I am trying to implement a 60kHz bandpass filter on the STM32F407 microcontroller and I'm having some issues. I have generated the filter with the help of MATLABs fdatool and then simulated it in MATLAB as well. The following MATLAB script simlates it.
% FIR Window Bandpass filter designed using the FIR1 function.
% All frequency values are in Hz.
Fs = 5250000; % Sampling Frequency
N = 1800; % Order
Fc1 = 59950; % First Cutoff Frequency
Fc2 = 60050; % Second Cutoff Frequency
flag = 'scale'; % Sampling Flag
% Create the window vector for the design algorithm.
win = hamming(N+1);
% Calculate the coefficients using the FIR1 function.
b = fir1(N, [Fc1 Fc2]/(Fs/2), 'bandpass', win, flag);
Hd = dfilt.dffir(b);
%----------------------------------------------------------
%----------------------------------------------------------
T = 1 / Fs; % sample time
L = 4500; % Length of signal
t = (0:L-1)*T; % Time vector
% Animate the passband frequency span
for f=55500:50:63500
signal = sin(2*pi*f*t);
plot(filter(Hd, signal));
axis([0 L -1 1]);
str=sprintf('Signal frequency (Hz) %d', f);
title(str);
drawnow;
end
pause;
close all;
signal = sin(2*pi*50000*t) + sin(2*pi*60000*t) + sin(2*pi*78000*t);
signal = signal / 3;
signal = signal(1:1:4500);
filterInput = signal;
filterOutput = filter(Hd,signal);
subplot(2,1,1);
plot(filterInput);
axis([0 4500 -1 1]);
subplot(2,1,2);
plot(filterOutput)
axis([0 4500 -1 1]);
pause;
close all;
From the fdatool I extract the filter co-efficents to 16-bit unsigned integers in q15 format, this because of the 12-bit ADC that I'm using. The filter co-efficents header that is generated by MATLAB is here and the resulting plot of the co-efficents can be seen in the following picture
Below is the code for the filter implementation which obviously isn't working and I don't really know what I can do differently, I've looked at some examples online Example 1 and Example 2
#include "fdacoefs.h"
#define FILTER_SAMPLES 4500
#define BLOCK_SIZE 900
static uint16_t firInput[FILTER_SAMPLES];
static uint16_t firOutput[FILTER_SAMPLES];
static uint16_t firState[NUM_TAPS + BLOCK_SIZE - 1];
uint16_t util_calculate_filter(uint16_t *buffer, uint32_t len)
{
uint16_t i;
uint16_t max;
uint16_t min;
uint32_t index;
// Create filter instance
arm_fir_instance_q15 instance;
// Ensure that the buffer length isn't longer than the sample size
if (len > FILTER_SAMPLES)
len = FILTER_SAMPLES;
for (i = 0; i < len ; i++)
{
firInput[i] = buffer[i];
}
// Call Initialization function for the filter
arm_fir_init_q15(&instance, NUM_TAPS, &firCoeffs, &firState, BLOCK_SIZE);
// Call the FIR process function, num of blocks to process = (FILTER_SAMPLES / BLOCK_SIZE)
for (i = 0; i < (FILTER_SAMPLES / BLOCK_SIZE); i++) //
{
// BLOCK_SIZE = samples to process per call
arm_fir_q15(&instance, &firInput[i * BLOCK_SIZE], &firOutput[i * BLOCK_SIZE], BLOCK_SIZE);
}
arm_max_q15(&firOutput, len, &max, &index);
arm_min_q15(&firOutput, len, &min, &index);
// Convert output back to uint16 for plotting
for (i = 0; i < (len); i++)
{
buffer[i] = (uint16_t)(firOutput[i] - 30967);
}
return (uint16_t)((max+min));
}
The ADC is sampling at 5.25 MSPS and it is sampling a 60kHz signal 4500 times and here you can see the Input to the filter and then the Output of the filter which is pretty weird..
Is there anything obvious that I've missed? Because I'm completely lost and any pointers and tips are helpful!
