3 files that slipped through: use ffmpeg's own copy of bswap.h to avoid

namespace conflict with xine; initial import for the faandct.* files

CVS patchset: 6097
CVS date: 2004/02/01 14:54:47

3 files changed, 380 insertions, 0 deletions

diff --git a/src/libffmpeg/libavcodec/bswap.h b/src/libffmpeg/libavcodec/bswap.h
new file mode 100644
index 000000000..460f7abd4
--- /dev/null
+++ b/src/libffmpeg/libavcodec/bswap.h
@@ -0,0 +1,129 @@
+/**
+ * @file bswap.h
+ * byte swap.
+ */
+
+#ifndef __BSWAP_H__
+#define __BSWAP_H__
+
+#ifdef HAVE_BYTESWAP_H
+#include <byteswap.h>
+#else
+
+#ifdef ARCH_X86
+static inline unsigned short ByteSwap16(unsigned short x)
+{
+  __asm("xchgb %b0,%h0"	:
+        "=q" (x)	:
+        "0" (x));
+    return x;
+}
+#define bswap_16(x) ByteSwap16(x)
+
+static inline unsigned int ByteSwap32(unsigned int x)
+{
+#if __CPU__ > 386
+ __asm("bswap	%0":
+      "=r" (x)     :
+#else
+ __asm("xchgb	%b0,%h0\n"
+      "	rorl	$16,%0\n"
+      "	xchgb	%b0,%h0":
+      "=q" (x)		:
+#endif
+      "0" (x));
+  return x;
+}
+#define bswap_32(x) ByteSwap32(x)
+
+static inline unsigned long long int ByteSwap64(unsigned long long int x)
+{
+  register union { __extension__ uint64_t __ll;
+          uint32_t __l[2]; } __x;
+  asm("xchgl	%0,%1":
+      "=r"(__x.__l[0]),"=r"(__x.__l[1]):
+      "0"(bswap_32((unsigned long)x)),"1"(bswap_32((unsigned long)(x>>32))));
+  return __x.__ll;
+}
+#define bswap_64(x) ByteSwap64(x)
+
+#elif defined(ARCH_SH4)
+
+static inline uint16_t ByteSwap16(uint16_t x) {
+	__asm__("swap.b %0,%0":"=r"(x):"0"(x));
+	return x;
+}
+
+static inline uint32_t ByteSwap32(uint32_t x) {
+	__asm__(
+	"swap.b %0,%0\n"
+	"swap.w %0,%0\n"
+	"swap.b %0,%0\n"
+	:"=r"(x):"0"(x));
+	return x;
+}
+
+#define bswap_16(x) ByteSwap16(x)
+#define bswap_32(x) ByteSwap32(x)
+
+static inline uint64_t ByteSwap64(uint64_t x)
+{
+    union { 
+        uint64_t ll;
+        struct {
+           uint32_t l,h;
+        } l;
+    } r;
+    r.l.l = bswap_32 (x);
+    r.l.h = bswap_32 (x>>32);
+    return r.ll;
+}
+#define bswap_64(x) ByteSwap64(x)
+
+#else
+
+#define bswap_16(x) (((x) & 0x00ff) << 8 | ((x) & 0xff00) >> 8)
+			
+
+// code from bits/byteswap.h (C) 1997, 1998 Free Software Foundation, Inc.
