On Sat, Nov 5, 2022 at 12:25 PM Richard Biener
<richard.guent...@gmail.com> wrote:
>
> On Wed, Nov 2, 2022 at 1:46 PM Uros Bizjak <ubiz...@gmail.com> wrote:
> >
> > On Wed, Nov 2, 2022 at 1:45 PM Robin Dapp <rd...@linux.ibm.com> wrote:
> > >
> > > > IIRC, I was trying to "fix" modeless operand by giving it a mode, but
> > > > since it made no difference for x86, I later dropped the patch.
> > > > However, operand with a known mode is preferred, so if it works for
> > > > you, just include my patch in your submission. My patch is somehow
> > > > trivial if we want operand to have known mode.
> > >
> > > I'd prefer to push it separately as my patch changes several things in
> > > the s390 backend that are kind of unrelated.  Is it OK to do an x86
> > > bootstrap and regtest and push it if everything looks good?  You can of
> > > course also do it yourself :)
> >
> > It is a middle-end patch, someone will have to approve it.
>
> The patch is OK

Thanks, pushed with the following ChangeLog:

optabs: Use operand[2] mode in can_vec_set_var_idx_p

Use operand[2] mode in can_vec_set_var_idx_p when checking vec_set_optab.

This change allows non-VOID index operand in vec_set_optab.

2022-11-06  Uroš Bizjak  <ubiz...@gmail.com>

gcc/ChangeLog:

    * optabs.cc (can_vec_set_var_idx_p): Use operand[2]
    mode when checking vec_set_optab.

Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}.

Uros.
diff --git a/gcc/optabs.cc b/gcc/optabs.cc
index c2a6f971d74..9fc9b1fc6e9 100644
--- a/gcc/optabs.cc
+++ b/gcc/optabs.cc
@@ -4344,12 +4344,17 @@ can_vec_set_var_idx_p (machine_mode vec_mode)
     return false;
 
   machine_mode inner_mode = GET_MODE_INNER (vec_mode);
+
   rtx reg1 = alloca_raw_REG (vec_mode, LAST_VIRTUAL_REGISTER + 1);
   rtx reg2 = alloca_raw_REG (inner_mode, LAST_VIRTUAL_REGISTER + 2);
-  rtx reg3 = alloca_raw_REG (VOIDmode, LAST_VIRTUAL_REGISTER + 3);
 
   enum insn_code icode = optab_handler (vec_set_optab, vec_mode);
 
+  const struct insn_data_d *data = &insn_data[icode];
+  machine_mode idx_mode = data->operand[2].mode;
+
+  rtx reg3 = alloca_raw_REG (idx_mode, LAST_VIRTUAL_REGISTER + 3);
+
   return icode != CODE_FOR_nothing && insn_operand_matches (icode, 0, reg1)
         && insn_operand_matches (icode, 1, reg2)
         && insn_operand_matches (icode, 2, reg3);

Reply via email to