By Topic

Speed enhancement of digital signal processing software via microprogramming a general purpose minicomputer

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Morris, L. ; Digital Equipment Corporation, Maynard, Massachusetts ; Mudge, J.

Summary form only given, as follows. Execution time of digital signal processing software can be substantially reduced using automatically generated code which incorporates precomputed, data independent, control and data access parameters. In this paper, further speed enhancement of such software via microprogramming of computational kernels is discussed and demonstrated. It is shown that, in additon to elimination of instruction fetch and decode overhead, and reduction of data acccess time via use of hih speed scratchpad registers, microprogramming may permit fundamental operations to be recoded to yield substantially reduced execution times. An example is given whereb Booth's multiplication algorithm is combined wit microcode to yield a fixed-point multiply/add time several times faster than an implementation using the machine-level multiply/add instructions. Moreover the systematic nature of the computational microcode allows it to be generated by programs using the technique described previously. Finally, program execution times approachin an order of magnitude less than that of conventional assembler language implementations are shown feasible by incorporation of all techniques discussed. [Full paper available only at conference.]

Published in:

Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '77.  (Volume:2 )

Date of Conference:

9-11 May 1977