[35/40] Handle references in OpenACC "private" clauses

Message ID 20211215155447.19379-36-frederik@codesourcery.com
State New
Headers
Series OpenACC "kernels" Improvements |

Commit Message

Frederik Harwath Dec. 15, 2021, 3:54 p.m. UTC
  From: Julian Brown <julian@codesourcery.com>

        gcc/
        * gimplify.c (localize_reductions): Rewrite references for
        OMP_CLAUSE_PRIVATE also.

        libgomp/
        * testsuite/libgomp.oacc-fortran/privatized-ref-1.f95: New test.
        * testsuite/libgomp.oacc-c++/privatized-ref-2.C: New test.
        * testsuite/libgomp.oacc-c++/privatized-ref-3.C: New test.
---
 gcc/gimplify.c                                | 15 ++++
 .../libgomp.oacc-c++/privatized-ref-2.C       | 64 +++++++++++++++++
 .../libgomp.oacc-c++/privatized-ref-3.C       | 64 +++++++++++++++++
 .../libgomp.oacc-fortran/privatized-ref-1.f95 | 71 +++++++++++++++++++
 4 files changed, 214 insertions(+)
 create mode 100644 libgomp/testsuite/libgomp.oacc-c++/privatized-ref-2.C
 create mode 100644 libgomp/testsuite/libgomp.oacc-c++/privatized-ref-3.C
 create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/privatized-ref-1.f95

--
2.33.0

-----------------
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634 München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht München, HRB 106955
  

Patch

diff --git a/gcc/gimplify.c b/gcc/gimplify.c
index daa69ccf6202..bf37388f947c 100644
--- a/gcc/gimplify.c
+++ b/gcc/gimplify.c
@@ -11976,6 +11976,21 @@  localize_reductions (tree clauses, tree body)

        OMP_CLAUSE_REDUCTION_PRIVATE_DECL (c) = new_var;
       }
+    else if (OMP_CLAUSE_CODE (c) == OMP_CLAUSE_PRIVATE)
+      {
+       var = OMP_CLAUSE_DECL (c);
+
+       if (!lang_hooks.decls.omp_privatize_by_reference (var))
+         continue;
+
+       type = TREE_TYPE (TREE_TYPE (var));
+       new_var = create_tmp_var (type, IDENTIFIER_POINTER (DECL_NAME (var)));
+
+       pr.ref_var = var;
+       pr.local_var = new_var;
+
+       walk_tree (&body, localize_reductions_r, &pr, NULL);
+      }
 }


