LDC is a moving target because it's actively developed, and generally things
improve with time.
This is a recent change by the quite active Frits van Bommel:
http://www.dsource.org/projects/ldc/changeset/1486%3A9ed0695cb93c
This is a cleaned up version discussed in this thread:
import tango.stdc.stdio: printf;
import Integer = tango.text.convert.Integer;
class AllocationItem {
int value;
this(int v) { this.value = v; }
}
int foo(int iters) {
int sum = 0;
for (int i = 0; i < iters; ++i) {
auto item = new AllocationItem(i);
sum += item.value;
}
return sum;
}
void main(char[][] args) {
int iters = Integer.parse(args[1]);
printf("%d\n", foo(iters));
}
The asm generated by the last LDC (based on DMD v1.045 and llvm 2.6svn (Tue Jun
9 22:34:25 2009)) (this is just the important part of the asm):
foo:
testl %eax, %eax
jle .LBB2_4
movl %eax, %ecx
xorl %eax, %eax
.align 16
.LBB2_2:
incl %eax
cmpl %ecx, %eax
jne .LBB2_2
leal -2(%ecx), %eax
leal -1(%ecx), %edx
mull %edx
shldl $31, %eax, %edx
leal -1(%edx,%ecx), %eax
ret
.LBB2_4:
xorl %eax, %eax
ret
*/
This is the same code with "scope" added:
import tango.stdc.stdio: printf;
import Integer = tango.text.convert.Integer;
class AllocationItem {
int value;
this(int v) { this.value = v; }
}
int foo(int iters) {
int sum = 0;
for (int i = 0; i < iters; ++i) {
scope auto item = new AllocationItem(i);
sum += item.value;
}
return sum;
}
void main(char[][] args) {
int iters = Integer.parse(args[1]);
printf("%d\n", foo(iters));
}
Its asm:
/*
foo:
pushl %ebx
pushl %edi
pushl %esi
subl $24, %esp
testl %eax, %eax
jle .LBB2_4
movl %eax, %esi
xorl %edi, %edi
leal 8(%esp), %ebx
.align 16
.LBB2_2:
movl $_D11gc_test2b_d14AllocationItem6__vtblZ, 8(%esp)
movl $0, 12(%esp)
movl %edi, 16(%esp)
movl %ebx, (%esp)
call _d_callfinalizer
incl %edi
cmpl %esi, %edi
jne .LBB2_2
leal -2(%esi), %eax
leal -1(%esi), %ecx
mull %ecx
shldl $31, %eax, %edx
leal -1(%edx,%esi), %eax
jmp .LBB2_5
.LBB2_4:
xorl %eax, %eax
.LBB2_5:
addl $24, %esp
popl %esi
popl %edi
popl %ebx
ret
*/
The running time:
...$ elaps ./gc_test1 250000000
-1782069568
real 0m0.170s
user 0m0.160s
sys 0m0.010s
The version with "scope":
...$ elaps ./gc_test2 250000000
-1782069568
real 0m6.430s
user 0m6.430s
sys 0m0.000s
(Later I may try again with a less simple and more realistic benchmark, because
this is too much a toy to be interesting.)
Bye,
bearophile
