From 18c107c58d42314128e485bb79892672a8feaa6b Mon Sep 17 00:00:00 2001
From: Julian Brown <julian@codesourcery.com>
Date: Mon, 13 Oct 2014 04:40:51 -0700
Subject: [PATCH 1/3] Tests for libgomp OpenACC support.
---
libgomp/testsuite/Makefile.in | 4 +
libgomp/testsuite/lib/libgomp.exp | 30 +
libgomp/testsuite/libgomp.oacc-c++/c++.exp | 37 +-
libgomp/testsuite/libgomp.oacc-c/abort-2.c | 17 +
libgomp/testsuite/libgomp.oacc-c/abort.c | 17 +
libgomp/testsuite/libgomp.oacc-c/acc_on_device-1.c | 25 +-
libgomp/testsuite/libgomp.oacc-c/c.exp | 50 +-
libgomp/testsuite/libgomp.oacc-c/clauses-1.c | 623 ++++++++++++++++++
libgomp/testsuite/libgomp.oacc-c/clauses-2.c | 67 ++
libgomp/testsuite/libgomp.oacc-c/context-1.c | 213 ++++++
libgomp/testsuite/libgomp.oacc-c/context-2.c | 223 +++++++
libgomp/testsuite/libgomp.oacc-c/context-3.c | 200 ++++++
libgomp/testsuite/libgomp.oacc-c/context-4.c | 213 ++++++
libgomp/testsuite/libgomp.oacc-c/data-1.c | 112 ++--
libgomp/testsuite/libgomp.oacc-c/deviceptr-1.c | 32 +
libgomp/testsuite/libgomp.oacc-c/goacc_kernels.c | 3 +-
libgomp/testsuite/libgomp.oacc-c/goacc_parallel.c | 3 +-
libgomp/testsuite/libgomp.oacc-c/if-1.c | 547 ++++++++++++++++
libgomp/testsuite/libgomp.oacc-c/kernels-1.c | 22 +-
libgomp/testsuite/libgomp.oacc-c/lib-1.c | 19 +-
libgomp/testsuite/libgomp.oacc-c/lib-10.c | 58 ++
libgomp/testsuite/libgomp.oacc-c/lib-11.c | 22 +
libgomp/testsuite/libgomp.oacc-c/lib-12.c | 37 ++
libgomp/testsuite/libgomp.oacc-c/lib-13.c | 60 ++
libgomp/testsuite/libgomp.oacc-c/lib-14.c | 61 ++
libgomp/testsuite/libgomp.oacc-c/lib-15.c | 33 +
libgomp/testsuite/libgomp.oacc-c/lib-16.c | 29 +
libgomp/testsuite/libgomp.oacc-c/lib-17.c | 31 +
libgomp/testsuite/libgomp.oacc-c/lib-18.c | 34 +
libgomp/testsuite/libgomp.oacc-c/lib-19.c | 60 ++
libgomp/testsuite/libgomp.oacc-c/lib-2.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-20.c | 29 +
libgomp/testsuite/libgomp.oacc-c/lib-21.c | 29 +
libgomp/testsuite/libgomp.oacc-c/lib-22.c | 29 +
libgomp/testsuite/libgomp.oacc-c/lib-23.c | 39 ++
libgomp/testsuite/libgomp.oacc-c/lib-24.c | 55 ++
libgomp/testsuite/libgomp.oacc-c/lib-25.c | 30 +
libgomp/testsuite/libgomp.oacc-c/lib-26.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-27.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-28.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-29.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-3.c | 15 +
libgomp/testsuite/libgomp.oacc-c/lib-30.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-31.c | 27 +
libgomp/testsuite/libgomp.oacc-c/lib-32.c | 38 ++
libgomp/testsuite/libgomp.oacc-c/lib-33.c | 31 +
libgomp/testsuite/libgomp.oacc-c/lib-34.c | 33 +
libgomp/testsuite/libgomp.oacc-c/lib-35.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-36.c | 26 +
libgomp/testsuite/libgomp.oacc-c/lib-37.c | 40 ++
libgomp/testsuite/libgomp.oacc-c/lib-38.c | 67 ++
libgomp/testsuite/libgomp.oacc-c/lib-39.c | 41 ++
libgomp/testsuite/libgomp.oacc-c/lib-4.c | 13 +
libgomp/testsuite/libgomp.oacc-c/lib-40.c | 42 ++
libgomp/testsuite/libgomp.oacc-c/lib-41.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-42.c | 35 +
libgomp/testsuite/libgomp.oacc-c/lib-43.c | 45 ++
libgomp/testsuite/libgomp.oacc-c/lib-44.c | 45 ++
libgomp/testsuite/libgomp.oacc-c/lib-45.c | 50 ++
libgomp/testsuite/libgomp.oacc-c/lib-46.c | 42 ++
libgomp/testsuite/libgomp.oacc-c/lib-47.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-48.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-49.c | 48 ++
libgomp/testsuite/libgomp.oacc-c/lib-5.c | 40 ++
libgomp/testsuite/libgomp.oacc-c/lib-50.c | 30 +
libgomp/testsuite/libgomp.oacc-c/lib-51.c | 41 ++
libgomp/testsuite/libgomp.oacc-c/lib-52.c | 28 +
libgomp/testsuite/libgomp.oacc-c/lib-53.c | 28 +
libgomp/testsuite/libgomp.oacc-c/lib-54.c | 28 +
libgomp/testsuite/libgomp.oacc-c/lib-55.c | 48 ++
libgomp/testsuite/libgomp.oacc-c/lib-56.c | 33 +
libgomp/testsuite/libgomp.oacc-c/lib-57.c | 28 +
libgomp/testsuite/libgomp.oacc-c/lib-58.c | 28 +
libgomp/testsuite/libgomp.oacc-c/lib-59.c | 55 ++
libgomp/testsuite/libgomp.oacc-c/lib-6.c | 39 ++
libgomp/testsuite/libgomp.oacc-c/lib-60.c | 54 ++
libgomp/testsuite/libgomp.oacc-c/lib-61.c | 70 ++
libgomp/testsuite/libgomp.oacc-c/lib-62.c | 49 ++
libgomp/testsuite/libgomp.oacc-c/lib-63.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-64.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-65.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-66.c | 47 ++
libgomp/testsuite/libgomp.oacc-c/lib-67.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-68.c | 43 ++
libgomp/testsuite/libgomp.oacc-c/lib-69.c | 124 ++++
libgomp/testsuite/libgomp.oacc-c/lib-7.c | 18 +
libgomp/testsuite/libgomp.oacc-c/lib-70.c | 136 ++++
libgomp/testsuite/libgomp.oacc-c/lib-71.c | 119 ++++
libgomp/testsuite/libgomp.oacc-c/lib-72.c | 121 ++++
libgomp/testsuite/libgomp.oacc-c/lib-73.c | 134 ++++
libgomp/testsuite/libgomp.oacc-c/lib-74.c | 139 ++++
libgomp/testsuite/libgomp.oacc-c/lib-75.c | 141 ++++
libgomp/testsuite/libgomp.oacc-c/lib-76.c | 147 +++++
libgomp/testsuite/libgomp.oacc-c/lib-77.c | 135 ++++
libgomp/testsuite/libgomp.oacc-c/lib-78.c | 140 ++++
libgomp/testsuite/libgomp.oacc-c/lib-79.c | 167 +++++
libgomp/testsuite/libgomp.oacc-c/lib-80.c | 132 ++++
libgomp/testsuite/libgomp.oacc-c/lib-81.c | 211 ++++++
libgomp/testsuite/libgomp.oacc-c/lib-82.c | 144 +++++
libgomp/testsuite/libgomp.oacc-c/lib-83.c | 58 ++
libgomp/testsuite/libgomp.oacc-c/lib-84.c | 66 ++
libgomp/testsuite/libgomp.oacc-c/lib-85.c | 52 ++
libgomp/testsuite/libgomp.oacc-c/lib-86.c | 42 ++
libgomp/testsuite/libgomp.oacc-c/lib-87.c | 42 ++
libgomp/testsuite/libgomp.oacc-c/lib-88.c | 111 ++++
libgomp/testsuite/libgomp.oacc-c/lib-89.c | 118 ++++
libgomp/testsuite/libgomp.oacc-c/lib-9.c | 70 ++
libgomp/testsuite/libgomp.oacc-c/lib-90.c | 137 ++++
libgomp/testsuite/libgomp.oacc-c/lib-91.c | 84 +++
libgomp/testsuite/libgomp.oacc-c/lib-92.c | 112 ++++
libgomp/testsuite/libgomp.oacc-c/nested-1.c | 680 ++++++++++++++++++++
libgomp/testsuite/libgomp.oacc-c/nested-2.c | 35 +
libgomp/testsuite/libgomp.oacc-c/offset-1.c | 97 +++
libgomp/testsuite/libgomp.oacc-c/parallel-1.c | 76 ++-
libgomp/testsuite/libgomp.oacc-c/pointer-align-1.c | 35 +
libgomp/testsuite/libgomp.oacc-c/present-1.c | 48 ++
libgomp/testsuite/libgomp.oacc-c/present-2.c | 48 ++
libgomp/testsuite/libgomp.oacc-c/subr.cu | 64 ++
libgomp/testsuite/libgomp.oacc-c/subr.ptx | 148 +++++
libgomp/testsuite/libgomp.oacc-c/timer.h | 103 +++
libgomp/testsuite/libgomp.oacc-c/update-1.c | 280 ++++++++
libgomp/testsuite/libgomp.oacc-fortran/abort-1.f90 | 10 +
libgomp/testsuite/libgomp.oacc-fortran/abort-2.f90 | 13 +
.../libgomp.oacc-fortran/acc_on_device-1-1.f90 | 17 +-
.../libgomp.oacc-fortran/acc_on_device-1-2.f | 17 +-
.../libgomp.oacc-fortran/acc_on_device-1-3.f | 17 +-
libgomp/testsuite/libgomp.oacc-fortran/fortran.exp | 42 +-
libgomp/testsuite/libgomp.oacc-fortran/lib-1.f90 | 10 +
libgomp/testsuite/libgomp.oacc-fortran/lib-10.f90 | 82 +++
libgomp/testsuite/libgomp.oacc-fortran/lib-11.f90 | 82 +++
libgomp/testsuite/libgomp.oacc-fortran/lib-2.f | 10 +
libgomp/testsuite/libgomp.oacc-fortran/lib-3.f | 10 +
libgomp/testsuite/libgomp.oacc-fortran/lib-4.f90 | 35 +
libgomp/testsuite/libgomp.oacc-fortran/lib-5.f90 | 31 +
libgomp/testsuite/libgomp.oacc-fortran/lib-6.f90 | 35 +
libgomp/testsuite/libgomp.oacc-fortran/lib-7.f90 | 31 +
libgomp/testsuite/libgomp.oacc-fortran/lib-8.f90 | 83 +++
libgomp/testsuite/libgomp.oacc-fortran/lib-9.f90 | 83 +++
libgomp/testsuite/libgomp.oacc-fortran/map-1.f90 | 97 +++
.../libgomp.oacc-fortran/pointer-align-1.f90 | 21 +
libgomp/testsuite/libgomp.oacc-fortran/pset-1.f90 | 229 +++++++
.../testsuite/libgomp.oacc-fortran/subarrays-1.f90 | 97 +++
.../testsuite/libgomp.oacc-fortran/subarrays-2.f90 | 100 +++
143 files changed, 10476 insertions(+), 93 deletions(-)
create mode 100644 libgomp/testsuite/libgomp.oacc-c/abort-2.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/abort.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/clauses-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/clauses-2.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/context-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/context-2.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/context-3.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/context-4.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/deviceptr-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/if-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-10.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-11.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-12.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-13.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-14.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-15.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-16.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-17.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-18.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-19.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-2.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-20.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-21.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-22.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-23.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-24.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-25.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-26.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-27.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-28.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-29.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-3.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-30.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-31.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-32.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-33.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-34.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-35.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-36.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-37.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-38.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-39.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-4.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-40.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-41.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-42.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-43.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-44.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-45.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-46.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-47.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-48.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-49.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-5.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-50.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-51.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-52.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-53.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-54.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-55.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-56.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-57.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-58.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-59.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-6.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-60.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-61.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-62.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-63.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-64.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-65.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-66.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-67.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-68.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-69.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-7.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-70.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-71.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-72.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-73.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-74.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-75.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-76.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-77.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-78.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-79.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-80.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-81.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-82.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-83.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-84.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-85.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-86.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-87.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-88.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-89.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-9.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-90.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-91.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/lib-92.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/nested-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/nested-2.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/offset-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/pointer-align-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/present-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/present-2.c
create mode 100644 libgomp/testsuite/libgomp.oacc-c/subr.cu
create mode 100644 libgomp/testsuite/libgomp.oacc-c/subr.ptx
create mode 100644 libgomp/testsuite/libgomp.oacc-c/timer.h
create mode 100644 libgomp/testsuite/libgomp.oacc-c/update-1.c
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/abort-1.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/abort-2.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-10.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-11.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-4.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-5.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-6.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-7.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-8.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/lib-9.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/map-1.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/pointer-align-1.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/pset-1.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/subarrays-1.f90
create mode 100644 libgomp/testsuite/libgomp.oacc-fortran/subarrays-2.f90
@@ -129,6 +129,10 @@ PACKAGE_URL = @PACKAGE_URL@
PACKAGE_VERSION = @PACKAGE_VERSION@
PATH_SEPARATOR = @PATH_SEPARATOR@
PERL = @PERL@
+PLUGIN_NVPTX = @PLUGIN_NVPTX@
+PLUGIN_NVPTX_CPPFLAGS = @PLUGIN_NVPTX_CPPFLAGS@
+PLUGIN_NVPTX_LDFLAGS = @PLUGIN_NVPTX_LDFLAGS@
+PLUGIN_NVPTX_LIBS = @PLUGIN_NVPTX_LIBS@
RANLIB = @RANLIB@
SECTION_LDFLAGS = @SECTION_LDFLAGS@
SED = @SED@
@@ -139,6 +139,8 @@ proc libgomp_init { args } {
lappend ALWAYS_CFLAGS "additional_flags=-B${blddir}/.libs"
lappend ALWAYS_CFLAGS "additional_flags=-I${blddir}"
lappend ALWAYS_CFLAGS "ldflags=-L${blddir}/.libs"
+ # The top-level include directory, for libgomp-constants.h.
+ lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}/../../include"
}
lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}/.."
@@ -239,3 +241,31 @@ proc libgomp_option_proc { option } {
return 0
}
}
+
+# Return 1 if at least one nvidia board is present.
+
+proc check_effective_target_openacc_nvidia_accel_present { } {
+ return [check_runtime openacc_nvidia_accel_present {
+ #include <openacc.h>
+ int main () {
+ return !(acc_get_num_devices (acc_device_nvidia) > 0);
+ }
+ } "" ]
+}
+
+# Return 1 if at least one nvidia board is present, and the nvidia device type
+# is selected by default by means of setting the environment variable
+# ACC_DEVICE_TYPE.
+
+proc check_effective_target_openacc_nvidia_accel_selected { } {
+ if { ![check_effective_target_openacc_nvidia_accel_present] } {
+ return 0;
+ }
+ if { ![info exists ::env(ACC_DEVICE_TYPE)] } {
+ return 0;
+ }
+ if { $::env(ACC_DEVICE_TYPE) == "nvidia" } {
+ return 1;
+ }
+ return 0;
+}
@@ -17,7 +17,8 @@ if [info exists lang_include_flags] then {
dg-init
# Turn on OpenACC.
-lappend ALWAYS_CFLAGS "additional_flags=-fopenacc"
+# XXX (TEMPORARY): Remove the -flto once that's properly integrated.
+lappend ALWAYS_CFLAGS "additional_flags=-fopenacc -flto"
set blddir [lookfor_file [get_multilibs] libgomp]
@@ -61,8 +62,38 @@ if { $lang_test_file_found } {
set libstdcxx_includes ""
}
- # Main loop.
- dg-runtest $tests "" $libstdcxx_includes
+ # Todo: get list of accelerators from configure options --enable-accelerator.
+ set accels { "nvidia" "host_nonshm" }
+
+ # Run on host (or fallback) accelerator.
+ lappend accels "host"
+
+ # Test OpenACC with available accelerators.
+ foreach accel $accels {
+ set tagopt "-DACC_DEVICE_TYPE_$accel=1"
+
+ # Todo: Determine shared memory or not using run-time test.
+ switch $accel {
+ host {
+ set acc_mem_shared 1
+ }
+ host_nonshm {
+ set acc_mem_shared 0
+ }
+ nvidia {
+ set acc_mem_shared 0
+ }
+ default {
+ set acc_mem_shared 0
+ }
+ }
+ set tagopt "$tagopt -DACC_MEM_SHARED=$acc_mem_shared"
+
+ # Todo: Verify that this works for both local and remote testing.
+ setenv ACC_DEVICE_TYPE $accel
+
+ dg-runtest $tests "$tagopt" $libstdcxx_includes
+ }
}
# All done.
new file mode 100644
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+
+#pragma acc parallel
+ {
+ if (argc != 1)
+ abort ();
+ }
+
+ return 0;
+}
+
new file mode 100644
@@ -0,0 +1,17 @@
+/* { dg-do run } */
+/* { dg-shouldfail "" { *-*-* } { "*" } { "" } } */
+
+#include <stdlib.h>
+
+int
+main (void)
+{
+
+#pragma acc parallel
+ {
+ abort ();
+ }
+
+ return 0;
+}
+
@@ -1,7 +1,6 @@
/* Disable the acc_on_device builtin; we want to test the libgomp library
function. */
-/* TODO: Remove -DACC_DEVICE_TYPE_host once that is set by the test harness. */
-/* { dg-additional-options "-fno-builtin-acc_on_device -DACC_DEVICE_TYPE_host" } */
+/* { dg-additional-options "-fno-builtin-acc_on_device" } */
#include <stdlib.h>
#include <openacc.h>
@@ -16,8 +15,12 @@ main (int argc, char *argv[])
abort ();
if (!acc_on_device (acc_device_host))
abort ();
+ if (acc_on_device (acc_device_host_nonshm))
+ abort ();
if (acc_on_device (acc_device_not_host))
abort ();
+ if (acc_on_device (acc_device_nvidia))
+ abort ();
}
@@ -29,8 +32,12 @@ main (int argc, char *argv[])
abort ();
if (!acc_on_device (acc_device_host))
abort ();
+ if (acc_on_device (acc_device_host_nonshm))
+ abort ();
if (acc_on_device (acc_device_not_host))
abort ();
+ if (acc_on_device (acc_device_nvidia))
+ abort ();
}
@@ -44,8 +51,22 @@ main (int argc, char *argv[])
abort ();
if (acc_on_device (acc_device_host))
abort ();
+#if ACC_DEVICE_TYPE_host_nonshm
+ if (!acc_on_device (acc_device_host_nonshm))
+ abort ();
+#else
+ if (acc_on_device (acc_device_host_nonshm))
+ abort ();
+#endif
if (!acc_on_device (acc_device_not_host))
abort ();
+#if ACC_DEVICE_TYPE_nvidia
+ if (!acc_on_device (acc_device_nvidia))
+ abort ();
+#else
+ if (acc_on_device (acc_device_nvidia))
+ abort ();
+#endif
}
#endif
@@ -23,17 +23,61 @@ if ![info exists DEFAULT_CFLAGS] then {
dg-init
# Turn on OpenACC.
-lappend ALWAYS_CFLAGS "additional_flags=-fopenacc"
+# XXX (TEMPORARY): Remove the -flto once that's properly integrated.
+lappend ALWAYS_CFLAGS "additional_flags=-fopenacc -flto"
# Gather a list of all tests.
set tests [lsort [find $srcdir/$subdir *.c]]
set ld_library_path $always_ld_library_path
append ld_library_path [gcc-set-multilib-library-path $GCC_UNDER_TEST]
+append ld_library_path ":/opt/nvidia/cuda-5.5/lib64"
set_ld_library_path_env_vars
-# Main loop.
-dg-runtest $tests "" $DEFAULT_CFLAGS
+# Todo: get list of accelerators from configure options --enable-accelerator.
+set accels { "nvidia" "host_nonshm" }
+
+# Run on host (or fallback) accelerator.
+lappend accels "host"
+
+# Test OpenACC with available accelerators.
+set SAVE_ALWAYS_CFLAGS "$ALWAYS_CFLAGS"
+foreach accel $accels {
+ set ALWAYS_CFLAGS "$SAVE_ALWAYS_CFLAGS"
+ set tagopt "-DACC_DEVICE_TYPE_$accel=1"
+
+ # Todo: Determine shared memory or not using run-time test.
+ switch $accel {
+ host {
+ set acc_mem_shared 1
+ }
+ host_nonshm {
+ set acc_mem_shared 0
+ }
+ nvidia {
+ # Copy ptx file (TEMPORARY)
+ remote_download host $srcdir/libgomp.oacc-c/subr.ptx
+
+ # Where cuda.h lives
+ # Todo: get that from configure option --with-cuda-driver.
+ lappend ALWAYS_CFLAGS "additional_flags=-I/opt/nvidia/cuda-5.5/include"
+ lappend ALWAYS_CFLAGS "additional_flags=-L/opt/nvidia/cuda-5.5/lib64"
+
+ # Where timer.h lives
+ lappend ALWAYS_CFLAGS "additional_flags=-I${srcdir}"
+ set acc_mem_shared 0
+ }
+ default {
+ set acc_mem_shared 0
+ }
+ }
+ set tagopt "$tagopt -DACC_MEM_SHARED=$acc_mem_shared"
+
+ # Todo: Verify that this works for both local and remote testing.
+ setenv ACC_DEVICE_TYPE $accel
+
+ dg-runtest $tests "$tagopt" $DEFAULT_CFLAGS
+}
# All done.
dg-finish
new file mode 100644
@@ -0,0 +1,623 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b, *c, *d;
+ int i;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+ c = (float *) malloc (N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 1.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+ d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc parallel present_or_copyin (a[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) present_or_copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 2.0;
+ }
+
+ d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present_or_copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 2.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 4.0;
+ }
+
+#pragma acc parallel copy (a[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = a[ii] + 1;
+ b[ii] = a[ii] + 2;
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 7.0;
+ }
+
+#pragma acc parallel present_or_copy (a[0:N]) present_or_copy (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = a[ii] + 1;
+ b[ii] = b[ii] + 2;
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 9.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 7.0;
+ }
+
+ d = (float *) acc_copyin (&a[0], N * sizeof (float));
+ d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc parallel present_or_copy (a[0:N]) present_or_copy (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = a[ii] + 1;
+ b[ii] = b[ii] + 2;
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 7.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_deviceptr (&a[0]);
+ acc_unmap_data (&a[0]);
+ acc_free (d);
+
+ d = (float *) acc_deviceptr (&b[0]);
+ acc_unmap_data (&b[0]);
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 7.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) create (c[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&c[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 8.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&c[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 2.0;
+ b[i] = 5.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 2.0)
+ abort ();
+
+ if (b[i] != 2.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_deviceptr (c);
+
+ acc_unmap_data (c);
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 8.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present (c[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ acc_unmap_data (c);
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 8.0;
+ }
+
+ acc_copyin (a, N * sizeof (float));
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (b, d, N * sizeof (float));
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel present (a[0:N]) present (c[0:N]) present (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ if (!acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ acc_copyout (b, N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ d = (float *) acc_deviceptr (a);
+
+ acc_unmap_data (a);
+
+ acc_free (d);
+
+ d = (float *) acc_deviceptr (c);
+
+ acc_unmap_data (c);
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 6.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) deviceptr (d) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ d[ii] = a[ii];
+ b[ii] = d[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+ d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc parallel pcopyin (a[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) pcopyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 7.0;
+ }
+
+#pragma acc parallel copyin (a[0:N]) pcreate (c[0:N]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&c[0], (N * sizeof (float))))
+ abort ();
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,67 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b, *c, *d;
+ int i;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+ c = (float *) malloc (N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 2.0;
+ b[i] = 5.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) present_or_create (c[0:N+1]) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 2.0)
+ abort ();
+
+ if (b[i] != 2.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_deviceptr (c);
+
+ acc_unmap_data (c);
+
+ acc_free (d);
+
+ return 0;
+}
+/* { dg-shouldfail "libgomp: \[\h+,\d+\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,213 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ {
+ y[i] = a * x[i] + y[i];
+ }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+ CUcontext ctx2, ctx3;
+ CUresult r;
+
+ r = cuCtxGetCurrent (&ctx2);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (ctx1 != ctx2)
+ {
+ fprintf (stderr, "new context established\n");
+ exit (EXIT_FAILURE);
+ }
+
+ ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+ if (ctx1 != ctx3)
+ {
+ fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return;
+}
+
+int
+main (int argc, char **argv)
+{
+ cublasStatus_t s;
+ cudaError_t e;
+ cublasHandle_t h;
+ CUcontext pctx, ctx;
+ CUresult r;
+ int dev;
+ int i;
+ const int N = 256;
+ float *h_X, *h_Y1, *h_Y2;
+ float *d_X,*d_Y;
+ float alpha = 2.0f;
+ float error_norm;
+ float ref_norm;
+
+ /* Test 1 - cuBLAS creates, OpenACC shares. */
+
+ s = cublasCreate (&h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasCreate failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ e = cudaGetDevice (&dev);
+ if (e != cudaSuccess)
+ {
+ fprintf (stderr, "cudaGetDevice failed: %d\n", e);
+ exit (EXIT_FAILURE);
+ }
+
+ acc_set_device_num (dev, acc_device_nvidia);
+
+ h_X = (float *) malloc (N * sizeof (float));
+ if (!h_X)
+ {
+ fprintf (stderr, "malloc failed: for h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y1 = (float *) malloc (N * sizeof (float));
+ if (!h_Y1)
+ {
+ fprintf (stderr, "malloc failed: for h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y2 = (float *) malloc (N * sizeof (float));
+ if (!h_Y2)
+ {
+ fprintf (stderr, "malloc failed: for h_Y2\n");
+ exit (EXIT_FAILURE);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ h_X[i] = rand () / (float) RAND_MAX;
+ h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+ }
+
+ d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+ if (d_X == NULL)
+ {
+ fprintf (stderr, "copyin error h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+ if (d_Y == NULL)
+ {
+ fprintf (stderr, "copyin error h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+ context_check (pctx);
+
+ saxpy (N, alpha, h_X, h_Y2);
+
+ error_norm = 0;
+ ref_norm = 0;
+
+ for (i = 0; i < N; ++i)
+ {
+ float diff;
+
+ diff = h_Y1[i] - h_Y2[i];
+ error_norm += diff * diff;
+ ref_norm += h_Y2[i] * h_Y2[i];
+ }
+
+ error_norm = (float) sqrt ((double) error_norm);
+ ref_norm = (float) sqrt ((double) ref_norm);
+
+ if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+ {
+ fprintf (stderr, "math error\n");
+ exit (EXIT_FAILURE);
+ }
+
+ free (h_X);
+ free (h_Y1);
+ free (h_Y2);
+
+ acc_free (d_X);
+ acc_free (d_Y);
+
+ context_check (pctx);
+
+ s = cublasDestroy (h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasDestroy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ acc_shutdown (acc_device_nvidia);
+
+ r = cuCtxGetCurrent (&ctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (!ctx)
+ {
+ fprintf (stderr, "Expected context\n");
+ exit (EXIT_FAILURE);
+ }
+
+ if (pctx != ctx)
+ {
+ fprintf (stderr, "Unexpected new context\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return EXIT_SUCCESS;
