alsabat: truncate sample frames for faster FFT analysis

Truncate the sample frames to powers of 2, since the FFTW algorithm
runs especially fast in this case, and other sizes may be computed
by means of a slow, general-purpose algorithm.
In my test environment applying the patch, a sound clip of 33072
frames is cut off to 32768 frames before analysis, and the time
cost is reduced from 6.128s to 0.224s.

Signed-off-by: Lu, Han <han.lu@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

diff --git a/bat/analyze.c b/bat/analyze.c
index 60e2d1c945b37ddac4375389669531e2ce8e6642..5cfdac38f19edb45669dc66cbb361263f3645330 100644 (file)
--- a/bat/analyze.c
+++ b/bat/analyze.c
@@ -256,6 +256,20 @@ static int reorder_data(struct bat *bat)
        return 0;
 }
 
+/* truncate sample frames for faster FFT analysis process */
+static int truncate_frames(struct bat *bat)
+{
+       int shift = SHIFT_MAX;
+
+       for (; shift > SHIFT_MIN; shift--)
+               if (bat->frames & (1 << shift)) {
+                       bat->frames = 1 << shift;
+                       return 0;
+               }
+
+       return -EINVAL;
+}
+
 int analyze_capture(struct bat *bat)
 {
        int err = 0;
@@ -263,6 +277,13 @@ int analyze_capture(struct bat *bat)
        int c;
        struct analyze a;
 
+       err = truncate_frames(bat);
+       if (err < 0) {
+               fprintf(bat->err, _("Invalid frame number for analysis: %d\n"),
+                               bat->frames);
+               return err;
+       }
+
        fprintf(bat->log, _("\nBAT analysis: signal has %d frames at %d Hz,"),
                        bat->frames, bat->rate);
        fprintf(bat->log, _(" %d channels, %d bytes per sample.\n"),

diff --git a/bat/common.h b/bat/common.h
index c04452db70b0f8ea3079ac71969844bc30c976cc..7346d9fab682b598273d08211aa3b0136b6543d7 100644 (file)
--- a/bat/common.h
+++ b/bat/common.h
@@ -63,6 +63,12 @@
 #define FOUND_DC                       (1<<1)
 #define FOUND_WRONG_PEAK               (1<<0)
 
+/* Truncate sample frames to (1 << N), for faster FFT analysis process. The
+ * valid range of N is (SHIFT_MIN, SHIFT_MAX). When N increases, the analysis
+ * will be more time-consuming, and the result will be more accurate. */
+#define SHIFT_MAX                      (sizeof(int) * 8 - 2)
+#define SHIFT_MIN                      8
+
 struct wav_header {
        unsigned int magic; /* 'RIFF' */
        unsigned int length; /* file len */