https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106688
Bug ID: 106688
Summary: leaving SSA emits assignment into the inner loop
Product: gcc
Version: 13.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: amonakov at gcc dot gnu.org
Target Milestone: ---
For the following testcase, gcc -O2
unsigned foo(const unsigned char *buf, long size);
unsigned bar(const unsigned char *buf, long size)
{
typedef char i8v8 __attribute__((vector_size(8)));
typedef short i16v8 __attribute__((vector_size(16)));
long chunk_sz = 15*16;
for (; size >= chunk_sz; size -= chunk_sz) {
i16v8 vs1 = { 0 };
const unsigned char *end = buf + chunk_sz;
for (; buf != end; buf += 16) {
i16v8 b;
asm("pmovzxbw %1, %0" : "=x"(b) : "m"(*(i8v8*)buf));
vs1 += b;
asm("pmovzxbw %1, %0" : "=x"(b) :
"m"(*(i8v8*)(buf+8)));
vs1 += b;
}
asm("" :: "x"(vs1));
}
return foo(buf, size);
}
(asms needed due to PR 31667)
generates
bar:
cmp rsi, 239
jle .L2
lea rdx, [rdi+240]
.L4:
lea rax, [rdx-240]
pxor xmm0, xmm0
.L3:
pmovzxbw QWORD PTR [rax], xmm1
add rax, 16
paddw xmm0, xmm1
mov rdi, rdx ; <<< ehhh
pmovzxbw QWORD PTR [rax-8], xmm1
paddw xmm0, xmm1
cmp rax, rdx
jne .L3
sub rsi, 240
add rdx, 240
cmp rsi, 239
jg .L4
.L2:
jmp foo
It looks as if going out of SSA places in the loop a register copy
corresponding to a phi node which is outside of the loop. Strangely, RTL
optimizations do not clean it up either.
