A disciplined approach to the development of platform architectures

Abstract Silicon capability has enabled the embedding of an entire system on a single silicon die. These devices are known as systems-on-a-chip. Currently, the design of these devices is undisciplined, expensive, and risky. One way of amortizing the cost and ameliorating this design risk is to make a single integrated circuit serve multiple applications, and the natural way of enabling this is through end-user programmability. The aim of the MESCAL project, which is the subject of this paper, is to introduce a disciplined approach to producing reusable architectural platforms that can be easily programmed to meet a variety of applications. (MESCAL stands for Modern Embedded Systems, Compilers, Architectures, and Languages.)

[1]  Heinrich Meyr,et al.  LISA—machine description language for cycle-accurate models of programmable DSP architectures , 1999, DAC '99.

[2]  Sharad Malik,et al.  Handling irregular ILP within conventional VLIW schedulers using artificial resource constraints , 2000, CASES '00.

[3]  Sharad Malik,et al.  Retargetable static timing analysis for embedded software , 2001, International Symposium on System Synthesis (IEEE Cat. No.01EX526).

[4]  Nikil D. Dutt,et al.  EXPRESSION: a language for architecture exploration through compiler/simulator retargetability , 1999, Design, Automation and Test in Europe Conference and Exhibition, 1999. Proceedings (Cat. No. PR00078).

[5]  Susan J. Eggers,et al.  The Marion system for retargetable instruction scheduling , 1991, PLDI '91.

[6]  Stan Y. Liao,et al.  Code generation and optimization for embedded digital signal processors , 1996 .

[7]  Gert Goossens,et al.  Chess: retargetable code generation for embedded DSP processors , 1994, Code Generation for Embedded Processors.

[8]  Edward A. Lee,et al.  Overview of the Ptolemy project , 2001 .

[9]  Chuck Siska,et al.  A processor description language supporting retargetable multi-pipeline DSP program development tools , 1998, Proceedings. 11th International Symposium on System Synthesis (Cat. No.98EX210).

[10]  G. D. La Hei,et al.  TriMedia CPU64 design space exploration , 1999, Proceedings 1999 IEEE International Conference on Computer Design: VLSI in Computers and Processors (Cat. No.99CB37040).

[11]  Evert-Jan D. Pol,et al.  PRMDL: a machine description language for clustered VLIW architectures , 2001, Proceedings Design, Automation and Test in Europe. Conference and Exhibition 2001.

[12]  Doug Burger,et al.  Measuring Experimental Error in Microprocessor Simulation , 2001, ISCA 2001.

[13]  Gert Goossens,et al.  Code Generation for Embedded Processors , 1995 .

[14]  Srinivas Devadas,et al.  Instruction selection, resource allocation, and scheduling in the AVIV retargetable code generator , 1998, Proceedings 1998 Design and Automation Conference. 35th DAC. (Cat. No.98CH36175).

[15]  Sharad Malik,et al.  Using the IMPACT VLIW compiler framework to implement a compiler for a fixed point DSP , 2001 .

[16]  S. Devadas,et al.  ISDL: An Instruction Set Description Language For Retargetability , 1997, Proceedings of the 34th Design Automation Conference.

[17]  John Paul Shen,et al.  Calibration of Microprocessor Performance Models , 1998, Computer.

[18]  Markus Freericks,et al.  Describing instruction set processors using nML , 1995, Proceedings the European Design and Test Conference. ED&TC 1995.