As Lundin pointed out I changed it to work with 32 bit integers instead and that actually solved my problem. Ofcourse I generated new filter co-efficents with MATLABS fdatool as signed 32 bit integers instead.
static signed int firInput[FILTER_SAMPLES];
static signed int firOutput[FILTER_SAMPLES];
static signed int firState[NUM_TAPS + BLOCK_SIZE -1];
uint16_t util_calculate_filter(uint16_t *buffer, uint32_t len)
{
uint16_t i;
int power;
uint32_t index;
// Create filter instance
arm_fir_instance_q31 instance;
// Ensure that the buffer length isn't longer than the sample size
if (len > FILTER_SAMPLES)
len = FILTER_SAMPLES;
for (i = 0; i < len ; i++)
{
firInput[i] = (int)buffer[i];
}
// Call Initialization function for the filter
arm_fir_init_q31(&instance, NUM_TAPS, &firCoeffs, &firState, BLOCK_SIZE);
// Call the FIR process function, num of blocks to process = (FILTER_SAMPLES / BLOCK_SIZE)
for (i = 0; i < (FILTER_SAMPLES / BLOCK_SIZE); i++) //
{
// BLOCK_SIZE = samples to process per call
//arm_fir_q31(&instance, &firInput[i * BLOCK_SIZE], &firOutput[i * BLOCK_SIZE], BLOCK_SIZE);
arm_fir_q31(&instance, &firInput[i * BLOCK_SIZE], &firOutput[i * BLOCK_SIZE], BLOCK_SIZE);
}
arm_power_q31(&firOutput, len, &power);
// Convert output back to uint16 for plotting
for (i = 0; i < (len); i++)
{
buffer[i] = (uint16_t)(firOutput[i] - 63500);
}
return (uint16_t)((power/10));
}
Related
I am trying to create a modulated waveform out of 2 sine waves.
To do this I need the modulo(fmodf) to know what amplitude a sine with a specific frequency(lo_frequency) has at that time(t). But I get a hardfault when the following line is executed:
j = fmodf(2 * PI * lo_frequency * t, 2 * PI);
Do you have an idea why this gives me a hardfault ?
Edit 1:
I exchanged fmodf with my_fmodf:
float my_fmodf(float x, float y){
if(y == 0){
return 0;
}
float n = x / y;
return x - n * y;
}
But still the hardfault occurs, and when I debug it it doesn't even jump into this function(my_fmodf).
Heres the whole function in which this error occurs:
int* create_wave(int* message){
/* Mixes the message signal at 10kHz and the carrier at 40kHz.
* When a bit of the message is 0 the amplitude is lowered to 10%.
* When a bit of the message is 1 the amplitude is 100%.
* The output of the STM32 can't be negative, thats why the wave swings between
* 0 and 256 (8bit precision for faster DAC)
*/
static int rf_frequency = 10000;
static int lo_frequency = 40000;
static int sample_rate = 100000;
int output[sample_rate];
int index, mix;
float j, t;
for(int i = 0; i <= sample_rate; i++){
t = i * 0.00000001f; // i * 10^-8
j = my_fmodf(2 * PI * lo_frequency * t, 2 * PI);
if (j < 0){
j += (float) 2 * PI;
}
index = floor((16.0f / (lo_frequency/rf_frequency * 0.0001f)) * t);
if (index < 16) {
if (!message[index]) {
mix = 115 + sin1(j) * 0.1f;
} else {
mix = sin1(j);
}
} else {
break;
}
output[i] = mix;
}
return output;
}
Edit 2:
I fixed the warning: function returns address of local variable [-Wreturn-local-addr] the way "chux - Reinstate Monica" suggested.
int* create_wave(int* message){
static uint16_t rf_frequency = 10000;
static uint32_t lo_frequency = 40000;
static uint32_t sample_rate = 100000;
int *output = malloc(sizeof *output * sample_rate);
uint8_t index, mix;
float j, n, t;
for(int i = 0; i < sample_rate; i++){
t = i * 0.00000001f; // i * 10^-8
j = fmodf(2 * PI * lo_frequency * t, 2 * PI);
if (j < 0){
j += 2 * PI;
}
index = floor((16.0f / (lo_frequency/rf_frequency * 0.0001f)) * t);
if (index < 16) {
if (!message[index]) {
mix = (uint8_t) floor(115 + sin1(j) * 0.1f);
} else {
mix = sin1(j);
}
} else {
break;
}
output[i] = mix;
}
return output;
}
But now I get the hardfault on this line:
output[i] = mix;
EDIT 3:
Because the previous code contained a very large buffer array that did not fit into the 16KB SRAM of the STM32F303K8 I needed to change it.
