Vect: Support loop len in vectorizable early exit

This patch adds early break auto-vectorization support for target which
use length on partial vectorization.  Consider this following example:

unsigned vect_a[802];
unsigned vect_b[802];

void test (unsigned x, int n)
{
  for (int i = 0; i < n; i++)
  {
    vect_b[i] = x + i;

    if (vect_a[i] > x)
      break;

    vect_a[i] = x;
  }
}

We use VCOND_MASK_LEN to simulate the generate (mask && i < len + bias).
And then the IR of RVV looks like below:

  ...
  _87 = .SELECT_VL (ivtmp_85, POLY_INT_CST [32, 32]);
  _55 = (int) _87;
  ...
  mask_patt_6.13_69 = vect_cst__62 < vect__3.12_67;
  vec_len_mask_72 = .VCOND_MASK_LEN (mask_patt_6.13_69, { -1, ... }, \
    {0, ... }, _87, 0);
  if (vec_len_mask_72 != { 0, ... })
    goto <bb 6>; [5.50%]
  else
    goto <bb 7>; [94.50%]

The below tests are passed for this patch:
1. The riscv fully regression tests.
2. The x86 bootstrap tests.
3. The x86 fully regression tests.

gcc/ChangeLog:

	* tree-vect-loop.cc (vect_gen_loop_len_mask): New func to gen
	the loop len mask.
	* tree-vect-stmts.cc (vectorizable_early_exit): Invoke the
	vect_gen_loop_len_mask for 1 or more stmt(s).
	* tree-vectorizer.h (vect_gen_loop_len_mask): New func decl
	for vect_gen_loop_len_mask.

Signed-off-by: Pan Li <pan2.li@intel.com>

3 files changed, 46 insertions, 2 deletions

diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 361aec0..83c0544 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -11416,6 +11416,33 @@ vect_get_loop_len (loop_vec_info loop_vinfo, gimple_stmt_iterator *gsi,
   return loop_len;
 }
 
+/* Generate the tree for the loop len mask and return it.  Given the lens,
+   nvectors, vectype, index and factor to gen the len mask as below.
+
+   tree len_mask = VCOND_MASK_LEN (compare_mask, ones, zero, len, bias)
+*/
+tree
+vect_gen_loop_len_mask (loop_vec_info loop_vinfo, gimple_stmt_iterator *gsi,
+			gimple_stmt_iterator *cond_gsi, vec_loop_lens *lens,
+			unsigned int nvectors, tree vectype, tree stmt,
+			unsigned int index, unsigned int factor)
+{
+  tree all_one_mask = build_all_ones_cst (vectype);
+  tree all_zero_mask = build_zero_cst (vectype);
+  tree len = vect_get_loop_len (loop_vinfo, gsi, lens, nvectors, vectype, index,
+				factor);
+  tree bias = build_int_cst (intQI_type_node,
+			     LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo));
+  tree len_mask = make_temp_ssa_name (TREE_TYPE (stmt), NULL, "vec_len_mask");
+  gcall *call = gimple_build_call_internal (IFN_VCOND_MASK_LEN, 5, stmt,
+					    all_one_mask, all_zero_mask, len,
+					    bias);
+  gimple_call_set_lhs (call, len_mask);
+  gsi_insert_before (cond_gsi, call, GSI_SAME_STMT);
+
+  return len_mask;
+}
+
 /* Scale profiling counters by estimation for LOOP which is vectorized
    by factor VF.
    If FLAT is true, the loop we started with had unrealistically flat
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index b8a7160..6729595 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -12895,7 +12895,9 @@ vectorizable_early_exit (vec_info *vinfo, stmt_vec_info stmt_info,
     ncopies = vect_get_num_copies (loop_vinfo, vectype);
 
   vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo);
+  vec_loop_lens *lens = &LOOP_VINFO_LENS (loop_vinfo);
   bool masked_loop_p = LOOP_VINFO_FULLY_MASKED_P (loop_vinfo);
+  bool len_loop_p = LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo);
 
   /* Now build the new conditional.  Pattern gimple_conds get dropped during
      codegen so we must replace the original insn.  */
@@ -12959,12 +12961,11 @@ vectorizable_early_exit (vec_info *vinfo, stmt_vec_info stmt_info,
 	{
 	  if (direct_internal_fn_supported_p (IFN_VCOND_MASK_LEN, vectype,
 					      OPTIMIZE_FOR_SPEED))
-	    return false;
+	    vect_record_loop_len (loop_vinfo, lens, ncopies, vectype, 1);
 	  else
 	    vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype, NULL);
 	}
 
-
       return true;
     }
 
@@ -13017,6 +13018,15 @@ vectorizable_early_exit (vec_info *vinfo, stmt_vec_info stmt_info,
 				  stmts[i], &cond_gsi);
 	    workset.quick_push (stmt_mask);
 	  }
+      else if (len_loop_p)
+	for (unsigned i = 0; i < stmts.length (); i++)
+	  {
+	    tree len_mask = vect_gen_loop_len_mask (loop_vinfo, gsi, &cond_gsi,
+						    lens, ncopies, vectype,
+						    stmts[i], i, 1);
+
+	    workset.quick_push (len_mask);
+	  }
       else
 	workset.splice (stmts);
 
@@ -13041,6 +13051,9 @@ vectorizable_early_exit (vec_info *vinfo, stmt_vec_info stmt_info,
 	  new_temp = prepare_vec_mask (loop_vinfo, TREE_TYPE (mask), mask,
 				       new_temp, &cond_gsi);
 	}
+      else if (len_loop_p)
+	new_temp = vect_gen_loop_len_mask (loop_vinfo, gsi, &cond_gsi, lens,
+					   ncopies, vectype, new_temp, 0, 1);
     }
 
   gcc_assert (new_temp);
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index db44d73..93bc30e 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -2408,6 +2408,10 @@ extern void vect_record_loop_len (loop_vec_info, vec_loop_lens *, unsigned int,
 extern tree vect_get_loop_len (loop_vec_info, gimple_stmt_iterator *,
 			       vec_loop_lens *, unsigned int, tree,
 			       unsigned int, unsigned int);
+extern tree vect_gen_loop_len_mask (loop_vec_info, gimple_stmt_iterator *,
+				    gimple_stmt_iterator *, vec_loop_lens *,
+				    unsigned int, tree, tree, unsigned int,
+				    unsigned int);
 extern gimple_seq vect_gen_len (tree, tree, tree, tree);
 extern stmt_vec_info info_for_reduction (vec_info *, stmt_vec_info);
 extern bool reduction_fn_for_scalar_code (code_helper, internal_fn *);