diff --git a/libgomp/testsuite/libgomp.oacc-c++/privatized-ref-2.C b/libgomp/testsuite/libgomp.oacc-c++/privatized-ref-2.C
new file mode 100644
index 000000000000..3884f163132c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c++/privatized-ref-2.C
@@ -0,0 +1,64 @@ 
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+void workers (void)
+{
+  double res[65536];
+  int i;
+
+#pragma acc parallel copyout(res) num_gangs(64) num_workers(64)
+  {
+    int i, j;
+#pragma acc loop gang
+    for (i = 0; i < 256; i++)
+      {
+#pragma acc loop worker
+       for (j = 0; j < 256; j++)
+         {
+           int tmpvar;
+           int &tmpref = tmpvar;
+           tmpref = (i * 256 + j) * 99;
+           res[i * 256 + j] = tmpref;
+         }
+      }
+  }
+
+  for (i = 0; i < 65536; i++)
+    if (res[i] != i * 99)
+      abort ();
+}
+
+void vectors (void)
+{
+  double res[65536];
+  int i;
+
+#pragma acc parallel copyout(res) num_gangs(64) num_workers(64)
+  {
+    int i, j;
+#pragma acc loop gang worker
+    for (i = 0; i < 256; i++)
+      {
+#pragma acc loop vector
+       for (j = 0; j < 256; j++)
+         {
+           int tmpvar;
+           int &tmpref = tmpvar;
+           tmpref = (i * 256 + j) * 101;
+           res[i * 256 + j] = tmpref;
+         }
+      }
+  }
+
+  for (i = 0; i < 65536; i++)
+    if (res[i] != i * 101)
+      abort ();
+}
+
+int main (int argc, char *argv[])
+{
+  workers ();
+  vectors ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-c++/privatized-ref-3.C b/libgomp/testsuite/libgomp.oacc-c++/privatized-ref-3.C
new file mode 100644
index 000000000000..c1a10cba31b3
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-c++/privatized-ref-3.C
@@ -0,0 +1,64 @@ 
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+void workers (void)
+{
+  double res[65536];
+  int i;
+
+#pragma acc parallel copyout(res) num_gangs(64) num_workers(64)
+  {
+    int i, j;
+    int tmpvar;
+    int &tmpref = tmpvar;
+#pragma acc loop gang
+    for (i = 0; i < 256; i++)
+      {
+#pragma acc loop worker private(tmpref)
+       for (j = 0; j < 256; j++)
+         {
+           tmpref = (i * 256 + j) * 99;
+           res[i * 256 + j] = tmpref;
+         }
+      }
+  }
+
+  for (i = 0; i < 65536; i++)
+    if (res[i] != i * 99)
+      abort ();
+}
+
+void vectors (void)
+{
+  double res[65536];
+  int i;
+
+#pragma acc parallel copyout(res) num_gangs(64) num_workers(64)
+  {
+    int i, j;
+    int tmpvar;
+    int &tmpref = tmpvar;
+#pragma acc loop gang worker
+    for (i = 0; i < 256; i++)
+      {
+#pragma acc loop vector private(tmpref)
+       for (j = 0; j < 256; j++)
+         {
+           tmpref = (i * 256 + j) * 101;
+           res[i * 256 + j] = tmpref;
+         }
+      }
+  }
+
+  for (i = 0; i < 65536; i++)
+    if (res[i] != i * 101)
+      abort ();
+}
+
+int main (int argc, char *argv[])
+{
+  workers ();
+  vectors ();
+  return 0;
+}
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/privatized-ref-1.f95 b/libgomp/testsuite/libgomp.oacc-fortran/privatized-ref-1.f95
new file mode 100644
index 000000000000..fe1520a8078c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/privatized-ref-1.f95
@@ -0,0 +1,71 @@ 
+! { dg-do run }
+
+program main
+  implicit none
+  integer :: myint
+  integer :: i
+  real :: res(65536), tmp
+
+  res(:) = 0.0
+
+  myint = 5
+  call workers(myint, res)
+
+  do i=1,65536
+    tmp = i * 99
+    if (res(i) .ne. tmp) stop 1
+  end do
+
+  res(:) = 0.0
+
+  myint = 7
+  call vectors(myint, res)
+
+  do i=1,65536
+    tmp = i * 101
+    if (res(i) .ne. tmp) stop 2
+  end do
+
+contains
+
+  subroutine workers(t1, res)
+    implicit none
+    integer :: t1
+    integer :: i, j
+    real, intent(out) :: res(:)
+
+    !$acc parallel copyout(res) num_gangs(64) num_workers(64) ! { dg-warning "using num_workers \\(32\\), ignoring 64" "" { target openacc_nvidia_accel_selected } }
+
+    !$acc loop gang
+    do i=0,255
+      !$acc loop worker private(t1)
+      do j=1,256
+        t1 = (i * 256 + j) * 99
+        res(i * 256 + j) = t1
+      end do
+    end do
+
+    !$acc end parallel
+  end subroutine workers
+
+  subroutine vectors(t1, res)
+    implicit none
+    integer :: t1
+    integer :: i, j
+    real, intent(out) :: res(:)
+
+    !$acc parallel copyout(res) num_gangs(64) num_workers(64) ! { dg-warning "using num_workers \\(32\\), ignoring 64" "" { target openacc_nvidia_accel_selected } }
+
+    !$acc loop gang worker
+    do i=0,255
+      !$acc loop vector private(t1)
+      do j=1,256
+        t1 = (i * 256 + j) * 101
+        res(i * 256 + j) = t1
+      end do
+    end do
+
+    !$acc end parallel
+  end subroutine vectors
+
+end program main