Now I use a "ping-pong" buffer where I use the callback of the DMA for "first-half-transmitted" and "completly-transmitted":
void HAL_DAC_ConvHalfCpltCallbackCh1(DAC_HandleTypeDef * hdac){
HAL_GPIO_WritePin(GPIOB, GPIO_PIN_3, GPIO_PIN_SET);
for(uint16_t i = 0; i < 128; i++){
new_value = sin_table[(i * 8) % 256];
if (message[message_index] == 0x0){
dac_buf[i] = new_value * 0.1f + 115;
} else {
dac_buf[i] = new_value;
}
}
}
void HAL_DAC_ConvCpltCallbackCh1 (DAC_HandleTypeDef * hdac){
HAL_GPIO_WritePin(GPIOB, GPIO_PIN_3, GPIO_PIN_RESET);
for(uint16_t i = 128; i < 256; i++){
new_value = sin_table[(i * 8) % 256];
if (message[message_index] == 0x0){
dac_buf[i] = new_value * 0.1f + 115;
} else {
dac_buf[i] = new_value;
}
}
message_index++;
if (message_index >= 16) {
message_index = 0;
// HAL_DAC_Stop_DMA (&hdac1, DAC_CHANNEL_1);
}
}
And it works the way I wanted:
But the frequency of the created sine is too low.
I cap at around 20kHz but I'd need 40kHz.
I allready increased the clock by a factor of 8 so that one is maxed out:
.
I can still decrease the counter period (it is 50 at the moment), but when I do so the interrupt callback seems to take longer than the period to the next one.
At least it seems so as the output becomes very distorted when I do that.
I also tried to decrease the precision by taking only every 8th sine value but
I cant do this any more because then the output does not look like a sine wave anymore.
Any ideas how I could optimize the callback so that it takes less time ?
Any other ideas ?
Does fmodf() cause a hardfault in stm32?
It is other code problems causing the hard fault here.
Failing to compile with ample warnings
Best code tip: enable all warnings. #KamilCuk
Faster feedback than Stackoverflow.
I'd expect something like below on a well enabled compiler.
return output;
warning: function returns address of local variable [-Wreturn-local-addr]
Returning a local Object
Cannot return a local array. Allocate instead.
// int output[sample_rate];
int *output = malloc(sizeof *output * sample_rate);
return output;
Calling code will need to free() the pointer.
Out of range array access
static int sample_rate = 100000;
int output[sample_rate];
// for(int i = 0; i <= sample_rate; i++){
for(int i = 0; i < sample_rate; i++){
...
output[i] = mix;
}
Stack overflow?
static int sample_rate = 100000; int output[sample_rate]; is a large local variable. Maybe allocate or try something smaller?
Advanced: loss of precision
A good fmodf() does not lose precision. For a more precise answer consider double math for the intermediate results. An even better approach is more involved.
float my_fmodf(float x, float y){
if(y == 0){
return 0;
}
double n = 1.0 * x / y;
return (float) (x - n * y);
}
Can I not use any function within another ?
Yes. Code has other issues.
1 value every 10uS makes only 100kSPS whis is not too much for this macro. In my designs I generate > 5MSPS signals without any problems. Usually I have one buffer and DMA in circular mode. First I fill the buffer and start generation. When the half transmition DMA interrupt is trigerred I fill the first half of the buffer with fresh data. The the transmition complete interrupt is trigerred I fill the second half and this process repeats all over again.
I've coded a simple sequencer in C with SDL 1.2 and SDL_mixer(to play .wav file). It works well and I want to add some audio synthesis to this program. I've look up the and I found this sinewave code using SDL2(https://github.com/lundstroem/synth-samples-sdl2/blob/master/src/synth_samples_sdl2_2.c)
Here's how the sinewave is coded in the program:
static void build_sine_table(int16_t *data, int wave_length)
{
/*
Build sine table to use as oscillator:
Generate a 16bit signed integer sinewave table with 1024 samples.