+}
new file mode 100644
@@ -0,0 +1,223 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ {
+ y[i] = a * x[i] + y[i];
+ }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+ CUcontext ctx2, ctx3;
+ CUresult r;
+
+ r = cuCtxGetCurrent (&ctx2);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (ctx1 != ctx2)
+ {
+ fprintf (stderr, "new context established\n");
+ exit (EXIT_FAILURE);
+ }
+
+ ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+ if (ctx1 != ctx3)
+ {
+ fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return;
+}
+
+int
+main (int argc, char **argv)
+{
+ cublasStatus_t s;
+ cudaError_t e;
+ cublasHandle_t h;
+ CUcontext pctx, ctx;
+ CUresult r;
+ int dev;
+ int i;
+ const int N = 256;
+ float *h_X, *h_Y1, *h_Y2;
+ float *d_X,*d_Y;
+ float alpha = 2.0f;
+ float error_norm;
+ float ref_norm;
+
+ /* Test 2 - cuBLAS creates, OpenACC shares. */
+
+ s = cublasCreate (&h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasCreate failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ e = cudaGetDevice (&dev);
+ if (e != cudaSuccess)
+ {
+ fprintf (stderr, "cudaGetDevice failed: %d\n", e);
+ exit (EXIT_FAILURE);
+ }
+
+ acc_set_device_num (dev, acc_device_nvidia);
+
+ h_X = (float *) malloc (N * sizeof (float));
+ if (h_X == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y1 = (float *) malloc (N * sizeof (float));
+ if (h_Y1 == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y2 = (float *) malloc (N * sizeof (float));
+ if (h_Y2 == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_Y2\n");
+ exit (EXIT_FAILURE);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ h_X[i] = rand () / (float) RAND_MAX;
+ h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+ }
+
+ d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+ if (d_X == NULL)
+ {
+ fprintf (stderr, "copyin error h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+ if (d_Y == NULL)
+ {
+ fprintf (stderr, "copyin error h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+ context_check (pctx);
+
+#pragma acc parallel copyin (h_X[0:N]), copy (h_Y2[0:N]) copyin (alpha)
+ {
+ int i;
+
+ for (i = 0; i < N; i++)
+ {
+ h_Y2[i] = alpha * h_X[i] + h_Y2[i];
+ }
+ }
+
+ context_check (pctx);
+
+ error_norm = 0;
+ ref_norm = 0;
+
+ for (i = 0; i < N; ++i)
+ {
+ float diff;
+
+ diff = h_Y1[i] - h_Y2[i];
+ error_norm += diff * diff;
+ ref_norm += h_Y2[i] * h_Y2[i];
+ }
+
+ error_norm = (float) sqrt ((double) error_norm);
+ ref_norm = (float) sqrt ((double) ref_norm);
+
+ if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+ {
+ fprintf (stderr, "math error\n");
+ exit (EXIT_FAILURE);
+ }
+
+ free (h_X);
+ free (h_Y1);
+ free (h_Y2);
+
+ acc_free (d_X);
+ acc_free (d_Y);
+
+ context_check (pctx);
+
+ s = cublasDestroy (h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasDestroy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ acc_shutdown (acc_device_nvidia);
+
+ r = cuCtxGetCurrent (&ctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (!ctx)
+ {
+ fprintf (stderr, "Expected context\n");
+ exit (EXIT_FAILURE);
+ }
+
+ if (pctx != ctx)
+ {
+ fprintf (stderr, "Unexpected new context\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return EXIT_SUCCESS;
+}
new file mode 100644
@@ -0,0 +1,200 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ {
+ y[i] = a * x[i] + y[i];
+ }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+ CUcontext ctx2, ctx3;
+ CUresult r;
+
+ r = cuCtxGetCurrent (&ctx2);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (ctx1 != ctx2)
+ {
+ fprintf (stderr, "new context established\n");
+ exit (EXIT_FAILURE);
+ }
+
+ ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+ if (ctx1 != ctx3)
+ {
+ fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return;
+}
+
+int
+main (int argc, char **argv)
+{
+ cublasStatus_t s;
+ cublasHandle_t h;
+ CUcontext pctx;
+ CUresult r;
+ int i;
+ const int N = 256;
+ float *h_X, *h_Y1, *h_Y2;
+ float *d_X,*d_Y;
+ float alpha = 2.0f;
+ float error_norm;
+ float ref_norm;
+
+ /* Test 3 - OpenACC creates, cuBLAS shares. */
+
+ acc_set_device_num (0, acc_device_nvidia);
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ h_X = (float *) malloc (N * sizeof (float));
+ if (h_X == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y1 = (float *) malloc (N * sizeof (float));
+ if (h_Y1 == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y2 = (float *) malloc (N * sizeof (float));
+ if (h_Y2 == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_Y2\n");
+ exit (EXIT_FAILURE);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ h_X[i] = rand () / (float) RAND_MAX;
+ h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+ }
+
+ d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+ if (d_X == NULL)
+ {
+ fprintf (stderr, "copyin error h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+ if (d_Y == NULL)
+ {
+ fprintf (stderr, "copyin error h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ s = cublasCreate (&h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasCreate failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+ context_check (pctx);
+
+ saxpy (N, alpha, h_X, h_Y2);
+
+ error_norm = 0;
+ ref_norm = 0;
+
+ for (i = 0; i < N; ++i)
+ {
+ float diff;
+
+ diff = h_Y1[i] - h_Y2[i];
+ error_norm += diff * diff;
+ ref_norm += h_Y2[i] * h_Y2[i];
+ }
+
+ error_norm = (float) sqrt ((double) error_norm);
+ ref_norm = (float) sqrt ((double) ref_norm);
+
+ if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+ {
+ fprintf (stderr, "math error\n");
+ exit (EXIT_FAILURE);
+ }
+
+ free (h_X);
+ free (h_Y1);
+ free (h_Y2);
+
+ acc_free (d_X);
+ acc_free (d_Y);
+
+ context_check (pctx);
+
+ s = cublasDestroy (h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasDestroy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ acc_shutdown (acc_device_nvidia);
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (pctx)
+ {
+ fprintf (stderr, "Unexpected context\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return EXIT_SUCCESS;
+}
new file mode 100644
@@ -0,0 +1,213 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda -lcublas -lcudart" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <cuda.h>
+#include <cuda_runtime_api.h>
+#include <cublas_v2.h>
+#include <openacc.h>
+
+void
+saxpy (int n, float a, float *x, float *y)
+{
+ int i;
+
+ for (i = 0; i < n; i++)
+ {
+ y[i] = a * x[i] + y[i];
+ }
+}
+
+void
+context_check (CUcontext ctx1)
+{
+ CUcontext ctx2, ctx3;
+ CUresult r;
+
+ r = cuCtxGetCurrent (&ctx2);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (ctx1 != ctx2)
+ {
+ fprintf (stderr, "new context established\n");
+ exit (EXIT_FAILURE);
+ }
+
+ ctx3 = (CUcontext) acc_get_current_cuda_context ();
+
+ if (ctx1 != ctx3)
+ {
+ fprintf (stderr, "acc_get_current_cuda_context returned wrong value\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return;
+}
+
+int
+main (int argc, char **argv)
+{
+ cublasStatus_t s;
+ cublasHandle_t h;
+ CUcontext pctx;
+ CUresult r;
+ int i;
+ const int N = 256;
+ float *h_X, *h_Y1, *h_Y2;
+ float *d_X,*d_Y;
+ float alpha = 2.0f;
+ float error_norm;
+ float ref_norm;
+
+ /* Test 4 - OpenACC creates, cuBLAS shares. */
+
+ acc_set_device_num (0, acc_device_nvidia);
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ h_X = (float *) malloc (N * sizeof (float));
+ if (h_X == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_X\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y1 = (float *) malloc (N * sizeof (float));
+ if (h_Y1 == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ h_Y2 = (float *) malloc (N * sizeof (float));
+ if (h_Y2 == 0)
+ {
+ fprintf (stderr, "malloc failed: for h_Y2\n");
+ exit (EXIT_FAILURE);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ h_X[i] = rand () / (float) RAND_MAX;
+ h_Y2[i] = h_Y1[i] = rand () / (float) RAND_MAX;
+ }
+
+#pragma acc parallel copyin (h_X[0:N]), copy (h_Y2[0:N]) copy (alpha)
+ {
+ int i;
+
+ for (i = 0; i < N; i++)
+ {
+ h_Y2[i] = alpha * h_X[i] + h_Y2[i];
+ }
+ }
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ d_X = (float *) acc_copyin (&h_X[0], N * sizeof (float));
+ if (d_X == NULL)
+ {
+ fprintf (stderr, "copyin error h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ d_Y = (float *) acc_copyin (&h_Y1[0], N * sizeof (float));
+ if (d_Y == NULL)
+ {
+ fprintf (stderr, "copyin error h_Y1\n");
+ exit (EXIT_FAILURE);
+ }
+
+ s = cublasCreate (&h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasCreate failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ s = cublasSaxpy (h, N, &alpha, d_X, 1, d_Y, 1);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasSaxpy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ acc_memcpy_from_device (&h_Y1[0], d_Y, N * sizeof (float));
+
+ context_check (pctx);
+
+ error_norm = 0;
+ ref_norm = 0;
+
+ for (i = 0; i < N; ++i)
+ {
+ float diff;
+
+ diff = h_Y1[i] - h_Y2[i];
+ error_norm += diff * diff;
+ ref_norm += h_Y2[i] * h_Y2[i];
+ }
+
+ error_norm = (float) sqrt ((double) error_norm);
+ ref_norm = (float) sqrt ((double) ref_norm);
+
+ if ((fabs (ref_norm) < 1e-7) || ((error_norm / ref_norm) >= 1e-6f))
+ {
+ fprintf (stderr, "math error\n");
+ exit (EXIT_FAILURE);
+ }
+
+ free (h_X);
+ free (h_Y1);
+ free (h_Y2);
+
+ acc_free (d_X);
+ acc_free (d_Y);
+
+ context_check (pctx);
+
+ s = cublasDestroy (h);
+ if (s != CUBLAS_STATUS_SUCCESS)
+ {
+ fprintf (stderr, "cublasDestroy failed: %d\n", s);
+ exit (EXIT_FAILURE);
+ }
+
+ context_check (pctx);
+
+ acc_shutdown (acc_device_nvidia);
+
+ r = cuCtxGetCurrent (&pctx);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuCtxGetCurrent failed: %d\n", r);
+ exit (EXIT_FAILURE);
+ }
+
+ if (pctx)
+ {
+ fprintf (stderr, "Unexpected context\n");
+ exit (EXIT_FAILURE);
+ }
+
+ return EXIT_SUCCESS;
+}
@@ -1,19 +1,30 @@
/* { dg-do run } */
-extern void abort ();
+#include <stdlib.h>
+#include <openacc.h>
int i;
+int
+is_mapped (void *p, size_t n)
+{
+#if ACC_MEM_SHARED
+ return 1;
+#else
+ return acc_is_present (p, n);
+#endif
+}
+
int main(void)
{
int j;
-#if 0
i = -1;
j = -2;
#pragma acc data copyin (i, j)
{
- // TODO: check that variables have been mapped.
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
if (i != -1 || j != -2)
abort ();
i = 2;
@@ -28,37 +39,30 @@ int main(void)
j = -2;
#pragma acc data copyout (i, j)
{
- // TODO: check that variables have been mapped.
- if (i != -1 || j != -2)
- abort ();
- i = 2;
- j = 1;
- if (i != 2 || j != 1)
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
abort ();
- }
- if (i != -1 || j != -2)
- abort ();
-
- i = -1;
- j = -2;
-#pragma acc data copy (i, j)
- {
- // TODO: check that variables have been mapped.
if (i != -1 || j != -2)
abort ();
i = 2;
j = 1;
if (i != 2 || j != 1)
abort ();
+
+#pragma acc parallel present (i, j)
+ {
+ i = 4;
+ j = 2;
+ }
}
- if (i != -1 || j != -2)
+ if (i != 4 || j != 2)
abort ();
i = -1;
j = -2;
#pragma acc data create (i, j)
{
- // TODO: check that variables have been mapped.
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
if (i != -1 || j != -2)
abort ();
i = 2;
@@ -66,15 +70,15 @@ int main(void)
if (i != 2 || j != 1)
abort ();
}
- if (i != -1 || j != -2)
+ if (i != 2 || j != 1)
abort ();
-#endif
i = -1;
j = -2;
#pragma acc data present_or_copyin (i, j)
{
- // TODO: check that variables have been mapped.
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
if (i != -1 || j != -2)
abort ();
i = 2;
@@ -85,28 +89,34 @@ int main(void)
if (i != 2 || j != 1)
abort ();
-#if 0
i = -1;
j = -2;
#pragma acc data present_or_copyout (i, j)
{
- // TODO: check that variables have been mapped.
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
if (i != -1 || j != -2)
abort ();
i = 2;
j = 1;
if (i != 2 || j != 1)
abort ();
+
+#pragma acc parallel present (i, j)
+ {
+ i = 4;
+ j = 2;
+ }
}
- if (i != -1 || j != -2)
+ if (i != 4 || j != 2)
abort ();
-#endif
i = -1;
j = -2;
#pragma acc data present_or_copy (i, j)
{
- // TODO: check that variables have been mapped.
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
if (i != -1 || j != -2)
abort ();
i = 2;
@@ -114,47 +124,56 @@ int main(void)
if (i != 2 || j != 1)
abort ();
}
+#if ACC_MEM_SHARED
+ if (i != 2 || j != 1)
+ abort ();
+#else
if (i != -1 || j != -2)
abort ();
+#endif
-#if 0
i = -1;
j = -2;
#pragma acc data present_or_create (i, j)
{
- // TODO: check that variables have been mapped.
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
i = 2;
j = 1;
if (i != 2 || j != 1)
abort ();
}
- if (i != -1 || j != -2)
+
+ if (i != 2 || j != 1)
abort ();
-#endif
-#if 0
i = -1;
j = -2;
-#pragma acc data present (i, j)
+#pragma acc data copyin (i, j)
{
- // TODO: check that variables have been mapped.
- if (i != -1 || j != -2)
- abort ();
- i = 2;
- j = 1;
- if (i != 2 || j != 1)
- abort ();
+#pragma acc data present (i, j)
+ {
+ if (!is_mapped (&i, sizeof (i)) || !is_mapped (&j, sizeof (j)))
+ abort ();
+ if (i != -1 || j != -2)
+ abort ();
+ i = 2;
+ j = 1;
+ if (i != 2 || j != 1)
+ abort ();
+ }
}
- if (i != -1 || j != -2)
+ if (i != 2 || j != 1)
abort ();
-#endif
-#if 0
i = -1;
j = -2;
#pragma acc data
{
- // TODO: check that variables have been mapped.
