From 931a223439642c2711148bcee787a4728af1c531 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sebastian=20Dr=C3=B6ge?= <slomo@circular-chaos.org>
Date: Sun, 2 Nov 2008 09:19:24 +0000
Subject: gst/speexresample/gstspeexresample.c: Fix format string and
 arguments.

Original commit message from CVS:
* gst/speexresample/gstspeexresample.c:
(gst_speex_resample_check_discont):
Fix format string and arguments.
* gst/speexresample/resample_sse.h:
Add missing file.
---
 ChangeLog                            |   9 +++
 gst/speexresample/gstspeexresample.c |   2 +-
 gst/speexresample/resample_sse.h     | 128 +++++++++++++++++++++++++++++++++++
 3 files changed, 138 insertions(+), 1 deletion(-)
 create mode 100644 gst/speexresample/resample_sse.h

diff --git a/ChangeLog b/ChangeLog
index 3ff5252c..be6de712 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2008-11-02  Sebastian Dröge  <sebastian.droege@collabora.co.uk>
+
+	* gst/speexresample/gstspeexresample.c:
+	(gst_speex_resample_check_discont):
+	Fix format string and arguments.
+
+	* gst/speexresample/resample_sse.h:
+	Add missing file.
+
 2008-11-01  Stefan Kost  <ensonic@users.sf.net>
 
