[FFmpeg-devel] [PATCH] Ticket #7124: Fixes compiler bug - replace vec_lvsl/vec_perm with vec_xl

[ckerchne]

A bug exist with the gcc compilers for Power in versions 6.x and 7.x 
(verified with 6.3 and 7.4). It was fixed in version 8.x (verified with 
8.3). I was using a Power 9 ppc64le machine for building and testing.

It appears the compiler is generating the wrong code for little endian 
machines for the vec_lvsl/vec_perm instruction combos in some cases. If 
these instructions are replaced with vec_xl, the problem goes away for 
all versions of the compilers.

---
  libswscale/ppc/yuv2rgb_altivec.c | 24 ++++--------------------
  1 file changed, 4 insertions(+), 20 deletions(-)

diff --git a/libswscale/ppc/yuv2rgb_altivec.c 
b/libswscale/ppc/yuv2rgb_altivec.c
index c1e2852adb..536545293d 100644
--- a/libswscale/ppc/yuv2rgb_altivec.c
+++ b/libswscale/ppc/yuv2rgb_altivec.c
@@ -305,9 +305,6 @@ static int altivec_ ## name(SwsContext *c, const 
unsigned char **in,          \
      vector signed short R1, G1, B1;                                     
       \
      vector unsigned char R, G, B;                                       
       \
                                                                          
       \
-    const vector unsigned char *y1ivP, *y2ivP, *uivP, *vivP;            
       \
-    vector unsigned char align_perm;                                    
       \
-                                                                        
       \
      vector signed short lCY       = c->CY;                              
       \
      vector signed short lOY       = c->OY;                              
       \
      vector signed short lCRV      = c->CRV;                             
       \
@@ -338,26 +335,13 @@ static int altivec_ ## name(SwsContext *c, const 
unsigned char **in,          \
          vec_dstst(oute, (0x02000002 | (((w * 3 + 32) / 32) << 16)), 1); 
       \
                                                                          
       \
          for (j = 0; j < w / 16; j++) {                                  
       \
-            y1ivP = (const vector unsigned char *) y1i;                 
       \
-            y2ivP = (const vector unsigned char *) y2i;                 
       \
-            uivP  = (const vector unsigned char *) ui;                  
       \
-            vivP  = (const vector unsigned char *) vi;                  
       \
-                                                                        
       \
-            align_perm = vec_lvsl(0, y1i);                              
       \
-            y0 = (vector unsigned char)                                 
       \
-                     vec_perm(y1ivP[0], y1ivP[1], align_perm);          
       \
+            y0 = vec_xl(0, y1i);                                        
       \
                                                                          
       \
-            align_perm = vec_lvsl(0, y2i);                              
       \
-            y1 = (vector unsigned char)                                 
       \
-                     vec_perm(y2ivP[0], y2ivP[1], align_perm);          
       \
+            y1 = vec_xl(0, y2i);                                        
       \
                                                                          
       \
-            align_perm = vec_lvsl(0, ui);                               
       \
-            u = (vector signed char)                                    
       \
-                    vec_perm(uivP[0], uivP[1], align_perm);             
       \
+            u = (vector signed char) vec_xl(0, ui);                     
       \
                                                                          
       \
-            align_perm = vec_lvsl(0, vi);                               
       \
-            v = (vector signed char)                                    
       \
-                    vec_perm(vivP[0], vivP[1], align_perm);             
       \
+            v = (vector signed char) vec_xl(0, vi);                     
       \
                                                                          
       \
              u = (vector signed char)                                    
       \
                      vec_sub(u,                                          
       \
--
2.17.1