+#if !ACC_MEM_SHARED
+ if (is_mapped (&i, sizeof (i)) || is_mapped (&j, sizeof (j)))
+ abort ();
+#endif
if (i != -1 || j != -2)
abort ();
i = 2;
@@ -162,9 +181,8 @@ int main(void)
if (i != 2 || j != 1)
abort ();
}
- if (i != -1 || j != -2)
+ if (i != 2 || j != 1)
abort ();
-#endif
return 0;
}
new file mode 100644
@@ -0,0 +1,32 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int main (void)
+{
+ void *a, *a_1, *a_2;
+
+#define A (void *) 0x123
+ a = A;
+
+#pragma acc data copyout (a_1, a_2)
+#pragma acc kernels deviceptr (a)
+ {
+ a_1 = a;
+ a_2 = &a;
+ }
+
+ if (a != A)
+ abort ();
+ if (a_1 != a)
+ abort ();
+#if ACC_MEM_SHARED
+ if (a_2 != &a)
+ abort ();
+#else
+ if (a_2 == &a)
+ abort ();
+#endif
+
+ return 0;
+}
@@ -1,4 +1,5 @@
/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_DEVICE_TYPE_host=1" } } */
#include "libgomp_g.h"
@@ -19,7 +20,7 @@ int main(void)
i = -1;
GOACC_kernels (0, f, (const void *) 0,
0, (void *) 0, (void *) 0, (void *) 0,
- 1, 1, 1);
+ 1, 1, 1, -2, -1);
if (i != 42)
abort ();
@@ -1,4 +1,5 @@
/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_DEVICE_TYPE_host=1" } } */
#include "libgomp_g.h"
@@ -19,7 +20,7 @@ int main(void)
i = -1;
GOACC_parallel (0, f, (const void *) 0,
0, (void *) 0, (void *) 0, (void *) 0,
- 1, 1, 1);
+ 1, 1, 1, -2, -1);
if (i != 42)
abort ();
new file mode 100644
@@ -0,0 +1,547 @@
+/* { dg-do run } */
+/* { dg-additional-options "-fno-builtin-acc_on_device" } */
+
+#include <openacc.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+#define N 32
+
+int
+main(int argc, char **argv)
+{
+ float *a, *b, *d_a, *d_b, exp, exp2;
+ int i;
+ const int one = 1;
+ const int zero = 0;
+ int n;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+ d_a = (float *) acc_malloc (N * sizeof (float));
+ d_b = (float *) acc_malloc (N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ a[i] = 4.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(1)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 5.0;
+#else
+ exp = 4.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 16.0;
+
+#pragma acc parallel if(0)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 17.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 8.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(one)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 9.0;
+#else
+ exp = 8.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 22.0;
+
+#pragma acc parallel if(zero)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 23.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 16.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(true)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 17.0;
+#else
+ exp = 16.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 76.0;
+
+#pragma acc parallel if(false)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 77.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 22.0;
+
+ n = 1;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(n)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 23.0;
+#else
+ exp = 22.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 18.0;
+
+ n = 0;
+
+#pragma acc parallel if(n)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 19.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 49.0;
+
+ n = 1;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(n + n)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 50.0;
+#else
+ exp = 49.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 38.0;
+
+ n = 0;
+
+#pragma acc parallel if(n + n)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 39.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 91.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(-2)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 92.0;
+#else
+ exp = 91.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 43.0;
+
+#pragma acc parallel copyin(a[0:N]) copyout(b[0:N]) if(one == 1)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+#if ACC_MEM_SHARED
+ exp = 44.0;
+#else
+ exp = 43.0;
+#endif
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != exp)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ a[i] = 87.0;
+
+#pragma acc parallel if(one == 0)
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ if (acc_on_device (acc_device_host))
+ b[ii] = a[ii] + 1;
+ else
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 88.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 9.0;
+ }
+
+#if ACC_MEM_SHARED
+ exp = 0.0;
+ exp2 = 0.0;
+#else
+ acc_map_data (a, d_a, N * sizeof (float));
+ acc_map_data (b, d_b, N * sizeof (float));
+ exp = 3.0;
+ exp2 = 9.0;
+#endif
+
+#pragma acc update device(a[0:N], b[0:N]) if(1)
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 0.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc update host(a[0:N], b[0:N]) if(1)
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != exp)
+ abort();
+
+ if (b[i] != exp2)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 12.0;
+ }
+
+#pragma acc update device(a[0:N], b[0:N]) if(0)
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 0.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc update host(a[0:N], b[0:N]) if(1)
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != exp)
+ abort();
+
+ if (b[i] != exp2)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 26.0;
+ b[i] = 21.0;
+ }
+
+#pragma acc update device(a[0:N], b[0:N]) if(1)
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 0.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc update host(a[0:N], b[0:N]) if(0)
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 0.0)
+ abort();
+
+ if (b[i] != 0.0)
+ abort();
+ }
+
+#if !ACC_MEM_SHARED
+ acc_unmap_data (a);
+ acc_unmap_data (b);
+#endif
+
+ acc_free (d_a);
+ acc_free (d_b);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc data copyin(a[0:N]) copyout(b[0:N]) if(1)
+{
+#pragma acc parallel present(a[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ b[ii] = a[ii];
+ }
+ }
+}
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 4.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 8.0;
+ b[i] = 1.0;
+ }
+
+#pragma acc data copyin(a[0:N]) copyout(b[0:N]) if(0)
+{
+#if !ACC_MEM_SHARED
+ if (acc_is_present (a, N * sizeof (float)))
+ abort ();
+#endif
+
+#if !ACC_MEM_SHARED
+ if (acc_is_present (b, N * sizeof (float)))
+ abort ();
+#endif
+}
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 18.0;
+ b[i] = 21.0;
+ }
+
+#pragma acc data copyin(a[0:N]) if(1)
+{
+#if !ACC_MEM_SHARED
+ if (!acc_is_present (a, N * sizeof (float)))
+ abort ();
+#endif
+
+#pragma acc data copyout(b[0:N]) if(0)
+ {
+#if !ACC_MEM_SHARED
+ if (acc_is_present (b, N * sizeof (float)))
+ abort ();
+#endif
+
+#pragma acc data copyout(b[0:N]) if(1)
+ {
+#pragma acc parallel present(a[0:N]) present(b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ b[ii] = a[ii];
+ }
+ }
+ }
+
+#if !ACC_MEM_SHARED
+ if (acc_is_present (b, N * sizeof (float)))
+ abort ();
+#endif
+ }
+}
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 18.0)
+ abort ();
+ }
+
+#ifdef XXX_TODO_ENTER_END_DATA
+#endif
+
+ return 0;
+}
@@ -1,10 +1,10 @@
/* { dg-do run } */
-extern void abort ();
+#include <stdlib.h>
int i;
-int main(void)
+int main (void)
{
int j, v;
@@ -83,8 +83,15 @@ int main(void)
abort ();
v = 1;
}
- if (v != 1 || i != -1 || j != -2)
+ if (v != 1)
+ abort ();
+#if ACC_MEM_SHARED
+ if (i != 2 || j != 1)
abort ();
+#else
+ if (i != -1 || j != -2)
+ abort ();
+#endif
i = -1;
j = -2;
@@ -127,8 +134,15 @@ int main(void)
abort ();
v = 1;
}
- if (v != 1 || i != -1 || j != -2)
+ if (v != 1)
+ abort ();
+#if ACC_MEM_SHARED
+ if (i != 2 || j != 1)
abort ();
+#else
+ if (i != -1 || j != -2)
+ abort ();
+#endif
#if 0
i = -1;
@@ -1,7 +1,24 @@
+/* { dg-do run } */
+
#include <openacc.h>
int
-main (void)
+main (int argc, char **argv)
{
+ acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+ devtype = acc_device_nvidia;
+
+ if (acc_get_num_devices (devtype) == 0)
+ return 0;
+#endif
+
+ acc_init (devtype);
+
+ acc_init (devtype);
+
return 0;
}
+
+/* { dg-shouldfail "libgomp: device already active" } */
new file mode 100644
@@ -0,0 +1,58 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ void *d;
+ acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+ devtype = acc_device_nvidia;
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+#endif
+
+ acc_init (devtype);
+
+ d = acc_malloc (0);
+ if (d != NULL)
+ abort ();
+
+ acc_free (0);
+
+ acc_shutdown (devtype);
+
+ acc_set_device_type (devtype);
+
+ d = acc_malloc (0);
+ if (d != NULL)
+ abort ();
+
+ acc_shutdown (devtype);
+
+ acc_init (devtype);
+
+ d = acc_malloc (1024);
+ if (d == NULL)
+ abort ();
+
+ acc_free (d);
+
+ acc_shutdown (devtype);
+
+ acc_set_device_type (devtype);
+
+ d = acc_malloc (1024);
+ if (d == NULL)
+ abort ();
+
+ acc_free (d);
+
+ acc_shutdown (devtype);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,22 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+#include <stdint.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 512;
+ void *d;
+
+ d = acc_malloc (N);
+ if (d == NULL)
+ abort ();
+
+ acc_free ((void *)((uintptr_t) d + (uintptr_t) (N >> 1)));
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: mem free failed 1" } */
new file mode 100644
@@ -0,0 +1,37 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ memset (h, 0, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+
+ if (acc_is_present (h, 1) != 1)
+ abort ();
+
+ if (acc_is_present (h, N + 1) != 0)
+ abort ();
+
+ if (acc_is_present (h + 1, N) != 0)
+ abort ();
+
+ if (acc_is_present (h - 1, N) != 0)
+ abort ();
+
+ if (acc_is_present (h - 1, N - 1) != 0)
+ abort ();
+
+ if (acc_is_present (h + N, 0) != 0)
+ abort ();
+
+ if (acc_is_present (h + N, N) != 0)
+ abort ();
+
+ if (acc_is_present (0, N) != 0)
+ abort ();
+
+ if (acc_is_present (h, 0) != 0)
+ abort ();
+
+ acc_free (d);
+
+ if (acc_is_present (h, 1) != 0)
+ abort ();
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,61 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+
+ if (acc_is_present (h, 1) != 1)
+ abort ();
+
+ if (acc_is_present (h + N - 1, 1) != 1)
+ abort ();
+
+ if (acc_is_present (h - 1, 1) != 0)
+ abort ();
+
+ if (acc_is_present (h + N, 1) != 0)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 1)
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, N - i) != 1)
+ abort ();
+ }
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, N - i) != 0)
+ abort ();
+ }
+
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 0)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ (void) acc_copyin (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+256\] already mapped to \[\h+,\+256\]" } */
new file mode 100644
@@ -0,0 +1,31 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ acc_copyout (h, N);
+
+ acc_copyout (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+
+ acc_free (d);
+
+ acc_copyout (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,60 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+#include <stdio.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h[N];
+
+ for (i = 0; i < N; i++)
+ {
+ int j;
+ unsigned char *p;
+
+ h[i] = (unsigned char *) malloc (N);
+ p = h[i];
+
+ for (j = 0; j < N; j++)
+ {
+ p[j] = i;
+ }
+
+ (void) acc_copyin (p, N);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ memset (h[i], 0, i);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ int j;
+ unsigned char *p;
+
+ acc_copyout (h[i], N);
+
+ p = h[i];
+
+ for (j = 0; j < N; j++)
+ {
+ if (p[j] != i)
+ abort ();
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ free (h[i]);
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+ devtype = acc_device_nvidia;
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+#endif
+
+ acc_init (devtype);
+
+ acc_shutdown (devtype);
+
+ acc_shutdown (devtype);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: no device initialized" } */
new file mode 100644
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ acc_copyout (h, N + 1);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surounds2 \[\h+,\+257\]" } */
new file mode 100644
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ acc_copyout (h, 0);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,29 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ (void) acc_copyin (h, N);
+
+ acc_copyout (h + 1, N - 1);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surrounds2 \[\h+,\+255\]" } */
new file mode 100644
@@ -0,0 +1,39 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h1, *h2;
+
+ h1 = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h1[i] = 0xab;
+ }
+
+ (void) acc_copyin (h1, N);
+
+ h2 = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h2[i] = 0xde;
+ }
+
+ (void) acc_copyin (h2, N);
+
+ acc_copyout (h1, N + N);
+
+ free (h1);
+ free (h2);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surrounds2 \[\h+,\+512\]" } */
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 1)
+ abort ();
+ }
+
+ acc_delete (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 0)
+ abort ();
+ }
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 1)
+ abort ();
+ }
+
+ acc_delete (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 0)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,30 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] already mapped to \[\h+,256\]" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (h, 0);
+ if (!d)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\] is a bad range" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (0, N);
+ if (!d)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\)\] is a bad range" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ acc_delete (0, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),256\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ acc_delete (h, 0);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,15 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ acc_init (acc_device_host);
+
+ acc_shutdown (acc_device_not_host);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: device 4(4) is initialized" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_create (h, N);
+ if (!d)
+ abort ();
+
+ acc_delete (h, N - 2);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] surrounds2 \[\h+,\+254\]" } */
new file mode 100644
