Math: FFT: First step for cold data twiddle factors

This patch makes a packed copy of twiddle factors to a new
allocated buffer from the sparse twiddle factors for max.
FFT size.

Signed-off-by: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>

Author: singalsu

src/include/sof/math/fft.h

@@ -52,6 +52,7 @@ struct fft_plan {
 	struct icomplex32 *outb32;	/* pointer to output integer complex buffer */
 	struct icomplex16 *inb16;	/* pointer to input integer complex buffer */
 	struct icomplex16 *outb16;	/* pointer to output integer complex buffer */
+	void *twiddle;
 };
 
 struct fft_multi_plan {
@@ -62,8 +63,8 @@ struct fft_multi_plan {
 	struct icomplex16 *tmp_o16[FFT_MULTI_COUNT_MAX]; /* pointer to output buffer */
 	struct icomplex32 *inb32;	/* pointer to input integer complex buffer */
 	struct icomplex32 *outb32;	/* pointer to output integer complex buffer */
-	struct icomplex16 *inb16;	/* pointer to input integer complex buffer */
-	struct icomplex16 *outb16;	/* pointer to output integer complex buffer */
+	int32_t *multi_twiddle;
+	int32_t *twiddle;
 	uint16_t *bit_reverse_idx;
 	uint32_t total_size;
 	uint32_t fft_size;

src/math/fft/fft_16.c

@@ -10,7 +10,6 @@
 #include <sof/math/fft.h>
 
 #ifdef FFT_GENERIC
-#include "coef/twiddle_16.h"
 
 /*
  * Helpers for 16 bit FFT calculation
@@ -75,6 +74,7 @@ void fft_execute_16(struct fft_plan *plan, bool ifft)
 	struct icomplex16 tmp2;
 	struct icomplex16 *inb;
 	struct icomplex16 *outb;
+	struct icomplex16 *twiddle;
 	int depth;
 	int top;
 	int bottom;
@@ -104,10 +104,11 @@ void fft_execute_16(struct fft_plan *plan, bool ifft)
 		icomplex16_shift(&inb[i], -(plan->len), &outb[plan->bit_reverse_idx[i]]);
 
 	/* step 2: loop to do FFT transform in smaller size */
+	twiddle = plan->twiddle;
 	for (depth = 1; depth <= plan->len; ++depth) {
 		m = 1 << depth;
 		n = m >> 1;
-		i = FFT_SIZE_MAX >> depth;
+		i = plan->size >> depth;
 
 		/* doing FFT transforms in size m */
 		for (k = 0; k < plan->size; k += m) {
@@ -116,8 +117,7 @@ void fft_execute_16(struct fft_plan *plan, bool ifft)
 				index = i * j;
 				top = k + j;
 				bottom = top + n;
-				tmp1.real = twiddle_real_16[index];
-				tmp1.imag = twiddle_imag_16[index];
+				tmp1 = twiddle[index];
 				/* calculate the accumulator: twiddle * bottom */
 				icomplex16_mul(&tmp1, &outb[bottom], &tmp2);
 				tmp1 = outb[top];

src/math/fft/fft_16_hifi3.c

@@ -10,7 +10,6 @@
 
 #ifdef FFT_HIFI3
 #include <xtensa/tie/xt_hifi3.h>
-#include "coef/twiddle_16.h"
 
 /**
  * \brief Execute the 16-bits Fast Fourier Transform (FFT) or Inverse FFT (IFFT)
@@ -29,6 +28,7 @@ void fft_execute_16(struct fft_plan *plan, bool ifft)
 	ae_int16 *out;
 	ae_int16x4 *in16x4;
 	ae_int16x4 *out16x4;
+	ae_int16 *twiddle;
 	ae_valign inu = AE_ZALIGN64();
 	ae_valign outu = AE_ZALIGN64();
 	int depth, top, bottom, index;
@@ -67,6 +67,7 @@ void fft_execute_16(struct fft_plan *plan, bool ifft)
 	}
 
