Add OpenACC target kinds for decomposed kernels regions

This patch is in preparation for changes that will cut up OpenACC kernels
regions into individual parts. For the new sub-regions that will be
generated, this adds the following new kinds of OpenACC regions for internal
use:

- GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED for parts of kernels
  regions to be executed in gang-redundant mode
- GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE for parts of kernels
  regions to be executed in gang-single mode
- GF_OMP_TARGET_KIND_OACC_DATA_KERNELS for data regions generated around the
  body of a kernels region

    gcc/
    * gimple.h (enum gf_mask): Add new target kinds
    GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED,
    GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE, and
    GF_OMP_TARGET_KIND_OACC_DATA_KERNELS.
    (is_gimple_omp_oacc): Handle new target kinds.
    (is_gimple_omp_offloaded): Likewise.
    * gimple-pretty-print.c (dump_gimple_omp_target): Likewise.
    * omp-expand.c (expand_omp_target): Likewise.
    (build_omp_regions_1): Likewise.
    (omp_make_gimple_edges): Likewise.
    * omp-low.c (is_oacc_parallel_or_serial): Likewise.
    (was_originally_oacc_kernels): New function.
    (scan_omp_for): Update check for illegal nesting.
    (check_omp_nesting_restrictions): Handle new target kinds.
    (lower_oacc_reductions): Likewise.
    (lower_omp_target): Likewise.
    * omp-offload.c (execute_oacc_device_lower): Likewise.

(cherry picked from openacc-gcc-9-branch commit
b24a8fc55b6d4fd38a8feff5bca4940e28a005ed)

diff --git a/gcc/ChangeLog.omp b/gcc/ChangeLog.omp
index 180cee10ec01bdb920a3a4444a0d1794269593c6..5191284441353694701683fbf693e2b05ff881b9 100644 (file)
--- a/gcc/ChangeLog.omp
+++ b/gcc/ChangeLog.omp
@@ -1,3 +1,23 @@
+2019-01-23  Thomas Schwinge  <thomas@codesourcery.com>
+
+       * gimple.h (enum gf_mask): Add new target kinds
+       GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED,
+       GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE, and
+       GF_OMP_TARGET_KIND_OACC_DATA_KERNELS.
+       (is_gimple_omp_oacc): Handle new target kinds.
+       (is_gimple_omp_offloaded): Likewise.
+       * gimple-pretty-print.c (dump_gimple_omp_target): Likewise.
+       * omp-expand.c (expand_omp_target): Likewise.
+       (build_omp_regions_1): Likewise.
+       (omp_make_gimple_edges): Likewise.
+       * omp-low.c (is_oacc_parallel_or_serial): Likewise.
+       (was_originally_oacc_kernels): New function.
+       (scan_omp_for): Update check for illegal nesting.
+       (check_omp_nesting_restrictions): Handle new target kinds.
+       (lower_oacc_reductions): Likewise.
+       (lower_omp_target): Likewise.
+       * omp-offload.c (execute_oacc_device_lower): Likewise.
+
 2019-01-30  Thomas Schwinge  <thomas@codesourcery.com>
 
        * flag-types.h (enum openacc_kernels): New type.

diff --git a/gcc/gimple-pretty-print.c b/gcc/gimple-pretty-print.c
index bae6d25ebb5e9c0f4eeccdb5f10414b0f1983feb..400c73b4b6a1151a32692e3b2346774cd7b4102a 100644 (file)
--- a/gcc/gimple-pretty-print.c
+++ b/gcc/gimple-pretty-print.c
@@ -1632,6 +1632,15 @@ dump_gimple_omp_target (pretty_printer *buffer, gomp_target *gs,
     case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
       kind = " oacc_host_data";
       break;
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+      kind = " oacc_parallel_kernels_parallelized";
+      break;
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+      kind = " oacc_parallel_kernels_gang_single";
+      break;
+    case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
+      kind = " oacc_data_kernels";
+      break;
     default:
       gcc_unreachable ();
     }

diff --git a/gcc/gimple.h b/gcc/gimple.h
index 5c3defd96fedc7106163442c3bb6f46518fedcc1..2cc5e6f87c38d296eecf7bf4ff884b81224a56d2 100644 (file)
--- a/gcc/gimple.h
+++ b/gcc/gimple.h
@@ -185,6 +185,15 @@ enum gf_mask {
     GF_OMP_TARGET_KIND_OACC_DECLARE = 10,
     GF_OMP_TARGET_KIND_OACC_HOST_DATA = 11,
     GF_OMP_TARGET_KIND_OACC_SERIAL = 12,
+    /* A GF_OMP_TARGET_KIND_OACC_PARALLEL that originates from a 'kernels'
+       construct, parallelized.  */
+    GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED = 13,
+    /* A GF_OMP_TARGET_KIND_OACC_PARALLEL that originates from a 'kernels'
+       construct, "gang-single".  */
+    GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE = 14,
+    /* A GF_OMP_TARGET_KIND_OACC_DATA that originates from a 'kernels'
+       construct.  */
+    GF_OMP_TARGET_KIND_OACC_DATA_KERNELS = 15,
     GF_OMP_TEAMS_GRID_PHONY    = 1 << 0,
     GF_OMP_TEAMS_HOST          = 1 << 1,
 
