GCC Benchmarks (coybench), AMD64 and i686, 14 August 2004

[Uros Bizjak]

>Without -xN, it does:
># parameter 1: 8 + %ebx
>..B3.1:                         # Preds ..B3.0
>        pushl     %ebx                                          #62.1
>        movl      %esp, %ebx                                    #62.1
>        andl      $-8, %esp                                     #62.1
>        fldl      8(%ebx)                                       #61.15
>        fldl      PI2                                           #63.28
>        fcom      %st(1)                                        #63.28
>        fnstsw    %ax                                           #63.28
>        sahf                                                    #63.28
>        ja        .L9           # Prob 50%                      #63.28
>        fst       %st(1)                                        #63.28
>.L9:                                                            #
>        fstp      %st(0)                                        #63.28
>        fsincos                                                 #63.18
>        fxch      %st(1)                                        #63.18
>        fadd      %st(0), %st                                   #63.18
>        fmulp     %st, %st(1)                                   #63.47
>        movl      %ebx, %esp                                    #63.47
>        popl      %ebx                                          #63.47
>        ret                                                     #63.47
>        .align    4,0x90
>                                # LOE
>

Icc transforms dv() function from:
{
  return 2.0 * sin (((x < PI2) ? x : PI2)) * cos (((x < PI2) ? x : PI2));
}

into:
{
  double tmp = (x < PI2) ? x : PI2;
  return 2.0 * sin (tmp) * cos (tmp);
}

By introducint temp variable, gcc is able to produce even better code 
for second line:
.L4:
        fsincos
        fmulp %st, %st(1)
        fadd  %st(0), %st
        ret

... and somewhat unoptimized first line (jumps!):
dv:
        fldl  .LC0
        fldl  4(%esp)
        fld %st(1)
        fxch  %st(1)
        fcom  %st(2)
        fnstsw %ax
        fstp  %st(2)
        sahf
        ja .L6
        fstp  %st(0)
        jmp .L4
        .p2align 4,,7
.L6:
        fstp  %st(1)
.L4:

It looks that gcc does not detect that parameters to sin() and cos() are 
actually the same.

Uros.