Dynamic microprogramming: processor organization and programming
Communications of the ACM
Compiler Construction for Digital Computers
Compiler Construction for Digital Computers
An approach to optimization of horizontal microprograms
MICRO 7 Conference record of the 7th annual workshop on Microprogramming
The heuristic tuning of virtual architectures for global system optimization
The heuristic tuning of virtual architectures for global system optimization
Dynamic problem oriented redefinition of computer architecture via microprogramming.
Dynamic problem oriented redefinition of computer architecture via microprogramming.
A self-tuning microprogrammed computer.
A self-tuning microprogrammed computer.
Migration implementation by integrating microprogramming and HLL programming
MICRO 17 Proceedings of the 17th annual workshop on Microprogramming
Identification of microprogrammable loops for problem oriented architecture synthesis
ACM SIGMICRO Newsletter
Toward type-oriented dynamic vertical migration
ACM SIGMICRO Newsletter
Microprogramming: A Tutorial and Survey of Recent Developments
IEEE Transactions on Computers
Control Overhead A Performance Metric for Evaluating Control-Unit Designs
IEEE Transactions on Computers
Dynamic Problem-Oriented Redefinition of Computer Architecture via Microprogramming
IEEE Transactions on Computers
Hi-index | 0.01 |
Manual tuning techniques are widely applied but are generally slow, costly and require a great deal of expertise. This paper addresses the problem of automatically tuning the virtual architecture of a microprogrammed computer by microprogramming techniques. Two algorithms are presented to automate the tuning process. The algorithms are implemented on the same dynamic microprogrammed computer that executes the given application. After execution of the program the algorithms are invoked and a tuning iteration performed on the architecture and the program. Several tuning iterations are performed with different data sets over a period of time to select the optimized architecture. It is demonstrated that individual code segments experience a 2-8 speed improvement over their corresponding non-tuned versions, while the overall execution time of the program is reduced by 30-45%. The computational requirements of the algorithms are shown to be very modest.