X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=libavcodec%2Fx86%2Fmathops.h;h=2c04d9d1bd0117a3d02f4992e047c27185450d16;hb=c3e83ad3b7d75f3597f47ada2616ba4479665009;hp=691a200fd4d25686deb25de46440262b1006456f;hpb=5e7dfb7de11dab3cbf8663d4fcb682935bd3a80b;p=ffmpeg

diff --git a/libavcodec/x86/mathops.h b/libavcodec/x86/mathops.h
index 691a200fd4d..2c04d9d1bd0 100644
--- a/libavcodec/x86/mathops.h
+++ b/libavcodec/x86/mathops.h
@@ -2,20 +2,20 @@
  * simple math operations
  * Copyright (c) 2006 Michael Niedermayer <michaelni@gmx.at> et al
  *
- * This file is part of FFmpeg.
+ * This file is part of Libav.
  *
- * FFmpeg is free software; you can redistribute it and/or
+ * Libav 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,
+ * Libav 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
+ * License along with Libav; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
@@ -23,35 +23,60 @@
 #define AVCODEC_X86_MATHOPS_H
 
 #include "config.h"
+
 #include "libavutil/common.h"
+#include "libavutil/x86/asm.h"
+
+#if HAVE_INLINE_ASM
 
 #if ARCH_X86_32
-#define MULL(ra, rb, shift) \
-        ({ int rt, dummy; __asm__ (\
-            "imull %3               \n\t"\
-            "shrdl %4, %%edx, %%eax \n\t"\
-            : "=a"(rt), "=d"(dummy)\
-            : "a" ((int)ra), "rm" ((int)rb), "i"(shift));\
-         rt; })
-
-#define MULH(ra, rb) \
-    ({ int rt, dummy;\
-     __asm__ ("imull %3\n\t" : "=d"(rt), "=a"(dummy): "a" ((int)ra), "rm" ((int)rb));\
-     rt; })
-
-#define MUL64(ra, rb) \
-    ({ int64_t rt;\
-     __asm__ ("imull %2\n\t" : "=A"(rt) : "a" ((int)ra), "g" ((int)rb));\
-     rt; })
-#endif
-
-#if HAVE_CMOV
+
+#define MULL MULL
+static av_always_inline av_const int MULL(int a, int b, unsigned shift)
+{
+    int rt, dummy;
+    __asm__ (
+        "imull %3               \n\t"
+        "shrdl %4, %%edx, %%eax \n\t"
+        :"=a"(rt), "=d"(dummy)
+        :"a"(a), "rm"(b), "ci"((uint8_t)shift)
+    );
+    return rt;
+}
+
+#define MULH MULH
+static av_always_inline av_const int MULH(int a, int b)
+{
+    int rt, dummy;
+    __asm__ (
+        "imull %3"
+        :"=d"(rt), "=a"(dummy)
+        :"a"(a), "rm"(b)
+    );
+    return rt;
+}
+
+#define MUL64 MUL64
+static av_always_inline av_const int64_t MUL64(int a, int b)
+{
+    int64_t rt;
+    __asm__ (
+        "imull %2"
+        :"=A"(rt)
+        :"a"(a), "rm"(b)
+    );
+    return rt;
+}
+
+#endif /* ARCH_X86_32 */
+
+#if HAVE_I686
 /* median of 3 */
 #define mid_pred mid_pred
 static inline av_const int mid_pred(int a, int b, int c)
 {
     int i=b;
-    __asm__ volatile(
+    __asm__ (
         "cmp    %2, %1 \n\t"
         "cmovg  %1, %0 \n\t"
         "cmovg  %2, %1 \n\t"
@@ -64,9 +89,8 @@ static inline av_const int mid_pred(int a, int b, int c)
     );
     return i;
 }
-#endif
 
-#if HAVE_CMOV
+#if HAVE_6REGS
 #define COPY3_IF_LT(x, y, a, b, c, d)\
 __asm__ volatile(\
     "cmpl  %0, %3       \n\t"\
@@ -76,6 +100,34 @@ __asm__ volatile(\
     : "+&r" (x), "+&r" (a), "+r" (c)\
     : "r" (y), "r" (b), "r" (d)\
 );
-#endif
+#endif /* HAVE_6REGS */
+
+#endif /* HAVE_I686 */
+
+#define MASK_ABS(mask, level)                   \
+    __asm__ ("cltd                   \n\t"      \
+             "xorl %1, %0            \n\t"      \
+             "subl %1, %0            \n\t"      \
+             : "+a"(level), "=&d"(mask))
+
+// avoid +32 for shift optimization (gcc should do that ...)
+#define NEG_SSR32 NEG_SSR32
+static inline  int32_t NEG_SSR32( int32_t a, int8_t s){
+    __asm__ ("sarl %1, %0\n\t"
+         : "+r" (a)
+         : "ic" ((uint8_t)(-s))
+    );
+    return a;
+}
+
+#define NEG_USR32 NEG_USR32
+static inline uint32_t NEG_USR32(uint32_t a, int8_t s){
+    __asm__ ("shrl %1, %0\n\t"
+         : "+r" (a)
+         : "ic" ((uint8_t)(-s))
+    );
+    return a;
+}
 
+#endif /* HAVE_INLINE_ASM */
 #endif /* AVCODEC_X86_MATHOPS_H */