This table will be used to produce the notes.
Different notes will be created by stepping through
the table at different intervals (phase).
*/
double phase_increment = (2.0f * pi) / (double)wave_length;
double current_phase = 0;
for(int i = 0; i < wave_length; i++) {
int sample = (int)(sin(current_phase) * INT16_MAX);
data[i] = (int16_t)sample;
current_phase += phase_increment;
}
}
static double get_pitch(double note) {
/*
Calculate pitch from note value.
offset note by 57 halfnotes to get correct pitch from the range we have chosen for the notes.
*/
double p = pow(chromatic_ratio, note - 57);
p *= 440;
return p;
}
static void audio_callback(void *unused, Uint8 *byte_stream, int byte_stream_length) {
/*
This function is called whenever the audio buffer needs to be filled to allow
for a continuous stream of audio.
Write samples to byteStream according to byteStreamLength.
The audio buffer is interleaved, meaning that both left and right channels exist in the same
buffer.
*/
// zero the buffer
memset(byte_stream, 0, byte_stream_length);
if(quit) {
return;
}
// cast buffer as 16bit signed int.
Sint16 *s_byte_stream = (Sint16*)byte_stream;
// buffer is interleaved, so get the length of 1 channel.
int remain = byte_stream_length / 2;
// split the rendering up in chunks to make it buffersize agnostic.
long chunk_size = 64;
int iterations = remain/chunk_size;
for(long i = 0; i < iterations; i++) {
long begin = i*chunk_size;
long end = (i*chunk_size) + chunk_size;
write_samples(s_byte_stream, begin, end, chunk_size);
}
}
static void write_samples(int16_t *s_byteStream, long begin, long end, long length) {
if(note > 0) {
double d_sample_rate = sample_rate;
double d_table_length = table_length;
double d_note = note;
/*
get correct phase increment for note depending on sample rate and table length.
*/
double phase_increment = (get_pitch(d_note) / d_sample_rate) * d_table_length;
/*
loop through the buffer and write samples.
*/
for (int i = 0; i < length; i+=2) {
phase_double += phase_increment;
phase_int = (int)phase_double;
if(phase_double >= table_length) {
double diff = phase_double - table_length;
phase_double = diff;
phase_int = (int)diff;
}
if(phase_int < table_length && phase_int > -1) {
if(s_byteStream != NULL) {
int16_t sample = sine_wave_table[phase_int];
sample *= 0.6; // scale volume.
s_byteStream[i+begin] = sample; // left channel
s_byteStream[i+begin+1] = sample; // right channel
}
}
}
}
}
I don't understand how I could change the sinewave formula to genrate other waveform like square/triangle/saw ect...
EDIT:
Because I forgot to explain it, here's what I tried.
I followed the example I've seen on this video series(https://www.youtube.com/watch?v=tgamhuQnOkM). The source code of the method provided by the video is on github, and the wave generation code is looking like this:
double w(double dHertz)
{
return dHertz * 2.0 * PI;
}
// General purpose oscillator
double osc(double dHertz, double dTime, int nType = OSC_SINE)
{
switch (nType)
{
case OSC_SINE: // Sine wave bewteen -1 and +1
return sin(w(dHertz) * dTime);
case OSC_SQUARE: // Square wave between -1 and +1
return sin(w(dHertz) * dTime) > 0 ? 1.0 : -1.0;
case OSC_TRIANGLE: // Triangle wave between -1 and +1
return asin(sin(w(dHertz) * dTime)) * (2.0 / PI);
}
Because the C++ code here uses windows soun api I could not copy/paste this method to make it work on the piece of code I've found using SDL2.
So I tried to this in order to obtain a square wave:
static void build_sine_table(int16_t *data, int wave_length)
{
double phase_increment = ((2.0f * pi) / (double)wave_length) > 0 ? 1.0 : -1.0;
double current_phase = 0;
for(int i = 0; i < wave_length; i++) {
int sample = (int)(sin(current_phase) * INT16_MAX);
data[i] = (int16_t)sample;
current_phase += phase_increment;
}
}
This didn't gave me a square wave but more a saw wave.