+#define bswap_32(x) \
+     ((((x) & 0xff000000) >> 24) | (((x) & 0x00ff0000) >>  8) | \
+      (((x) & 0x0000ff00) <<  8) | (((x) & 0x000000ff) << 24))
+
+static inline uint64_t ByteSwap64(uint64_t x)
+{
+    union { 
+        uint64_t ll;
+        uint32_t l[2]; 
+    } w, r;
+    w.ll = x;
+    r.l[0] = bswap_32 (w.l[1]);
+    r.l[1] = bswap_32 (w.l[0]);
+    return r.ll;
+}
+#define bswap_64(x) ByteSwap64(x)
+
+#endif	/* !ARCH_X86 */
+
+#endif	/* !HAVE_BYTESWAP_H */
+
+// be2me ... BigEndian to MachineEndian
+// le2me ... LittleEndian to MachineEndian
+
+#ifdef WORDS_BIGENDIAN
+#define be2me_16(x) (x)
+#define be2me_32(x) (x)
+#define be2me_64(x) (x)
+#define le2me_16(x) bswap_16(x)
+#define le2me_32(x) bswap_32(x)
+#define le2me_64(x) bswap_64(x)
+#else
+#define be2me_16(x) bswap_16(x)
+#define be2me_32(x) bswap_32(x)
+#define be2me_64(x) bswap_64(x)
+#define le2me_16(x) (x)
+#define le2me_32(x) (x)
+#define le2me_64(x) (x)
+#endif
+
+#endif /* __BSWAP_H__ */
diff --git a/src/libffmpeg/libavcodec/faandct.c b/src/libffmpeg/libavcodec/faandct.c
new file mode 100644
index 000000000..2a9118495
--- /dev/null
+++ b/src/libffmpeg/libavcodec/faandct.c
@@ -0,0 +1,220 @@
+/*
+ * Floating point AAN DCT
+ * Copyright (c) 2003 Michael Niedermayer <michaelni@gmx.at>
+ *
+ * This library 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 of the License, or (at your option) any later version.
+ *
+ * This library 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 this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * this implementation is based upon the IJG integer AAN DCT (see jfdctfst.c)
+ */
+
+/**
+ * @file faandct.c
+ * @brief 
+ *     Floating point AAN DCT
+ * @author Michael Niedermayer <michaelni@gmx.at>
+ */
+
+#include <math.h>
+
+#include "dsputil.h"
+#include "faandct.h"
+
+#define FLOAT float
+#ifdef FAAN_POSTSCALE
+#    define SCALE(x) postscale[x]
+#else
+#    define SCALE(x) 1
+#endif
+
+//numbers generated by simple c code (not as accurate as they could be)
+/*
+for(i=0; i<8; i++){
+    printf("#define B%d %1.20llf\n", i, (long double)1.0/(cosl(i*acosl(-1.0)/(long double)16.0)*sqrtl(2)));
+}
+*/
+#define B0 1.00000000000000000000
+#define B1 0.72095982200694791383 // (cos(pi*1/16)sqrt(2))^-1
+#define B2 0.76536686473017954350 // (cos(pi*2/16)sqrt(2))^-1
+#define B3 0.85043009476725644878 // (cos(pi*3/16)sqrt(2))^-1
+#define B4 1.00000000000000000000 // (cos(pi*4/16)sqrt(2))^-1
+#define B5 1.27275858057283393842 // (cos(pi*5/16)sqrt(2))^-1
+#define B6 1.84775906502257351242 // (cos(pi*6/16)sqrt(2))^-1
+#define B7 3.62450978541155137218 // (cos(pi*7/16)sqrt(2))^-1
+
+
+#define A1 0.70710678118654752438 // cos(pi*4/16)
+#define A2 0.54119610014619698435 // cos(pi*6/16)sqrt(2)
+#define A5 0.38268343236508977170 // cos(pi*6/16)
+#define A4 1.30656296487637652774 // cos(pi*2/16)sqrt(2)
+
+static FLOAT postscale[64]={
