confused at code generation for a empty loop

["PRC" <panruochen@gmail.com>]

Here is my code:
=================================================================================
#include <pthread.h>
#include <stdio.h>
#define NUM_THREADS 1
static int flag = 0;
void *thread(void *threadid)
{
    int ret = rand();
    printf("thread return %d!\n", ret);
    sleep(10);
    flag = 1;
    return (void *)ret;
}

int main (int argc, char *argv[])
{
   pthread_t threads[NUM_THREADS];
   int rc;
   rc = pthread_create(&threads[0], NULL, thread, (void *)0);
   if (rc){
         printf("ERROR; return code from pthread_create() is %d\n", rc);
         exit(-1);
   }
   while( flag == 0 ) ;
   return 0;
}
=================================================================================
gcc -O2 -g -lpthread a.c
objdump -S a.out > a.S


`cat a.S` shows:
=================================================================================
   if (rc){
 80484d4:   85 c0                   test   %eax,%eax
 80484d6:   75 15                   jne    80484ed <main+0x4d>
 80484d8:   a1 68 97 04 08          mov    0x8049768,%eax
 80484dd:   85 c0                   test   %eax,%eax
 80484df:   90                      nop
         printf("ERROR; return code from pthread_create() is %d\n", rc);
         exit(-1);
   }
   while( flag == 0 ) ;
 80484e0:   74 fe                   je     80484e0 <main+0x40>
================================================================================
You can see the variable `flag` is read only once. If the value of `flag` is 0 at the first time, 
the program will trap into a dead loop and never exit. And gcc knows the value of `flag` could
be modified in the routine `thread`.


But if I modify the line "while( flag == 0 ) ;" to "while(flag == 0) printf("waiting..\n");"
and recompile the source code, the output assembly code becomes:
=================================================================================
while( flag == 0 ) printf("waiting..\n");
 8048510:   c7 04 24 74 86 04 08    movl   $0x8048674,(%esp)
 8048517:   e8 90 fe ff ff          call   80483ac <puts@plt>
 804851c:   a1 b8 97 04 08          mov    0x80497b8,%eax
 8048521:   85 c0                   test   %eax,%eax
 8048523:   74 eb                   je     8048510 <main+0x40>
=================================================================================
`flag` is read in each loop. Then when the value of `flag` is modified, the loop terminates.

I wonder why gcc generates code for a empty loop like that. Is it a bug or for optimization in some case?

My gcc is:
Using built-in specs.
Target: i386-redhat-linux
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-libgcj-multifile --enable-languages=c,c++,objc,obj-c++,java,fortran,ada --enable-java-awt=gtk --disable-dssi --with-java-home=/usr/lib/jvm/java-1.4.2-gcj-1.4.2.0/jre --with-cpu=generic --host=i386-redhat-linux
Thread model: posix
gcc version 4.1.1 20060525 (Red Hat 4.1.1-1)