https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97194
--- Comment #13 from Richard Biener <rguenth at gcc dot gnu.org> ---
(In reply to Richard Biener from comment #12)
> (In reply to Alexander Monakov from comment #11)
> > Yeah, for inserts such tactic would be inappropriate due to bad store
> > forwarding stalls anyway. As you've shown in earlier comments, inserts have
> > a very nice generic way to expand them (that does not touch stack).
>
> Unfortunately it doesn't work (the CSE). Patch:
>
> diff --git a/gcc/cfgexpand.c b/gcc/cfgexpand.c
> index 1eaa1da11b9..f7b1a92dd95 100644
> --- a/gcc/cfgexpand.c
> +++ b/gcc/cfgexpand.c
> @@ -6102,7 +6102,11 @@ discover_nonconstant_array_refs_r (tree * tp, int
> *walk_subtrees,
> || CONVERT_EXPR_P (t))
> t = TREE_OPERAND (t, 0);
>
> - if (TREE_CODE (t) == ARRAY_REF || TREE_CODE (t) == ARRAY_RANGE_REF)
> + if ((TREE_CODE (t) == ARRAY_REF
> + && !(TREE_CODE (TREE_OPERAND (t, 0)) == VIEW_CONVERT_EXPR
> + && DECL_P (TREE_OPERAND (TREE_OPERAND (t, 0), 0)))
> + && VECTOR_TYPE_P (TREE_TYPE (TREE_OPERAND (TREE_OPERAND (t,
> 0), 0))))
> + || TREE_CODE (t) == ARRAY_RANGE_REF)
> {
> t = get_base_address (t);
> if (t && DECL_P (t)
>
>
> and for
>
> typedef int v4si __attribute__((vector_size(16)));
>
> int foo (v4si v, int i)
> {
> v = v + v;
> return v[i] + v[2*i];
> }
>
> at -O2 we get
>
> foo:
> .LFB0:
> .cfi_startproc
> leal (%rdi,%rdi), %edx
> paddd %xmm0, %xmm0
> movslq %edi, %rdi
> movslq %edx, %rdx
> movaps %xmm0, -24(%rsp)
> movaps %xmm0, -40(%rsp)
> movl -40(%rsp,%rdi,4), %eax
> addl -24(%rsp,%rdx,4), %eax
> ret
and unpatched
foo:
.LFB0:
.cfi_startproc
leal (%rdi,%rdi), %edx
paddd %xmm0, %xmm0
movslq %edi, %rdi
movslq %edx, %rdx
movaps %xmm0, -24(%rsp)
movl -24(%rsp,%rdi,4), %eax
addl -24(%rsp,%rdx,4), %eax
ret
so we're able to elide the stack slot usage for the add and retain a single
slot.
