Robert A. Walker

Algorithmic and Register-Transfer Level Synthesis: The System Architect's Workbench

1. Introduction.- 1.1. Synthesis of Integrated Circuits.- 1.2 The System Architects Workbench.- 1.3 Contrasting Approaches to Synthesis.- 1.4. Historical Note.- 1.5. Overview of the Book.- 2. Design Representations and Synthesis.- 2.1 The Model of Design Representation.- 2.2. Behavioral Representations at the ALGORITHMIC Level.- 2.3. Behavioral and Structural Representations at the REGISTER-TRANSFER Level.- 2.4. Modeling ALGORITHMIC and RT Level Synthesis.- 2.6 Summary.- 3. Transformations.- 3.1. Vtbody Transformations.- 3.2. SELECT Transformations.- 3.3. Adding Processes To The Workbench.- 3.4. Process Creation.- 3.5. Pipestage Creation.- 3.6. Structural Transformations.- 3.7. Summary.- 4. Architectural Partitioning (APARTY).- 4.1. Architectural Partitioning.- 4.2. Previous Work: Clustering.- 4.3. Multi-Stage Clustering.- 4.4. Methodology.- 4.5. Guiding Other Synthesis Tools.- 4.6. A Partitioning Example.- 4.7. Summary.- 5. Control Step Scheduling (CSTEP).- 5.1. The Scheduling Problem.- 5.2. Related Work.- 5.3. The CSTEP Scheduling Approach.- 5.4. Scheduling Examples.- 5.5. Summary.- 6. Data Path Allocation (EMUCS).- 6.1. Other Data Path Allocators.- 6.2. EMUCS Overview.- 6.3. Initialization.- 6.4. Prebinding and Manual Binding.- 6.5. Automatic Binding.- 6.6. Post-Processing.- 6.7. Finish Up.- 6.9. Summary.- 7. Microprocessor Synthesis (SUGAR).- 7.1. Organization of SUGAR.- 7.2. Behavioral Transformations.- 7.3. Execution Unit Organization Analysis.- 7.4. Code Generation.- 7.5. Code Selection.- 7.6. Register and Bus Assignment.- 7.7. Phase Structure of SUGAR.- 7.8. Summary.- 8. Synthesis Results.- 8.1. Fifth Order Digital Elliptic Wave Filter.- 8.2. Kalman Filter.- 8.3. BTL310.- 8.4. MCS6502.- 8.5. MC68000.- 8.6. Summary.- 9. Correlating the Multilevel Design Representation (CORAL).- 9.1 Linking Design Representations.- 9.2 Applications.- 9.3 Summary.- 10. Observations and Future Work.- 10.1. Are The Two Synthesis Paths Different?.- 10.2. You Need More Than Synthesis.- 10.3. Algorithmic Level Synthesis.- 10.4. Logic Synthesis, Module Generation and Physical Design.- 10.5. Design Languages.- 10.6. Summary.- References.

Introduction to the scheduling problem

Scheduling-a central task in high-level synthesis-involves determining the execution order of operations in a behavioral description. After introducing the scheduling problem, this paper describes four scheduling algorithms commonly used to solve it. >

Behavioral transformation for algorithmic level IC design

An attempt was made to define the algorithmic level of design (also known as the behavioral level) and to provide the designer with the means to explore various design issues. Within the framework of the System Architects Workbench, a new set of behavioral and structural transformations was developed to allow the interactive exploration of algorithmic-level design alternatives. A description is given of these transformations, and a set of examples is presented both to demonstrate the application of the transformations and to further illustrate their effects. >

A Model of Design Representation and Synthesis

To represent the increasingly complex designs being produced today, we have developed 1 a unified model of design representation that uses three hierarchical, non-isomorphic domains of description that can be coordinated to represent the entire design. Each of these domains contains multiple levels of abstraction; both the domains and the levels are described in detail in this paper. We then show how this model of design representation can be used as a model of design synthesis. It is hoped that this work will lead to a better understanding of design representation and its relationship to the synthesis process.

A solution methodology for exact design space exploration in a three-dimensional design space

This paper describes an exact solution methodology, implemented in Rensselaers Voyager design space exploration system, for solving the scheduling problem in a three-dimensional (3-D) design space: the usual two-dimensional (2-D) design space (which trades off area and schedule length), plus a third dimension representing clock length. Unlike design space exploration methodologies which rely on bounds or estimates, this methodology is guaranteed to find the globally optimal solution to a 3-D scheduling problem. Furthermore, this methodology efficiently prunes the search space, eliminating provably inferior design points through the following: 1) a careful selection of candidate clock lengths and 2) tight bounds on the number of functional units or on the schedule length. Both chaining and multicycle operations are supported.

Computing lower bounds on functional units before scheduling

The authors present a new polynomial-time algorithm for computing lower bounds on the number of functional units (FUs) of each type required to schedule a data flow graph in a specified number of control steps. A formal approach is presented that is guaranteed to find the tightest possible bounds that can be found by relaxing either the precedence constraints or integrality constraints on the scheduling problem. This tight, yet fairly efficient, bounding method can be used to estimate FU area, to generate resource constraints for reducing the search space, or in conjunction with exact techniques for efficient optimal design space exploration.

Implementing associative processing: rethinking earlier architectural decisions

This paper describes an initial design of an associative processor for implementation using field-programmable logic devices (FPLDs). The processor is based loosely on earlier work on the STARAN computer, but updated to reflect modern design practices. We also draw on a large body of research at Kent State on the ASC and MASC models of associative processing, and take advantage of an existing compiler for the ASC model. The resulting design consists of an associative array of 8-bit RISC Processing Elements (PEs), operating in byte-serial fashion under the control of an Instruction Stream (IS) Control Unit that can execute assembly language code produced by a machine-specific back-end compiler.

Efficient optimal design space characterization methodologies

One of the primary advantages of a high-level synthesis system is its ability to explore the design space. This paper presents several methodologies for design space exploration that compute all optimal tradeoff points for the combined problem of scheduling, clock-length determination, and module selection. We discuss how each methodology takes advantage of the structure within the design space itself as well as the structure of, and interactions among, each of the three subproblems. (CAD)

An exact methodology for scheduling in a 3D design space

Abstract: This paper describes an exact solution methodology, implemented in Rensselaers Voyager design space exploration system, for solving the scheduling problem in a 3-dimensional (3D) design space: the usual 2D design space (which trades off area and schedule length), plus a third dimension representing clock length. Unlike design space exploration methodologies which rely on bounds or estimates, this methodology is guaranteed to find the globally optimal solution to the 3D scheduling problem. Furthermore, this methodology efficiently prunes the search space, eliminating provably inferior design points through: a careful selection of candidate clock lengths; and tight bounds on the number of functional units of each type or on the schedule length.

Interrupt Triggered Software Prefetching for Embedded CPU Instruction Cache

In embedded systems, handling time-critical real-time tasks is a challenge. The software may not only multi-task to improve response time, but also support events and interrupts, forcing the system to balance multiple priorities. Further, pre-emptive task switching hampers efficient interrupt processing, leading to instruction cache misses. This research provides a methodology for using software prefetch instructions in the interrupt handler to improve efficiency, thus making instruction caches more attractive in a real-time environment. The benefits of this technique are illustrated on an ARM processor running application benchmarks with different cache configurations and interrupt arrival patterns.