===================================================================
cis-lclient02:~/2012/intel64>more fsum.c
double sum(double a, double b);
main () {
   double a, b;
   a = 5.0; b = 10.0;
   return sum(a, b);
}
double sum(double a, double b) {
   double x;
   x = a + b;
   return x;
}
===================================================================
cis-lclient02:~/2012/intel64>gcc -O0 -o fsum0.s -S fsum.c
cis-lclient02:~/2012/intel64>more fsum0.s
        .file   "fsum.c"
        .text
.globl main
        .type   main, @function
main:
        pushl   %ebp
        movl    %esp, %ebp
        andl    $-16, %esp
        subl    $48, %esp
        fldl    .LC0
        fstpl   32(%esp)
        fldl    .LC1
        fstpl   40(%esp)
        fldl    40(%esp)
        fstpl   8(%esp)
        fldl    32(%esp)
        fstpl   (%esp)
        call    sum
        fnstcw  30(%esp)
        movzwl  30(%esp), %eax
        movb    $12, %ah
        movw    %ax, 28(%esp)
        fldcw   28(%esp)
        fistpl  24(%esp)
        fldcw   30(%esp)
        movl    24(%esp), %eax
        leave
        ret
        .size   main, .-main
.globl sum
        .type   sum, @function
sum:
        pushl   %ebp
        movl    %esp, %ebp
        subl    $32, %esp
        movl    8(%ebp), %eax
        movl    %eax, -24(%ebp)
        movl    12(%ebp), %eax
        movl    %eax, -20(%ebp)
        movl    16(%ebp), %eax
        movl    %eax, -32(%ebp)
        movl    20(%ebp), %eax
        movl    %eax, -28(%ebp)
        fldl    -24(%ebp)
        faddl   -32(%ebp)
        fstpl   -8(%ebp)
        fldl    -8(%ebp)
        leave
        ret
        .size   sum, .-sum
        .section        .rodata
        .align 8
.LC0:
        .long   0
        .long   1075052544
        .align 8
.LC1:
        .long   0
        .long   1076101120
        .ident  "GCC: (GNU) 4.4.4 20100630 (Red Hat 4.4.4-10)"
        .section        .note.GNU-stack,"",@progbits
===================================================================
cis-lclient02:~/2012/intel64>more fsum1.s
        .file   "fsum.c"
        .text
.globl sum
        .type   sum, @function
sum:
        pushl   %ebp
        movl    %esp, %ebp
        fldl    16(%ebp)
        faddl   8(%ebp)
        popl    %ebp
        ret
        .size   sum, .-sum
.globl main
        .type   main, @function
main:
        pushl   %ebp
        movl    %esp, %ebp
        subl    $24, %esp
        flds    .LC1
        fstpl   8(%esp)
        flds    .LC2
        fstpl   (%esp)
        call    sum
        fnstcw  22(%esp)
        movzwl  22(%esp), %eax
        movb    $12, %ah
        movw    %ax, 20(%esp)
        fldcw   20(%esp)
        fistpl  16(%esp)
        fldcw   22(%esp)
        movl    16(%esp), %eax
        leave
        ret
        .size   main, .-main
        .section        .rodata.cst4,"aM",@progbits,4
        .align 4
.LC1:
        .long   1092616192
        .align 4
.LC2:
        .long   1084227584
        .ident  "GCC: (GNU) 4.4.4 20100630 (Red Hat 4.4.4-10)"
        .section        .note.GNU-stack,"",@progbits
===================================================================
cis-lclient02:~/2012/intel64>gcc -O2 -o fsum2.s -S fsum.c
cis-lclient02:~/2012/intel64>more fsum2.s
        .file   "fsum.c"
        .text
        .p2align 4,,15
.globl main
        .type   main, @function
main:
        pushl   %ebp
        movl    $15, %eax
        movl    %esp, %ebp
        popl    %ebp
        ret
        .size   main, .-main
        .p2align 4,,15
.globl sum
        .type   sum, @function
sum:
        pushl   %ebp
        movl    %esp, %ebp
        fldl    16(%ebp)
        faddl   8(%ebp)
        popl    %ebp
        ret
        .size   sum, .-sum
        .ident  "GCC: (GNU) 4.4.4 20100630 (Red Hat 4.4.4-10)"
        .section        .note.GNU-stack,"",@progbits
===================================================================
cis-lclient02:~/2012/intel64>gcc -O1 -o fsum686.s -S -march=i686 fsum.c
cis-lclient02:~/2012/intel64>more fsum686.s
        .file   "fsum.c"
        .text
.globl sum
        .type   sum, @function
sum:
        pushl   %ebp
        movl    %esp, %ebp
        fldl    16(%ebp)
        faddl   8(%ebp)
        popl    %ebp
        ret
        .size   sum, .-sum
.globl main
        .type   main, @function
main:
        pushl   %ebp
        movl    %esp, %ebp
        subl    $24, %esp
        flds    .LC1
        fstpl   8(%esp)
        flds    .LC2
        fstpl   (%esp)
        call    sum
        fnstcw  22(%esp)
        movzwl  22(%esp), %eax
        movb    $12, %ah
        movw    %ax, 20(%esp)
        fldcw   20(%esp)
        fistpl  16(%esp)
        fldcw   22(%esp)
        movl    16(%esp), %eax
        leave
        ret
        .size   main, .-main
        .section        .rodata.cst4,"aM",@progbits,4
        .align 4
.LC1:
        .long   1092616192
        .align 4
.LC2:
        .long   1084227584
        .ident  "GCC: (GNU) 4.4.4 20100630 (Red Hat 4.4.4-10)"
        .section        .note.GNU-stack,"",@progbits
===================================================================
CIS-Linux2:~/2012/intel64>gcc -O1 -o fsum64O1.s -S fsum.c
CIS-Linux2:~/2012/intel64>more fsum64O1.s
        .file   "fsum.c"
        .text
        .globl  sum
        .type   sum, @function
sum:
.LFB1:
        .cfi_startproc
        addsd   %xmm1, %xmm0
        ret
        .cfi_endproc
.LFE1:
        .size   sum, .-sum
        .globl  main
        .type   main, @function
main:
.LFB0:
        .cfi_startproc
        movsd   .LC0(%rip), %xmm1
        movsd   .LC1(%rip), %xmm0
        call    sum
        cvttsd2si       %xmm0, %eax
        ret
        .cfi_endproc
.LFE0:
        .size   main, .-main
        .section        .rodata.cst8,"aM",@progbits,8
        .align 8
.LC0:
        .long   0
        .long   1076101120
        .align 8
.LC1:
        .long   0
        .long   1075052544
        .ident  "GCC: (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3"
        .section        .note.GNU-stack,"",@progbits
CIS-Linux2:~/2012/intel64>
===================================================================