With this change the arm platform can now be fully compiled with Clang.
Tested by comparing the output with GCC 4.8.2, and Clang 4.0, using a
variety of arches, big/little endianness, and arm/thumb mode to verify
the generated assembly output matches between GCC vs Clang with UAL, and
also GCC with UAL vs GCC with non-UAL, for all preprocessor code blocks.
The only difference found is an extra nop at the end of the function
when compiled with GCC using armv7-a/thumb/little-endian/-O2 compared to
Clang. The nop is not emitted when compiled in big-endian mode.
strcpy (char* dst, const char* src)
{
asm (
+ ".syntax unified\n\t"
#if !(defined(__OPTIMIZE_SIZE__) || defined (PREFER_SIZE_OVER_SPEED) || \
(defined (__thumb__) && !defined (__thumb2__)))
#ifdef _ISA_ARM_7
#ifdef __ARMEB__
"tst r2, #0xff00\n\t"
"iteet ne\n\t"
- "strneh r2, [ip], #2\n\t"
+ "strhne r2, [ip], #2\n\t"
"lsreq r2, r2, #8\n\t"
- "streqb r2, [ip]\n\t"
+ "strbeq r2, [ip]\n\t"
"tstne r2, #0xff\n\t"
#else
"tst r2, #0xff\n\t"
"itet ne\n\t"
- "strneh r2, [ip], #2\n\t"
- "streqb r2, [ip]\n\t"
+ "strhne r2, [ip], #2\n\t"
+ "strbeq r2, [ip]\n\t"
"tstne r2, #0xff00\n\t"
#endif
"bne 5b\n\t"
"mov r3, r0\n\t"
"1:\n\t"
"ldrb r2, [r1]\n\t"
- "add r1, r1, #1\n\t"
+ "adds r1, #1\n\t"
"strb r2, [r3]\n\t"
- "add r3, r3, #1\n\t"
+ "adds r3, #1\n\t"
"cmp r2, #0\n\t"
"bne 1b\n\t"
"bx lr\n\t"