Re: [PATCH, 16/16] Add libgomp.oacc-fortran/kernels-*.f95

[Tom de Vries]

On 09/11/15 21:12, Tom de Vries wrote:

On 09/11/15 16:35, Tom de Vries wrote:

Hi,

this patch series for stage1 trunk adds support to:
- parallelize oacc kernels regions using parloops, and
- map the loops onto the oacc gang dimension.

The patch series contains these patches:

      1    Insert new exit block only when needed in
         transform_to_exit_first_loop_alt
      2    Make create_parallel_loop return void
      3    Ignore reduction clause on kernels directive
      4    Implement -foffload-alias
      5    Add in_oacc_kernels_region in struct loop
      6    Add pass_oacc_kernels
      7    Add pass_dominator_oacc_kernels
      8    Add pass_ch_oacc_kernels
      9    Add pass_parallelize_loops_oacc_kernels
     10    Add pass_oacc_kernels pass group in passes.def
     11    Update testcases after adding kernels pass group
     12    Handle acc loop directive
     13    Add c-c++-common/goacc/kernels-*.c
     14    Add gfortran.dg/goacc/kernels-*.f95
     15    Add libgomp.oacc-c-c++-common/kernels-*.c
     16    Add libgomp.oacc-fortran/kernels-*.f95

The first 9 patches are more or less independent, but patches 10-16 are
intended to be committed at the same time.

Bootstrapped and reg-tested on x86_64.

Build and reg-tested with nvidia accelerator, in combination with a
patch that enables accelerator testing (which is submitted at
https://gcc.gnu.org/ml/gcc-patches/2015-10/msg01771.html ).

I'll post the individual patches in reply to this message.

This patch adds Fortran oacc kernels execution tests.

Retested on current trunk.

Committed, minus the kernels-parallel-loop-data-enter-exit.f95 test.

Thanks,
- Tom

0016-Add-libgomp.oacc-fortran-kernels-.f95.patch


Add libgomp.oacc-fortran/kernels-*.f95

2015-11-09  Tom de Vries  <t...@codesourcery.com>

        * testsuite/libgomp.oacc-fortran/kernels-loop-2.f95: New test.
        * testsuite/libgomp.oacc-fortran/kernels-loop-data-2.f95: Same.
        * testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit-2.f95:
        Same.
        * testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit.f95: Same.
        * testsuite/libgomp.oacc-fortran/kernels-loop-data-update.f95: Same.
        * testsuite/libgomp.oacc-fortran/kernels-loop-data.f95: Same.
        * testsuite/libgomp.oacc-fortran/kernels-loop.f95: Same.
        * 
testsuite/libgomp.oacc-fortran/kernels-parallel-loop-data-enter-exit.f95:
        Same.
---
  .../libgomp.oacc-fortran/kernels-loop-2.f95        | 32 ++++++++++++++++++
  .../libgomp.oacc-fortran/kernels-loop-data-2.f95   | 38 ++++++++++++++++++++++
  .../kernels-loop-data-enter-exit-2.f95             | 38 ++++++++++++++++++++++
  .../kernels-loop-data-enter-exit.f95               | 36 ++++++++++++++++++++
  .../kernels-loop-data-update.f95                   | 36 ++++++++++++++++++++
  .../libgomp.oacc-fortran/kernels-loop-data.f95     | 36 ++++++++++++++++++++
  .../libgomp.oacc-fortran/kernels-loop.f95          | 28 ++++++++++++++++
  .../kernels-parallel-loop-data-enter-exit.f95      | 37 +++++++++++++++++++++
  8 files changed, 281 insertions(+)
  create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-2.f95
  create mode 100644 
libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-2.f95
  create mode 100644 
libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit-2.f95
  create mode 100644 
libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit.f95
  create mode 100644 
libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-update.f95
  create mode 100644 
libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data.f95
  create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/kernels-loop.f95
  create mode 100644 
libgomp/testsuite/libgomp.oacc-fortran/kernels-parallel-loop-data-enter-exit.f95

