HalfFloat neon armv7 fix for destination pointer.

source/row_neon.cc

 /*
  *  Copyright 2011 The LibYuv Project Authors. All rights reserved.
  *
  *  Use of this source code is governed by a BSD-style license
  *  that can be found in the LICENSE file in the root of the source
  *  tree. An additional intellectual property rights grant can be found
  *  in the file PATENTS. All contributing project authors may
  *  be found in the AUTHORS file in the root of the source tree.
  */
 
@@ skipping 2724 matching lines @@
 }
 
 void HalfFloat1Row_NEON(const uint16* src, uint16* dst, float, int width) {
   asm volatile (
     "vdup.32    q0, %3                         \n"
 
   "1:                                          \n"
     MEMACCESS(0)
     "vld1.8     {q1}, [%0]!                    \n"  // load 8 shorts
     "subs       %2, %2, #8                     \n"  // 8 pixels per loop
-    "vmovl.u8   q2, d2                         \n"  // 8 int's
-    "vmovl.u8   q3, d3                         \n"
+    "vmovl.u16  q2, d2                         \n"  // 8 int's
+    "vmovl.u16  q3, d3                         \n"
     "vcvt.f32.u32  q2, q2                      \n"  // 8 floats
     "vcvt.f32.u32  q3, q3                      \n"
     "vmul.f32   q2, q2, q0                     \n"  // adjust exponent
     "vmul.f32   q3, q3, q0                     \n"
-    "vqshrn.u32 d2, q2, #13                    \n"   // isolate halffloat
+    "vqshrn.u32 d2, q2, #13                    \n"  // isolate halffloat
     "vqshrn.u32 d3, q3, #13                    \n"
     MEMACCESS(1)
-    "vst1.8     {q1}, [%0]!                    \n"
+    "vst1.8     {q1}, [%1]!                    \n"
     "bgt        1b                             \n"
   : "+r"(src),    // %0
     "+r"(dst),    // %1
     "+r"(width)   // %2
   : "r"(1.9259299444e-34f)    // %3
   : "cc", "memory", "q0", "q1", "q2", "q3"
   );
 }
 
 // TODO(fbarchard): multiply by element.
 void HalfFloatRow_NEON(const uint16* src, uint16* dst, float scale, int width) {
   asm volatile (
     "vdup.32    q0, %3                         \n"
 
   "1:                                          \n"
     MEMACCESS(0)
     "vld1.8     {q1}, [%0]!                    \n"  // load 8 shorts
     "subs       %2, %2, #8                     \n"  // 8 pixels per loop
-    "vmovl.u8   q2, d2                         \n"  // 8 int's
-    "vmovl.u8   q3, d3                         \n"
+    "vmovl.u16  q2, d2                         \n"  // 8 int's
+    "vmovl.u16  q3, d3                         \n"
     "vcvt.f32.u32  q2, q2                      \n"  // 8 floats
     "vcvt.f32.u32  q3, q3                      \n"
     "vmul.f32   q2, q2, q0                     \n"  // adjust exponent
     "vmul.f32   q3, q3, q0                     \n"
-    "vqshrn.u32 d2, q2, #13                    \n"   // isolate halffloat
+    "vqshrn.u32 d2, q2, #13                    \n"  // isolate halffloat
     "vqshrn.u32 d3, q3, #13                    \n"
     MEMACCESS(1)
-    "vst1.8     {q1}, [%0]!                    \n"
+    "vst1.8     {q1}, [%1]!                    \n"
     "bgt        1b                             \n"
   : "+r"(src),    // %0
     "+r"(dst),    // %1
     "+r"(width)   // %2
   : "r"(scale * 1.9259299444e-34f)    // %3
   : "cc", "memory", "q0", "q1", "q2", "q3"
   );
 }
 
 #endif  // !defined(LIBYUV_DISABLE_NEON) && defined(__ARM_NEON__)..
 
 #ifdef __cplusplus
 }  // extern "C"
 }  // namespace libyuv
 #endif