https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65832
Bug ID: 65832
Summary: Inefficient vector construction
Product: gcc
Version: 6.0
Status: UNCONFIRMED
Keywords: missed-optimization
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: rguenth at gcc dot gnu.org
Target: x86_64-*-*, i?86-*-*
typedef int v4si __attribute__((vector_size(16)));
v4si foo (int i, int j, int k, int l)
{
return (v4si) { i, j, k, l };
}
produces
movl %edx, -12(%rsp)
movd -12(%rsp), %xmm1
movl %ecx, -12(%rsp)
movd -12(%rsp), %xmm2
movl %edi, -12(%rsp)
movd -12(%rsp), %xmm0
movl %esi, -12(%rsp)
movd -12(%rsp), %xmm3
punpckldq %xmm2, %xmm1
punpckldq %xmm3, %xmm0
punpcklqdq %xmm1, %xmm0
ret
as we spill everything to the stack we could as well use a vector load, thus
something like
movl %edx, -12(%rsp)
movl %ecx, -16(%rsp)
movl %edi, -20(%rsp)
movl %esi, -24(%rsp)
movdqu -12(%rsp), %xmm0
ret