@@ -0,0 +1,27 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_present_or_create (h, N);
+ if (!d)
+ abort ();
+
+ if (acc_is_present (h, 1) != 1)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,38 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d1, *d2;
+
+ h = (unsigned char *) malloc (N);
+
+ d1 = acc_present_or_create (h, N);
+ if (!d1)
+ abort ();
+
+ d2 = acc_present_or_create (h, N);
+ if (!d2)
+ abort ();
+
+ if (d1 != d2)
+ abort ();
+
+ d2 = acc_pcreate (h, N);
+ if (!d2)
+ abort ();
+
+ if (d1 != d2)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,31 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d1, *d2;
+
+ h = (unsigned char *) malloc (N);
+
+ d1 = acc_present_or_create (h, N);
+ if (!d1)
+ abort ();
+
+ d2 = acc_present_or_create (h, N - 2);
+ if (!d2)
+ abort ();
+
+ if (d1 != d2)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d1, *d2;
+
+ h = (unsigned char *) malloc (N);
+
+ d1 = acc_present_or_create (h, N);
+ if (!d1)
+ abort ();
+
+ d2 = acc_present_or_create (h + 2, N);
+ if (!d2)
+ abort ();
+
+ if (d1 != d2)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+256\] not mapped" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_present_or_create (0, N);
+ if (!d)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),+256\] is a bad range" } */
new file mode 100644
@@ -0,0 +1,26 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_present_or_create (h, 0);
+ if (!d)
+ abort ();
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\] is a bad range" } */
new file mode 100644
@@ -0,0 +1,40 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_present_or_copyin (h, N);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,67 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d1, *d2;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d1 = acc_present_or_copyin (h, N);
+ if (!d1)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = 0xab;
+ }
+
+ d2 = acc_present_or_copyin (h, N);
+ if (!d2)
+ abort ();
+
+ if (d1 != d2)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ d2 = acc_pcopyin (h, N);
+ if (!d2)
+ abort ();
+
+ if (d1 != d2)
+ abort ();
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_present_or_copyin (0, N);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),+256\] is a bad range" } */
new file mode 100644
@@ -0,0 +1,13 @@
+/* { dg-do run } */
+
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ acc_init ((acc_device_t) 99);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: device 99 is out of range" } */
new file mode 100644
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_present_or_copyin (h, 0);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\] is a bad range" } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = 0xab;
+ }
+
+ acc_update_device (h, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != 0xab)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ acc_update_device (h, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != 0xab)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,256\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,45 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = 0xab;
+ }
+
+ acc_update_device (0, N);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != 0xab)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),256\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,45 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = 0xab;
+ }
+
+ acc_update_device (h, 0);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != 0xab)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,50 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = 0xab;
+ }
+
+ acc_update_device (h, N - 2);
+
+ acc_copyout (h, N);
+
+ for (i = 0; i < N - 2; i++)
+ {
+ if (h[i] != 0xab)
+ abort ();
+ }
+
+ for (i = N - 2; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_update_self (h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_update_self (0, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\(nil\),256\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_update_self (h, 0);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,0\] is not mapped" } */
new file mode 100644
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_copyin (h, N);
+ if (!d)
+ abort ();
+
+ memset (&h[0], 0, N);
+
+ acc_update_self (h, N - 2);
+
+ for (i = 0; i < N - 2; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ for (i = N - 2; i < N; i++)
+ {
+ if (h[i] != 0)
+ abort ();
+ }
+
+ acc_delete (h, N);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,40 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ if (acc_get_device_type () == acc_device_default)
+ abort ();
+
+ acc_init (acc_device_default);
+
+ if (acc_get_device_type () == acc_device_default)
+ abort ();
+
+ acc_shutdown (acc_device_default);
+
+ if (acc_get_num_devices (acc_device_nvidia) != 0)
+ {
+ acc_init (acc_device_nvidia);
+
+ if (acc_get_device_type () != acc_device_nvidia)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ acc_init (acc_device_default);
+
+ acc_set_device_type (acc_device_nvidia);
+
+ if (acc_get_device_type () != acc_device_nvidia)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+ }
+
+ return 0;
+
+}
new file mode 100644
@@ -0,0 +1,30 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, N);
+
+ if (acc_is_present (h, N) != 1)
+ abort ();
+
+ acc_unmap_data (h);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h[N];
+ void *d[N];
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = (unsigned char *) malloc (N);
+ d[i] = acc_malloc (N);
+
+ acc_map_data (h[i], d[i], N);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h[i], N) != 1)
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ acc_unmap_data (h[i]);
+
+ if (acc_is_present (h[i], N) != 0)
+ abort ();
+
+ acc_free (d[i]);
+ free (h[i]);
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (0, d, N);
+
+ acc_unmap_data (h);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[(nil),+256\]->\[\h+,\+256\] is a bad map" } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, 0, N);
+
+ acc_unmap_data (h);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+256\]->\[(nil),\+256\] is a bad map" } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, 0);
+
+ acc_unmap_data (h);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \[\h+,\+0\]->\[\h+,\+0\] is a bad map" } */
new file mode 100644
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+#include <stdint.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ int i;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ acc_map_data ((void *)((uintptr_t) h + (uintptr_t) i),
+ (void *)((uintptr_t) d + (uintptr_t) i), 1);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + 1, 1) != 1)
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ acc_unmap_data (h + i);
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + 1, 1) != 0)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, N >> 1);
+
+ if (acc_is_present (h, 1) != 1)
+ abort ();
+
+ if (acc_is_present (h + (N >> 1), 1) != 0)
+ abort ();
+
+ acc_unmap_data (h);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, N);
+
+ acc_unmap_data (d);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \h+ is not a mapped block" } */
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, N);
+
+ acc_unmap_data (0);
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: \(nil\) is not a mapped block" } */
new file mode 100644
@@ -0,0 +1,55 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <stdlib.h>
+#include <openacc.h>
+#include <stdint.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_hostptr ((void *)((uintptr_t) d + (uintptr_t) i)) !=
+ (void *)((uintptr_t) h + (uintptr_t) i))
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_deviceptr ((void *)((uintptr_t) h + (uintptr_t) i)) !=
+ (void *)((uintptr_t) d + (uintptr_t) i))
+ abort ();
+ }
+
+ acc_unmap_data (h);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_hostptr ((void *)((uintptr_t) d + (uintptr_t) i)) != 0)
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_deviceptr (h + i) != 0)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,39 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ int devnum;
+
+ if (acc_get_device_type () == acc_device_default)
+ abort ();
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ acc_set_device_type (acc_device_nvidia);
+
+ if (acc_get_device_type () != acc_device_nvidia)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ acc_set_device_type (acc_device_nvidia);
+
+ if (acc_get_device_type () != acc_device_nvidia)
+ abort ();
+
+ devnum = acc_get_num_devices (acc_device_host);
+ if (devnum != 1)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ if (acc_get_device_type () == acc_device_default)
+ abort ();
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,54 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, h, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 0)
+ abort ();
+ }
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_from_device (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_is_present (h + i, 1) != 0)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,70 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h[N];
+ void *d[N];
+
+ for (i = 0; i < N; i++)
+ {
+ int j;
+ unsigned char *p;
+
+ h[i] = (unsigned char *) malloc (N);
+
+ p = h[i];
+
+ for (j = 0; j < N; j++)
+ {
+ p[j] = i;
+ }
+
+ d[i] = acc_malloc (N);
+
+ acc_memcpy_to_device (d[i], h[i], N);
+
+ for (j = 0; j < N; j++)
+ {
+ if (acc_is_present (h[i] + j, 1) != 0)
+ abort ();
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ int j;
+ unsigned char *p;
+
+ memset (h[i], 0, N);
+
+ acc_memcpy_from_device (h[i], d[i], N);
+
+ p = h[i];
+
+ for (j = 0; j < N; j++)
+ {
+ if (p[j] != i)
+ abort ();
+ }
+
+ for (j = 0; j < N; j++)
+ {
+ if (acc_is_present (h[i] + j, 1) != 0)
+ abort ();
+ }
+
+ acc_free (d[i]);
+
+ free (h[i]);
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,49 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ acc_init (acc_device_nvidia);
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, h, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_to_device (d, h, N << 1);
+
+ acc_memcpy_from_device (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid size" } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (0, h, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_from_device (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid device address" } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, 0, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_from_device (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid host address" } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, d, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_from_device (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid host or device address" } */
new file mode 100644
@@ -0,0 +1,47 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ acc_init (acc_device_nvidia);
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, h, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_to_device (d, h, 0);
+
+ acc_memcpy_from_device (h, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, h, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_from_device (0, d, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid host address" } */
new file mode 100644
@@ -0,0 +1,43 @@
+/* { dg-do run } */
+
+#include <string.h>
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 256;
+ int i;
+ unsigned char *h;
+ void *d;
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_memcpy_to_device (d, h, N);
+
+ memset (&h[0], 0, N);
+
+ acc_memcpy_from_device (h, 0, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (h[i] != i)
+ abort ();
+ }
+
+ acc_free (d);
+
+ free (h);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: invalid device address" } */
new file mode 100644
@@ -0,0 +1,124 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ stream = (CUstream) acc_get_cuda_stream (0);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ if (acc_async_test (0) != 0)
+ {
+ fprintf (stderr, "asynchronous operation not running\n");
+ abort ();
+ }
+
+ sleep (1);
+
+ if (acc_async_test (0) != 1)
+ {
+ fprintf (stderr, "found asynchronous operation still running\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,18 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ if (acc_get_num_devices (acc_device_none) != 0)
+ abort ();
+
+ if (acc_get_num_devices (acc_device_host) == 0)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,136 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ const int N = 10;
+ int i;
+ CUstream streams[N];
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ for (i = 0; i < N; i++)
+ {
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ if (acc_async_test (i) != 0)
+ {
+ fprintf (stderr, "asynchronous operation not running\n");
+ abort ();
+ }
+ }
+
+ sleep ((int) (dtime / 1000.0f) + 1);
+
+ for (i = 0; i < N; i++)
+ {
+ if (acc_async_test (i) != 1)
+ {
+ fprintf (stderr, "found asynchronous operation still running\n");
+ abort ();
+ }
+ }
+
+ acc_unmap_data (a);
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,119 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ acc_set_cuda_stream (0, stream);
+
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ if (acc_async_test (1) != 0)
+ {
+ fprintf (stderr, "asynchronous operation not running\n");
+ abort ();
+ }
+
+ sleep ((int) (dtime / 1000.0f) + 1);
+
+ if (acc_async_test (1) != 1)
+ {
+ fprintf (stderr, "found asynchronous operation still running\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: unknown async \d" } */
new file mode 100644
@@ -0,0 +1,121 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ if (acc_async_test_all () != 0)
+ {
+ fprintf (stderr, "asynchronous operation not running\n");
+ abort ();
+ }
+
+ sleep ((int) (dtime / 1000.f) + 1);
+
+ if (acc_async_test_all () != 1)
+ {
+ fprintf (stderr, "found asynchronous operation still running\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,134 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ const int N = 10;
+ int i;
+ CUstream streams[N];
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ for (i = 0; i < N; i++)
+ {
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ }
+
+ if (acc_async_test_all () != 0)
+ {
+ fprintf (stderr, "asynchronous operation not running\n");
+ abort ();
+ }
+
+ sleep ((int) (dtime / 1000.0f) + 1);
+
+ if (acc_async_test_all () != 1)
+ {
+ fprintf (stderr, "asynchronous operation not running\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,139 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ stream = (CUstream) acc_get_cuda_stream (0);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ init_timers (1);
+
+ start_timer (0);
+
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ acc_wait (0);
+
+ atime = stop_timer (0);
+
+ if (atime < dtime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ start_timer (0);
+
+ acc_wait (0);
+
+ atime = stop_timer (0);
+
+ if (0.010 < atime)
+ {
+ fprintf (stderr, "actual time too long\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,141 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ int N;
+ int i;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime, hitime, lotime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ N = nprocs;
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ stream = (CUstream) acc_get_cuda_stream (0);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ init_timers (1);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ start_timer (0);
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ acc_wait (0);
+ }
+
+ atime = stop_timer (0);
+
+ hitime = dtime * N;
+ hitime += hitime * 0.02;
+
+ lotime = dtime * N;
+ lotime -= lotime * 0.02;
+
+ if (atime > hitime || atime < lotime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,147 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ int N;
+ int i;
+ CUstream *streams;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime, hitime, lotime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ N = nprocs;
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ streams = (CUstream *) malloc (N * sizeof (void *));
+
+ for (i = 0; i < N; i++)
+ {
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ init_timers (1);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ start_timer (0);
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ acc_wait (i);
+ }
+
+ atime = stop_timer (0);
+
+ hitime = dtime * N;
+ hitime += hitime * 0.02;
+
+ lotime = dtime * N;
+ lotime -= lotime * 0.02;
+
+ if (atime > hitime || atime < lotime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (streams);
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,135 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ acc_set_cuda_stream (0, stream);
+
+ init_timers (1);
+
+ start_timer (0);
+
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ acc_wait (1);
+
+ atime = stop_timer (0);
+
+ if (atime < dtime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ start_timer (0);
+
+ acc_wait (1);
+
+ atime = stop_timer (0);
+
+ if (0.010 < atime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: unknown async \d" } */
new file mode 100644
@@ -0,0 +1,140 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ stream = (CUstream) acc_get_cuda_stream (0);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ init_timers (1);
+
+ start_timer (0);
+
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ acc_wait_all ();
+
+ atime = stop_timer (0);
+
+ if (atime < dtime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ start_timer (0);
+
+ acc_wait_all ();
+
+ atime = stop_timer (0);
+
+ if (0.010 < atime)
+ {
+ fprintf (stderr, "actual time too long\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,167 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ int N;
+ int i;
+ CUstream stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime, hitime, lotime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ devnum = 2;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ N = nprocs;
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (1, stream))
+ abort ();
+
+ stream = (CUstream) acc_get_cuda_stream (0);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ init_timers (1);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ start_timer (0);
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+ }
+
+ acc_wait_async (0, 1);
+
+ if (acc_async_test (0) != 0)
+ abort ();
+
+ if (acc_async_test (1) != 0)
+ abort ();
+
+ acc_wait (1);
+
+ atime = stop_timer (0);
+
+ if (acc_async_test (0) != 1)
+ abort ();
+
+ if (acc_async_test (1) != 1)
+ abort ();
+
+ hitime = dtime * N;
+ hitime += hitime * 0.02;
+
+ lotime = dtime * N;
+ lotime -= lotime * 0.02;
+
+ if (atime > hitime || atime < lotime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,132 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ CUstream stream;
+ int N;
+ int i;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 200.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ N = nprocs;
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ acc_set_cuda_stream (1, stream);
+
+ init_timers (1);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ start_timer (0);
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+ }
+
+ acc_wait_async (1, 1);
+
+ acc_wait (1);
+
+ atime = stop_timer (0);
+
+ if (atime < dtime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-shouldfail "libgomp: identical parameters" } */
new file mode 100644
@@ -0,0 +1,211 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay;
+ CUmodule module;
+ CUresult r;
+ int N;
+ int i;
+ CUstream *streams, stream;
+ unsigned long *a, *d_a, dticks;
+ int nbytes;
+ float atime, dtime;
+ void *kargs[2];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay, module, "delay");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = nprocs * sizeof (unsigned long);
+
+ dtime = 500.0;
+
+ dticks = (unsigned long) (dtime * clkrate);
+
+ N = nprocs;
+
+ a = (unsigned long *) malloc (nbytes);
+ d_a = (unsigned long *) acc_malloc (nbytes);
+
+ acc_map_data (a, d_a, nbytes);
+
+ streams = (CUstream *) malloc (N * sizeof (void *));
+
+ for (i = 0; i < N; i++)
+ {
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ init_timers (1);
+
+ kargs[0] = (void *) &d_a;
+ kargs[1] = (void *) &dticks;
+
+ stream = (CUstream) acc_get_cuda_stream (N);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (N, stream))
+ abort ();
+
+ start_timer (0);
+
+ for (i = 0; i < N; i++)
+ {
+ r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+ }
+
+ acc_wait_all_async (N);
+
+ for (i = 0; i <= N; i++)
+ {
+ if (acc_async_test (i) != 0)
+ abort ();
+ }
+
+ acc_wait (N);
+
+ for (i = 0; i <= N; i++)
+ {
+ if (acc_async_test (i) != 1)
+ abort ();
+ }
+
+ atime = stop_timer (0);
+
+ if (atime < dtime)
+ {
+ fprintf (stderr, "actual time < delay time\n");
+ abort ();
+ }
+
+ start_timer (0);
+
+ stream = (CUstream) acc_get_cuda_stream (N + 1);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (N + 1, stream))
+ abort ();
+
+ acc_wait_all_async (N + 1);
+
+ acc_wait (N + 1);
+
+ atime = stop_timer (0);
+
+ if (0.10 < atime)
+ {
+ fprintf (stderr, "actual time too long\n");
+ abort ();
+ }
+
+ start_timer (0);
+
+ acc_wait_all_async (N);
+
+ acc_wait (N);
+
+ atime = stop_timer (0);
+
+ if (0.10 < atime)
+ {
+ fprintf (stderr, "actual time too long\n");
+ abort ();
+ }
+
+ acc_unmap_data (a);
+
+ fini_timers ();
+
+ free (streams);
+ free (a);
+ acc_free (d_a);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,144 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ CUdevice dev;
+ CUfunction delay2;
+ CUmodule module;
+ CUresult r;
+ int N;
+ int i;
+ CUstream *streams;
+ unsigned long **a, **d_a, *tid, ticks;
+ int nbytes;
+ void *kargs[3];
+ int clkrate;
+ int devnum, nprocs;
+
+ acc_init (acc_device_nvidia);
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+
+ r = cuDeviceGet (&dev, devnum);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGet failed: %d\n", r);
+ abort ();
+ }
+
+ r =
+ cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
+ dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleLoad (&module, "subr.ptx");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleLoad failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuModuleGetFunction (&delay2, module, "delay2");
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
+ abort ();
+ }
+
+ nbytes = sizeof (int);
+
+ ticks = (unsigned long) (200.0 * clkrate);
+
+ N = nprocs;
+
+ streams = (CUstream *) malloc (N * sizeof (void *));
+
+ a = (unsigned long **) malloc (N * sizeof (unsigned long *));
+ d_a = (unsigned long **) malloc (N * sizeof (unsigned long *));
+ tid = (unsigned long *) malloc (N * sizeof (unsigned long));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = (unsigned long *) malloc (sizeof (unsigned long));
+ *a[i] = N;
+ d_a[i] = (unsigned long *) acc_malloc (nbytes);
+ tid[i] = i;
+
+ acc_map_data (a[i], d_a[i], nbytes);
+
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ kargs[0] = (void *) &d_a[i];
+ kargs[1] = (void *) &ticks;
+ kargs[2] = (void *) &tid[i];
+
+ r = cuLaunchKernel (delay2, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
+ abort ();
+ }
+
+ ticks = (unsigned long) (50.0 * clkrate);
+ }
+
+ acc_wait_all_async (0);
+
+ for (i = 0; i < N; i++)
+ {
+ acc_copyout (a[i], nbytes);
+ if (*a[i] != i)
+ abort ();
+ }
+
+ free (streams);
+
+ for (i = 0; i < N; i++)
+ {
+ free (a[i]);
+ }
+
+ free (a);
+ free (d_a);
+ free (tid);
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,58 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include "timer.h"
+
+int
+main (int argc, char **argv)
+{
+ float atime;
+ CUstream stream;
+ CUresult r;
+
+ acc_init (acc_device_nvidia);
+
+ (void) acc_get_device_num (acc_device_nvidia);
+
+ init_timers (1);
+
+ stream = (CUstream) acc_get_cuda_stream (0);
+ if (stream != NULL)
+ abort ();
+
+ r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, stream))
+ abort ();
+
+ start_timer (0);
+
+ acc_wait_all_async (0);
+
+ acc_wait (0);
+
+ atime = stop_timer (0);
+
+ if (0.010 < atime)
+ {
+ fprintf (stderr, "actual time too long\n");
+ abort ();
+ }
+
+ fini_timers ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,66 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <openacc.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 100;
+ int i;
+ CUstream *streams;
+ CUstream s;
+ CUresult r;
+
+ acc_init (acc_device_nvidia);
+
+ (void) acc_get_device_num (acc_device_nvidia);
+
+ streams = (CUstream *) malloc (N * sizeof (void *));
+
+ for (i = 0; i < N; i++)
+ {
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ int j;
+ int cnt;
+
+ cnt = 0;
+
+ s = streams[i];
+
+ for (j = 0; j < N; j++)
+ {
+ if (s == streams[j])
+ cnt++;
+ }
+
+ if (cnt != 1)
+ abort ();
+ }
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,52 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <stdio.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 100;
+ int i;
+ CUstream *streams;
+ CUstream s;
+ CUresult r;
+
+ acc_init (acc_device_nvidia);
+
+ (void) acc_get_device_num (acc_device_nvidia);
+
+ streams = (CUstream *) malloc (N * sizeof (void *));
+
+ for (i = 0; i < N; i++)
+ {
+ streams[i] = (CUstream) acc_get_cuda_stream (i);
+ if (streams[i] != NULL)
+ abort ();
+
+ r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (i, streams[i]))
+ abort ();
+ }
+
+ s = NULL;
+
+ if (acc_set_cuda_stream (N + 1, s) != 0)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ exit (0);
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ if (acc_get_current_cuda_device () != 0)
+ abort ();
+
+ acc_init (acc_device_host);
+
+ if (acc_get_current_cuda_device () != 0)
+ abort ();
+
+ acc_shutdown (acc_device_host);
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ if (acc_get_current_cuda_device () != 0)
+ abort ();
+
+ acc_init (acc_device_nvidia);
+
+ if (acc_get_current_cuda_device () == 0)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ if (acc_get_current_cuda_device () != 0)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,42 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ if (acc_get_current_cuda_context () != 0)
+ abort ();
+
+ acc_init (acc_device_host);
+
+ if (acc_get_current_cuda_context () != 0)
+ abort ();
+
+ acc_shutdown (acc_device_host);
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ if (acc_get_current_cuda_context () != 0)
+ abort ();
+
+ acc_init (acc_device_nvidia);
+
+ if (acc_get_current_cuda_context () == 0)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ if (acc_get_current_cuda_context () != 0)
+ abort ();
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,111 @@
+/* { dg-do run } */
+
+#include <stdio.h>
+#include <pthread.h>
+#include <string.h>
+#include <stdlib.h>
+#include <ctype.h>
+#include <openacc.h>
+
+unsigned char *x;
+void *d_x;
+const int N = 256;
+
+static void *
+test (void *arg)
+{
+ int i;
+
+ if (acc_get_current_cuda_context () != NULL)
+ abort ();
+
+ if (acc_is_present (x, N) != 1)
+ abort ();
+
+ memset (x, 0, N);
+
+ acc_copyout (x, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (x[i] != i)
+ abort ();
+
+ x[i] = N - i - 1;
+ }
+
+ d_x = acc_copyin (x, N);
+
+ return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+ const int nthreads = 1;
+ int i;
+ pthread_attr_t attr;
+ pthread_t *tid;
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ acc_init (acc_device_nvidia);
+
+ x = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ x[i] = i;
+ }
+
+ d_x = acc_copyin (x, N);
+
+ if (acc_is_present (x, N) != 1)
+ abort ();
+
+ if (pthread_attr_init (&attr) != 0)
+ perror ("pthread_attr_init failed");
+
+ tid = (pthread_t *) malloc (nthreads * sizeof (pthread_t));
+
+ for (i = 0; i < nthreads; i++)
+ {
+ if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+ != 0)
+ perror ("pthread_create failed");
+ }
+
+ if (pthread_attr_destroy (&attr) != 0)
+ perror ("pthread_attr_destroy failed");
+
+ for (i = 0; i < nthreads; i++)
+ {
+ void *res;
+
+ if (pthread_join (tid[i], &res) != 0)
+ perror ("pthread join failed");
+ }
+
+ if (acc_is_present (x, N) != 1)
+ abort ();
+
+ memset (x, 0, N);
+
+ acc_copyout (x, N);
+
+ for (i = 0; i < N; i++)
+ {
+ if (x[i] != N - i - 1)
+ abort ();
+ }
+
+ if (acc_is_present (x, N) != 0)
+ abort ();
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,118 @@
+/* { dg-do run } */
+
+#include <stdio.h>
+#include <pthread.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <ctype.h>
