dsputil: Add ff_ prefix to the dsputil*_init* functions

[ffmpeg] / libavcodec / x86 / dsputil_mmx.h

diff --git a/libavcodec/x86/dsputil_mmx.h b/libavcodec/x86/dsputil_mmx.h
index 52c5f8dd09037d88239f33987ac423ced4fb0798..097739cf981ae06bd2042bc1608d65614f577532 100644 (file)
--- a/libavcodec/x86/dsputil_mmx.h
+++ b/libavcodec/x86/dsputil_mmx.h
@@ -2,20 +2,20 @@
  * MMX optimized DSP utils
  * Copyright (c) 2007  Aurelien Jacobs <aurel@gnuage.org>
  *
- * 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
  */
 
@@ -24,6 +24,7 @@
 
 #include <stdint.h>
 #include "libavcodec/dsputil.h"
+#include "libavutil/x86_cpu.h"
 
 typedef struct { uint64_t a, b; } xmm_reg;
 
@@ -32,29 +33,35 @@ extern const uint64_t ff_wtwo;
 
 extern const uint64_t ff_pdw_80000000[2];
 
-extern const uint64_t ff_pw_3;
-extern const uint64_t ff_pw_4;
+extern const xmm_reg  ff_pw_3;
+extern const xmm_reg  ff_pw_4;
 extern const xmm_reg  ff_pw_5;
 extern const xmm_reg  ff_pw_8;
 extern const uint64_t ff_pw_15;
 extern const xmm_reg  ff_pw_16;
+extern const xmm_reg  ff_pw_18;
 extern const uint64_t ff_pw_20;
+extern const xmm_reg  ff_pw_27;
 extern const xmm_reg  ff_pw_28;
 extern const xmm_reg  ff_pw_32;
 extern const uint64_t ff_pw_42;
+extern const uint64_t ff_pw_53;
+extern const xmm_reg  ff_pw_63;
 extern const xmm_reg  ff_pw_64;
 extern const uint64_t ff_pw_96;
 extern const uint64_t ff_pw_128;
 extern const uint64_t ff_pw_255;
 
-extern const uint64_t ff_pb_1;
-extern const uint64_t ff_pb_3;
+extern const xmm_reg  ff_pb_1;
+extern const xmm_reg  ff_pb_3;
 extern const uint64_t ff_pb_7;
 extern const uint64_t ff_pb_1F;
 extern const uint64_t ff_pb_3F;
 extern const uint64_t ff_pb_81;
-extern const uint64_t ff_pb_A1;
+extern const xmm_reg  ff_pb_A1;
+extern const xmm_reg  ff_pb_F8;
 extern const uint64_t ff_pb_FC;
+extern const xmm_reg  ff_pb_FE;
 
 extern const double ff_pd_1[2];
 extern const double ff_pd_2[2];
@@ -88,6 +95,34 @@ extern const double ff_pd_2[2];
     SBUTTERFLY(a,c,d,dq,q) /* a=aeim d=bfjn */\
     SBUTTERFLY(t,b,c,dq,q) /* t=cgko c=dhlp */
 
+static inline void transpose4x4(uint8_t *dst, uint8_t *src, x86_reg dst_stride, x86_reg src_stride){
+    __asm__ volatile( //FIXME could save 1 instruction if done as 8x4 ...
+        "movd  (%1), %%mm0              \n\t"
+        "add   %3, %1                   \n\t"
+        "movd  (%1), %%mm1              \n\t"
+        "movd  (%1,%3,1), %%mm2         \n\t"
+        "movd  (%1,%3,2), %%mm3         \n\t"
+        "punpcklbw %%mm1, %%mm0         \n\t"
+        "punpcklbw %%mm3, %%mm2         \n\t"
+        "movq %%mm0, %%mm1              \n\t"
+        "punpcklwd %%mm2, %%mm0         \n\t"
+        "punpckhwd %%mm2, %%mm1         \n\t"
+        "movd  %%mm0, (%0)              \n\t"
+        "add   %2, %0                   \n\t"
+        "punpckhdq %%mm0, %%mm0         \n\t"
+        "movd  %%mm0, (%0)              \n\t"
+        "movd  %%mm1, (%0,%2,1)         \n\t"
+        "punpckhdq %%mm1, %%mm1         \n\t"
+        "movd  %%mm1, (%0,%2,2)         \n\t"
+
+        :  "+&r" (dst),
+           "+&r" (src)
+        :  "r" (dst_stride),
+           "r" (src_stride)
+        :  "memory"
+    );
+}
+
 // e,f,g,h can be memory
 // out: a,d,t,c
 #define TRANSPOSE8x4(a,b,c,d,e,f,g,h,t)\
@@ -149,6 +184,35 @@ extern const double ff_pd_2[2];
     "pcmpeqd %%" #regd ", %%" #regd " \n\t" \
     "psrlw $15, %%" #regd ::)
 
-void dsputilenc_init_mmx(DSPContext* c, AVCodecContext *avctx);
+void ff_dsputilenc_init_mmx(DSPContext* c, AVCodecContext *avctx);
+void ff_dsputil_init_pix_mmx(DSPContext* c, AVCodecContext *avctx);
+
+void ff_add_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
+void ff_put_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
+void ff_put_signed_pixels_clamped_mmx(const DCTELEM *block, uint8_t *pixels, int line_size);
+
+void ff_put_cavs_qpel8_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
+void ff_avg_cavs_qpel8_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
+void ff_put_cavs_qpel16_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
+void ff_avg_cavs_qpel16_mc00_mmx2(uint8_t *dst, uint8_t *src, int stride);
+
+void ff_put_vc1_mspel_mc00_mmx(uint8_t *dst, const uint8_t *src, int stride, int rnd);
+void ff_avg_vc1_mspel_mc00_mmx2(uint8_t *dst, const uint8_t *src, int stride, int rnd);
+
+void ff_mmx_idct(DCTELEM *block);
+void ff_mmxext_idct(DCTELEM *block);
+
+
+void ff_deinterlace_line_mmx(uint8_t *dst,
+                             const uint8_t *lum_m4, const uint8_t *lum_m3,
+                             const uint8_t *lum_m2, const uint8_t *lum_m1,
+                             const uint8_t *lum,
+                             int size);
+
+void ff_deinterlace_line_inplace_mmx(const uint8_t *lum_m4,
+                                     const uint8_t *lum_m3,
+                                     const uint8_t *lum_m2,
+                                     const uint8_t *lum_m1,
+                                     const uint8_t *lum, int size);
 
 #endif /* AVCODEC_X86_DSPUTIL_MMX_H */