https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65965
Bug ID: 65965
Summary: Straight-line memcpy/memset not vectorized when
equivalent loop is
Product: gcc
Version: 5.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: middle-end
Assignee: unassigned at gcc dot gnu.org
Reporter: alalaw01 at gcc dot gnu.org
Target Milestone: ---
Testcase:
void
test(int *__restrict__ a, int *__restrict__ b)
{
a[0] = b[0];
a[1] = b[1];
a[2] = b[2];
a[3] = b[3];
a[5] = 0;
a[6] = 0;
a[7] = 0;
a[8] = 0;
}
produces (at -O3) on AArch64:
test:
ldp w4, w3, [x1]
ldp w2, w1, [x1, 8]
stp w4, w3, [x0]
stp w2, w1, [x0, 8]
stp wzr, wzr, [x0, 20]
stp wzr, wzr, [x0, 28]
ret
or on x86_64/-mavx:
test:
.LFB0:
movl (%rsi), %eax
movl $0, 20(%rdi)
movl $0, 24(%rdi)
movl $0, 28(%rdi)
movl $0, 32(%rdi)
movl %eax, (%rdi)
movl 4(%rsi), %eax
movl %eax, 4(%rdi)
movl 8(%rsi), %eax
movl %eax, 8(%rdi)
movl 12(%rsi), %eax
movl %eax, 12(%rdi)
ret
(there is no -fdump-tree-vect)
In contrast, testcase
void
test(int *__restrict__ a, int *__restrict__ b)
{
for (int i = 0; i < 4; i++) a[i] = b[i];
for (int i = 0; i < 4; i++) a[i+4] = 0;
}
the memcpy is recognized by ldist, and the 'memset' by slp1 (neither of which
triggers on the first case), producing (superior) AArch64:
test:
movi v0.4s, 0
ldp x2, x3, [x1]
stp x2, x3, [x0]
str q0, [x0, 16]
ret
or x86_64:
test:
.LFB0:
movq (%rsi), %rax
movq 8(%rsi), %rdx
vpxor %xmm0, %xmm0, %xmm0
movq %rax, (%rdi)
movq %rdx, 8(%rdi)
vmovups %xmm0, 16(%rdi)
ret
