prinft performance problem

[bearophile]

I have reduced another performance problem, Windows 32 bit.

--------------------------

A test C program:


#include <stdio.h>
int main() {
     for (double i = 0; i < 200000; i++)
         printf("%f\n", i);
     return 0;
}

--------------------------

A similar D program:


import core.stdc.stdio: printf;
int main() {
     for (double i = 0; i < 200000; i++)
         printf("%f\n", i);
     return 0;
}

--------------------------

I compile with:

gcc -std=gnu99 -Ofast -flto -s test1.c -o test1
gcc 4.8.0

ldmd2 -wi -O -release -inline -noboundscheck test2.d
ldc2 0.13.0-alpha1

If I redirect the output to file, the run-times for me are about 
0.30 seconds for the C version, and about 1.12 seconds for the D 
version.

--------------------------

GCC asm:

_main:
	pushl	%ebp
	movl	%esp, %ebp
	andl	$-16, %esp
	subl	$32, %esp
	call	___main
	fldz
	.p2align 4,,7
L4:
	fstl	4(%esp)
	movl	$LC1, (%esp)
	fstpl	24(%esp)
	call	_printf
	fldl	24(%esp)
	fadds	LC2
	flds	LC3
	fcomip	%st(1), %st
	ja	L4

	fstp	%st(0)
	xorl	%eax, %eax
	leave
	ret

--------------------------

LDC2 asm:

__Dmain:
	pushl	%esi
	subl	$24, %esp
	xorps	%xmm0, %xmm0
	movl	$200000, %esi
	.align	16, 0x90
LBB0_1:
	movsd	%xmm0, 16(%esp)
	movsd	%xmm0, 4(%esp)
	movl	$_.str, (%esp)
	calll	___mingw_printf
	movsd	16(%esp), %xmm0
	addsd	LCPI0_0, %xmm0
	decl	%esi
	jne	LBB0_1

	xorl	%eax, %eax
	addl	$24, %esp
	popl	%esi
	ret

--------------------------

Bye,
bearophile