A PARALLEL APPROACH FOR MATRIX MULTIPLICATION ON THE TMS320C4X DSPMatrix multiplication used in areas such as graph theory, numerical algorithms, signal processing, and digital control, requires the high computational throughput provided by parallel processing. This document describes the fundamentals of matrix multiplication and parallel processing. It shows using the 32-bit floating-point TMS320C4x parallel digital signal processor to perform matrix multiplication and analyses the results. Code examples are given in a mixture of C and assembly language. Though the focus of this document is on parallel solutions for matrix multiplication, the concepts are relevant to other parallel processing applications. View the complete PDF document: spra107.pdf (82 K Bytes) (Requires Acrobat Reader 3.x) Go to the Engineering Design Center to locate information on other TI Semiconductor devices.
(c) Copyright 1998 Texas Instruments Incorporated. All rights reserved. Trademarks, Important Notice! |