Flexible instruction processor systems and methods

Inactive Publication Date: 2009-09-17
LUK WAYNE +2
View PDF16 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

[0013]It is an aim of the present invention to provide design-time and run-time environments for flexible instruction processors (FIPs) which provide for

Problems solved by technology

However, such processors have fixed architectures, and tend to lose performance when dealing with non-standard operations and non-standard data which are not supported by the instruction set formats [1].
However, the design and fabrication of such integrated circuits is still expensive, and, once designed, its customised function is fixed and cannot be altered.
This approach does not, however, encompass customising the overall architecture of the defined execution unit and programmable exec

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Flexible instruction processor systems and methods
  • Flexible instruction processor systems and methods
  • Flexible instruction processor systems and methods

Examples

Experimental program
Comparison scheme
Effect test

first embodiment

[0344]In a first embodiment a FIP JVM has been developed which utilises shared segregated resources. This embodiment provides good area utilisation, but at the expense of speed, because of routing congestion.

second embodiment

[0345]In a second embodiment a FIP JVM has been developed which utilises two stages of pipelining and only shares irreplaceable resources, such as the stack and main memory. Stack-based processors are intrinsically sequential. Speed optimisation of the FIP JVM introduces parallelism which is manifested as register-style instruction implementations.

third embodiment

[0346]In a third embodiment a FIP JVM has been developed which incorporates deeper pipelines for certain instructions and ‘register’ style improvements, such as having top-of-stack registers. The top-of-stack registers are replicated. Instructions can be read from different top-of-stack registers, but are written back to the stack directly. Replicated registers are updated during the fetch cycle. Most instructions are processed by four pipeline stages, although certain instructions, such as the instruction for invoking functions, require deeper logic and the implementation of those instructions has been partitioned into five or six pipeline stages. Routing has also been pipelined to reduce the effects of congestion.

[0347]These FIP JVM embodiments demonstrate trade-offs between possible parameterisations.

[0348]Maximising sharing methods for re-programmable hardware through conventional resource sharing may introduce significant routing overheads. Congestion management is necessary to...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A design system for generating configuration information and associated executable code based on a customisation specification, which includes application information including application source code and customisation information including design constraints, for implementing an instruction processor using re-programmable hardware, the system comprises a template generator for generating a template for each processor style identified as a candidate for implementation; an analyser for analysing instruction information for each template and determining instruction optimisations; a compiler for compiling the application source code to include the instruction optimisations and generate executable code; an instantiator for analysing architecture information for each template, determining architecture optimisations and generating configuration information including the architecture optimisations; and a builder for generating device-specific configuration information from the configuration information including the architecture optimisations. In another aspect, a management system for managing run-time re-configuration of an instruction processor implemented using re-programmable hardware, comprises a configuration library containing configuration information for a plurality of instruction processor implementations; a code library for containing associated executable code for the implementations; a loader for loading application data and, as required, configuration information and associated executable code into re-programmable hardware for implementation and execution of an instruction processor; a loader controller for signalling the loader to load application data and, as required, configuration information and associated executable code, and execute the executable code; a run-time monitor for obtaining run-time statistics relating to operation of the instruction processor; an optimisation determiner configured to receive the run-time statistics, and being operable to instruct the loader to load new configuration information and associated executable code for a new implementation into the re-programmable hardware; and an optimisation instructor for invoking the optimisation determiner.

Description

RELATED APPLICATION DATA[0001]This application is a continuation of U.S. patent application Ser. No. 10 / 416,977, filed Oct. 30, 2003, which is a national phase of International Patent Application No. PCT / GB01 / 05080 filed Nov. 19, 2001, which U.S. patent application issued on Jun. 2, 2009 as U.S. Pat. No. 7,543,283, all of which are hereby incorporated by reference in their entireties.FIELD OF THE INVENTION[0002]The present invention relates to the design-time and run-time environments of re-programmable instruction processors, such instruction processors being referred in the specification as flexible instruction processors (FIPs).[0003]In one aspect the present invention relates to a FIP design system for generating FIP configuration information and associated executable FIP code for FIP implementations based on user-specified customisation specifications, and a related method of generating FIP configuration information and associated executable FIP code for FIP implementations bas...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F9/45G06F15/76G06F9/02G06F9/318H03K19/173G06F9/44G06F9/445G06F15/78G06F17/50
CPCG06F8/443G06F17/5045G06F15/7867G06F8/447G06F9/30181G06F30/30
Inventor LUK, WAYNECHEUNG, PETER Y.K.SENG, SHAY PING
Owner LUK WAYNE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products