amdgcn: Enable OpenACC worker partitioning for AMD GCN

	gcc/
	* config/gcn/gcn.c (gcn_init_builtins): Override decls for
	BUILT_IN_GOACC_SINGLE_START, BUILT_IN_GOACC_SINGLE_COPY_START,
	BUILT_IN_GOACC_SINGLE_COPY_END and BUILT_IN_GOACC_BARRIER.
	(gcn_goacc_validate_dims): Turn on worker partitioning unconditionally.
	(gcn_fork_join): Update comment.
	* config/gcn/gcn.opt (flag_worker_partitioning): Remove.
	(macc_experimental_workers): Remove unused option.
	libgomp/
	* plugin/plugin-gcn.c (gcn_exec): Change default number of workers to
	16.
	* testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c
	[acc_device_radeon]: Update.
	* testsuite/libgomp.oacc-c-c++-common/loop-dim-default.c
	[ACC_DEVICE_TYPE_radeon]: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/parallel-dims.c
	[acc_device_radeon]: Likewise.
	* testsuite/libgomp.oacc-c-c++-common/routine-wv-2.c
	[ACC_DEVICE_TYPE_radeon]: Likewise.
	* testsuite/libgomp.oacc-fortran/optional-reduction.f90: XFAIL for
	'openacc_radeon_accel_selected' and '-O0'.
	* testsuite/libgomp.oacc-fortran/reduction-7.f90: Likewise.

Co-Authored-By: Kwok Cheung Yeung <kcy@codesourcery.com>
Co-Authored-By: Thomas Schwinge <thomas@codesourcery.com>

diff --git a/gcc/config/gcn/gcn.c b/gcc/config/gcn/gcn.c
index 87af5d18f420cba3de408c8d22aacaef6f6292bf..9df282774989d16b35e4e78ea9a80053cfb26ebb 100644 (file)
--- a/gcc/config/gcn/gcn.c
+++ b/gcc/config/gcn/gcn.c
@@ -3712,8 +3712,6 @@ gcn_init_builtins (void)
       TREE_NOTHROW (gcn_builtin_decls[i]) = 1;
     }
 
-/* FIXME: remove the ifdef once OpenACC support is merged upstream.  */
-#ifdef BUILT_IN_GOACC_SINGLE_START
   /* These builtins need to take/return an LDS pointer: override the generic
      versions here.  */
 
@@ -3730,7 +3728,6 @@ gcn_init_builtins (void)
 
   set_builtin_decl (BUILT_IN_GOACC_BARRIER,
                    gcn_builtin_decls[GCN_BUILTIN_ACC_BARRIER], false);
-#endif
 }
 
 /* Implement TARGET_INIT_LIBFUNCS.  */
@@ -5019,11 +5016,7 @@ gcn_goacc_validate_dims (tree decl, int dims[], int fn_level,
                         unsigned /*used*/)
 {
   bool changed = false;
-
-  /* FIXME: remove -facc-experimental-workers when they're ready.  */
-  int max_workers = flag_worker_partitioning ? 16 : 1;
-
-  gcc_assert (!flag_worker_partitioning);
+  const int max_workers = 16;
 
   /* The vector size must appear to be 64, to the user, unless this is a
      SEQ routine.  The real, internal value is always 1, which means use
@@ -5060,8 +5053,7 @@ gcn_goacc_validate_dims (tree decl, int dims[], int fn_level,
     {
       dims[GOMP_DIM_VECTOR] = GCN_DEFAULT_VECTORS;
       if (dims[GOMP_DIM_WORKER] < 0)
-       dims[GOMP_DIM_WORKER] = (flag_worker_partitioning
-                                ? GCN_DEFAULT_WORKERS : 1);
+       dims[GOMP_DIM_WORKER] = GCN_DEFAULT_WORKERS;
       if (dims[GOMP_DIM_GANG] < 0)
        dims[GOMP_DIM_GANG] = GCN_DEFAULT_GANGS;
       changed = true;
@@ -5126,8 +5118,7 @@ static bool
 gcn_fork_join (gcall *ARG_UNUSED (call), const int *ARG_UNUSED (dims),
               bool ARG_UNUSED (is_fork))
 {
-  /* GCN does not use the fork/join concept invented for NVPTX.
-     Instead we use standard autovectorization.  */
+  /* GCN does not need to expand fork/join markers at the RTL level.  */
   return false;
 }
 

