From 8992cb1d0d07edc33d274f6d7924ecdf6f83d994 Mon Sep 17 00:00:00 2001
From: Tim Redfern <tim@eclectronics.org>
Date: Thu, 5 Sep 2013 17:57:22 +0100
Subject: making act segmenter

---
 ffmpeg/libavcodec/x86/lpc.c | 154 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 154 insertions(+)
 create mode 100644 ffmpeg/libavcodec/x86/lpc.c

(limited to 'ffmpeg/libavcodec/x86/lpc.c')

diff --git a/ffmpeg/libavcodec/x86/lpc.c b/ffmpeg/libavcodec/x86/lpc.c
new file mode 100644
index 0000000..1962212
--- /dev/null
+++ b/ffmpeg/libavcodec/x86/lpc.c
@@ -0,0 +1,154 @@
+/*
+ * MMX optimized LPC DSP utils
+ * Copyright (c) 2007 Loren Merritt
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * FFmpeg is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with FFmpeg; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#include "libavutil/x86/asm.h"
+#include "libavutil/attributes.h"
+#include "libavutil/cpu.h"
+#include "libavcodec/lpc.h"
+
+#if HAVE_SSE2_INLINE
+
+static void lpc_apply_welch_window_sse2(const int32_t *data, int len,
+                                        double *w_data)
+{
+    double c = 2.0 / (len-1.0);
+    int n2 = len>>1;
+    x86_reg i = -n2*sizeof(int32_t);
+    x86_reg j =  n2*sizeof(int32_t);
+    __asm__ volatile(
+        "movsd   %4,     %%xmm7                \n\t"
+        "movapd  "MANGLE(ff_pd_1)", %%xmm6     \n\t"
+        "movapd  "MANGLE(ff_pd_2)", %%xmm5     \n\t"
+        "movlhps %%xmm7, %%xmm7                \n\t"
+        "subpd   %%xmm5, %%xmm7                \n\t"
+        "addsd   %%xmm6, %%xmm7                \n\t"
+        "test    $1,     %5                    \n\t"
+        "jz      2f                            \n\t"
+#define WELCH(MOVPD, offset)\
+        "1:                                    \n\t"\
+        "movapd   %%xmm7,  %%xmm1              \n\t"\
+        "mulpd    %%xmm1,  %%xmm1              \n\t"\
+        "movapd   %%xmm6,  %%xmm0              \n\t"\
+        "subpd    %%xmm1,  %%xmm0              \n\t"\
+        "pshufd   $0x4e,   %%xmm0, %%xmm1      \n\t"\
+        "cvtpi2pd (%3,%0), %%xmm2              \n\t"\
+        "cvtpi2pd "#offset"*4(%3,%1), %%xmm3   \n\t"\
+        "mulpd    %%xmm0,  %%xmm2              \n\t"\
+        "mulpd    %%xmm1,  %%xmm3              \n\t"\
+        "movapd   %%xmm2, (%2,%0,2)            \n\t"\
+        MOVPD"    %%xmm3, "#offset"*8(%2,%1,2) \n\t"\
+        "subpd    %%xmm5,  %%xmm7              \n\t"\
+        "sub      $8,      %1                  \n\t"\
+        "add      $8,      %0                  \n\t"\
+        "jl 1b                                 \n\t"\
+
+        WELCH("movupd", -1)
+        "jmp 3f                                \n\t"
+        "2:                                    \n\t"
+        WELCH("movapd", -2)
+        "3:                                    \n\t"
+        :"+&r"(i), "+&r"(j)
+        :"r"(w_data+n2), "r"(data+n2), "m"(c), "r"(len)
+         XMM_CLOBBERS_ONLY("%xmm0", "%xmm1", "%xmm2", "%xmm3",
+                                    "%xmm5", "%xmm6", "%xmm7")
+    );
+#undef WELCH
+}
+
+static void lpc_compute_autocorr_sse2(const double *data, int len, int lag,
+                                      double *autoc)
+{
+    int j;
+
+    if((x86_reg)data & 15)
+        data++;
+
