openmp: Add IFN_GOMP_MAX_VF

Delay omp_max_vf call until after the host and device compilers have diverged
so that the max_vf value can be tuned exactly right on both variants.

This change means that the ompdevlow pass must be enabled for functions that
use OpenMP directives with both "simd" and "schedule" enabled.

gcc/ChangeLog:

	* internal-fn.cc (expand_GOMP_MAX_VF): New function.
	* internal-fn.def (GOMP_MAX_VF): New internal function.
	* omp-expand.cc (omp_adjust_chunk_size): Emit IFN_GOMP_MAX_VF when
	called in offload context, otherwise assume host context.
	* omp-offload.cc (execute_omp_device_lower): Expand IFN_GOMP_MAX_VF.

gcc/internal-fn.cc

@@ -510,6 +510,14 @@ expand_GOMP_SIMT_VF (internal_fn, gcall *)
 
 /* This should get expanded in omp_device_lower pass.  */
 
+static void
+expand_GOMP_MAX_VF (internal_fn, gcall *)
+{
+  gcc_unreachable ();
+}
+
+/* This should get expanded in omp_device_lower pass.  */
+
 static void
 expand_GOMP_TARGET_REV (internal_fn, gcall *)
 {

gcc/internal-fn.def

@@ -465,6 +465,7 @@ DEF_INTERNAL_FN (GOMP_SIMT_ENTER_ALLOC, ECF_LEAF | ECF_NOTHROW, NULL)
 DEF_INTERNAL_FN (GOMP_SIMT_EXIT, ECF_LEAF | ECF_NOTHROW, NULL)
 DEF_INTERNAL_FN (GOMP_SIMT_LANE, ECF_NOVOPS | ECF_LEAF | ECF_NOTHROW, NULL)
 DEF_INTERNAL_FN (GOMP_SIMT_VF, ECF_NOVOPS | ECF_LEAF | ECF_NOTHROW, NULL)
+DEF_INTERNAL_FN (GOMP_MAX_VF, ECF_CONST | ECF_LEAF | ECF_NOTHROW, NULL)
 DEF_INTERNAL_FN (GOMP_SIMT_LAST_LANE, ECF_NOVOPS | ECF_LEAF | ECF_NOTHROW, NULL)
 DEF_INTERNAL_FN (GOMP_SIMT_ORDERED_PRED, ECF_LEAF | ECF_NOTHROW, NULL)
 DEF_INTERNAL_FN (GOMP_SIMT_VOTE_ANY, ECF_NOVOPS | ECF_LEAF | ECF_NOTHROW, NULL)

gcc/omp-expand.cc

@@ -229,15 +229,29 @@ omp_adjust_chunk_size (tree chunk_size, bool simd_schedule, bool offload)
   if (!simd_schedule || integer_zerop (chunk_size))
     return chunk_size;
 
-  poly_uint64 vf = omp_max_vf (offload);
+  tree vf;
-  if (known_eq (vf, 1U))
-    return chunk_size;
-
   tree type = TREE_TYPE (chunk_size);
-  chunk_size = fold_build2 (PLUS_EXPR, type, chunk_size,
+
-			    build_int_cst (type, vf - 1));
+  if (offload)
-  return fold_build2 (BIT_AND_EXPR, type, chunk_size,
+    {
-		      build_int_cst (type, -vf));
+      cfun->curr_properties &= ~PROP_gimple_lomp_dev;
+      vf = build_call_expr_internal_loc (UNKNOWN_LOCATION, IFN_GOMP_MAX_VF,
+					 unsigned_type_node, 0);
+      vf = fold_convert (type, vf);
+    }
+  else
+    {
+      poly_uint64 vf_num = omp_max_vf (false);
+      if (known_eq (vf_num, 1U))
+	return chunk_size;
+      vf = build_int_cst (type, vf_num);
+    }
+
+  tree vf_minus_one = fold_build2 (MINUS_EXPR, type, vf,
+				   build_int_cst (type, 1));
+  tree negative_vf = fold_build1 (NEGATE_EXPR, type, vf);
+  chunk_size = fold_build2 (PLUS_EXPR, type, chunk_size, vf_minus_one);
+  return fold_build2 (BIT_AND_EXPR, type, chunk_size, negative_vf);
 }
 
 /* Collect additional arguments needed to emit a combined

gcc/omp-offload.cc

@@ -2754,6 +2754,9 @@ execute_omp_device_lower ()
 	  case IFN_GOMP_SIMT_VF:
 	    rhs = build_int_cst (type, vf);
 	    break;
+	  case IFN_GOMP_MAX_VF:
+	    rhs = build_int_cst (type, omp_max_vf (false));
+	    break;
 	  case IFN_GOMP_SIMT_ORDERED_PRED:
 	    rhs = vf == 1 ? integer_zero_node : NULL_TREE;
 	    if (rhs || !lhs)