Hi!

The following testcase fails -fcompare-debug, because expand_vector_comparison
since r11-1786-g1ac9258cca8030745d3c0b8f63186f0adf0ebc27 sets
vec_cond_expr_only when it sees some use other than VEC_COND_EXPR that uses
the lhs in its condition.
Obviously we should ignore debug stmts when doing so, e.g. by not pushing
them to uses.
That would be a 2 liner change, but while looking at it, I'm also worried
about VEC_COND_EXPRs that would use the lhs in more than one operand,
like VEC_COND_EXPR <lhs, lhs, something> or VEC_COND_EXPR <lhs, something, lhs>
(sure, they ought to be folded, but what if they weren't).  Because if
something like that happens, then FOR_EACH_IMM_USE_FAST would push the same
stmt multiple times and expand_vector_condition can return true even when
it modifies it (for vector bool masking).
And lastly, it seems quite wasteful to safe_push statements that will just
cause vec_cond_expr_only = false; and break; in the second loop, both for
cases like 1000 immediate non-VEC_COND_EXPR uses and for cases like
999 VEC_COND_EXPRs with lhs in cond followed by a single non-VEC_COND_EXPR
use.  So this patch only pushes VEC_COND_EXPRs there.  As
expand_vector_condition modifies the IL, it checks the condition again as
before.

Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?

2022-02-01  Jakub Jelinek  <ja...@redhat.com>

        PR middle-end/104307
        * tree-vect-generic.cc (expand_vector_comparison): Don't push debug
        stmts to uses vector, just set vec_cond_expr_only to false for
        non-VEC_COND_EXPRs instead of pushing them into uses.  Treat
        VEC_COND_EXPRs that use lhs not just in rhs1, but rhs2 or rhs3 too
        like non-VEC_COND_EXPRs.

        * gcc.target/i386/pr104307.c: New test.

--- gcc/tree-vect-generic.cc.jj 2022-01-20 11:30:45.641577244 +0100
+++ gcc/tree-vect-generic.cc    2022-01-31 18:01:29.062568721 +0100
@@ -436,29 +436,43 @@ expand_vector_comparison (gimple_stmt_it
      feeding a VEC_COND_EXPR statement.  */
   auto_vec<gimple *> uses;
   FOR_EACH_IMM_USE_FAST (use_p, iterator, lhs)
-    uses.safe_push (USE_STMT (use_p));
-
-  for (unsigned i = 0; i < uses.length (); i ++)
     {
-      gassign *use = dyn_cast<gassign *> (uses[i]);
-      if (use != NULL
+      gimple *use = USE_STMT (use_p);
+      if (is_gimple_debug (use))
+       continue;
+      if (is_gimple_assign (use)
          && gimple_assign_rhs_code (use) == VEC_COND_EXPR
-         && gimple_assign_rhs1 (use) == lhs)
-       {
-         gimple_stmt_iterator it = gsi_for_stmt (use);
-         if (!expand_vector_condition (&it, dce_ssa_names))
-           {
-             vec_cond_expr_only = false;
-             break;
-           }
-       }
+         && gimple_assign_rhs1 (use) == lhs
+         && gimple_assign_rhs2 (use) != lhs
+         && gimple_assign_rhs3 (use) != lhs)
+       uses.safe_push (use);
       else
-       {
-         vec_cond_expr_only = false;
-         break;
-       }
+       vec_cond_expr_only = false;
     }
 
+  if (vec_cond_expr_only)
+    for (gimple *use : uses)
+      {
+       if (is_gimple_assign (use)
+           && gimple_assign_rhs_code (use) == VEC_COND_EXPR
+           && gimple_assign_rhs1 (use) == lhs
+           && gimple_assign_rhs2 (use) != lhs
+           && gimple_assign_rhs3 (use) != lhs)
+         {
+           gimple_stmt_iterator it = gsi_for_stmt (use);
+           if (!expand_vector_condition (&it, dce_ssa_names))
+             {
+               vec_cond_expr_only = false;
+               break;
+             }
+         }
+       else
+         {
+           vec_cond_expr_only = false;
+           break;
+         }
+      }
+
   if (!uses.is_empty () && vec_cond_expr_only)
     return NULL_TREE;
 
--- gcc/testsuite/gcc.target/i386/pr104307.c.jj 2022-01-31 17:34:42.163145798 
+0100
+++ gcc/testsuite/gcc.target/i386/pr104307.c    2022-01-31 17:35:14.111696698 
+0100
@@ -0,0 +1,6 @@
+/* PR middle-end/104307 */
+/* { dg-do compile } */
+/* { dg-require-effective-target int128 } */
+/* { dg-options "-O2 -mavx512f -fcompare-debug " } */
+
+#include "pr78669.c"

        Jakub

Reply via email to