Methods and apparatus for efficient vocoder implementations
AssigneePTS Corporation
InventorsAli Soheil Sadri, Navin Jaffer, Anissim A. Silivra, Bin Huang, Matthew Plonski
Life of this patent
Estimating the term…
Abstract
Techniques for implementing vocoders in parallel digital signal processors are described. A preferred approach is implemented in conjunction with the BOPS® Manifold Array (ManArray™) processing architecture so that in an array of N parallel processing elements, N channels of voice communication are processed in parallel. Techniques for forcing vocoder processing of one data-frame to take the same number of cycles are described. Improved throughput and lower clock rates can be achieved.
Claims15
A digital signal processor having:
- N parallel processing elements;
- a cluster switch mechanism connecting the N parallel processing elements;
- a sequence processor for controlling the N parallel processing elements to operate as a single instruction multiple data parallel processor array;
- and
- N channels of voice communication data, data from one of said channels provided to each one of said parallel processing elements, whereby the data for the voice communication channels are processed in parallel.
A method for efficiently implementing a vocoder in a digital signal processor comprising the steps of:
- providing N channels of voice communication;
- connecting one of said channels to one of N parallel processing elements;
- communicating between the N parallel processing elements utilizing a cluster switch mechanism connecting the N parallel processing elements;
- and
- utilizing a sequence processor to control the N parallel processing elements to operate as a single instruction multiple data parallel processor array and process the voice communication channels in parallel.
A digital signal processor supporting conditional execution and having:
- N parallel processing elements;
- a sequence processor for distributing the same conditional instructions to each of the N parallel processing elements;
- and
- N channels of voice communication data, one of said channels connected to each one of said parallel processing elements, whereby the voice communication data is processed in parallel in response to said conditional instructions.
Dependencies are inferred from the claim text.