[FFmpeg-cvslog] ppc: pixblockdsp: do unaligned block accesses correctly again

[Andreas Cadhalpun]

ffmpeg | branch: release/3.0 | Andreas Cadhalpun <Andreas.Cadhalpun at googlemail.com> | Wed Nov  2 21:28:49 2016 +0100| [087b77741526e701d392c038ae765993d60b5fab] | committer: Andreas Cadhalpun

ppc: pixblockdsp: do unaligned block accesses correctly again

This was broken by the following Libav commit:
4c387c7 ppc: dsputil: do unaligned block accesses correctly

The following tests fail due to this:
fate-checkasm
fate-vsynth1-dnxhd-2k-hr-hq fate-vsynth1-dnxhd-edge1-hr
fate-vsynth1-dnxhd-edge2-hr fate-vsynth1-dnxhd-edge3-hr
fate-vsynth1-dnxhd-hr-sq-mov fate-vsynth1-dnxhd-hr-hq-mov
fate-vsynth2-dnxhd-2k-hr-hq fate-vsynth2-dnxhd-edge1-hr
fate-vsynth2-dnxhd-edge2-hr fate-vsynth2-dnxhd-edge3-hr
fate-vsynth2-dnxhd-hr-sq-mov fate-vsynth2-dnxhd-hr-hq-mov
fate-vsynth3-dnxhd-2k-hr-hq fate-vsynth3-dnxhd-edge1-hr
fate-vsynth3-dnxhd-edge2-hr fate-vsynth3-dnxhd-edge3-hr
fate-vsynth3-dnxhd-hr-sq-mov fate-vsynth3-dnxhd-hr-hq-mov

Fixes trac ticket #5508.

Reviewed-by: Carl Eugen Hoyos <ceffmpeg at gmail.com>
Signed-off-by: Andreas Cadhalpun <Andreas.Cadhalpun at googlemail.com>
(cherry picked from commit 3932ccc472ad4f4d370dcfc1c2f574b0f3acb88c)
Signed-off-by: Andreas Cadhalpun <Andreas.Cadhalpun at googlemail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=087b77741526e701d392c038ae765993d60b5fab
---

 libavcodec/ppc/pixblockdsp.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/libavcodec/ppc/pixblockdsp.c b/libavcodec/ppc/pixblockdsp.c
index 84aa562..f3a5050 100644
--- a/libavcodec/ppc/pixblockdsp.c
+++ b/libavcodec/ppc/pixblockdsp.c
@@ -67,10 +67,10 @@ static void get_pixels_altivec(int16_t *restrict block, const uint8_t *pixels,
                                ptrdiff_t line_size)
 {
     int i;
-    vec_u8 perm = vec_lvsl(0, pixels);
     const vec_u8 zero = (const vec_u8)vec_splat_u8(0);
 
     for (i = 0; i < 8; i++) {
+        vec_u8 perm = vec_lvsl(0, pixels);
         /* Read potentially unaligned pixels.
          * We're reading 16 pixels, and actually only want 8,
          * but we simply ignore the extras. */
@@ -157,8 +157,7 @@ static void diff_pixels_altivec(int16_t *restrict block, const uint8_t *s1,
                                 const uint8_t *s2, int stride)
 {
     int i;
-    vec_u8 perm1 = vec_lvsl(0, s1);
-    vec_u8 perm2 = vec_lvsl(0, s2);
+    vec_u8 perm;
     const vec_u8 zero = (const vec_u8)vec_splat_u8(0);
     vec_s16 shorts1, shorts2;
 
@@ -166,17 +165,19 @@ static void diff_pixels_altivec(int16_t *restrict block, const uint8_t *s1,
         /* Read potentially unaligned pixels.
          * We're reading 16 pixels, and actually only want 8,
          * but we simply ignore the extras. */
+        perm = vec_lvsl(0, s1);
         vec_u8 pixl  = vec_ld(0,  s1);
         vec_u8 pixr  = vec_ld(15, s1);
-        vec_u8 bytes = vec_perm(pixl, pixr, perm1);
+        vec_u8 bytes = vec_perm(pixl, pixr, perm);
 
         // Convert the bytes into shorts.
         shorts1 = (vec_s16)vec_mergeh(zero, bytes);
 
         // Do the same for the second block of pixels.
+        perm = vec_lvsl(0, s2);
         pixl  = vec_ld(0,  s2);
         pixr  = vec_ld(15, s2);
-        bytes = vec_perm(pixl, pixr, perm2);
+        bytes = vec_perm(pixl, pixr, perm);
 
         // Convert the bytes into shorts.
         shorts2 = (vec_s16)vec_mergeh(zero, bytes);
@@ -197,17 +198,19 @@ static void diff_pixels_altivec(int16_t *restrict block, const uint8_t *s1,
         /* Read potentially unaligned pixels.
          * We're reading 16 pixels, and actually only want 8,
          * but we simply ignore the extras. */
+        perm = vec_lvsl(0, s1);
         pixl  = vec_ld(0,  s1);
         pixr  = vec_ld(15, s1);
-        bytes = vec_perm(pixl, pixr, perm1);
+        bytes = vec_perm(pixl, pixr, perm);
 
         // Convert the bytes into shorts.
         shorts1 = (vec_s16)vec_mergeh(zero, bytes);
 
         // Do the same for the second block of pixels.
+        perm = vec_lvsl(0, s2);
         pixl  = vec_ld(0,  s2);
         pixr  = vec_ld(15, s2);
-        bytes = vec_perm(pixl, pixr, perm2);
+        bytes = vec_perm(pixl, pixr, perm);
 
         // Convert the bytes into shorts.
         shorts2 = (vec_s16)vec_mergeh(zero, bytes);