diff --git a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-2.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-2.f95
new file mode 100644
index 0000000..1fb40ee
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-2.f95
@@ -0,0 +1,32 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc kernels copyout (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+
+  !$acc kernels copyout (b(0:n-1))
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+  !$acc end kernels
+
+  !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-2.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-2.f95
new file mode 100644
index 0000000..7b52253
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-2.f95
@@ -0,0 +1,38 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc data copyout (a(0:n-1))
+  !$acc kernels present (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+  !$acc end data
+
+  !$acc data copyout (b(0:n-1))
+  !$acc kernels present (b(0:n-1))
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+  !$acc end kernels
+  !$acc end data
+
+  !$acc data copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1))
+  !$acc kernels present (a(0:n-1), b(0:n-1), c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+  !$acc end data
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git 
a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit-2.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit-2.f95
new file mode 100644
index 0000000..af98efa
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit-2.f95
@@ -0,0 +1,38 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc enter data create (a(0:n-1))
+  !$acc kernels present (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+  !$acc exit data copyout (a(0:n-1))
+
+  !$acc enter data create (b(0:n-1))
+  !$acc kernels present (b(0:n-1))
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+  !$acc end kernels
+  !$acc exit data copyout (b(0:n-1))
+
+  !$acc enter data copyin (a(0:n-1), b(0:n-1)) create (c(0:n-1))
+  !$acc kernels present (a(0:n-1), b(0:n-1), c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+  !$acc exit data copyout (c(0:n-1))
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git 
a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit.f95
new file mode 100644
index 0000000..bb6f8dc
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-enter-exit.f95
@@ -0,0 +1,36 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc enter data create (a(0:n-1), b(0:n-1), c(0:n-1))
+
+  !$acc kernels present (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+
+  !$acc kernels present (b(0:n-1))
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+  !$acc end kernels
+
+  !$acc kernels present (a(0:n-1), b(0:n-1), c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+
+  !$acc exit data copyout (a(0:n-1), b(0:n-1), c(0:n-1))
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git 
a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-update.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-update.f95
new file mode 100644
index 0000000..cab1f2c
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data-update.f95
@@ -0,0 +1,36 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc enter data create (a(0:n-1), b(0:n-1), c(0:n-1))
+
+  !$acc kernels present (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+
+  !$acc update device (b(0:n-1))
+
+  !$acc kernels present (a(0:n-1), b(0:n-1), c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+
+  !$acc exit data copyout (a(0:n-1), c(0:n-1))
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data.f95
new file mode 100644
index 0000000..f26671d
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop-data.f95
@@ -0,0 +1,36 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc data copyout (a(0:n-1), b(0:n-1), c(0:n-1))
+
+  !$acc kernels present (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+
+  !$acc kernels present (b(0:n-1))
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+  !$acc end kernels
+
+  !$acc kernels present (a(0:n-1), b(0:n-1), c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+
+  !$acc end data
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git a/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop.f95 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop.f95
new file mode 100644
index 0000000..b02dd57
--- /dev/null
+++ b/libgomp/testsuite/libgomp.oacc-fortran/kernels-loop.f95
@@ -0,0 +1,28 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+
+  !$acc kernels copyin (a(0:n-1), b(0:n-1)) copyout (c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main
diff --git 
a/libgomp/testsuite/libgomp.oacc-fortran/kernels-parallel-loop-data-enter-exit.f95
 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-parallel-loop-data-enter-exit.f95
new file mode 100644
index 0000000..2322152
--- /dev/null
+++ 
b/libgomp/testsuite/libgomp.oacc-fortran/kernels-parallel-loop-data-enter-exit.f95
@@ -0,0 +1,37 @@
+! { dg-do run }
+! { dg-options "-ftree-parallelize-loops=32" }
+
+program main
+  implicit none
+  integer, parameter         :: n = 1024
+  integer, dimension (0:n-1) :: a, b, c
+  integer                    :: i, ii
+
+  !$acc enter data create (a(0:n-1), b(0:n-1), c(0:n-1))
+
+  !$acc kernels present (a(0:n-1))
+  do i = 0, n - 1
+     a(i) = i * 2
+  end do
+  !$acc end kernels
+
+  !$acc parallel present (b(0:n-1))
+  !$acc loop
+  do i = 0, n -1
+     b(i) = i * 4
+  end do
+  !$acc end parallel
+
+  !$acc kernels present (a(0:n-1), b(0:n-1), c(0:n-1))
+  do ii = 0, n - 1
+     c(ii) = a(ii) + b(ii)
+  end do
+  !$acc end kernels
+
+  !$acc exit data copyout (a(0:n-1), b(0:n-1), c(0:n-1))
+
+  do i = 0, n - 1
+     if (c(i) .ne. a(i) + b(i)) call abort
+  end do
+
+end program main