summaryrefslogtreecommitdiffstats
path: root/media/libspeex_resampler/src/resample_sse.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-28 14:29:10 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-28 14:29:10 +0000
commit2aa4a82499d4becd2284cdb482213d541b8804dd (patch)
treeb80bf8bf13c3766139fbacc530efd0dd9d54394c /media/libspeex_resampler/src/resample_sse.c
parentInitial commit. (diff)
downloadfirefox-2aa4a82499d4becd2284cdb482213d541b8804dd.tar.xz
firefox-2aa4a82499d4becd2284cdb482213d541b8804dd.zip
Adding upstream version 86.0.1.upstream/86.0.1upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'media/libspeex_resampler/src/resample_sse.c')
-rw-r--r--media/libspeex_resampler/src/resample_sse.c130
1 files changed, 130 insertions, 0 deletions
diff --git a/media/libspeex_resampler/src/resample_sse.c b/media/libspeex_resampler/src/resample_sse.c
new file mode 100644
index 0000000000..53d47776e9
--- /dev/null
+++ b/media/libspeex_resampler/src/resample_sse.c
@@ -0,0 +1,130 @@
+/* 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 "simd_detect.h"
+
+#include <xmmintrin.h>
+
+#define OVERRIDE_INNER_PRODUCT_SINGLE
+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
+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
+
+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, _mm_unpackhi_pd(sum, sum));
+ _mm_store_sd(&ret, sum);
+ return ret;
+}
+
+#define OVERRIDE_INTERPOLATE_PRODUCT_DOUBLE
+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, _mm_unpackhi_pd(sum, sum));
+ _mm_store_sd(&ret, sum);
+ return ret;
+}
+
+#endif