+    for(j=0; j<lag; j+=2){
+        x86_reg i = -len*sizeof(double);
+        if(j == lag-2) {
+            __asm__ volatile(
+                "movsd    "MANGLE(ff_pd_1)", %%xmm0 \n\t"
+                "movsd    "MANGLE(ff_pd_1)", %%xmm1 \n\t"
+                "movsd    "MANGLE(ff_pd_1)", %%xmm2 \n\t"
+                "1:                                 \n\t"
+                "movapd   (%2,%0), %%xmm3           \n\t"
+                "movupd -8(%3,%0), %%xmm4           \n\t"
+                "movapd   (%3,%0), %%xmm5           \n\t"
+                "mulpd     %%xmm3, %%xmm4           \n\t"
+                "mulpd     %%xmm3, %%xmm5           \n\t"
+                "mulpd -16(%3,%0), %%xmm3           \n\t"
+                "addpd     %%xmm4, %%xmm1           \n\t"
+                "addpd     %%xmm5, %%xmm0           \n\t"
+                "addpd     %%xmm3, %%xmm2           \n\t"
+                "add       $16,    %0               \n\t"
+                "jl 1b                              \n\t"
+                "movhlps   %%xmm0, %%xmm3           \n\t"
+                "movhlps   %%xmm1, %%xmm4           \n\t"
+                "movhlps   %%xmm2, %%xmm5           \n\t"
+                "addsd     %%xmm3, %%xmm0           \n\t"
+                "addsd     %%xmm4, %%xmm1           \n\t"
+                "addsd     %%xmm5, %%xmm2           \n\t"
+                "movsd     %%xmm0,   (%1)           \n\t"
+                "movsd     %%xmm1,  8(%1)           \n\t"
+                "movsd     %%xmm2, 16(%1)           \n\t"
+                :"+&r"(i)
+                :"r"(autoc+j), "r"(data+len), "r"(data+len-j)
+                :"memory"
+            );
+        } else {
+            __asm__ volatile(
+                "movsd    "MANGLE(ff_pd_1)", %%xmm0 \n\t"
+                "movsd    "MANGLE(ff_pd_1)", %%xmm1 \n\t"
+                "1:                                 \n\t"
+                "movapd   (%3,%0), %%xmm3           \n\t"
+                "movupd -8(%4,%0), %%xmm4           \n\t"
+                "mulpd     %%xmm3, %%xmm4           \n\t"
+                "mulpd    (%4,%0), %%xmm3           \n\t"
+                "addpd     %%xmm4, %%xmm1           \n\t"
+                "addpd     %%xmm3, %%xmm0           \n\t"
+                "add       $16,    %0               \n\t"
+                "jl 1b                              \n\t"
+                "movhlps   %%xmm0, %%xmm3           \n\t"
+                "movhlps   %%xmm1, %%xmm4           \n\t"
+                "addsd     %%xmm3, %%xmm0           \n\t"
+                "addsd     %%xmm4, %%xmm1           \n\t"
+                "movsd     %%xmm0, %1               \n\t"
+                "movsd     %%xmm1, %2               \n\t"
+                :"+&r"(i), "=m"(autoc[j]), "=m"(autoc[j+1])
+                :"r"(data+len), "r"(data+len-j)
+            );
+        }
+    }
+}
+
+#endif /* HAVE_SSE2_INLINE */
+
+av_cold void ff_lpc_init_x86(LPCContext *c)
+{
+#if HAVE_SSE2_INLINE
+    int mm_flags = av_get_cpu_flags();
+
+    if (mm_flags & (AV_CPU_FLAG_SSE2|AV_CPU_FLAG_SSE2SLOW)) {
+        c->lpc_apply_welch_window = lpc_apply_welch_window_sse2;
+        c->lpc_compute_autocorr   = lpc_compute_autocorr_sse2;
+    }
+#endif /* HAVE_SSE2_INLINE */
+}
-- 
cgit v1.2.3