The following code:
struct S
{
int count;
char *addr;
};
void func(const char*, const char*, int, const char*);
void test(struct S *p)
{
int off = p->count;
while (p->count >= 0)
{
const char *s = "xyz";
if (*p->addr) s = "pqr";
func("abcde", p->addr + off, off, s);
p->count--;
}
}
is compiled by GCC 4.2.1 to 64 bytes, and by GCC 4.4.0 to 76 bytes. Bisection
shows that size is increased several times:
123918 -> 123919: 64 -> 72
124041 -> 124042: 72 -> 76
I already filed a bug for 123919
(http://gcc.gnu.org/bugzilla/show_bug.cgi?id=39837), so let's take a look at
http://gcc.gnu.org/viewcvs?view=rev&revision=124042
GCC rev124041 (with -march=armv5te -mthumb -mthumb-interwork -fpic -Os)
test:
push {r4, r5, r6, r7, lr}
ldr r3, .L9
ldr r2, .L9+4
.LPIC0:
add r3, pc
add r7, r3, r2
ldr r2, .L9+8
ldr r5, [r0]
sub sp, sp, #4
mov r4, r0
add r6, r3, r2
b .L2
.L3:
ldr r0, [r4, #4]
ldrb r3, [r0]
cmp r3, #0
beq .L4
mov r2, r6
b .L6
.L4:
mov r2, r7
.L6:
add r0, r0, r5
lsl r1, r5, #1
bl func
ldr r3, [r4]
sub r3, r3, #1
str r3, [r4]
.L2:
ldr r3, [r4]
cmp r3, #0
bge .L3
add sp, sp, #4
@ sp needed for prologue
pop {r4, r5, r6, r7, pc}
.L10:
GCC rev124042:
test:
push {r4, r5, r6, r7, lr}
ldr r3, .L9
ldr r2, .L9+4
.LPIC0:
add r3, pc
add r2, r3, r2
sub sp, sp, #12
ldr r5, [r0]
str r2, [sp, #4]
ldr r2, .L9+8
mov r4, r0
lsl r6, r5, #1
add r7, r3, r2
b .L2
.L3:
ldr r0, [r4, #4]
ldrb r3, [r0]
cmp r3, #0
beq .L4
mov r2, r7
b .L6
.L4:
ldr r2, [sp, #4]
.L6:
add r0, r0, r5
mov r1, r6
bl func
ldr r3, [r4]
sub r3, r3, #1
str r3, [r4]
.L2:
ldr r3, [r4]
cmp r3, #0
bge .L3
add sp, sp, #12
@ sp needed for prologue
pop {r4, r5, r6, r7, pc}
The first different dump is 090t.lim, which moves (off << 1) out of the loop.
But this extra variable causes extra stack spill, so it actually a loss, not a
win. Any ideas about what to tweak?
--
Summary: [4.3/4.4/4.5 regression] loop invariant motion causes
stack spill
Product: gcc
Version: 4.4.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: regression
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: alexvod at google dot com
GCC build triplet: x86_64-unknown-linux-gnu
GCC host triplet: x86_64-unknown-linux-gnu
GCC target triplet: arm-eabi
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=39839
