New single instruction math operation header

git-svn-id: file:///var/local/repositories/ffmpeg/trunk@6291 9553f0bf-9b14-0410-a0b8-cfaf0461ba5b

libavcodec/armv4l/mathops.h

+/*
+ * simple math operations
+ * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifdef FRAC_BITS
+#   define MULL(a, b) \
+        ({  int lo, hi;\
+         asm("smull %0, %1, %2, %3     \n\t"\
+             "mov   %0, %0,     lsr %4\n\t"\
+             "add   %1, %0, %1, lsl %5\n\t"\
+             : "=&r"(lo), "=&r"(hi)\
+             : "r"(b), "r"(a), "i"(FRAC_BITS), "i"(32-FRAC_BITS));\
+         hi; })
+#endif
+
+#define MULH(a, b) \
+    ({ int lo, hi;\
+     asm ("smull %0, %1, %2, %3" : "=&r"(lo), "=&r"(hi) : "r"(b), "r"(a));\
+     hi; })
+
+#if defined(HAVE_ARMV5TE)
+
+/* signed 16x16 -> 32 multiply add accumulate */
+#   define MAC16(rt, ra, rb) \
+        asm ("smlabb %0, %2, %3, %0" : "=r" (rt) : "0" (rt), "r" (ra), "r" (rb));
+/* signed 16x16 -> 32 multiply */
+#   define MUL16(ra, rb) \
+        ({ int __rt;\
+         asm ("smulbb %0, %1, %2" : "=r" (__rt) : "r" (ra), "r" (rb));
+         __rt; })
+
+#endif

libavcodec/i386/mathops.h

+/*
+ * simple math operations
+ * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifdef FRAC_BITS
+#   define MULL(ra, rb) \
+        ({ int rt, dummy; asm (\
+            "imull %3               \n\t"\
+            "shrdl %4, %%edx, %%eax \n\t"\
+            : "=a"(rt), "=d"(dummy)\
+            : "a" (ra), "rm" (rb), "i"(FRAC_BITS));\
+         rt; })
+#endif
+
+#define MULH(ra, rb) \
+    ({ int rt, dummy;\
+     asm ("imull %3\n\t" : "=d"(rt), "=a"(dummy): "a" (ra), "rm" (rb));\
+     rt; })
+
+#define MUL64(ra, rb) \
+    ({ int64_t rt;\
+     asm ("imull %2\n\t" : "=A"(rt) : "a" (ra), "g" (rb));\
+     rt; })
+

libavcodec/mathops.h

+/*
+ * simple math operations
+ * Copyright (c) 2001, 2002 Fabrice Bellard.
+ * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#ifndef MATHOPS_H
+#define MATHOPS_H
+
+#ifdef ARCH_X86
+
+#include "i386/mathops.h"
+
+#elif defined(ARCH_ARMV4L)
+
+#include "armv4l/mathops.h"
+
+#elif defined(ARCH_PPC)
+
+#include "ppc/mathops.h"
+
+#endif
+
+/* generic implementation */
+
+#ifndef MULL
+#   define MULL(a,b) (((int64_t)(a) * (int64_t)(b)) >> FRAC_BITS)
+#endif
+
+#ifndef MULH
+//gcc 3.4 creates an incredibly bloated mess out of this
+//#    define MULH(a,b) (((int64_t)(a) * (int64_t)(b))>>32)
+
+static always_inline int MULH(int a, int b){
+    return ((int64_t)(a) * (int64_t)(b))>>32;
+}
+#endif
+
+#ifndef MUL64
+#   define MUL64(a,b) ((int64_t)(a) * (int64_t)(b))
+#endif
+
+/* signed 16x16 -> 32 multiply add accumulate */
+#ifndef MAC16
+#   define MAC16(rt, ra, rb) rt += (ra) * (rb)
+#endif
+
+/* signed 16x16 -> 32 multiply */
+#ifndef MUL16
+#   define MUL16(ra, rb) ((ra) * (rb))
+#endif
+
+#endif //MATHOPS_H
+

libavcodec/ppc/mathops.h

+/*
+ * simple math operations
+ * Copyright (c) 2001, 2002 Fabrice Bellard.
+ * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
+ *
+ * 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#if defined(ARCH_POWERPC_405)
+/* signed 16x16 -> 32 multiply add accumulate */
+#   define MAC16(rt, ra, rb) \
+        asm ("maclhw %0, %2, %3" : "=r" (rt) : "0" (rt), "r" (ra), "r" (rb));
+
+/* signed 16x16 -> 32 multiply */
+#   define MUL16(ra, rb) \
+        ({ int __rt;
+         asm ("mullhw %0, %1, %2" : "=r" (__rt) : "r" (ra), "r" (rb));
+         __rt; })
+#endif