android_full_debug x86 fix - use +rm for width count

Work around for android full debug build runnign out of registers.
5 functions were running out of registers causing the compiler error
error: 'asm' operand has impossible constraints
These functions mostly have 4 pointers, a counter (width) and a tempory
eax register.  With fpic and debug using stackframes, 2 registers are
unavailable.  So a total of 8 registers are used.
Although fpic and stack frame dont apply to assembly, the compiler
reserves 2 registers.  The optimized version builds, so its likely
freeing up the registers once it knows they are not used.
These functions used to build, so compile options and/or compiler may
have updated.. likely fpic was turned on.
An attribute can be done to disable each, and will avoid using the
2 GPR registers, but they are still reserved and unavailable in debug
builds on current compilers (gcc 4.9 and clang 3.8).

R=dhrosa@google.com
BUG=libyuv:602

Review URL: https://codereview.chromium.org/2066933002 .

README.chromium

 Name: libyuv
 URL: http://code.google.com/p/libyuv/
-Version: 1596
+Version: 1597
 License: BSD
 License File: LICENSE
 

include/libyuv/version.h

@@ -11,6 +11,6 @@
 #ifndef INCLUDE_LIBYUV_VERSION_H_  // NOLINT
 #define INCLUDE_LIBYUV_VERSION_H_
 
-#define LIBYUV_VERSION 1596
+#define LIBYUV_VERSION 1597
 
 #endif  // INCLUDE_LIBYUV_VERSION_H_  NOLINT

source/row_gcc.cc

@@ -3596,7 +3596,7 @@ void BlendPlaneRow_SSSE3(const uint8* src0, const uint8* src1,
     "+r"(src1),       // %1
     "+r"(alpha),      // %2
     "+r"(dst),        // %3
-    "+r"(width)       // %4
+    "+rm"(width)      // %4
   :: "memory", "cc", "eax", "xmm0", "xmm1", "xmm2", "xmm5", "xmm6", "xmm7"
   );
 }
@@ -3653,7 +3653,7 @@ void BlendPlaneRow_AVX2(const uint8* src0, const uint8* src1,
     "+r"(src1),       // %1
     "+r"(alpha),      // %2
     "+r"(dst),        // %3
-    "+r"(width)       // %4
+    "+rm"(width)      // %4
   :: "memory", "cc", "eax",
      "xmm0", "xmm1", "xmm2", "xmm3", "xmm4", "xmm5", "xmm6", "xmm7"
   );
@@ -4936,9 +4936,9 @@ void InterpolateRow_SSSE3(uint8* dst_ptr, const uint8* src_ptr,
     "jg        100b                            \n"
 
   "99:                                         \n"
-  : "+r"(dst_ptr),    // %0
-    "+r"(src_ptr),    // %1
-    "+r"(dst_width),  // %2
+  : "+r"(dst_ptr),     // %0
+    "+r"(src_ptr),     // %1
+    "+rm"(dst_width),  // %2
     "+r"(source_y_fraction)  // %3
   : "r"((intptr_t)(src_stride))  // %4
   : "memory", "cc", "eax", NACL_R14
@@ -5014,7 +5014,7 @@ void InterpolateRow_AVX2(uint8* dst_ptr, const uint8* src_ptr,
   "999:                                        \n"
   : "+D"(dst_ptr),    // %0
     "+S"(src_ptr),    // %1
-    "+c"(dst_width),  // %2
+    "+cm"(dst_width),  // %2
     "+r"(source_y_fraction)  // %3
   : "r"((intptr_t)(src_stride))  // %4
   : "memory", "cc", "eax", NACL_R14