 	/* step 2: loop to do FFT transform in smaller size */
+	twiddle = plan->twiddle;
 	for (depth = 1; depth <= plan->len; ++depth) {
 		m = 1 << depth;
 		n = m >> 1;
@@ -76,13 +77,12 @@ void fft_execute_16(struct fft_plan *plan, bool ifft)
 		for (k = 0; k < plan->size; k += m) {
 			/* doing one FFT transform for size m */
 			for (j = 0; j < n; ++j) {
-				index = i * j;
+				index = 2 * i * j;
 				top = k + j;
 				bottom = top + n;
 				/* store twiddle and bottom as Q9.23*/
 				temp1 = AE_CVTP24A16X2_LL(outb[bottom].real, outb[bottom].imag);
-				temp2 = AE_CVTP24A16X2_LL(twiddle_real_16[index],
-							  twiddle_imag_16[index]);
+				temp2 = AE_CVTP24A16X2_LL(twiddle[index], twiddle[index + 1]);
 				/* calculate the accumulator: twiddle * bottom */
 				res = AE_MULFC24RA(temp1, temp2);
 				/* saturate and round the result to 16bit and put it in

src/math/fft/fft_32.c

@@ -14,8 +14,6 @@
 
 #ifdef FFT_GENERIC
 #include "fft_32.h"
-#include "coef/twiddle_32.h"
-
 
 /**
  * \brief Execute the 32-bits Fast Fourier Transform (FFT) or Inverse FFT (IFFT)
@@ -29,6 +27,7 @@ void fft_execute_32(struct fft_plan *plan, bool ifft)
 	struct icomplex32 tmp2;
 	struct icomplex32 *inb;
 	struct icomplex32 *outb;
+	struct icomplex32 *twiddle;
 	int depth;
 	int top;
 	int bottom;
@@ -58,10 +57,11 @@ void fft_execute_32(struct fft_plan *plan, bool ifft)
 		icomplex32_shift(&inb[i], -(plan->len), &outb[plan->bit_reverse_idx[i]]);
 
 	/* step 2: loop to do FFT transform in smaller size */
+	twiddle = plan->twiddle;
 	for (depth = 1; depth <= plan->len; ++depth) {
 		m = 1 << depth;
 		n = m >> 1;
-		i = FFT_SIZE_MAX >> depth;
+		i = plan->size >> depth;
 
 		/* doing FFT transforms in size m */
 		for (k = 0; k < plan->size; k += m) {
@@ -70,8 +70,7 @@ void fft_execute_32(struct fft_plan *plan, bool ifft)
 				index = i * j;
 				top = k + j;
 				bottom = top + n;
-				tmp1.real = twiddle_real_32[index];
-				tmp1.imag = twiddle_imag_32[index];
+				tmp1 = twiddle[index];
 				/* calculate the accumulator: twiddle * bottom */
 				icomplex32_mul(&tmp1, &outb[bottom], &tmp2);
 				tmp1 = outb[top];

src/math/fft/fft_32_hifi3.c

@@ -11,7 +11,6 @@
 
 #ifdef FFT_HIFI3
 #include <xtensa/tie/xt_hifi3.h>
-#include "coef/twiddle_32.h"
 
 void fft_execute_32(struct fft_plan *plan, bool ifft)
 {
@@ -23,6 +22,7 @@ void fft_execute_32(struct fft_plan *plan, bool ifft)
 	ae_int32x2 *outx = (ae_int32x2 *)plan->outb32;
 	ae_int32x2 *outtop;
 	ae_int32x2 *outbottom;
+	ae_int32x2 *twiddle;
 	uint16_t *idx = &plan->bit_reverse_idx[0];
 	int depth, top, bottom, index;
 	int i, j, k, m, n;
@@ -55,23 +55,22 @@ void fft_execute_32(struct fft_plan *plan, bool ifft)
 	}
 
 	/* step 2: loop to do FFT transform in smaller size */
+	twiddle = plan->twiddle;
 	for (depth = 1; depth <= len; ++depth) {
 		m = 1 << depth;
 		n = m >> 1;
-		i = FFT_SIZE_MAX >> depth;
+		i = size >> depth;
 
 		/* doing FFT transforms in size m */
 		for (k = 0; k < size; k += m) {
 			/* doing one FFT transform for size m */
 			for (j = 0; j < n; ++j) {
-				index = i * j;
+				index = i * j * sizeof(ae_int32x2);
 				top = k + j;
 				bottom = top + n;
 
 				/* load twiddle factor to sample1 */
-				sample1 = twiddle_real_32[index];
-				sample2 = twiddle_imag_32[index];
-				sample1 = AE_SEL32_LH(sample1, sample2);
+				sample1 = AE_L32X2_X(twiddle, index);
 
 				/* calculate the accumulator: twiddle * bottom */
 				sample2 = outx[bottom];