TI E2E Community
Digital Signal Processors (DSP)
C6000 Multicore DSP
Keystone Multicore Forum (C66, 66A, AM5)
Hi, I have two questions about the FFTC coprocessor:
1 - Is it possible to use float values instead of integer values? I am working with values between +-1. Which would be the best way of dealing with this? Tranforming this +-1 interval into +-2^15?
2 - About the scaling factor, the User Guide says it can be 0, 1, 2 or 3. However, in some cases I get 65535, 65534, 65533; which seems to be a representation of -1, -2 and -3 in Two's complement. Actually when I get these values of exponent, the FFT result appears to be 2x, 4x or 8x the result obtained in Matlab. I only get "negative" scaling factors when the output results are small (close to 0). Is this done to avoid the loss of precission when working with small values? The User Guide does not say anything regarding this.
All content and materials on this site are provided "as is". TI and its respective suppliers and providers of content make no representations about the suitability of these materials for any purpose and disclaim all warranties and conditions with regard to these materials, including but not limited to all implied warranties and conditions of merchantability, fitness for a particular purpose, title and non-infringement of any third party intellectual property right. TI and its respective suppliers and providers of content make no representations about the suitability of these materials for any purpose and disclaim all warranties and conditions with respect to these materials. No license, either express or implied, by estoppel or otherwise, is granted by TI. Use of the information on this site may require a license from a third party, or a license from TI.
TI is a global semiconductor design and manufacturing company. Innovate with 100,000+ analog ICs andembedded processors, along with software, tools and the industry’s largest sales/support staff.