From: Peter Meerwald <p.meerwald@xxxxxxxxxxxxxxxxxx>
Input channels may just be copied to output channels, no mixing; this
avoids the generic (slow) matrix remapping code in cases where channels
are dropped or reordered.
This makes use of the remap struct state introduced earlier.
on Intel Core i7-870 @ 2.93 GHz (GCC 4.6, 64-bit):
Checking special remap (s16, stereo rearrange)
func: 126117 usec (avg: 1261.17, min = 1150, max = 2111, stddev = 117.332).
orig: 190509 usec (avg: 1905.09, min = 1807, max = 2402, stddev = 100.984).
Checking special remap (float, stereo rearrange)
func: 194329 usec (avg: 1943.29, min = 1876, max = 2127, stddev = 64.3486).
orig: 205263 usec (avg: 2052.63, min = 2005, max = 2452, stddev = 70.177).
Checking special remap (s16, 4-channel rearrange)
func: 278754 usec (avg: 2787.54, min = 2719, max = 3093, stddev = 78.22).
orig: 383885 usec (avg: 3838.85, min = 3634, max = 4121, stddev = 128.522).
Checking special remap (float, 4-channel rearrange)
func: 312429 usec (avg: 3124.29, min = 3017, max = 3498, stddev = 120.127).
orig: 388198 usec (avg: 3881.98, min = 3768, max = 4655, stddev = 138.441).
on ARM Cortex-A8 (TI OMAP3 DM3730 @ 1GHz) (Linaro GCC 4.6):
Checking special remap (s16, stereo rearrange)
func: 1204647 usec (avg: 12046.5, min = 10406, max = 25451, stddev = 2491.9).
orig: 1660311 usec (avg: 16603.1, min = 14740, max = 20416, stddev = 1708.07).
Checking special remap (float, stereo rearrange)
func: 1391392 usec (avg: 13913.9, min = 12207, max = 28260, stddev = 2238.12).
orig: 9246707 usec (avg: 92467.1, min = 87525, max = 125611, stddev = 5494.64).
Checking special remap (s16, 4-channel rearrange)
func: 2540225 usec (avg: 25402.2, min = 16937, max = 68268, stddev = 10786.7).
orig: 3319852 usec (avg: 33198.5, min = 29571, max = 36957, stddev = 1250.39).
Checking special remap (float, 4-channel rearrange)
func: 3024414 usec (avg: 30244.1, min = 26153, max = 58105, stddev = 4506.01).
orig: 12643624 usec (avg: 126436, min = 120575, max = 159088, stddev = 5519.28).
benchmark code will be posted as follow-up patches
Signed-off-by: Peter Meerwald <pmeerw at pmeerw.net>
---
src/pulsecore/remap.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 73 insertions(+), 1 deletion(-)
diff --git a/src/pulsecore/remap.c b/src/pulsecore/remap.c
index c3de424..80194a4 100644
--- a/src/pulsecore/remap.c
+++ b/src/pulsecore/remap.c
@@ -26,6 +26,7 @@
#include <string.h>
+#include <pulse/xmalloc.h>
#include <pulse/sample.h>
#include <pulse/volume.h>
#include <pulsecore/log.h>
@@ -158,6 +159,60 @@ bool pa_setup_remap_arrange(const pa_remap_t *m, int8_t arrange[PA_CHANNELS_MAX]
return true;
}
+static void remap_arrange_stereo_s16ne_c(pa_remap_t *m, int16_t *dst, const int16_t *src, unsigned n) {
+ const unsigned n_ic = m->i_ss.channels;
+ const int8_t *arrange = m->state;
+ const int8_t ic0 = arrange[0], ic1 = arrange[1];
+
+ for (; n > 0; n--) {
+ *dst++ = (ic0 >= 0) ? *(src + ic0) : 0;
