A pipelined microprocessor for logic programming languages

نویسندگان

  • Hiroshi Nakashima
  • Yasutaka Takeda
  • Katsuto Nakajima
  • Hideki Andou
  • Kiyohiro Furutani
چکیده

In the Japanese Fifth Generation Computer Systems Project, a large scale parallel inference machine, PIM/m, is being developed. In PIM/m, up to 256 processor elements are connected to form a two-dimensional mesh network. The processor element has a pipelined microprocessor specialized to the execution of logic programming languages. The microprocessor, called PU (Processing Unit), is also used as a key component of AI workstations. Thus, PU has capability to execute two di erent type logic programming languages, KL1 for PIM/mand ESP for the AI workstation. For e cient implementation of both languages, data typing and dereference are very important. For these operations, PU has powerful mechanisms to manipulate tagged data. Especially, the pipelined data typing and dereference are the most unique features of PU. Those mechanisms greatly contribute to the high performance, 833 KLIPS for KL1 append, and 1282 KLIPS for ESP.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Automatic Verication of Pipelined Microprocessor Control

We describe a technique for verifying the control logic of pipelined microprocessors. It handles more complicated designs, and requires less human intervention, than existing methods. The technique automatically compares a pipelined implementation to an architectural description. The CPU time needed for veri cation is independent of the data path width, the register le size, and the number of A...

متن کامل

Exploiting Positive Equality and Partial Non-Consistency in the Formal Verification of Pipelined Microprocessors1

We study the applicability of the logic of Positive Equality with Uninterpreted Functions (PEUF) [2][3] to the verification of pipelined microprocessors with very large Instruction Set Architectures (ISAs). Abstraction of memory arrays and functional units is employed, while the control logic of the processors is kept intact from the original gate-level designs. PEUF is an extension of the logi...

متن کامل

Algebraic Models of Temporal Abstraction for Initialised Iterated State Systems: An Abstract Pipelined Case Study

The data and temporal abstractions of a pipelined case study are explored in an algebraic setting. We apply a set of algebraic tools for modelling microprocessors to the specification, pipelined implementation, and formal verification of an abstract case study. We employ a model of time based on counting events by means of a clock. We model systems as iterated maps that evolve over time from so...

متن کامل

Verification of Pipelined Microprocessors Using Invariants

This paper presents a new approach for the verification of a pipelined microprocessor which is based on the definition of invariants to characterize the reachable states of the pipelined machine. To express many machine-relevant properties, we have modelled the stream of instructions with the system Maude which is based on Rewriting Logic. It is also used to run and debug the pipelined machine ...

متن کامل

MPC for Deeply Pipelined FPGA Implementation: Algorithms and Circuitry

Model predictive control (MPC) is an optimization-based scheme that imposes a real-time constraint on computing the solution of a quadratic programming (QP) problem. The implementation of MPC in fast embedded systems presents new technological challenges. In this paper we present a parameterized field-programmable gate array (FPGA) implementation of a customized QP solver for optimal control of...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1990