https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124697
--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to H.J. Lu from comment #3)
> [hjl@gnu-tgl-3 pr124697]$ cat foo.c
> typedef double v4df __attribute__((vector_size(32)));
> typedef double v2df __attribute__((vector_size(16)));
> typedef struct {
> v2df a[2];
> } c __attribute__((aligned(32)));
> extern v4df d;
> void
> e (float a1, float a2, float a3, float a4, float a5, float a6, c f)
> {
> d = *(v4df *) &f;
> }
> [hjl@gnu-tgl-3 pr124697]$ make foo.s
> /export/build/gnu/tools-build/gcc-gitlab-debug/build-x86_64-linux/gcc/xgcc
> -B/export/build/gnu/tools-build/gcc-gitlab-debug/build-x86_64-linux/gcc/ -O2
> -march=x86-64-v4 -S foo.c
> [hjl@gnu-tgl-3 pr124697]$ cat foo.s
> .file "foo.c"
> .text
> .p2align 4
> .globl e
> .type e, @function
> e:
> .LFB0:
> .cfi_startproc
> pushq %rbp
> .cfi_def_cfa_offset 16
> .cfi_offset 6, -16
> movq %rsp, %rbp
> .cfi_def_cfa_register 6
> vmovapd 16(%rbp), %ymm0 <<<<<<< f is aligned at 16 bytes.
Yes. This is wrong code. My patch would have fixed it, doing
effectively (but restricted to x86 at this point)
diff --git a/gcc/function.cc b/gcc/function.cc
index 46c0d8b54c2..d44815afc16 100644
--- a/gcc/function.cc
+++ b/gcc/function.cc
@@ -2840,7 +2840,7 @@ assign_parm_adjust_stack_rtl (tree parm, struct
assign_parm_data_one *data)
MEM_ALIGN (stack_parm))))
|| (data->nominal_type
&& TYPE_ALIGN (data->nominal_type) > MEM_ALIGN (stack_parm)
- && (MEM_ALIGN (stack_parm) < PREFERRED_STACK_BOUNDARY
+ && (MEM_ALIGN (stack_parm) < BIGGEST_ALIGNMENT
/* If its address is taken, make a local copy whose
maximum alignment is MAX_SUPPORTED_STACK_ALIGNMENT.
*/
> vmovapd %ymm0, d(%rip)
> vzeroupper
> popq %rbp
> .cfi_def_cfa 7, 8
> ret
> .cfi_endproc
> .LFE0:
> .size e, .-e
> .ident "GCC: (GNU) 16.0.1 20260331 (experimental)"
> .section .note.GNU-stack,"",@progbits
> [hjl@gnu-tgl-3 pr124697]$
