Skip to content

Math: Inline function sofm_lut_sin_fixed_16b() for performance #9798

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
singalsu wants to merge 1 commit into from
Closed

Math: Inline function sofm_lut_sin_fixed_16b() for performance #9798

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 48 additions & 1 deletion src/include/sof/math/lut_trig.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,53 @@

#include <stdint.h>

int16_t sofm_lut_sin_fixed_16b(int32_t w); /* Input is Q4.28, output is Q1.15 */
#define SOFM_LUT_SINE_C_Q20 341782638 /* 2 * SINE_NQUART / pi in Q12.20 */
#define SOFM_LUT_SINE_NQUART 512 /* Must be 2^N */
#define SOFM_LUT_SINE_SIZE (SOFM_LUT_SINE_NQUART + 1)

extern const uint16_t sofm_lut_sine_table_s16[];

/* Sine lookup table read */
static inline int32_t sofm_sine_lookup_16b(int idx)
{
uint16_t s;
int i1;

i1 = idx & (2 * SOFM_LUT_SINE_NQUART - 1);
if (i1 > SOFM_LUT_SINE_NQUART)
i1 = 2 * SOFM_LUT_SINE_NQUART - i1;

s = sofm_lut_sine_table_s16[i1];
if (idx > 2 * SOFM_LUT_SINE_NQUART)
return -((int32_t)s);

return (int32_t)s;
}

/**
* Compute fixed point sine with table lookup and interpolation
* @param w Input angle in radians Q4.28
* @return Sine value Q1.15
*/
static inline int16_t sofm_lut_sin_fixed_16b(int32_t w)
{
int64_t idx;
int32_t sine;
int32_t frac;
int32_t delta;
int32_t s0;
int32_t s1;
int64_t idx_tmp;

/* Q4.28 x Q12.20 -> Q16.48 --> Q16.31*/
idx_tmp = ((int64_t)w * SOFM_LUT_SINE_C_Q20) >> 17;
idx = (idx_tmp >> 31); /* Shift to Q0 */
frac = (int32_t)(idx_tmp - (idx << 31)); /* Get fraction Q1.31*/
s0 = sofm_sine_lookup_16b(idx); /* Q1.16 */
s1 = sofm_sine_lookup_16b(idx + 1); /* Q1.16 */
delta = s1 - s0; /* Q1.16 */
sine = s0 + q_mults_32x32(frac, delta, Q_SHIFT_BITS_64(31, 16, 16)); /* Q1.16 */
return sat_int16((sine + 1) >> 1); /* Round to Q1.15 */
}
Copy link
Collaborator

@lyakh lyakh Jan 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

with this every call to sofm_lut_sin_fixed_16b() inlines sofm_sine_lookup_16b() twice. The former is called from drc_sin_fixed(), which is also an inline function in drc_math.h. That one is called from C code 4 times from C, HiFi3 and HiFi4 DRC versions. So that should make the resulting image (or the DRC module) somewhat larger. @singalsu have you compared sizes? You could also try to only inline one of them, wondering how much performance improvement would that give. Also, you could convert lines 55-56 to a 2-iteration loop, which would reduce the size a bit, unless the compiler decides to unroll that loop.
In general, I'd guess, that we could make similar performance improvements by identifying and moving to headers all the functions, called when processing data


#endif /* __SOF_MATH_LUT_TRIG_H__ */
47 changes: 1 addition & 46 deletions src/math/lut_trig.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,21 +5,16 @@
// Author: Seppo Ingalsuo <seppo.ingalsuo@linux.intel.com>

#include <sof/audio/format.h>
#include <sof/math/lut_trig.h>
#include <rtos/symbol.h>
#include <stdint.h>

#define SOFM_LUT_SINE_C_Q20 341782638 /* 2 * SINE_NQUART / pi in Q12.20 */
#define SOFM_LUT_SINE_NQUART 512 /* Must be 2^N */
#define SOFM_LUT_SINE_SIZE (SOFM_LUT_SINE_NQUART + 1)

/* Sine values 0 to pi/2, calculated with Octave
* w = linspace(0, pi/2, 513);
* s = 2^16;
* x = min(round(s * sin(w)), s - 1);
*/

static const uint16_t sofm_lut_sine_table_s16[SOFM_LUT_SINE_SIZE] = {
const uint16_t sofm_lut_sine_table_s16[] = {
0, 201, 402, 603, 804, 1005, 1206, 1407, 1608, 1809, 2010,
2211, 2412, 2613, 2814, 3015, 3216, 3417, 3617, 3818, 4019, 4219,
4420, 4621, 4821, 5022, 5222, 5422, 5623, 5823, 6023, 6224, 6424,
Expand Down Expand Up @@ -68,43 +63,3 @@ static const uint16_t sofm_lut_sine_table_s16[SOFM_LUT_SINE_SIZE] = {
65447, 65457, 65467, 65476, 65484, 65492, 65499, 65505, 65511, 65516, 65521,
65525, 65528, 65531, 65533, 65535, 65535, 65535
};

/* Sine lookup table read */
static inline int32_t sofm_sine_lookup_16b(int idx)
{
uint16_t s;
int i1;

i1 = idx & (2 * SOFM_LUT_SINE_NQUART - 1);
if (i1 > SOFM_LUT_SINE_NQUART)
i1 = 2 * SOFM_LUT_SINE_NQUART - i1;

s = sofm_lut_sine_table_s16[i1];
if (idx > 2 * SOFM_LUT_SINE_NQUART)
return -((int32_t)s);

return (int32_t)s;
}

/* Compute fixed point sine with table lookup and interpolation */
int16_t sofm_lut_sin_fixed_16b(int32_t w)
{
int64_t idx;
int32_t sine;
int32_t frac;
int32_t delta;
int32_t s0;
int32_t s1;
int64_t idx_tmp;

/* Q4.28 x Q12.20 -> Q16.48 --> Q16.31*/
idx_tmp = ((int64_t)w * SOFM_LUT_SINE_C_Q20) >> 17;
idx = (idx_tmp >> 31); /* Shift to Q0 */
frac = (int32_t)(idx_tmp - (idx << 31)); /* Get fraction Q1.31*/
s0 = sofm_sine_lookup_16b(idx); /* Q1.16 */
s1 = sofm_sine_lookup_16b(idx + 1); /* Q1.16 */
delta = s1 - s0; /* Q1.16 */
sine = s0 + q_mults_32x32(frac, delta, Q_SHIFT_BITS_64(31, 16, 16)); /* Q1.16 */
return sat_int16((sine + 1) >> 1); /* Round to Q1.15 */
}
EXPORT_SYMBOL(sofm_lut_sin_fixed_16b);
Loading