+B0*B0, B0*B1, B0*B2, B0*B3, B0*B4, B0*B5, B0*B6, B0*B7,
+B1*B0, B1*B1, B1*B2, B1*B3, B1*B4, B1*B5, B1*B6, B1*B7,
+B2*B0, B2*B1, B2*B2, B2*B3, B2*B4, B2*B5, B2*B6, B2*B7,
+B3*B0, B3*B1, B3*B2, B3*B3, B3*B4, B3*B5, B3*B6, B3*B7,
+B4*B0, B4*B1, B4*B2, B4*B3, B4*B4, B4*B5, B4*B6, B4*B7,
+B5*B0, B5*B1, B5*B2, B5*B3, B5*B4, B5*B5, B5*B6, B5*B7,
+B6*B0, B6*B1, B6*B2, B6*B3, B6*B4, B6*B5, B6*B6, B6*B7,
+B7*B0, B7*B1, B7*B2, B7*B3, B7*B4, B7*B5, B7*B6, B7*B7,
+};
+
+static always_inline void row_fdct(FLOAT temp[64], DCTELEM * data)
+{
+    FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
+    FLOAT tmp10, tmp11, tmp12, tmp13;
+    FLOAT z1, z2, z3, z4, z5, z11, z13;
+    int i;
+
+    for (i=0; i<8*8; i+=8) {
+        tmp0= data[0 + i] + data[7 + i];
+        tmp7= data[0 + i] - data[7 + i];
+        tmp1= data[1 + i] + data[6 + i];
+        tmp6= data[1 + i] - data[6 + i];
+        tmp2= data[2 + i] + data[5 + i];
+        tmp5= data[2 + i] - data[5 + i];
+        tmp3= data[3 + i] + data[4 + i];
+        tmp4= data[3 + i] - data[4 + i];
+        
+        tmp10= tmp0 + tmp3;
+        tmp13= tmp0 - tmp3;
+        tmp11= tmp1 + tmp2;
+        tmp12= tmp1 - tmp2;
+        
+        temp[0 + i]= tmp10 + tmp11;
+        temp[4 + i]= tmp10 - tmp11;
+        
+        z1= (tmp12 + tmp13)*A1;
+        temp[2 + i]= tmp13 + z1;
+        temp[6 + i]= tmp13 - z1;
+        
+        tmp10= tmp4 + tmp5;
+        tmp11= tmp5 + tmp6;
+        tmp12= tmp6 + tmp7;
+
+        z5= (tmp10 - tmp12) * A5;
+        z2= tmp10*A2 + z5;
+        z4= tmp12*A4 + z5;
+        z3= tmp11*A1;
+
+        z11= tmp7 + z3;
+        z13= tmp7 - z3;
+
+        temp[5 + i]= z13 + z2;
+        temp[3 + i]= z13 - z2;
+        temp[1 + i]= z11 + z4;
+        temp[7 + i]= z11 - z4;
+    }    
+}
+
+void ff_faandct(DCTELEM * data)
+{
+    FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
+    FLOAT tmp10, tmp11, tmp12, tmp13;
+    FLOAT z1, z2, z3, z4, z5, z11, z13;
+    FLOAT temp[64];
+    int i;
+
+    emms_c();
+
+    row_fdct(temp, data);
+
+    for (i=0; i<8; i++) {
+        tmp0= temp[8*0 + i] + temp[8*7 + i];
+        tmp7= temp[8*0 + i] - temp[8*7 + i];
+        tmp1= temp[8*1 + i] + temp[8*6 + i];
+        tmp6= temp[8*1 + i] - temp[8*6 + i];
+        tmp2= temp[8*2 + i] + temp[8*5 + i];
+        tmp5= temp[8*2 + i] - temp[8*5 + i];
+        tmp3= temp[8*3 + i] + temp[8*4 + i];
+        tmp4= temp[8*3 + i] - temp[8*4 + i];
+        
+        tmp10= tmp0 + tmp3;
+        tmp13= tmp0 - tmp3;
+        tmp11= tmp1 + tmp2;
+        tmp12= tmp1 - tmp2;
+        
+        data[8*0 + i]= lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
+        data[8*4 + i]= lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
+        
+        z1= (tmp12 + tmp13)* A1;
+        data[8*2 + i]= lrintf(SCALE(8*2 + i) * (tmp13 + z1));