+ *dst++ = (ic1 >= 0) ? *(src + ic1) : 0;
+ src += n_ic;
+ }
+}
+
+static void remap_arrange_ch4_s16ne_c(pa_remap_t *m, int16_t *dst, const int16_t *src, unsigned n) {
+ const unsigned n_ic = m->i_ss.channels;
+ const int8_t *arrange = m->state;
+ const int8_t ic0 = arrange[0], ic1 = arrange[1],
+ ic2 = arrange[2], ic3 = arrange[3];
+
+ for (; n > 0; n--) {
+ *dst++ = (ic0 >= 0) ? *(src + ic0) : 0;
+ *dst++ = (ic1 >= 0) ? *(src + ic1) : 0;
+ *dst++ = (ic2 >= 0) ? *(src + ic2) : 0;
+ *dst++ = (ic3 >= 0) ? *(src + ic3) : 0;
+ src += n_ic;
+ }
+}
+
+static void remap_arrange_stereo_float32ne_c(pa_remap_t *m, float *dst, const float *src, unsigned n) {
+ const unsigned n_ic = m->i_ss.channels;
+ const int8_t *arrange = m->state;
+ const int ic0 = arrange[0], ic1 = arrange[1];
+
+ for (; n > 0; n--) {
+ *dst++ = (ic0 >= 0) ? *(src + ic0) : 0.0f;
+ *dst++ = (ic1 >= 0) ? *(src + ic1) : 0.0f;
+ src += n_ic;
+ }
+}
+
+static void remap_arrange_ch4_float32ne_c(pa_remap_t *m, float *dst, const float *src, unsigned n) {
+ const unsigned n_ic = m->i_ss.channels;
+ const int8_t *arrange = m->state;
+ const int ic0 = arrange[0], ic1 = arrange[1],
+ ic2 = arrange[2], ic3 = arrange[3];
+
+ for (; n > 0; n--) {
+ *dst++ = (ic0 >= 0) ? *(src + ic0) : 0.0f;
+ *dst++ = (ic1 >= 0) ? *(src + ic1) : 0.0f;
+ *dst++ = (ic2 >= 0) ? *(src + ic2) : 0.0f;
+ *dst++ = (ic3 >= 0) ? *(src + ic3) : 0.0f;
+ src += n_ic;
+ }
+}
+
void pa_set_remap_func(pa_remap_t *m, pa_do_remap_func_t func_s16,
pa_do_remap_func_t func_float) {
@@ -174,6 +229,7 @@ void pa_set_remap_func(pa_remap_t *m, pa_do_remap_func_t func_s16,
/* set the function that will execute the remapping based on the matrices */
static void init_remap_c(pa_remap_t *m) {
unsigned n_oc, n_ic;
+ int8_t arrange[PA_CHANNELS_MAX];
n_oc = m->o_ss.channels;
n_ic = m->i_ss.channels;
@@ -185,9 +241,25 @@ static void init_remap_c(pa_remap_t *m) {
pa_log_info("Using mono to stereo remapping");
pa_set_remap_func(m, (pa_do_remap_func_t) remap_mono_to_stereo_s16ne_c,
(pa_do_remap_func_t) remap_mono_to_stereo_float32ne_c);
+ } else if (pa_setup_remap_arrange(m, arrange) && n_oc == 2) {
+
+ pa_log_info("Using stereo arrange remapping");
+ pa_set_remap_func(m, (pa_do_remap_func_t) remap_arrange_stereo_s16ne_c,
+ (pa_do_remap_func_t) remap_arrange_stereo_float32ne_c);
+
+ /* setup state */
+ m->state = pa_xnewdup(int8_t, arrange, PA_CHANNELS_MAX);
+ } else if (pa_setup_remap_arrange(m, arrange) && n_oc == 4) {
+
+ pa_log_info("Using 4-channel arrange remapping");
+ pa_set_remap_func(m, (pa_do_remap_func_t) remap_arrange_ch4_s16ne_c,
+ (pa_do_remap_func_t) remap_arrange_ch4_float32ne_c);
+
+ /* setup state */
+ m->state = pa_xnewdup(int8_t, arrange, PA_CHANNELS_MAX);
} else {
- pa_log_info("Using generic matrix remapping");
+ pa_log_info("Using generic matrix remapping");
pa_set_remap_func(m, (pa_do_remap_func_t) remap_channels_matrix_s16ne_c,
(pa_do_remap_func_t) remap_channels_matrix_float32ne_c);
}
--
1.9.1