 	* ext/resindvd/Makefile.am:
diff --git a/gst/speexresample/gstspeexresample.c b/gst/speexresample/gstspeexresample.c
index f2fa4859..84057e64 100644
--- a/gst/speexresample/gstspeexresample.c
+++ b/gst/speexresample/gstspeexresample.c
@@ -864,7 +864,7 @@ gst_speex_resample_check_discont (GstSpeexResample * resample,
     if (ABS (diff) > (GST_SECOND + resample->inrate - 1) / resample->inrate) {
       GST_WARNING_OBJECT (resample,
           "encountered timestamp discontinuity of %s%" GST_TIME_FORMAT,
-          (diff < 0) ? "-" : "", ABS (diff));
+          (diff < 0) ? "-" : "", GST_TIME_ARGS ((GstClockTime) ABS (diff)));
       return TRUE;
     }
   }
diff --git a/gst/speexresample/resample_sse.h b/gst/speexresample/resample_sse.h
new file mode 100644
index 00000000..4bd35a2d
--- /dev/null
+++ b/gst/speexresample/resample_sse.h
@@ -0,0 +1,128 @@
+/* Copyright (C) 2007-2008 Jean-Marc Valin
+ * Copyright (C) 2008 Thorvald Natvig
+ */
+/**
+   @file resample_sse.h
+   @brief Resampler functions (SSE version)
+*/
+/*
+   Redistribution and use in source and binary forms, with or without
+   modification, are permitted provided that the following conditions
+   are met:
+   
+   - Redistributions of source code must retain the above copyright
+   notice, this list of conditions and the following disclaimer.
+   
+   - Redistributions in binary form must reproduce the above copyright
+   notice, this list of conditions and the following disclaimer in the
+   documentation and/or other materials provided with the distribution.
+   
+   - Neither the name of the Xiph.org Foundation nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+   
+   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+   ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+   A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR
+   CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+   EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+   PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+   PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+   LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+   NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+   SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+*/
+
+#include <xmmintrin.h>
+
+#define OVERRIDE_INNER_PRODUCT_SINGLE
+static inline float inner_product_single(const float *a, const float *b, unsigned int len)
+{
+   int i;
+   float ret;
+   __m128 sum = _mm_setzero_ps();
+   for (i=0;i<len;i+=8)
+   {
+      sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i)));
+      sum = _mm_add_ps(sum, _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4)));
+   }
+   sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));
+   sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
+   _mm_store_ss(&ret, sum);
+   return ret;
+}
+
+#define OVERRIDE_INTERPOLATE_PRODUCT_SINGLE
+static inline float interpolate_product_single(const float *a, const float *b, unsigned int len, const spx_uint32_t oversample, float *frac) {
+  int i;
+  float ret;
+  __m128 sum = _mm_setzero_ps();
+  __m128 f = _mm_loadu_ps(frac);
+  for(i=0;i<len;i+=2)
+  {
+    sum = _mm_add_ps(sum, _mm_mul_ps(_mm_load1_ps(a+i), _mm_loadu_ps(b+i*oversample)));
+    sum = _mm_add_ps(sum, _mm_mul_ps(_mm_load1_ps(a+i+1), _mm_loadu_ps(b+(i+1)*oversample)));
+  }
+   sum = _mm_mul_ps(f, sum);
+   sum = _mm_add_ps(sum, _mm_movehl_ps(sum, sum));
+   sum = _mm_add_ss(sum, _mm_shuffle_ps(sum, sum, 0x55));
+   _mm_store_ss(&ret, sum);
+   return ret;
+}
+
+#ifdef _USE_SSE2
+#include <emmintrin.h>
+#define OVERRIDE_INNER_PRODUCT_DOUBLE
+
+static inline double inner_product_double(const float *a, const float *b, unsigned int len)
+{
+   int i;
+   double ret;
+   __m128d sum = _mm_setzero_pd();
+   __m128 t;
+   for (i=0;i<len;i+=8)
+   {
+      t = _mm_mul_ps(_mm_loadu_ps(a+i), _mm_loadu_ps(b+i));
+      sum = _mm_add_pd(sum, _mm_cvtps_pd(t));
+      sum = _mm_add_pd(sum, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
+
+      t = _mm_mul_ps(_mm_loadu_ps(a+i+4), _mm_loadu_ps(b+i+4));
+      sum = _mm_add_pd(sum, _mm_cvtps_pd(t));
+      sum = _mm_add_pd(sum, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
+   }
+   sum = _mm_add_sd(sum, (__m128d) _mm_movehl_ps((__m128) sum, (__m128) sum));
+   _mm_store_sd(&ret, sum);
+   return ret;
+}
+
+#define OVERRIDE_INTERPOLATE_PRODUCT_DOUBLE
+static inline double interpolate_product_double(const float *a, const float *b, unsigned int len, const spx_uint32_t oversample, float *frac) {
+  int i;
+  double ret;
+  __m128d sum;
+  __m128d sum1 = _mm_setzero_pd();
+  __m128d sum2 = _mm_setzero_pd();
+  __m128 f = _mm_loadu_ps(frac);
+  __m128d f1 = _mm_cvtps_pd(f);
+  __m128d f2 = _mm_cvtps_pd(_mm_movehl_ps(f,f));
+  __m128 t;
+  for(i=0;i<len;i+=2)
+  {
+    t = _mm_mul_ps(_mm_load1_ps(a+i), _mm_loadu_ps(b+i*oversample));
+    sum1 = _mm_add_pd(sum1, _mm_cvtps_pd(t));
+    sum2 = _mm_add_pd(sum2, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
+
+    t = _mm_mul_ps(_mm_load1_ps(a+i+1), _mm_loadu_ps(b+(i+1)*oversample));
+    sum1 = _mm_add_pd(sum1, _mm_cvtps_pd(t));
+    sum2 = _mm_add_pd(sum2, _mm_cvtps_pd(_mm_movehl_ps(t, t)));
+  }
+  sum1 = _mm_mul_pd(f1, sum1);
+  sum2 = _mm_mul_pd(f2, sum2);
+  sum = _mm_add_pd(sum1, sum2);
+  sum = _mm_add_sd(sum, (__m128d) _mm_movehl_ps((__m128) sum, (__m128) sum));
+  _mm_store_sd(&ret, sum);
+  return ret;
+}
+
+#endif
-- 
cgit v1.2.1