+#include <openacc.h>
+
+unsigned char **x;
+void **d_x;
+const int N = 16;
+const int NTHREADS = 32;
+
+static void *
+test (void *arg)
+{
+ int i;
+ int tid;
+ unsigned char *p;
+ int devnum;
+
+ tid = (int) (long) arg;
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+ acc_set_device_num (devnum, acc_device_nvidia);
+
+ if (acc_get_current_cuda_context () == NULL)
+ abort ();
+
+ p = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ p[i] = tid;
+ }
+
+ x[tid] = p;
+
+ d_x[tid] = acc_copyin (p, N);
+
+ return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+ int i;
+ pthread_attr_t attr;
+ pthread_t *tid;
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ acc_init (acc_device_nvidia);
+
+ x = (unsigned char **) malloc (NTHREADS * N);
+ d_x = (void **) malloc (NTHREADS * N);
+
+ if (pthread_attr_init (&attr) != 0)
+ perror ("pthread_attr_init failed");
+
+ tid = (pthread_t *) malloc (NTHREADS * sizeof (pthread_t));
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+ != 0)
+ perror ("pthread_create failed");
+ }
+
+ if (pthread_attr_destroy (&attr) != 0)
+ perror ("pthread_attr_destroy failed");
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ void *res;
+
+ if (pthread_join (tid[i], &res) != 0)
+ perror ("pthread join failed");
+ }
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ if (acc_is_present (x[i], N) != 1)
+ abort ();
+ }
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ memset (x[i], 0, N);
+ acc_copyout (x[i], N);
+ }
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ unsigned char *p;
+ int j;
+
+ p = x[i];
+
+ for (j = 0; j < N; j++)
+ {
+ if (p[j] != i)
+ abort ();
+ }
+
+ if (acc_is_present (x[i], N) != 0)
+ abort ();
+ }
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,70 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+#include <openacc.h>
+
+int
+main (int argc, char **argv)
+{
+ int i;
+ int num_devices;
+ int devnum;
+ acc_device_t devtype = acc_device_host;
+
+#if ACC_DEVICE_TYPE_nvidia
+ devtype = acc_device_nvidia;
+#endif
+
+ num_devices = acc_get_num_devices (devtype);
+ if (num_devices == 0)
+ return 0;
+
+ acc_init (devtype);
+
+ for (i = 0; i < num_devices; i++)
+ {
+ acc_set_device_num (i, devtype);
+ devnum = acc_get_device_num (devtype);
+ if (devnum != i)
+ abort ();
+ }
+
+ acc_shutdown (devtype);
+
+ num_devices = acc_get_num_devices (devtype);
+ if (num_devices == 0)
+ abort ();
+
+ for (i = 0; i < num_devices; i++)
+ {
+ acc_set_device_num (i, devtype);
+ devnum = acc_get_device_num (devtype);
+ if (devnum != i)
+ abort ();
+ }
+
+ acc_shutdown (devtype);
+
+ acc_init (devtype);
+
+ acc_set_device_num (0, devtype);
+
+ devnum = acc_get_device_num (devtype);
+ if (devnum != 0)
+ abort ();
+
+ if (num_devices > 1)
+ {
+ acc_set_device_num (1, (acc_device_t) 0);
+
+ devnum = acc_get_device_num (devtype);
+ if (devnum != 1)
+ abort ();
+ }
+
+ acc_shutdown (devtype);
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,137 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <pthread.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <ctype.h>
+#include <openacc.h>
+#include <cuda.h>
+
+unsigned char **x;
+void **d_x;
+const int N = 16;
+const int NTHREADS = 32;
+
+static void *
+test (void *arg)
+{
+ int i;
+ int tid;
+ unsigned char *p;
+ int devnum;
+
+ tid = (int) (long) arg;
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+ acc_set_device_num (devnum, acc_device_nvidia);
+
+ if (acc_get_current_cuda_context () == NULL)
+ abort ();
+
+ p = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ p[i] = tid;
+ }
+
+ x[tid] = p;
+
+ d_x[tid] = acc_copyin (p, N);
+
+ acc_wait_all ();
+
+ return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+ int i;
+ pthread_attr_t attr;
+ pthread_t *tid;
+ CUresult r;
+ CUstream s;
+
+ acc_init (acc_device_nvidia);
+
+ x = (unsigned char **) malloc (NTHREADS * N);
+ d_x = (void **) malloc (NTHREADS * N);
+
+ if (pthread_attr_init (&attr) != 0)
+ perror ("pthread_attr_init failed");
+
+ tid = (pthread_t *) malloc (NTHREADS * sizeof (pthread_t));
+
+ r = cuStreamCreate (&s, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, s))
+ abort ();
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+ != 0)
+ perror ("pthread_create failed");
+ }
+
+ if (pthread_attr_destroy (&attr) != 0)
+ perror ("pthread_attr_destroy failed");
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ void *res;
+
+ if (pthread_join (tid[i], &res) != 0)
+ perror ("pthread join failed");
+ }
+
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ if (acc_is_present (x[i], N) != 1)
+ abort ();
+ }
+
+ acc_get_cuda_stream (1);
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ memset (x[i], 0, N);
+ acc_copyout (x[i], N);
+ }
+
+ acc_wait_all ();
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ unsigned char *p;
+ int j;
+
+ p = x[i];
+
+ for (j = 0; j < N; j++)
+ {
+ if (p[j] != i)
+ abort ();
+ }
+
+ if (acc_is_present (x[i], N) != 0)
+ abort ();
+ }
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,84 @@
+/* { dg-do run { target openacc_nvidia_accel_selected } } */
+/* { dg-additional-options "-lcuda" } */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <openacc.h>
+#include <sys/time.h>
+#include <stdio.h>
+#include <cuda.h>
+
+int
+main (int argc, char **argv)
+{
+ const int N = 1024 * 1024;
+ int i;
+ unsigned char *h;
+ void *d;
+ float async, sync;
+ struct timeval start, stop;
+ CUresult r;
+ CUstream s;
+
+ acc_init (acc_device_nvidia);
+
+ h = (unsigned char *) malloc (N);
+
+ for (i = 0; i < N; i++)
+ {
+ h[i] = i;
+ }
+
+ d = acc_malloc (N);
+
+ acc_map_data (h, d, N);
+
+ gettimeofday (&start, NULL);
+
+ for (i = 0; i < 100; i++)
+ {
+#pragma acc update device(h[0:N])
+ }
+
+ gettimeofday (&stop, NULL);
+
+ sync = (float) (stop.tv_sec - start.tv_sec);
+ sync += (float) ((stop.tv_usec - start.tv_usec) / 1000000.0);
+
+ gettimeofday (&start, NULL);
+
+ r = cuStreamCreate (&s, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ if (!acc_set_cuda_stream (0, s))
+ abort ();
+
+ for (i = 0; i < 100; i++)
+ {
+#pragma acc update device(h[0:N]) async(0)
+ }
+
+ acc_wait_all ();
+
+ gettimeofday (&stop, NULL);
+
+ async = (float) (stop.tv_sec - start.tv_sec);
+ async += (float) ((stop.tv_usec - start.tv_usec) / 1000000.0);
+
+ if (async > (sync * 1.5))
+ abort ();
+
+ acc_free (d);
+
+ free (h);
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,112 @@
+/* { dg-do run } */
+
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <ctype.h>
+#include <openacc.h>
+
+unsigned char **x;
+void **d_x;
+const int N = 32;
+const int NTHREADS = 32;
+
+static void *
+test (void *arg)
+{
+ int i;
+ int tid;
+ unsigned char *p;
+ int devnum;
+
+ tid = (int) (long) arg;
+
+ devnum = acc_get_device_num (acc_device_nvidia);
+ acc_set_device_num (devnum, acc_device_nvidia);
+
+ if (acc_get_current_cuda_context () == NULL)
+ abort ();
+
+ acc_copyout (x[tid], N);
+
+ p = x[tid];
+
+ for (i = 0; i < N; i++)
+ {
+ if (p[i] != i)
+ abort ();
+ }
+
+ return 0;
+}
+
+int
+main (int argc, char **argv)
+{
+ int i;
+ pthread_attr_t attr;
+ pthread_t *tid;
+ unsigned char *p;
+
+ if (acc_get_num_devices (acc_device_nvidia) == 0)
+ return 0;
+
+ acc_init (acc_device_nvidia);
+
+ x = (unsigned char **) malloc (NTHREADS * N);
+ d_x = (void **) malloc (NTHREADS * N);
+
+ for (i = 0; i < N; i++)
+ {
+ int j;
+
+ p = (unsigned char *) malloc (N);
+
+ x[i] = p;
+
+ for (j = 0; j < N; j++)
+ {
+ p[j] = j;
+ }
+
+ d_x[i] = acc_copyin (p, N);
+ }
+
+ if (pthread_attr_init (&attr) != 0)
+ perror ("pthread_attr_init failed");
+
+ tid = (pthread_t *) malloc (NTHREADS * sizeof (pthread_t));
+
+ acc_get_cuda_stream (1);
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ if (pthread_create (&tid[i], &attr, &test, (void *) (unsigned long) (i))
+ != 0)
+ perror ("pthread_create failed");
+ }
+
+ if (pthread_attr_destroy (&attr) != 0)
+ perror ("pthread_attr_destroy failed");
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ void *res;
+
+ if (pthread_join (tid[i], &res) != 0)
+ perror ("pthread join failed");
+ }
+
+ for (i = 0; i < NTHREADS; i++)
+ {
+ if (acc_is_present (x[i], N) != 0)
+ abort ();
+ }
+
+ acc_shutdown (acc_device_nvidia);
+
+ return 0;
+}
+
+/* { dg-output "" } */
new file mode 100644
@@ -0,0 +1,680 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b, *c, *d;
+ int i;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+ c = (float *) malloc (N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc data copyin (a[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 1.0;
+ }
+
+#pragma acc data copyin (a[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+ d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc data present_or_copyin (a[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc data copyin (a[0:N]) present_or_copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 2.0;
+ }
+
+ d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc data copyin (a[0:N]) present_or_copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 2.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 4.0;
+ }
+
+#pragma acc data copy (a[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = a[ii] + 1;
+ b[ii] = a[ii] + 2;
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 7.0;
+ }
+
+#pragma acc data present_or_copy (a[0:N]) present_or_copy (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = a[ii] + 1;
+ b[ii] = b[ii] + 2;
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 9.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 7.0;
+ }
+
+ d = (float *) acc_copyin (&a[0], N * sizeof (float));
+ d = (float *) acc_copyin (&b[0], N * sizeof (float));
+
+#pragma acc data present_or_copy (a[0:N]) present_or_copy (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = a[ii] + 1;
+ b[ii] = b[ii] + 2;
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 7.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_deviceptr (&a[0]);
+ acc_unmap_data (&a[0]);
+ acc_free (d);
+
+ d = (float *) acc_deviceptr (&b[0]);
+ acc_unmap_data (&b[0]);
+ acc_free (d);
+
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 7.0;
+ }
+
+#pragma acc data copyin (a[0:N]) create (c[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&c[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 8.0;
+ }
+
+#pragma acc data copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&c[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 2.0;
+ b[i] = 5.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc data copyin (a[0:N]) present_or_create (c[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 2.0)
+ abort ();
+
+ if (b[i] != 2.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_deviceptr (c);
+
+ acc_unmap_data (c);
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 8.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc data copyin (a[0:N]) present (c[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ acc_unmap_data (c);
+
+ if (acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (b, d, N * sizeof (float));
+
+ if (!acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (a, d, N * sizeof (float));
+
+ if (!acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+#pragma acc data present (a[0:N]) present (c[0:N]) present (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ a[ii] = 1.0;
+ c[ii] = 2.0;
+ b[ii] = 4.0;
+ }
+ }
+ }
+
+ if (!acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (c, (N * sizeof (float))))
+ abort ();
+
+ acc_copyout (b, N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ d = (float *) acc_deviceptr (a);
+
+ acc_unmap_data (a);
+
+ acc_free (d);
+
+ d = (float *) acc_deviceptr (c);
+
+ acc_unmap_data (c);
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 6.0;
+ }
+
+ d = (float *) acc_malloc (N * sizeof (float));
+
+#pragma acc parallel copyin (a[0:N]) deviceptr (d) copyout (b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ d[ii] = a[ii];
+ b[ii] = d[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+ d = (float *) acc_copyin (&a[0], N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc data pcopyin (a[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ acc_free (d);
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc data copyin (a[0:N]) pcopyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 7.0;
+ }
+
+#pragma acc data copyin (a[0:N]) pcreate (c[0:N]) copyout (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ if (acc_is_present (&c[0], (N * sizeof (float))))
+ abort ();
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run } */
+
+#include <stdlib.h>
+
+int
+main (int argc, char *argv[])
+{
+#define N 10
+ char a[N];
+
+ {
+ int i;
+ for (i = 0; i < N; ++i)
+ a[i] = 0;
+ }
+
+#pragma acc data copyout (a)
+ {
+#pragma acc parallel /* will result in a "dummy frame" */ present (a)
+ {
+ int i;
+ for (i = 0; i < N; ++i)
+ a[i] = i;
+ }
+ }
+
+ {
+ int i;
+ for (i = 0; i < N; ++i)
+ if (a[i] != i)
+ abort ();
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,97 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main(int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b;
+ int i;
+
+ a = (float *) malloc(N * sizeof (float));
+ b = (float *) malloc(N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 2.0;
+ b[i] = 5.0;
+ }
+
+#pragma acc parallel copyin(a[2:4]) copyout(b[2:4])
+ {
+ b[2] = a[2];
+ b[3] = a[3];
+ }
+
+ for (i = 2; i < 4; i++)
+ {
+ if (a[i] != 2.0)
+ abort();
+
+ if (b[i] != 2.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 1.0;
+ }
+
+#pragma acc parallel copyin(a[0:4]) copyout(b[0:4])
+ {
+ b[0] = a[0];
+ b[1] = a[1];
+ b[2] = a[2];
+ b[3] = a[3];
+ }
+
+ for (i = 0; i < 4; i++)
+ {
+ if (a[i] != 3.0)
+ abort();
+
+ if (b[i] != 3.0)
+ abort();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ b[i] = 6.0;
+ }
+
+#pragma acc parallel copyin(a[0:4]) copyout(b[4:4])
+ {
+ b[4] = a[0];
+ b[5] = a[1];
+ b[6] = a[2];
+ b[7] = a[3];
+ }
+
+ for (i = 0; i < 4; i++)
+ {
+ if (a[i] != 9.0)
+ abort();
+ }
+
+ for (i = 4; i < 8; i++)
+ {
+ if (b[i] != 9.0)
+ abort();
+ }
+
+ if (acc_is_present (a, (N * sizeof (float))))
+ abort();
+
+ if (acc_is_present (b, (N * sizeof (float))))
+ abort();
+
+ return 0;
+}
@@ -1,6 +1,6 @@
/* { dg-do run } */
-extern void abort ();
+#include <stdlib.h>
int i;
@@ -8,7 +8,6 @@ int main(void)