Here's what I tried to get a triangle wave:
static void build_sine_table(int16_t *data, int wave_length)
{
double phase_increment = (2.0f * pi) / (double)wave_length;
double current_phase = 0;
for(int i = 0; i < wave_length; i++) {
int sample = (int)(asin(sin(current_phase) * INT16_MAX)) * (2 / pi);
data[i] = (int16_t)sample;
current_phase += phase_increment;
}
}
This also gave me another type of waveform, not triangle.
You’d replace the sin function call with call to one of the following:
// this is a helper function only
double normalize(double phase)
{
double cycles = phase/(2.0*M_PI);
phase -= trunc(cycles) * 2.0 * M_PI;
if (phase < 0) phase += 2.0*M_PI;
return phase;
}
double square(double phase)
{ return (normalize(phase) < M_PI) ? 1.0 : -1.0; }
double sawtooth(double phase)
{ return -1.0 + normalize(phase) / M_PI; }
double triangle(double phase)
{
phase = normalize(phase);
if (phase >= M_PI)
phase = 2*M_PI - phase;
return -1.0 + 2.0 * phase / M_PI;
}
You’d be building tables just like you did for the sine, except they’d be the square, sawtooth and triangle tables, respectively.
In short, I am reading a .wav file in MATLAB for the purposes of sending it to the ESP32 for an FFT analysis. The .wav file in question contains a recording of a Corona effect. My file has 96223 samples when inputted into MATLAB.
For now, I am trying to just get back a checksum so I can know that the data is sent correctly.
I have already tried using the code I've written for smaller sample sizes. For example, I get back the correct checksum when I send 200 samples although the code takes longer than I want it to take which is not good. More than that though, and I never get anything back because of timeouts.
This is my MATLAB code:
esp = serial('COM3');
set(esp, 'DataBits' , 8);
set(esp, 'StopBits', 1);
set(esp, 'BaudRate', 9600);
set(esp, 'Parity', 'none');
set(esp, 'terminator', 'LF');
%filename = 'test100.wav';
%corona = audioread(filename);
load('corona')
fopen(esp);
pause(0.1)
for i = 1:200
fprintf(esp, '%5.9f\n', corona(i,1));
pause(0.1);
end
output = fscanf(esp, '%f\n') %read the checksum
fclose(instrfind);
And this is my Arduino code:
#include <Arduino.h>
float sentData[200]; //initialize data array
int i = 0;
const int ledPin = 26;
float checksum = 0;
int CNT = 0;
void printFloat(float value, int places);
void setup()
{
Serial.begin(9600);
pinMode(ledPin, OUTPUT);
while (Serial.available() < 200)
{
digitalWrite(ledPin, HIGH); //keep the LED on while the data is being sent
}
while (Serial.available() != 0)
{
sentData[i] = Serial.parseFloat(); //parse the data to the array
i++;
}
Serial.flush();
delay(500);
digitalWrite(ledPin, LOW); //turn off the LED when data is fully parsed
for (size_t x = 0; x < 200; ++x)
{
checksum += sentData[x]; //calculate the sum of all elements in the sentData array
}
printFloat(checksum, 10); //send the checksum to the serial port for reading
}
void loop()
{
}
void printFloat(float value, int places)
{
// this is used to cast digits
int digit;
float tens = 0.1;
int tenscount = 0;
int i;
float tempfloat = value;
// if this rounding step isn't here, the value 54.321 prints as 54.3209
// calculate rounding term d: 0.5/pow(10,places)
float d = 0.5;
if (value < 0)
d *= -1.0;
// divide by ten for each decimal place
for (i = 0; i < places; i++)
d /= 10.0;
tempfloat += d;
// first get value tens to be the large power of ten less than value
if (value < 0)
tempfloat *= -1.0;
while ((tens * 10.0) <= tempfloat)
{
tens *= 10.0;
tenscount += 1;
}
// write out the negative if needed
if (value < 0)
Serial.print('-');
if (tenscount == 0)
Serial.print(0, DEC);
for (i = 0; i < tenscount; i++)
{
digit = (int)(tempfloat / tens);
Serial.print(digit, DEC);
tempfloat = tempfloat - ((float)digit * tens);
tens /= 10.0;
}
// if no places after decimal, stop now and return
if (places <= 0)
return;
// otherwise, write the point and continue on
Serial.print('.');
// now write out each decimal place by shifting digits one by one into the ones place and writing the truncated value
for (i = 0; i < places; i++)
{
tempfloat *= 10.0;
digit = (int)tempfloat;
Serial.print(digit, DEC);
// once written, subtract off that digit
tempfloat = tempfloat - (float)digit;
}
}
I expected to get back a checksum but I get a timeout when using very large sample sizes. I should also add that even though the ESP32 should be able to handle my file, I can't just push the whole file into the serial port because I get a buffer overflow error. Is there a solution to this?