@@ -6426,6 +6435,9 @@ is_gimple_omp_oacc (const gimple *stmt)
        case GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA:
        case GF_OMP_TARGET_KIND_OACC_DECLARE:
        case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
+       case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+       case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+       case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
          return true;
        default:
          return false;
@@ -6451,6 +6463,8 @@ is_gimple_omp_offloaded (const gimple *stmt)
        case GF_OMP_TARGET_KIND_OACC_PARALLEL:
        case GF_OMP_TARGET_KIND_OACC_KERNELS:
        case GF_OMP_TARGET_KIND_OACC_SERIAL:
+       case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+       case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
          return true;
        default:
          return false;

diff --git a/gcc/omp-expand.c b/gcc/omp-expand.c
index e30d8e78aaee44d475be422a6fb83c22111de717..c93348037a33d5ca9fc680d3ecbb4b9270d23a7e 100644 (file)
--- a/gcc/omp-expand.c
+++ b/gcc/omp-expand.c
@@ -7317,6 +7317,8 @@ expand_omp_target (struct omp_region *region)
     {
     case GF_OMP_TARGET_KIND_OACC_PARALLEL:
     case GF_OMP_TARGET_KIND_OACC_SERIAL:
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
       oacc_parallel = true;
       gcc_fallthrough ();
     case GF_OMP_TARGET_KIND_REGION:
@@ -7332,6 +7334,7 @@ expand_omp_target (struct omp_region *region)
     case GF_OMP_TARGET_KIND_DATA:
     case GF_OMP_TARGET_KIND_OACC_DATA:
     case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
+    case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
       data_region = true;
       break;
     default:
@@ -7354,26 +7357,33 @@ expand_omp_target (struct omp_region *region)
   entry_bb = region->entry;
   exit_bb = region->exit;
 
+  /* Further down, all OpenACC compute constructs will be mapped to
+     BUILT_IN_GOACC_PARALLEL, and to distinguish between them, we now attach
+     attributes.  */
   switch (gimple_omp_target_kind (entry_stmt))
     {
     case GF_OMP_TARGET_KIND_OACC_KERNELS:
       mark_loops_in_oacc_kernels_region (region->entry, region->exit);
 
-      /* Further down, all OpenACC compute constructs will be mapped to
-        BUILT_IN_GOACC_PARALLEL, and to distinguish between them, there
-        is an "oacc kernels" attribute set for OpenACC kernels.  */
       DECL_ATTRIBUTES (child_fn)
        = tree_cons (get_identifier ("oacc kernels"),
                     NULL_TREE, DECL_ATTRIBUTES (child_fn));
       break;
     case GF_OMP_TARGET_KIND_OACC_SERIAL:
-      /* Further down, all OpenACC compute constructs will be mapped to
-        BUILT_IN_GOACC_PARALLEL, and to distinguish between them, there
-        is an "oacc serial" attribute set for OpenACC serial.  */
       DECL_ATTRIBUTES (child_fn)
        = tree_cons (get_identifier ("oacc serial"),
                     NULL_TREE, DECL_ATTRIBUTES (child_fn));
       break;
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+      DECL_ATTRIBUTES (child_fn)
+       = tree_cons (get_identifier ("oacc parallel_kernels_parallelized"),
+                    NULL_TREE, DECL_ATTRIBUTES (child_fn));
+      break;
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+      DECL_ATTRIBUTES (child_fn)
+       = tree_cons (get_identifier ("oacc parallel_kernels_gang_single"),
+                    NULL_TREE, DECL_ATTRIBUTES (child_fn));
+      break;
     default:
       break;
     }
@@ -7581,10 +7591,13 @@ expand_omp_target (struct omp_region *region)
     case GF_OMP_TARGET_KIND_OACC_KERNELS:
     case GF_OMP_TARGET_KIND_OACC_PARALLEL:
     case GF_OMP_TARGET_KIND_OACC_SERIAL:
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
       start_ix = BUILT_IN_GOACC_PARALLEL;
       break;
     case GF_OMP_TARGET_KIND_OACC_DATA:
     case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
+    case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
       start_ix = BUILT_IN_GOACC_DATA_START;
       break;
     case GF_OMP_TARGET_KIND_OACC_UPDATE:
@@ -8377,6 +8390,9 @@ build_omp_regions_1 (basic_block bb, struct omp_region *parent,
                case GF_OMP_TARGET_KIND_OACC_SERIAL:
                case GF_OMP_TARGET_KIND_OACC_DATA:
                case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
+               case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+               case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+               case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
                  break;
                case GF_OMP_TARGET_KIND_UPDATE:
                case GF_OMP_TARGET_KIND_ENTER_DATA:
@@ -8632,6 +8648,9 @@ omp_make_gimple_edges (basic_block bb, struct omp_region **region,
        case GF_OMP_TARGET_KIND_OACC_SERIAL:
        case GF_OMP_TARGET_KIND_OACC_DATA:
        case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
+       case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+       case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+       case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
          break;
        case GF_OMP_TARGET_KIND_UPDATE:
        case GF_OMP_TARGET_KIND_ENTER_DATA:

diff --git a/gcc/omp-low.c b/gcc/omp-low.c
index 7cdbfbb2ed40ccae4f419279d596601d5e334f2c..fcbc90834b0470035890deb05875b8ee75e86281 100644 (file)
--- a/gcc/omp-low.c
+++ b/gcc/omp-low.c
@@ -181,7 +181,11 @@ is_oacc_parallel_or_serial (omp_context *ctx)
          && ((gimple_omp_target_kind (ctx->stmt)
               == GF_OMP_TARGET_KIND_OACC_PARALLEL)
              || (gimple_omp_target_kind (ctx->stmt)
-                 == GF_OMP_TARGET_KIND_OACC_SERIAL)));
+                 == GF_OMP_TARGET_KIND_OACC_SERIAL)
+             || (gimple_omp_target_kind (ctx->stmt)
+                 == GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED)
+             || (gimple_omp_target_kind (ctx->stmt)
+                 == GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE)));
 }
 
 /* Return true if CTX corresponds to an oacc kernels region.  */
@@ -195,6 +199,22 @@ is_oacc_kernels (omp_context *ctx)
              == GF_OMP_TARGET_KIND_OACC_KERNELS));
 }
 
+/* Return true if CTX corresponds to an oacc region that was generated from
+   an original kernels region that has been lowered to parallel regions.  */
+
+static bool
+was_originally_oacc_kernels (omp_context *ctx)
+{
+  enum gimple_code outer_type = gimple_code (ctx->stmt);
+  return ((outer_type == GIMPLE_OMP_TARGET)
+         && ((gimple_omp_target_kind (ctx->stmt)
+              == GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED)
+             || (gimple_omp_target_kind (ctx->stmt)
+                 == GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE)
+             || (gimple_omp_target_kind (ctx->stmt)
+                 == GF_OMP_TARGET_KIND_OACC_DATA_KERNELS)));
+}
+
 /* If DECL is the artificial dummy VAR_DECL created for non-static
    data member privatization, return the underlying "this" parameter,
    otherwise return NULL.  */
@@ -2561,7 +2581,8 @@ scan_omp_for (gomp_for *stmt, omp_context *outer_ctx)
     {
       omp_context *tgt = enclosing_target_ctx (outer_ctx);
 
-      if (!tgt || is_oacc_parallel_or_serial (tgt))
+      if (!tgt || (is_oacc_parallel_or_serial (tgt)
+                    && !was_originally_oacc_kernels (tgt)))
        for (tree c = clauses; c; c = OMP_CLAUSE_CHAIN (c))
          {
            char const *check = NULL;
@@ -3128,6 +3149,8 @@ check_omp_nesting_restrictions (gimple *stmt, omp_context *ctx)
                  case GF_OMP_TARGET_KIND_OACC_PARALLEL:
                  case GF_OMP_TARGET_KIND_OACC_KERNELS:
                  case GF_OMP_TARGET_KIND_OACC_SERIAL:
+                 case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+                 case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
                    ok = true;
                    break;
 