+        data[8*6 + i]= lrintf(SCALE(8*6 + i) * (tmp13 - z1));
+        
+        tmp10= tmp4 + tmp5;
+        tmp11= tmp5 + tmp6;
+        tmp12= tmp6 + tmp7;
+
+        z5= (tmp10 - tmp12) * A5;
+        z2= tmp10*A2 + z5;
+        z4= tmp12*A4 + z5;
+        z3= tmp11*A1;
+
+        z11= tmp7 + z3;
+        z13= tmp7 - z3;
+
+        data[8*5 + i]= lrintf(SCALE(8*5 + i) * (z13 + z2));
+        data[8*3 + i]= lrintf(SCALE(8*3 + i) * (z13 - z2));
+        data[8*1 + i]= lrintf(SCALE(8*1 + i) * (z11 + z4));
+        data[8*7 + i]= lrintf(SCALE(8*7 + i) * (z11 - z4));
+    }
+}
+
+void ff_faandct248(DCTELEM * data)
+{
+    FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
+    FLOAT tmp10, tmp11, tmp12, tmp13;
+    FLOAT z1;
+    FLOAT temp[64];
+    int i;
+
+    emms_c();
+
+    row_fdct(temp, data);
+
+    for (i=0; i<8; i++) {
+        tmp0 = temp[8*0 + i] + temp[8*1 + i];
+        tmp1 = temp[8*2 + i] + temp[8*3 + i];
+        tmp2 = temp[8*4 + i] + temp[8*5 + i];
+        tmp3 = temp[8*6 + i] + temp[8*7 + i];
+        tmp4 = temp[8*0 + i] - temp[8*1 + i];
+        tmp5 = temp[8*2 + i] - temp[8*3 + i];
+        tmp6 = temp[8*4 + i] - temp[8*5 + i];
+        tmp7 = temp[8*6 + i] - temp[8*7 + i];
+        
+        tmp10 = tmp0 + tmp3;
+        tmp11 = tmp1 + tmp2;
+        tmp12 = tmp1 - tmp2;
+        tmp13 = tmp0 - tmp3;
+        
+        data[8*0 + i] = lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
+        data[8*4 + i] = lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
+        
+        z1 = (tmp12 + tmp13)* A1;
+        data[8*2 + i] = lrintf(SCALE(8*2 + i) * (tmp13 + z1));
+        data[8*6 + i] = lrintf(SCALE(8*6 + i) * (tmp13 - z1));
+        
+        tmp10 = tmp4 + tmp7;
+	tmp11 = tmp5 + tmp6;
+	tmp12 = tmp5 - tmp6;
+	tmp13 = tmp4 - tmp7;
+
+	data[8*1 + i] = lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
+	data[8*5 + i] = lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
+
+	z1 = (tmp12 + tmp13)* A1;
+	data[8*3 + i] = lrintf(SCALE(8*2 + i) * (tmp13 + z1));
+	data[8*7 + i] = lrintf(SCALE(8*6 + i) * (tmp13 - z1));
+    }
+}
diff --git a/src/libffmpeg/libavcodec/faandct.h b/src/libffmpeg/libavcodec/faandct.h
new file mode 100644
index 000000000..c40f8016b
--- /dev/null
+++ b/src/libffmpeg/libavcodec/faandct.h
@@ -0,0 +1,31 @@
+/*
+ * Floating point AAN DCT
+ * Copyright (c) 2003 Michael Niedermayer <michaelni@gmx.at>
+ *
+ * This library 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 of the License, or (at your option) any later version.
+ *
+ * This library 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 this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+/**
+ * @file faandct.h
+ * @brief 
+ *     Floating point AAN DCT
+ * @author Michael Niedermayer <michaelni@gmx.at>
+ */
+ 
+#define FAAN_POSTSCALE
+ 
+void ff_faandct(DCTELEM * data);
+void ff_faandct248(DCTELEM * data);