arm: asm decode_block_coeffs_internal is vp8 specific

[ffmpeg] / libavcodec / arm / fft_neon.S

diff --git a/libavcodec/arm/fft_neon.S b/libavcodec/arm/fft_neon.S
index c90333466d3ca2d63f176befc5542c98fe4e0acd..c4d89189ea7906545ea83bd9377b6603a4feee39 100644 (file)
--- a/libavcodec/arm/fft_neon.S
+++ b/libavcodec/arm/fft_neon.S
@@ -4,28 +4,30 @@
  * Copyright (c) 2009 Mans Rullgard <mans@mansr.com>
  * Copyright (c) 2009 Naotoshi Nojiri
  *
- * This file is part of FFmpeg.
+ * This algorithm (though not any of the implementation details) is
+ * based on libdjbfft by D. J. Bernstein.
  *
- * FFmpeg is free software; you can redistribute it and/or
+ * This file is part of Libav.
+ *
+ * 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
  */
 
-#include "asm.S"
+#include "libavutil/arm/asm.S"
 
 #define M_SQRT1_2 0.70710678118654752440
 
-        .text
 
 function fft4_neon
         vld1.32         {d0-d3}, [r0,:128]
@@ -141,7 +143,7 @@ function fft16_neon
         vswp            d29, d30                @ q14{r12,i12,i14,r15} q15{r13,i13,i15,r14}
         vadd.f32        q0,  q12, q13           @ {t1,t2,t5,t6}
         vadd.f32        q1,  q14, q15           @ {t1a,t2a,t5a,t6a}
-        movrel          r2,  X(ff_cos_16)
+        movrelx         r2,  X(ff_cos_16)
         vsub.f32        q13, q12, q13           @ {t3,t4,t7,t8}
         vrev64.32       d1,  d1
         vsub.f32        q15, q14, q15           @ {t3a,t4a,t7a,t8a}
@@ -288,7 +290,7 @@ function fft\n\()_neon
         bl              fft\n4\()_neon
         mov             r0,  r4
         pop             {r4, lr}
-        movrel          r1,  X(ff_cos_\n)
+        movrelx         r1,  X(ff_cos_\n)
         mov             r2,  #\n4/2
         b               fft_pass_neon
 endfunc
@@ -346,9 +348,7 @@ function ff_fft_permute_neon, export=1
         pop             {r4,pc}
 endfunc
 
-        .section .rodata
-        .align 4
-fft_tab_neon:
+const   fft_tab_neon
         .word fft4_neon
         .word fft8_neon
         .word fft16_neon
@@ -364,8 +364,12 @@ fft_tab_neon:
         .word fft16384_neon
         .word fft32768_neon
         .word fft65536_neon
-        .size fft_tab_neon, . - fft_tab_neon
+endconst
+
+const   pmmp, align=4
+        .float          +1.0, -1.0, -1.0, +1.0
+endconst
 
-        .align 4
-pmmp:   .float  +1.0, -1.0, -1.0, +1.0
-mppm:   .float  -M_SQRT1_2, M_SQRT1_2, M_SQRT1_2, -M_SQRT1_2
+const   mppm, align=4
+        .float          -M_SQRT1_2, M_SQRT1_2, M_SQRT1_2, -M_SQRT1_2
+endconst