[Bug rtl-optimization/24810] [4.1 Regression] mov + mov + testl generated instead of testb

[dann at godzilla dot ics dot uci dot edu]

------- Comment #2 from dann at godzilla dot ics dot uci dot edu  2005-11-13 
02:47 -------
Simplified testcase: 
struct cpuinfo_x86 {
  unsigned char x86;
  unsigned char x86_vendor;
  unsigned char x86_model;
  unsigned char x86_mask;
  char wp_works_ok;
  char hlt_works_ok;
  char hard_math;
  char rfu;
  int cpuid_level;
  unsigned long x86_capability[7];
} __attribute__((__aligned__((1 << (7)))));

struct task_struct;
extern void foo (struct task_struct *tsk);
extern void bar (struct task_struct *tsk);

extern struct cpuinfo_x86 boot_cpu_data;

static inline __attribute__((always_inline)) int
constant_test_bit(int nr, const volatile unsigned long *addr)
{
 return ((1UL << (nr & 31)) & (addr[nr >> 5])) != 0;
}

void
restore_fpu(struct task_struct *tsk)
{
  if (constant_test_bit(24, boot_cpu_data.x86_capability))
    foo (tsk);
  else
    bar (tsk);
}

The generated code for this simplified tescase shows one additional issue:

restore_fpu:
        movl    %eax, %edx
        movl    boot_cpu_data+12, %eax  ; edx could be used here
        testl   $16777216, %eax         ; and here
        je      .L2
        movl    %edx, %eax  ; then all the mov %eax, %edx and mov %edx, %eax
        jmp     foo         ; instructions could be eliminated.
        .p2align 4,,7
.L2:
        movl    %edx, %eax
        jmp     bar


-- 

dann at godzilla dot ics dot uci dot edu changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
            Summary|mov + mov + testl generated |[4.1 Regression] mov + mov +
                   |instead of testb            |testl generated instead of
                   |                            |testb


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=24810