Re: Processing Time in TI eZdsp F2812
- From: Jack Klein <jackklein@xxxxxxxxxxx>
- Date: Thu, 30 Mar 2006 17:28:45 -0600
On Thu, 30 Mar 2006 11:33:48 -0600, "vickykulkarni"
<vickykulkarni@xxxxxxxxxxx> wrote in comp.dsp:
Hi
I have a question regarding the flow of my code. I am oversampling my
input signal using the ADC at a rate 3.125 MHz. I have 2 inputs & am using
simultaneous sampling. I am using the adcseqovdtest code of TI as a
framework. So I have 16 samples from the ADC Result registers. My question
is with sampling rate of 3.125 and clock frequency of 150 MHz, I have
(150/3.125) 48 instructions per sample to do signal processing right? So
if i process each sample before reading the next sample, will that work in
real time? The code is
fir.input=( (AdcRegs.ADCRESULT0)>>4);
fir.calc(&fir);
output=fir.output;
fir.input=( (AdcRegs.ADCRESULT1)>>4);
fir.calc(&fir);
output=fir.output;
fir.input=( (AdcRegs.ADCRESULT2)>>4);
fir.calc(&fir);
output=fir.output;
......etc for all other result registers.
Any help is highly appreciated. Thanks.
Vik
I hope you have built your executable so this code, and the
calculation subroutine, are moved to internal RAM and executed from
there.
The real question is how long your FIR calculation function takes. See
my reply in today's thread "flash and external ram timing on TI 2812"
as to how to use one of the 3 general purpose timers to get exactly
cycle counts for code execution on the 2812.
--
Jack Klein
Home: http://JK-Technology.Com
FAQs for
comp.lang.c http://c-faq.com/
comp.lang.c++ http://www.parashift.com/c++-faq-lite/
alt.comp.lang.learn.c-c++
http://www.contrib.andrew.cmu.edu/~ajo/docs/FAQ-acllc.html
.
- References:
- Processing Time in TI eZdsp F2812
- From: vickykulkarni
- Processing Time in TI eZdsp F2812
- Prev by Date: Re: flash and external ram timing on TI 2812
- Next by Date: Re: f240_hex.exe ERROR: Unable to open fastdrive.out
- Previous by thread: Processing Time in TI eZdsp F2812
- Next by thread: OT: Speech Enhancement Results (WAV FILES): Please feel free to listen and comment
- Index(es):