A 553K-transistor LISP processor chip

@article{Bosshart1987A5L,
  title={A 553K-transistor LISP processor chip},
  author={Patrick W. Bosshart and C. Robert Hewes and Mi-Chang Chang and Kwok K. Chau and C. C. Hoac and Ted Houston and Vibhu Kalyan and Stephen L. Lusky and Shivaling S. Mahant-Shetti and D. Matzke and Kamalesh N. Ruparel and Ching-Hao Shaw and Thirumalai Sridhar and D. Stark},
  journal={1987 IEEE International Solid-State Circuits Conference. Digest of Technical Papers},
  year={1987},
  volume={XXX},
  pages={202-203}
}
  • P. Bosshart, C. Hewes, +11 authors D. Stark
  • Published 1987
  • 1987 IEEE International Solid-State Circuits Conference. Digest of Technical Papers
A 1cm2LISP processor, fabricated in a 1.25μm CMOS technology, will be described. The chip contains 114Kb of on-chip RAM, can run off-chip microcode, and can execute instructions in a single 40ns clock cycle. 

Figures and Tables from this paper

Dynamic RAM for on-chip instruction caches
TLDR
A simple design approach, based on the use of dynamic RAM, is introduced for implementing on-chip instruction caches without complicating the processor control.
Lisp on a reduced-instruction-set processor: characterization and optimization
TLDR
The factors that motivated the choice of a reduced-instruction-set computer (RISC) on which to implement Lisp are examined and execution results for various benchmarks are presented and discussed.
Non-refreshing dynamic RAM for on-chip cache memories
  • D.D. Lee, R. Katz
  • Computer Science
    Digest of Technical Papers., 1990 Symposium on VLSI Circuits
  • 1990
It is shown that, by using simple circuit techniques and a few modifications to cache organization, one can effectively eliminate the refreshing requirement of a DRAM. A selective invalidation scheme
Trap architectures for Lisp systems
TLDR
This paper looks at requirements for Lisp traps, evaluates current trap architectures, and proposes enhancements for meeting those requirements, which increase performance for Lisp 11%-35% at a cost of about 1.6% more CPU logic.
Lisp hardware architecture: the Explorer II and beyond
TLDR
Lisp is a run-tlme typed language; there can be multiple references to an object but there is only one stored representation of this object.
Run-time checking in Lisp by integrating memory addressing and range checking
TLDR
The BL addressing mode and the address tag are described and used to check the number of arguments and multiple return values and to check array-bounds to support faster execution of Common Lisp program.
Tags and type checking in LISP: hardware and software approaches
TLDR
The role and necessity of special-purpose hardware for tag handling are understood, and the cost of type checking operations for a group of LISP programs is measured and it is shown that minimal levels of support provide most of the benefits, and that tag operations can be relatively inexpensive, even when no special hardware support is present.