First %5.9f doesn't make sense to me.
Thats minimum 5 characters with 9 digit precision. That 5 doesn't make sense as you'll always have at least 11 characters with 9 digit precision
Then let me do some maths for you:
96000 samples, 12 characters each (including \n) is a total of 10368000 bits.
At 9600 baud that's 1080 seconds of transfer time. -> 18 minutes.
As you add 0.1s pause after each sample you add another 9600 seconds to that.
Which leaves you with a total of 178 minutes (3 hours) of transfer time.
What do you expect?
For 200 samples its still 22,25s.
I'm designing a guitar tuner through an atmel mega16 processor and CodeVisionAVR for my university's second project. I have connected a mono jack to the processor's PINA.7 (ADC converter) and GND. I have 7 LEDs (PORTB.0..6) that should turn on through a series of if/elseif based on the frequency of the fundamental of the signal.
I'm taking the fundamental of the signal through a DFT (i know there are faster FTs but our university told us we should use a DFT, they know why) of 800 samples. Out of the 800 samples selected, it calculates the frequency spectrum. Then the next for is used to calculate the absolute value of each frequency, and picks the largest, so it can be a good refrence point for a guitar tuner.
Momentairly, i have included in the main function just a large frequency condition to see if the LED lights up, but it doesn't.
I have tried switching on LEDs from 0 to 6 throughout the code and it seems to stop at F = computeDft();, so i removed the variable, and just let the computeDft(); run, but the next leds did not light up. Is the function never getting called? I have tried the function in Visual Studio with a generated cosine function and it works perfectly. It always detects the fundamental. Why doesn't it work in CVAVR?
#define M_PI 3.1415926f
#define N 800
unsigned char read_adc(void)
{
ADCSRA |= 0x40; //start conversion;
while (ADCSRA&(0x40)); //wait conversion end
return (float)ADCH;
}
typedef struct
{
float re;
float im;
} Complex;
float computeDft()
{
unsigned char x[N] = {0};
float max = 0;
float maxi = 0;
float magnitude = 0;
Complex X1[N] = {0};
int n = N;
int k;
for (n = 0; n < N; ++n)
{
for (k = 0; k < n; k++)
{
x[k] = read_adc();
X1[n].re += x[k] * cos(n * k * M_PI / N);
X1[n].im -= x[k] * sin(n * k * M_PI / N);
}
}
for (k = 0; k < n; k++)
{
magnitude = sqrt(X1[k].re * X1[k].re + X1[k].im * X1[k].im);
if (magnitude > maxi)
{
maxi = magnitude;
max = k;
}
}
return max;
}
/*
* main function of program
*/
void main (void)
{
float F = 0;
Init_initController(); // this must be the first "init" action/call!
#asm("sei") // enable interrupts
LED1 = 1; // initial state, will be changed by timer 1
L0 = 0;
L1 = 0;
L2 = 0;
L3 = 0;
L4 = 0;
L5 = 0;
L6 = 0;
ADMUX = 0b10100111; // set ADC0
ADCSRA = 0b10000111; //set ADEN, precale by 128
while(TRUE)
{
wdogtrig(); // call often else processor will reset ;
F = computeDft();
if (F > 50 && F < 200)
{
L3 = 1;
}
}
}// end main loop
The result i'm trying to achieve is a signal from a phone or a computer (probably a YouTube video of a guy tuning his guitar) is sent through the jack to the processor in the AD converter (PINA.7). The main function calls the computeDft; function, which will ask the read_adc(); to add to x[k] the value of the voltage that is being sent through the cable, then compute it's Dft. The same function then selects the frequency of the fundamental (the one with the highest absolute value), then returns it. Inside the main function, a variable will be assigned the value of the fundamental, and through a series of ifs, it will compare it's value to the standard guitar strings frequencies of 82.6, 110, etc...
