Add single-lane SLP support to .GOMP_SIMD_LANE vectorization

The following adds basic support for single-lane SLP .GOMP_SIMD_LANE
vectorization, in particular it enables SLP discovery.

	* tree-vect-slp.cc (no_arg_map): New.
	(vect_get_operand_map): Handle IFN_GOMP_SIMD_LANE.
	(vect_build_slp_tree_1): Likewise.
	* tree-vect-stmts.cc (vectorizable_call): Handle single-lane SLP
	for .GOMP_SIMD_LANE calls.

diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 2274d0e428e9ce0af75cfa33a94cd96fb6d397e1..125e69cf0eb02f14acb30dc049498bb7dcaf1eee 100644 (file)
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -507,6 +507,7 @@ static const int cond_expr_maps[3][5] = {
   { 4, -2, -1, 1, 2 },
   { 4, -1, -2, 2, 1 }
 };
+static const int no_arg_map[] = { 0 };
 static const int arg0_map[] = { 1, 0 };
 static const int arg1_map[] = { 1, 1 };
 static const int arg2_map[] = { 1, 2 };
@@ -587,6 +588,9 @@ vect_get_operand_map (const gimple *stmt, bool gather_scatter_p = false,
          case IFN_CTZ:
            return arg0_map;
 
+         case IFN_GOMP_SIMD_LANE:
+           return no_arg_map;
+
          default:
            break;
          }
@@ -1175,6 +1179,8 @@ vect_build_slp_tree_1 (vec_info *vinfo, unsigned char *swap,
              ldst_p = true;
              rhs_code = CFN_MASK_STORE;
            }
+         else if (cfn == CFN_GOMP_SIMD_LANE)
+           ;
          else if ((cfn != CFN_LAST
                    && cfn != CFN_MASK_CALL
                    && internal_fn_p (cfn)
@@ -1273,6 +1279,11 @@ vect_build_slp_tree_1 (vec_info *vinfo, unsigned char *swap,
              need_same_oprnds = true;
              first_op1 = gimple_call_arg (call_stmt, 1);
            }
+         else if (rhs_code == CFN_GOMP_SIMD_LANE)
+           {
+             need_same_oprnds = true;
+             first_op1 = gimple_call_arg (call_stmt, 1);
+           }
        }
       else
        {

diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 584be52f423726402eda4fa2f1babb8cb02502fc..0b0cf8f114e36d602f6d4124d7a789d18323cdac 100644 (file)
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -3392,7 +3392,7 @@ vectorizable_call (vec_info *vinfo,
   if (ifn == IFN_LAST && !fndecl)
     {
       if (cfn == CFN_GOMP_SIMD_LANE
-         && !slp_node
+         && (!slp_node || SLP_TREE_LANES (slp_node) == 1)
          && loop_vinfo
          && LOOP_VINFO_LOOP (loop_vinfo)->simduid
          && TREE_CODE (gimple_call_arg (stmt, 0)) == SSA_NAME
@@ -3538,8 +3538,30 @@ vectorizable_call (vec_info *vinfo,
          /* Build argument list for the vectorized call.  */
          if (slp_node)
            {
-             vec<tree> vec_oprnds0;
+             if (cfn == CFN_GOMP_SIMD_LANE)
+               {
+                 for (i = 0; i < SLP_TREE_NUMBER_OF_VEC_STMTS (slp_node); ++i)
+                   {
+                     /* ???  For multi-lane SLP we'd need to build
+                        { 0, 0, .., 1, 1, ... }.  */
+                     tree cst = build_index_vector (vectype_out,
+                                                    i * nunits_out, 1);
+                     tree new_var
+                         = vect_get_new_ssa_name (vectype_out, vect_simple_var,
+                                                  "cst_");
+                     gimple *init_stmt = gimple_build_assign (new_var, cst);
+                     vect_init_vector_1 (vinfo, stmt_info, init_stmt, NULL);
+                     new_temp = make_ssa_name (vec_dest);
+                     gimple *new_stmt
+                       = gimple_build_assign (new_temp, new_var);
+                     vect_finish_stmt_generation (vinfo, stmt_info, new_stmt,
+                                                  gsi);
+                     slp_node->push_vec_def (new_stmt);
+                   }
+                 continue;
+               }
 
+             vec<tree> vec_oprnds0;
              vect_get_slp_defs (vinfo, slp_node, &vec_defs);
              vec_oprnds0 = vec_defs[0];