and or out-of-order instruction execution behavior defined by the computer architecture under test. Modifications to instruction fetch resources and data fetch resources by the behavioral model are respectively recorded separately in a respective instruction fetch resource event queue and data fetch resource event queue. Upon detection of a fetch instruction event by the behavioral model, each instruction fetch resource event stored in the instruction fetch resource event queue which has a corresponding timestamp earlier than the timestamp of the detected fetch instruction event is applied to the architectural model in timestamp order. Separately, upon detection of a data access request event by the behavioral model, each data fetch resource event stored in the data fetch resource event queue which has a corresponding timestamp earlier than the timestamp of the detected data access event is applied to the architectural model in timestamp order.

Verification of instruction and data fetch resources in a functional model of a speculative out-of order computer system

A new reliability model is introduced for selecting the best software fault-tolerant (FT) design. This model uses a task graph technique that allows different candidate FT configurations to be analyzed based on the structure and organization of different distributed embedded systems. Reliability prediction with this approach can be useful for addressing system dependability issues (i.e., fault detection/recovery processes and steady-state availability) in addition to ascertaining fault coverage (i.e., the likelihood of missing and/or false faults). The results of analyzing three different Simplified Unmanned Vehicle System (SUVS) FT configurations are presented. This work is described within the framework of the Conservative and Do-best FT design policies and fits consistent with a software development model for real-time control systems that was introduced in earlier work by the authors.

Reliability prediction of distributed embedded fault-tolerant systems

UTARK (University of Texas at Arlington Real-time Kernel) is a real-time kernel designed to cope with the complexity of software for real-time embedded systems. The concepts behind the design of UTARK are described. Three major issues, i.e., communication, scheduling, and fault tolerance support, are discussed, along with a new development model for large, complex, distributed embedded real-time systems. >

UTARK: an object-based real-time kernel for distributed embedded systems

This paper presents an approach to developing Real-time Dependable Systems (RDSs) based on a real-time object model. A system development process can be divided into two phases, that is, Specification Phase and Construction Phase. In the Specification Phase, especially for an RDS, system requirements are decomposed into a group of Real-Time Objects (RTOs) and appropriate objects are identified by means of a decomposition scheme such as Multi-Dimensional Decomposition (MDD). In the Construction Phase, the identified objects are instantiated and combined. RTO.e, which is an extension of the RTO.k model proposed earlier by Kim and Kopetz (1994), plays the role of a connector and also that of a firewall between the two phases. In this paper, we present design tools that are required in developing RDSs. The tools provide a seamless system implementation method and an information base that can be utilized through the development process.

Real-time system design tools for RTO.e (real-time object.extended)

The paper presents an approach to developing real time dependable systems (RDSs) based on a real time object model. A process to develop an RDS is divided into two phases (specification phase and construction phase), and a real time object model, named RTO.e, plays the role of a connector as well as that of a fire wall between two phases. RTO.e, an extension of the RTO.k model proposed earlier by K.H. Kim and H. Kopetz (1994), embeds the Z specification language and the exception section. Discussions are focused on the concept of the two phased development process and a real time object identification procedure using the RTO.e specification. An IVS (intelligent vehicle system) prototype is under development to confirm the ideas and techniques investigated.

System development based on a real-time object model

The research approach presented focuses on the investigation of real-time distributed (RTD) systems development and simulation. The authors are developing a formalized simulation method for performance modeling and analysis of RTD systems. In more specific terms, a system model is defined as an abstraction of the RTD system, which consists of both a conceptual and physical model. The conceptual model controls activities which sense and control the dynamics of the functional description, while the physical model defines the structural architecture. The behavioral model is the visible part of the system which displays how the reactive and dynamic activities of the system are affected by different simulated environmental stresses. The authors investigate the modeling of discrete event systems in a distributed context, as well as problems of a nature related to the mapping of a simulation onto a parallel or distributed architecture. >

T.L. Bornejko

Papers

Simulation-based analysis for real-time systems development