1. First of all: just picking the bigger harmonic in DFT, is not good as a tuner, since, depending on the instrument played, overtones may have a larger amplitude. The decent tuner may be done by using e.g. auto-correlation algorithm.
2. I see this line in your project:
wdogtrig(); // call often else processor will reset ;
Why you need the watchdog in the first place? Where it is configured? What timeout it is set for? How you think, how long would it take to perform both nested loops in computeDft()? With a lot of floating point operations inside including calculation of sine and cosine at each step? On a 16MHz 8-bit MCU? I think that will take several seconds at least, so do not use the watchdog at all, or reset it more often.
3. Look at
cos(n * k * M_PI / N);
(by the way, are you sure it is cos(n * k * M_PI / N); not cos(n * k * 2 * M_PI / N);?)
since cos(x) = cos(x + 2 * M_PI), you can see this formula can be expressed as cos((n * k * 2) % (2 * N) * M_PI / N). I.e. you can precalculate all 2*N possible values and put them as a constant table into the flash memory.
4. Look at nested loops in computeDft()
Inside the inner loop, you are calling read_adc() each time!
You want to pick the signal into the buffer once, and then perform DFT over the saved signal. I.e. first you read ADC values into x[k] array:
for (k = 0; k < N; k++)
{
x[k] = read_adc();
}
and only then you perform DFT calculations over it:
for (n = 0; n < N; ++n)
{
for (k = 0; k < n; k++)
{
X1[n].re += x[k] * cos(n * k * M_PI / N);
X1[n].im -= x[k] * sin(n * k * M_PI / N);
}
}
5. Look carefully at two cycles:
for (n = 0; n < N; ++n)
..
X1[n].re += x[k] * cos(n * k * M_PI / N);
X1[n].im -= x[k] * sin(n * k * M_PI / N);
}
Here at each step, you are calculating the value of X1[n], none of the previous X1 values are used.
And another loop below:
for (k = 0; k < n; k++)
{
magnitude = sqrt(X1[k].re * X1[k].re + X1[k].im * X1[k].im);
...
}
here you are calculating the magnitude of X1[k] and no previous of next values of X1 are used. So, you can simply combine them together:
for (n = 0; n < N; ++n)
{
for (k = 0; k < n; k++)
{
X1[n].re += x[k] * cos(n * k * M_PI / N);
X1[n].im -= x[k] * sin(n * k * M_PI / N);
}
magnitude = sqrt(X1[n].re * X1[n].re + X1[n].im * X1[n].im);
if (magnitude > maxi)
{
maxi = magnitude;
max = k;
}
}
Here you can clearly see, you need no reason to store X1[n].re and X1[n].im in any array. Just get rid of them!
for (n = 0; n < N; ++n)
{
float re = 0;
float im = 0;
for (k = 0; k < n; k++)
{
re += x[k] * cos(n * k * M_PI / N);
im -= x[k] * sin(n * k * M_PI / N);
}
magnitude = sqrt(re * re + im * im);
if (magnitude > maxi)
{
maxi = magnitude;
max = k;
}
}
That's all! You have saved 6 KB by removing pointless Complex X1[N] array
6. There is a error in your initialization code:
ADMUX = 0b10100111; // set ADC0
I don't know what is "ATmega16P", I assume it works the same as "ATmega16". So most significant bits of this register, called REFS1 and REFS0 are used to select the reference voltage. Possible values are:
00 - external voltage from AREF pin;
01 - AVCC voltage taken as reference
11 - internal regulator (2.56V for ATmega16, 1.1V for ATmega168PA)
10 is an incorrect value.
