[Bug c/54231] LTO generates code for the wrong CPU if different options used

["thiago at kde dot org" <gcc-bugzilla at gcc dot gnu dot org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54231

--- Comment #2 from Thiago Macieira <thiago at kde dot org> 2012-08-11 22:33:31 UTC ---
When adding the following source file to the library build:
====
#include <stdlib.h>
void bzero_sse2(char *, size_t);
void bzero_avx(char *, size_t);

extern int avx_supported;

void my_bzero(char *ptr, size_t n)
{
    if (avx_supported)
        bzero_avx(ptr, n);
    else
        bzero_sse2(ptr, n);
}
====

and compiling everything with -O2 -flto, GCC produces the following function:

00000000000002e0 <my_bzero>:
 2e0:   mov    0x200171(%rip),%rax        # 200458 <my_bzero+0x200178>
 2e7:   mov    (%rax),%eax
 2e9:   test   %eax,%eax
 2eb:   jne    310 <my_bzero+0x30>
 2ed:   test   %rsi,%rsi
 2f0:   vpxor  %xmm0,%xmm0,%xmm0
 2f4:   je     30e <my_bzero+0x2e>
 2f6:   nopw   %cs:0x0(%rax,%rax,1)
 300:   vmovntdq %xmm0,(%rdi)
 304:   add    $0x10,%rdi
 308:   sub    $0x1,%rsi
 30c:   jne    300 <my_bzero+0x20>
 30e:   repz retq 
 310:   test   %rsi,%rsi
 313:   je     30e <my_bzero+0x2e>
 315:   vpxor  %xmm0,%xmm0,%xmm0
 319:   nopl   0x0(%rax)
 320:   vmovntdq %xmm0,(%rdi)
 324:   add    $0x10,%rdi
 328:   sub    $0x1,%rsi
 32c:   jne    320 <my_bzero+0x40>
 32e:   repz retq 

As can be seen, VEX-prefixed instructions were used in both cases.