diff --git a/gcc/config/gcn/gcn.opt b/gcc/config/gcn/gcn.opt
index b2b10b0794c859b098c1fa5756962e3f985c813b..6faacca42bbb063a5d0358a1d7092f32eaf8573c 100644 (file)
--- a/gcc/config/gcn/gcn.opt
+++ b/gcc/config/gcn/gcn.opt
@@ -62,11 +62,6 @@ bool flag_bypass_init_error = false
 mbypass-init-error
 Target RejectNegative Var(flag_bypass_init_error)
 
-bool flag_worker_partitioning = false
-
-macc-experimental-workers
-Target Var(flag_worker_partitioning) Init(0)
-
 int stack_size_opt = -1
 
 mstack-size=

diff --git a/libgomp/plugin/plugin-gcn.c b/libgomp/plugin/plugin-gcn.c
index f26d73611067115062969fba9175efacaf1c2bcc..9e7377c91f9489aa94be23270efee29dbdfe8c49 100644 (file)
--- a/libgomp/plugin/plugin-gcn.c
+++ b/libgomp/plugin/plugin-gcn.c
@@ -3038,8 +3038,7 @@ gcn_exec (struct kernel_info *kernel, size_t mapnum, void **hostaddrs,
      64 gangs matches a typical Fiji device.  */
 
   if (dims[0] == 0) dims[0] = get_cu_count (kernel->agent); /* Gangs.  */
-  /* NOTE: Until support for middle-end worker partitioning is merged, force 'num_workers (1)'.  */
-  if (/*TODO dims[1] == 0*/ true) dims[1] = 1;  /* Workers.  */
+  if (dims[1] == 0) dims[1] = 16; /* Workers.  */
 
   /* The incoming dimensions are expressed in terms of gangs, workers, and
      vectors.  The HSA dimensions are expressed in terms of "work-items",

diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c
index 6c136c26c939399ede26e38b74735ccb3ca41c3d..ad33f72e2fb6b24658b54b01f83d60f5da02b6b5 100644 (file)
--- a/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/acc_prof-kernels-1.c
@@ -93,9 +93,6 @@ static void cb_enqueue_launch_start (acc_prof_info *prof_info, acc_event_info *e
     }
   if (num_workers < 1)
     assert (event_info->launch_event.num_workers >= 1);
-  /* GCN currently enforces 'num_workers (1)'.  */
-  else if (acc_device_type == acc_device_radeon)
-    assert (event_info->launch_event.num_workers == 1);
   else
     {
 #ifdef __OPTIMIZE__

diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/loop-dim-default.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/loop-dim-default.c
index ca7716466558c2eae164aa36adbce08fd2afbc30..419bc33ad536ee2cbd690f81957f4f6508eeee7f 100644 (file)
--- a/libgomp/testsuite/libgomp.oacc-c-c++-common/loop-dim-default.c
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/loop-dim-default.c
@@ -132,9 +132,7 @@ int main ()
   /* AMD GCN uses the autovectorizer for the vector dimension: the use
      of a function call in vector-partitioned code in this test is not
      currently supported.  */
-  /* AMD GCN does not currently support multiple workers.  This should be
-     set to 16 when that changes.  */
-  return test_1 (16, 1, 1);
+  return test_1 (16, 16, 1);
 #else
   return test_1 (16, 16, 32);
 #endif

diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-dims.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-dims.c
index fe0dacd5aac409c2ba3b2c8431816170e746826e..9392e1d88c5862831fb5e0cc17dceb9603fc0189 100644 (file)
--- a/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-dims.c
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/parallel-dims.c
@@ -261,9 +261,8 @@ int main ()
        }
       else if (acc_on_device (acc_device_radeon))
        {
-         /* The GCC GCN back end is limited to num_workers (16).
-            Temporarily set this to 1 until multiple workers are permitted. */
-         workers_actual = 1; // 16;
+         /* The GCC GCN back end is limited to num_workers (16).  */
+         workers_actual = 16;
        }
       else
        __builtin_abort ();
@@ -313,9 +312,8 @@ int main ()
        }
       else if (acc_on_device (acc_device_radeon))
        {
-         /* The GCC GCN back end is limited to num_workers (16).
-            Temporarily set this to 1 until multiple workers are permitted. */
-         workers_actual = 1; // 16;
+         /* The GCC GCN back end is limited to num_workers (16).  */
+         workers_actual = 16;
        }
       else
        __builtin_abort ();
@@ -465,8 +463,6 @@ int main ()
        }
       else if (acc_on_device (acc_device_radeon))
        {
-         /* Temporary setting, until multiple workers are permitted.  */
-         workers_actual = 1;
          /* See above comments about GCN vectors_actual.  */
          vectors_actual = 1;
        }

diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/routine-wv-2.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/routine-wv-2.c
index 624ec24e43747c28d4e500cd9a82c64c2a57405e..4f88b1c0779037bd4a6ae3be6b26ef0b2c56a640 100644 (file)
--- a/libgomp/testsuite/libgomp.oacc-c-c++-common/routine-wv-2.c
+++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/routine-wv-2.c
@@ -5,12 +5,13 @@
 #include <openacc.h>
 #include <gomp-constants.h>
 
+#define NUM_WORKERS 16
 #ifdef ACC_DEVICE_TYPE_radeon
-/* Temporarily set this to 1 until multiple workers are permitted.  */
-#define NUM_WORKERS 1
+/* AMD GCN uses the autovectorizer for the vector dimension: the use
+   of a function call in vector-partitioned code in this test is not
+   currently supported.  */
 #define NUM_VECTORS 1
 #else
-#define NUM_WORKERS 16
 #define NUM_VECTORS 32
 #endif
 #define WIDTH 64

diff --git a/libgomp/testsuite/libgomp.oacc-fortran/optional-reduction.f90 b/libgomp/testsuite/libgomp.oacc-fortran/optional-reduction.f90
index 29f92c0d4c38b66d26695005b12ffd1ec54c18d1..69b69b66c71ae15a9e319c6129ad24c6a859ddbd 100644 (file)
--- a/libgomp/testsuite/libgomp.oacc-fortran/optional-reduction.f90
+++ b/libgomp/testsuite/libgomp.oacc-fortran/optional-reduction.f90
@@ -4,6 +4,9 @@
 
 ! { dg-do run }
 
+!TODO
+! { dg-xfail-run-if TODO { openacc_radeon_accel_selected && { ! __OPTIMIZE__ } } }
+
 program optional_reduction
   implicit none
 

diff --git a/libgomp/testsuite/libgomp.oacc-fortran/reduction-7.f90 b/libgomp/testsuite/libgomp.oacc-fortran/reduction-7.f90
index 8cffac93a22c1b41fb0355de1a04730db61cd8bf..a8b0c60e420b63de1553bcde197784303edb1120 100644 (file)
--- a/libgomp/testsuite/libgomp.oacc-fortran/reduction-7.f90
+++ b/libgomp/testsuite/libgomp.oacc-fortran/reduction-7.f90
@@ -1,5 +1,8 @@
 ! { dg-do run }
 
+!TODO
+! { dg-xfail-run-if TODO { openacc_radeon_accel_selected && { ! __OPTIMIZE__ } } }
+
 ! subroutine reduction with private and firstprivate variables
 
 program reduction