7. the guitar output is a small signal, maybe several dozens of millivolts. Also, it is an AC signal, which can be as positive, so negative as well. So, before putting the signal onto MCU's input you have to shift it (otherwise you'll see only the positive half wave) and amplify it.
I.e. it is not enough just to connect jack plug to GND and ADC input, you need some schematics which will make the signal of the appropriate level.
You can google for it. For example this:
(from This project)
I am doing some FFT calculations on a STM32F407 and I want to compare the different FFT functions that is available in the CMSIS DSP library. When I am using the f32 CFFT functions it works as one would expect but when I try to use the q31/q15 functions I get an error saying "arm_cfft_sR_q31_len4096" or arm_cfft_sR_q15_len4096 undeclared when I call their respective cfft functions. I have included arm_const_structs.h where it should be defined but apparently it isn't? It works with arm_cfft_sR_f32_len4096 for the f32 version of the functions so what might be the problem?
Here is how the f32 version of my fft calculations look:
#include "arm_const_structs.h"
float32_t fft_data[FFT_SIZE * 2];
uint16_t util_calculate_fft_value(uint16_t *buffer, uint32_t len, uint32_t fft_freq, uint32_t fft_freq2)
{
uint16_t i;
float32_t maxValue; // Max FFT value is stored here
uint32_t maxIndex; // Index in Output array where max value is
tmStartMeasurement(&time); // Record clock cycles
// Ensure in buffer is not longer than FFT buffer
if (len > FFT_SIZE)
len = FFT_SIZE;
// Convert buffer uint16 to fft input float32
for (i = 0; i < len ; i++)
{
fft_data[i*2] = (float32_t)buffer[i] / 2048.0 - 1.0; // Real part
fft_data[i*2 + 1] = 0; // Imaginary part
}
// Process the data through the CFFT module intFlag = 0, doBitReverse = 1
arm_cfft_f32(&arm_cfft_sR_f32_len4096, fft_data, 0, 1);
// Process the data through the Complex Magniture Module for calculating the magnitude at each bin
arm_cmplx_mag_f32(fft_data, fft_data, FFT_SIZE / 2);
// Find maxValue as max in fft_data
arm_max_f32(fft_data, FFT_SIZE, &maxValue, &maxIndex);
if (fft_freq == 0)
{ // Find maxValue as max in fft data
arm_max_f32(fft_data, FFT_SIZE, &maxValue, &maxIndex);
}
else
{ // Grab maxValue from fft data at freq position
arm_max_f32(&fft_data[fft_freq * FFT_SIZE / ADC_SAMP_SPEED - 1], 3, &maxValue, &maxIndex);
if (fft_freq2 != 0)
{
// Grab maxValue from fft data at freq2 position
float32_t maxValue2; // Max FFT value is stored here
uint32_t maxIndex2; // Index in Output array where max value is
arm_max_f32(&fft_data[fft_freq * FFT_SIZE / ADC_SAMP_SPEED - 1], 3, &maxValue2, &maxIndex2);
maxValue = (maxValue + maxValue2) / 2.0;
}
}
tmStopMeasurement(&time); // Get number of clock cycles
// Convert output back to uint16 for plotting
for (i = 0; i < len / 2; i++)
{
buffer[i] = (uint16_t)(fft_data[i] * 10.0);
}
// Zero the rest of the buffer
for (i = len / 2; i < len; i++)
{
buffer[i] = 0;
}
LOG_INFO("FFT number of cycles: %i\n", time.worst);
return ((uint16_t)(maxValue * 10.0));
}
I found a copy of arm_const_structs.h online. It includes the following line:
extern const arm_cfft_instance_q31 arm_cfft_sR_q31_len4096;
The extern keyword means that this line is a declaration of arm_cfft_SR_q31_len4096, not a definition. The variable must also be defined somewhere else in your code.
I found the definition in arm_const_structs.c.
const arm_cfft_instance_q31 arm_cfft_sR_q31_len4096 = {
4096, twiddleCoef_4096_q31, armBitRevIndexTable_fixed_4096, ARMBITREVINDEXTABLE_FIXED_4096_TABLE_LENGTH
};
Make sure you have included arm_const_structs.c in your project so that it compiles and links with your program.