[Bug optimization/14886] New: strength reduction on floating point

[amodra at bigpond dot net dot au]

/* I found an interesting xlc strength reduction optimization recently,
   that had xlc producing fp code that ran over twice as fast as gcc
   code on a powerpc benchmark.  Some improvement on the benchmark code
   was due to xlc using floating multiply-add more aggressively, but the
   main improvement was converting code as in f1 to as in f2.  */

float bar;

void f1 (void)
{
  int i;
  for (i = 0; i < 500; i++)
    __asm__ __volatile__ ("# %0" : : "f" (i * bar));
}

void f2 (void)
{
  register long i;
  register float f, bar2 = bar;
  for (i = 500, f = 0.0; --i >= 0;)
    {
      __asm__ __volatile__ ("# %0" : : "f" (f));
      f += bar2;
    }
}

/* On ppc32, the f1 loop generates
.L9:
        xoris 0,9,0x8000
        stw 11,8(1)
        stw 0,12(1)
        lfd 0,8(1)
        fsub 0,0,13
        frsp 0,0
        fmuls 0,0,12
#APP
        # 0
#NO_APP
        addi 9,9,1
        bdnz .L9

the f2 loop is
.L19:
#APP
        # 0
#NO_APP
        fadds 0,0,13
        bdnz .L19
*/

-- 
           Summary: strength reduction on floating point
           Product: gcc
           Version: 3.5.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P2
         Component: optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: amodra at bigpond dot net dot au
                CC: gcc-bugs at gcc dot gnu dot org
GCC target triplet: powerpc-linux


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=14886