This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug rtl-optimization/50728] Inefficient vector loads from aggregates passed by value
- From: "rguenth at gcc dot gnu.org" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: Fri, 14 Oct 2011 13:40:31 +0000
- Subject: [Bug rtl-optimization/50728] Inefficient vector loads from aggregates passed by value
- Auto-submitted: auto-generated
- References: <bug-50728-4@http.gcc.gnu.org/bugzilla/>
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50728
--- Comment #2 from Richard Guenther <rguenth at gcc dot gnu.org> 2011-10-14 13:40:31 UTC ---
typedef __complex__ float Value;
struct A {
Value a[16 / sizeof (Value)];
} __attribute__ ((aligned(16)));
Value get(A a)
{
return a.a[0];
}
_Z3get1A:
.LFB0:
.cfi_startproc
movq %xmm0, -24(%rsp)
movss -24(%rsp), %xmm0
movss %xmm0, -32(%rsp)
movss -20(%rsp), %xmm0
movss %xmm0, -28(%rsp)
movq -32(%rsp), %xmm0
ret
eh ...