http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46012
Summary: 256bit vectorizer failed on int->double
Product: gcc
Version: 4.6.0
Status: UNCONFIRMED
Severity: enhancement
Priority: P3
Component: tree-optimization
AssignedTo: unassig...@gcc.gnu.org
ReportedBy: hjl.to...@gmail.com
CC: rgue...@gcc.gnu.org
For
---
double a[1024];
float b[1024];
int c[1024];
void dependence_distance_4_mixed_0 (void)
{
int i;
for (i = 0; i < 1020; ++i)
a[i + 4] = a[i] + a[i + 4] + c[i];
}
---
with -O3 -ffast-math -mavx, vect256 branch generates:
.L2:
vmovapd a(%rax,%rax), %ymm0
vcvtdq2pd c(%rax), %ymm1
vaddpd a+32(%rax,%rax), %ymm0, %ymm0
vaddpd %ymm1, %ymm0, %ymm0
vmovapd %ymm0, a+32(%rax,%rax)
addq $16, %rax
cmpq $4080, %rax
jne .L2
Trunk at revision 165455 generates
.L2:
vmovapd 16(%rax), %xmm2
vaddpd -16(%rax), %xmm2, %xmm2
vmovdqa (%rdx), %xmm0
addq $16, %rdx
vpshufd $238, %xmm0, %xmm1
vcvtdq2pd %xmm0, %xmm0
vcvtdq2pd %xmm1, %xmm1
vaddpd %xmm1, %xmm2, %xmm1
vmovapd (%rax), %xmm2
vaddpd -32(%rax), %xmm2, %xmm2
vmovapd %xmm1, 16(%rax)
vaddpd %xmm0, %xmm2, %xmm0
vmovapd %xmm0, (%rax)
addq $32, %rax
cmpq %rax, %rcx
jne .L2
