Design Con 2015
Welcome Guest Log In | Register

TI's new TMS320C66x fixed- and floating-point DSP core conquers the 'Need for Speed'

Authored on: Nov 4, 2010 by Arnon Friedmann

Technical Paper / Product Paper

0 1
More InfoLess Info
Integrating fixed- and floating-point capability in the same DSP core enables a fundamental change in the way algorithms for embedded systems are developed and deployed. This may sound overstated, but it is true. The amount of effort that has been spent on implementing algorithms in fixed point digital systems is enormous. The "need for speed" mandated the effort because fast floating-point DSPs simply weren't available until now. Algorithms developed with floating-point tools like Matlab can be ported simply and easily to the DSP without a laborious conversion to fixed point. With TI's new C66x DSP floating-point computation capabilities, most of this effort is no longer necessary.
View
 
1 comment
write a comment

No Avatar

Circuitcode Posted Mar 29, 2011

There are two bottlenecks we face in floating point processing - (1) generating normalized floating point variables and (2) computing with the normalized floating point variables. If I understood the paper correctly TI has architectured a speed-up solution for the overhead and slow-down problem associated with generating 'normalized' floating point variables as well as a speed-up solution for the floating point computations themselves - exciting - it is such innovation that will help drive middle-class USA back to prosperity - the vision enhanced products that can be affordably generated with technology such as this is almost limitless.

reply

Please Login

You will be redirected to the login page

×

Please Login

You will be redirected to the login page

×

Please Login

You will be redirected to the login page