@@ -3583,6 +3606,11 @@ check_omp_nesting_restrictions (gimple *stmt, omp_context *ctx)
              stmt_name = "enter/exit data"; break;
            case GF_OMP_TARGET_KIND_OACC_HOST_DATA: stmt_name = "host_data";
              break;
+           case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+           case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+           case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
+             /* These three cases arise from kernels conversion.  */
+             stmt_name = "kernels"; break;
            default: gcc_unreachable ();
            }
          switch (gimple_omp_target_kind (ctx->stmt))
@@ -3598,6 +3626,11 @@ check_omp_nesting_restrictions (gimple *stmt, omp_context *ctx)
            case GF_OMP_TARGET_KIND_OACC_DATA: ctx_stmt_name = "data"; break;
            case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
              ctx_stmt_name = "host_data"; break;
+           case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+           case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
+           case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
+             /* These three cases arise from kernels conversion.  */
+             ctx_stmt_name = "kernels"; break;
            default: gcc_unreachable ();
            }
 
@@ -6136,7 +6169,11 @@ lower_oacc_reductions (location_t loc, tree clauses, tree level, bool inner,
                    if ((gimple_omp_target_kind (probe->stmt)
                         != GF_OMP_TARGET_KIND_OACC_PARALLEL)
                        && (gimple_omp_target_kind (probe->stmt)
-                           != GF_OMP_TARGET_KIND_OACC_SERIAL))
+                           != GF_OMP_TARGET_KIND_OACC_SERIAL)
+                       && (gimple_omp_target_kind (probe->stmt)
+                           != GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED)
+                       && (gimple_omp_target_kind (probe->stmt)
+                           != GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE))
                      goto do_lookup;
 
                    cls = gimple_omp_target_clauses (probe->stmt);
@@ -9805,11 +9842,14 @@ lower_omp_target (gimple_stmt_iterator *gsi_p, omp_context *ctx)
     case GF_OMP_TARGET_KIND_OACC_UPDATE:
     case GF_OMP_TARGET_KIND_OACC_ENTER_EXIT_DATA:
     case GF_OMP_TARGET_KIND_OACC_DECLARE:
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_PARALLELIZED:
+    case GF_OMP_TARGET_KIND_OACC_PARALLEL_KERNELS_GANG_SINGLE:
       data_region = false;
       break;
     case GF_OMP_TARGET_KIND_DATA:
     case GF_OMP_TARGET_KIND_OACC_DATA:
     case GF_OMP_TARGET_KIND_OACC_HOST_DATA:
+    case GF_OMP_TARGET_KIND_OACC_DATA_KERNELS:
       data_region = true;
       break;
     default:

diff --git a/gcc/omp-offload.c b/gcc/omp-offload.c
index f5aa80b24045458d6fcc9f455c9c99efc2161523..29492563cc3fe36c60a97b3694d23ca02d39e123 100644 (file)
--- a/gcc/omp-offload.c
+++ b/gcc/omp-offload.c
@@ -1595,6 +1595,20 @@ execute_oacc_device_lower ()
   bool is_oacc_kernels_parallelized
     = (lookup_attribute ("oacc kernels parallelized",
                         DECL_ATTRIBUTES (current_function_decl)) != NULL);
+  if (is_oacc_kernels_parallelized)
+    gcc_checking_assert (is_oacc_kernels);
+  bool is_oacc_parallel_kernels_parallelized
+    = (lookup_attribute ("oacc parallel_kernels_parallelized",
+                        DECL_ATTRIBUTES (current_function_decl)) != NULL);
+  if (is_oacc_parallel_kernels_parallelized)
+    gcc_checking_assert (!is_oacc_kernels);
+  bool is_oacc_parallel_kernels_gang_single
+    = (lookup_attribute ("oacc parallel_kernels_gang_single",
+                        DECL_ATTRIBUTES (current_function_decl)) != NULL);
+  if (is_oacc_parallel_kernels_gang_single)
+    gcc_checking_assert (!is_oacc_kernels);
+  gcc_checking_assert (!(is_oacc_parallel_kernels_parallelized
+                        && is_oacc_parallel_kernels_gang_single));
 
   /* Unparallelized OpenACC kernels constructs must get launched as 1 x 1 x 1
      kernels, so remove the parallelism dimensions function attributes
@@ -1618,6 +1632,12 @@ execute_oacc_device_lower ()
        fprintf (dump_file, "Function is %s OpenACC kernels offload\n",
                 (is_oacc_kernels_parallelized
                  ? "parallelized" : "unparallelized"));
+      else if (is_oacc_parallel_kernels_parallelized)
+       fprintf (dump_file, "Function is %s OpenACC kernels offload\n",
+                "parallel_kernels_parallelized");
+      else if (is_oacc_parallel_kernels_gang_single)
+       fprintf (dump_file, "Function is %s OpenACC kernels offload\n",
+                "parallel_kernels_gang_single");
       else
        fprintf (dump_file, "Function is OpenACC parallel offload\n");
     }