{
int j, v;
-#if 0
i = -1;
j = -2;
v = 0;
@@ -22,8 +21,13 @@ int main(void)
abort ();
v = 1;
}
+#if ACC_MEM_SHARED
+ if (v != 1 || i != 2 || j != 1)
+ abort ();
+#else
if (v != 1 || i != -1 || j != -2)
abort ();
+#endif
i = -1;
j = -2;
@@ -66,6 +70,10 @@ int main(void)
abort ();
v = 1;
}
+#if ACC_MEM_SHARED
+ if (v != 1 || i != 2 || j != 1)
+ abort ();
+#else
if (v != 1 || i != -1 || j != -2)
abort ();
#endif
@@ -83,8 +91,15 @@ int main(void)
abort ();
v = 1;
}
+ if (v != 1)
+ abort ();
+#if ACC_MEM_SHARED
+ if (v != 1 || i != 2 || j != 1)
+ abort ();
+#else
if (v != 1 || i != -1 || j != -2)
abort ();
+#endif
i = -1;
j = -2;
@@ -127,43 +142,64 @@ int main(void)
abort ();
v = 1;
}
+ if (v != 1)
+ abort ();
+#if ACC_MEM_SHARED
+ if (v != 1 || i != 2 || j != 1)
+ abort ();
+#else
if (v != 1 || i != -1 || j != -2)
abort ();
+#endif
-#if 0
i = -1;
j = -2;
v = 0;
-#pragma acc parallel /* copyout */ present_or_copyout (v) present (i, j)
+
+#pragma acc data copyin (i, j)
{
- if (i != -1 || j != -2)
- abort ();
- i = 2;
- j = 1;
- if (i != 2 || j != 1)
- abort ();
- v = 1;
+#pragma acc parallel /* copyout */ present_or_copyout (v) present (i, j)
+ {
+ if (i != -1 || j != -2)
+ abort ();
+ i = 2;
+ j = 1;
+ if (i != 2 || j != 1)
+ abort ();
+ v = 1;
+ }
}
+#if ACC_MEM_SHARED
if (v != 1 || i != 2 || j != 1)
abort ();
+#else
+ if (v != 1 || i != -1 || j != -2)
+ abort ();
#endif
-#if 0
i = -1;
j = -2;
v = 0;
-#pragma acc parallel /* copyout */ present_or_copyout (v)
+
+#pragma acc data copyin(i, j)
{
- if (i != -1 || j != -2)
- abort ();
- i = 2;
- j = 1;
- if (i != 2 || j != 1)
- abort ();
- v = 1;
+#pragma acc parallel /* copyout */ present_or_copyout (v)
+ {
+ if (i != -1 || j != -2)
+ abort ();
+ i = 2;
+ j = 1;
+ if (i != 2 || j != 1)
+ abort ();
+ v = 1;
+ }
}
+#if ACC_MEM_SHARED
if (v != 1 || i != 2 || j != 1)
abort ();
+#else
+ if (v != 1 || i != -1 || j != -2)
+ abort ();
#endif
return 0;
new file mode 100644
@@ -0,0 +1,35 @@
+/* { dg-do run } */
+
+/* PR middle-end/63247 */
+
+#include <stdlib.h>
+
+int
+main(int argc, char **argv)
+{
+#define N 4
+ short a[N];
+
+ a[0] = 10;
+ a[1] = 10;
+ a[2] = 10;
+ a[3] = 10;
+
+#pragma acc parallel copy(a[1:N-1])
+ {
+ a[1] = 51;
+ a[2] = 52;
+ a[3] = 53;
+ }
+
+ if (a[0] != 10)
+ abort ();
+ if (a[1] != 51)
+ abort ();
+ if (a[2] != 52)
+ abort ();
+ if (a[3] != 53)
+ abort ();
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b, *c, *d;
+ int i;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+ c = (float *) malloc (N * sizeof (float));
+
+ d = (float *) acc_malloc (N * sizeof (float));
+ acc_map_data (c, d, N * sizeof (float));
+
+#pragma acc data present (a[0:N]) present (c[0:N]) present (b[0:N])
+ {
+#pragma acc parallel
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ c[ii] = a[ii];
+ b[ii] = c[ii];
+ }
+ }
+ }
+
+ d = (float *) acc_deviceptr (c);
+ acc_unmap_data (c);
+ acc_free (d);
+
+ free (a);
+ free (b);
+ free (c);
+
+ return 0;
+}
+/* { dg-shouldfail "libgomp: present clause: !acc_is_present" } */
new file mode 100644
@@ -0,0 +1,48 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <stdlib.h>
+
+int
+main (int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b;
+ int i;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 4.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc data copyin(a[0:N]) copyout(b[0:N])
+ {
+
+#pragma acc parallel present(a[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ {
+ b[ii] = a[ii];
+ }
+ }
+
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 4.0)
+ abort ();
+
+ if (b[i] != 4.0)
+ abort ();
+ }
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,64 @@
+
+extern "C" __global__ void
+delay (clock_t * d_o, clock_t delay)
+{
+ clock_t start, ticks;
+
+ start = clock ();
+
+ ticks = 0;
+
+ while (ticks < delay)
+ ticks = clock () - start;
+}
+
+extern "C" __global__ void
+delay2 (unsigned long *d_o, clock_t delay, unsigned long tid)
+{
+ clock_t start, ticks;
+
+ start = clock ();
+
+ ticks = 0;
+
+ while (ticks < delay)
+ ticks = clock () - start;
+
+ d_o[0] = tid;
+}
+
+extern "C" __global__ void
+sum (clock_t * d_o, int N)
+{
+ int i;
+ clock_t sum;
+ __shared__ clock_t ticks[32];
+
+ sum = 0;
+
+ for (i = threadIdx.x; i < N; i += blockDim.x)
+ sum += d_o[i];
+
+ ticks[threadIdx.x] = sum;
+
+ syncthreads ();
+
+ for (i = 16; i >= 1; i >>= 1)
+ {
+ if (threadIdx.x < i)
+ ticks[threadIdx.x] += ticks[threadIdx.x + i];
+
+ syncthreads ();
+ }
+
+ d_o[0] = ticks[0];
+}
+
+extern "C" __global__ void
+mult (int n, float *x, float *y)
+{
+ int i = blockIdx.x * blockDim.x + threadIdx.x;
+
+ for (i = 0; i < n; i++)
+ y[i] = x[i] * x[i];
+}
new file mode 100644
@@ -0,0 +1,148 @@
+// BEGIN PREAMBLE
+ .version 3.1
+ .target sm_30
+ .address_size 64
+// END PREAMBLE
+
+// BEGIN FUNCTION DEF: clock
+.func (.param.u32 %out_retval)clock
+{
+.reg.u32 %retval;
+ .reg.u64 %hr10;
+ .reg.u32 %r22;
+ .reg.u32 %r23;
+ .reg.u32 %r24;
+ .local.align 8 .b8 %frame[8];
+ // #APP
+// 7 "subr.c" 1
+ mov.u32 %r24, %clock;
+// 0 "" 2
+ // #NO_APP
+ st.local.u32 [%frame], %r24;
+ ld.local.u32 %r22, [%frame];
+ mov.u32 %r23, %r22;
+ mov.u32 %retval, %r23;
+ st.param.u32 [%out_retval], %retval;
+ ret;
+ }
+// END FUNCTION DEF
+// BEGIN GLOBAL FUNCTION DEF: delay
+.visible .entry delay(.param.u64 %in_ar1, .param.u64 %in_ar2)
+{
+ .reg.u64 %ar1;
+ .reg.u64 %ar2;
+ .reg.u64 %hr10;
+ .reg.u64 %r22;
+ .reg.u32 %r23;
+ .reg.u64 %r24;
+ .reg.u64 %r25;
+ .reg.u32 %r26;
+ .reg.u32 %r27;
+ .reg.u32 %r28;
+ .reg.u32 %r29;
+ .reg.u32 %r30;
+ .reg.u64 %r31;
+ .reg.pred %r32;
+ .local.align 8 .b8 %frame[24];
+ ld.param.u64 %ar1, [%in_ar1];
+ ld.param.u64 %ar2, [%in_ar2];
+ mov.u64 %r24, %ar1;
+ st.u64 [%frame+8], %r24;
+ mov.u64 %r25, %ar2;
+ st.local.u64 [%frame+16], %r25;
+ {
+ .param.u32 %retval_in;
+ {
+ call (%retval_in), clock;
+ }
+ ld.param.u32 %r26, [%retval_in];
+}
+ st.local.u32 [%frame+4], %r26;
+ mov.u32 %r27, 0;
+ st.local.u32 [%frame], %r27;
+ bra $L4;
+$L5:
+ {
+ .param.u32 %retval_in;
+ {
+ call (%retval_in), clock;
+ }
+ ld.param.u32 %r28, [%retval_in];
+}
+ mov.u32 %r23, %r28;
+ ld.local.u32 %r30, [%frame+4];
+ sub.u32 %r29, %r23, %r30;
+ st.local.u32 [%frame], %r29;
+$L4:
+ ld.local.s32 %r22, [%frame];
+ ld.local.u64 %r31, [%frame+16];
+ setp.lo.u64 %r32,%r22,%r31;
+ @%r32 bra $L5;
+ ret;
+ }
+// END FUNCTION DEF
+// BEGIN GLOBAL FUNCTION DEF: delay2
+.visible .entry delay2(.param.u64 %in_ar1, .param.u64 %in_ar2, .param.u64 %in_ar3)
+{
+ .reg.u64 %ar1;
+ .reg.u64 %ar2;
+ .reg.u64 %ar3;
+ .reg.u64 %hr10;
+ .reg.u64 %r22;
+ .reg.u32 %r23;
+ .reg.u64 %r24;
+ .reg.u64 %r25;
+ .reg.u64 %r26;
+ .reg.u32 %r27;
+ .reg.u32 %r28;
+ .reg.u32 %r29;
+ .reg.u32 %r30;
+ .reg.u32 %r31;
+ .reg.u64 %r32;
+ .reg.pred %r33;
+ .reg.u64 %r34;
+ .reg.u64 %r35;
+ .local.align 8 .b8 %frame[32];
+ ld.param.u64 %ar1, [%in_ar1];
+ ld.param.u64 %ar2, [%in_ar2];
+ ld.param.u64 %ar3, [%in_ar3];
+ mov.u64 %r24, %ar1;
+ st.local.u64 [%frame+8], %r24;
+ mov.u64 %r25, %ar2;
+ st.local.u64 [%frame+16], %r25;
+ mov.u64 %r26, %ar3;
+ st.local.u64 [%frame+24], %r26;
+ {
+ .param.u32 %retval_in;
+ {
+ call (%retval_in), clock;
+ }
+ ld.param.u32 %r27, [%retval_in];
+}
+ st.local.u32 [%frame+4], %r27;
+ mov.u32 %r28, 0;
+ st.local.u32 [%frame], %r28;
+ bra $L8;
+$L9:
+ {
+ .param.u32 %retval_in;
+ {
+ call (%retval_in), clock;
+ }
+ ld.param.u32 %r29, [%retval_in];
+}
+ mov.u32 %r23, %r29;
+ ld.local.u32 %r31, [%frame+4];
+ sub.u32 %r30, %r23, %r31;
+ st.local.u32 [%frame], %r30;
+$L8:
+ ld.local.s32 %r22, [%frame];
+ ld.local.u64 %r32, [%frame+16];
+ setp.lo.u64 %r33,%r22,%r32;
+ @%r33 bra $L9;
+ ld.local.u64 %r34, [%frame+8];
+ ld.local.u64 %r35, [%frame+24];
+ st.u64 [%r34], %r35;
+ ret;
+ }
+// END FUNCTION DEF
new file mode 100644
@@ -0,0 +1,103 @@
+
+#include <stdio.h>
+#include <cuda.h>
+
+static int _Tnum_timers;
+static CUevent *_Tstart_events, *_Tstop_events;
+static CUstream _Tstream;
+
+void
+init_timers (int ntimers)
+{
+ int i;
+ CUresult r;
+
+ _Tnum_timers = ntimers;
+
+ _Tstart_events = (CUevent *) malloc (_Tnum_timers * sizeof (CUevent));
+ _Tstop_events = (CUevent *) malloc (_Tnum_timers * sizeof (CUevent));
+
+ r = cuStreamCreate (&_Tstream, CU_STREAM_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuStreamCreate failed: %d\n", r);
+ abort ();
+ }
+
+ for (i = 0; i < _Tnum_timers; i++)
+ {
+ r = cuEventCreate (&_Tstart_events[i], CU_EVENT_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuEventCreate failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuEventCreate (&_Tstop_events[i], CU_EVENT_DEFAULT);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuEventCreate failed: %d\n", r);
+ abort ();
+ }
+ }
+}
+
+void
+fini_timers (void)
+{
+ int i;
+
+ for (i = 0; i < _Tnum_timers; i++)
+ {
+ cuEventDestroy (_Tstart_events[i]);
+ cuEventDestroy (_Tstop_events[i]);
+ }
+
+ cuStreamDestroy (_Tstream);
+
+ free (_Tstart_events);
+ free (_Tstop_events);
+}
+
+void
+start_timer (int timer)
+{
+ CUresult r;
+
+ r = cuEventRecord (_Tstart_events[timer], _Tstream);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuEventRecord failed: %d\n", r);
+ abort ();
+ }
+}
+
+float
+stop_timer (int timer)
+{
+ CUresult r;
+ float etime;
+
+ r = cuEventRecord (_Tstop_events[timer], _Tstream);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuEventRecord failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuEventSynchronize (_Tstop_events[timer]);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuEventSynchronize failed: %d\n", r);
+ abort ();
+ }
+
+ r = cuEventElapsedTime (&etime, _Tstart_events[timer], _Tstop_events[timer]);
+ if (r != CUDA_SUCCESS)
+ {
+ fprintf (stderr, "cuEventElapsedTime failed: %d\n", r);
+ abort ();
+ }
+
+ return etime;
+}
new file mode 100644
@@ -0,0 +1,280 @@
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-DACC_MEM_SHARED=0" } } */
+
+#include <openacc.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+
+int
+main (int argc, char **argv)
+{
+ int N = 8;
+ float *a, *b, *c;
+ float *d_a, *d_b, *d_c;
+ int i;
+
+ a = (float *) malloc (N * sizeof (float));
+ b = (float *) malloc (N * sizeof (float));
+ c = (float *) malloc (N * sizeof (float));
+
+ d_a = (float *) acc_malloc (N * sizeof (float));
+ d_b = (float *) acc_malloc (N * sizeof (float));
+ d_c = (float *) acc_malloc (N * sizeof (float));
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 3.0;
+ b[i] = 0.0;
+ }
+
+ acc_map_data (a, d_a, N * sizeof (float));
+ acc_map_data (b, d_b, N * sizeof (float));
+ acc_map_data (c, d_c, N * sizeof (float));
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 3.0)
+ abort ();
+
+ if (b[i] != 3.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 1.0;
+ }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ b[i] = 1.0;
+ }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update self (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ b[i] = 0.0;
+ }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 6.0)
+ abort ();
+
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 7.0;
+ b[i] = 2.0;
+ }
+
+#pragma acc update device (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 7.0)
+ abort ();
+
+ if (b[i] != 7.0)
+ abort ();
+ }
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 9.0;
+ }
+
+#pragma acc update device (a[0:N])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ if (a[i] != 9.0)
+ abort ();
+
+ if (b[i] != 9.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 5.0;
+ }
+
+#pragma acc update device (a[0:N])
+
+ for (i = 0; i < N; i++)
+ {
+ a[i] = 6.0;
+ }
+
+#pragma acc update device (a[0:N >> 1])
+
+#pragma acc parallel present (a[0:N], b[0:N])
+ {
+ int ii;
+
+ for (ii = 0; ii < N; ii++)
+ b[ii] = a[ii];
+ }
+
+#pragma acc update host (a[0:N], b[0:N])
+
+ for (i = 0; i < (N >> 1); i++)
+ {
+ if (a[i] != 6.0)
+ abort ();
+
+ if (b[i] != 6.0)
+ abort ();
+ }
+
+ for (i = (N >> 1); i < N; i++)
+ {
+ if (a[i] != 5.0)
+ abort ();
+
+ if (b[i] != 5.0)
+ abort ();
+ }
+
+ if (!acc_is_present (&a[0], (N * sizeof (float))))
+ abort ();
+
+ if (!acc_is_present (&b[0], (N * sizeof (float))))
+ abort ();
+
+ return 0;
+}
new file mode 100644
@@ -0,0 +1,10 @@
+! { dg-shouldfail "" { *-*-* } { "*" } { "" } }
+
+program main
+ implicit none
+
+ !$acc parallel
+ call abort
+ !$acc end parallel
+
+end program main
new file mode 100644
@@ -0,0 +1,13 @@
+program main
+ implicit none
+
+ integer :: argc
+ argc = command_argument_count ()
+
+ !$acc parallel copyin(argc)
+ if (argc .ne. 0) then
+ call abort
+ end if
+ !$acc end parallel
+
+end program main
@@ -1,5 +1,4 @@
-! TODO: Remove -DACC_DEVICE_TYPE_host once that is set by the test harness.
-! { dg-additional-options "-cpp -DACC_DEVICE_TYPE_host" }
+! { dg-additional-options "-cpp" }
! TODO: Have to disable the acc_on_device builtin for we want to test the
! libgomp library function? The command line option
! '-fno-builtin-acc_on_device' is valid for C/C++/ObjC/ObjC++ but not for
@@ -12,7 +11,9 @@ implicit none
if (.not. acc_on_device (acc_device_none)) call abort
if (.not. acc_on_device (acc_device_host)) call abort
+if (acc_on_device (acc_device_host_nonshm)) call abort
if (acc_on_device (acc_device_not_host)) call abort
+if (acc_on_device (acc_device_nvidia)) call abort
! Host via offloading fallback mode.
@@ -20,7 +21,9 @@ if (acc_on_device (acc_device_not_host)) call abort
!$acc parallel if(.false.)
if (.not. acc_on_device (acc_device_none)) call abort
if (.not. acc_on_device (acc_device_host)) call abort
+if (acc_on_device (acc_device_host_nonshm)) call abort
if (acc_on_device (acc_device_not_host)) call abort
+if (acc_on_device (acc_device_nvidia)) call abort
!$acc end parallel
@@ -31,7 +34,17 @@ if (acc_on_device (acc_device_not_host)) call abort
!$acc parallel
if (acc_on_device (acc_device_none)) call abort
if (acc_on_device (acc_device_host)) call abort
+#if ACC_DEVICE_TYPE_host_nonshm
+if (.not. acc_on_device (acc_device_host_nonshm)) call abort
+#else
+if (acc_on_device (acc_device_host_nonshm)) call abort
+#endif
if (.not. acc_on_device (acc_device_not_host)) call abort
+#if ACC_DEVICE_TYPE_nvidia
+if (.not. acc_on_device (acc_device_nvidia)) call abort
+#else
+if (acc_on_device (acc_device_nvidia)) call abort
+#endif
!$acc end parallel
#endif
@@ -1,5 +1,4 @@
-! TODO: Remove -DACC_DEVICE_TYPE_host once that is set by the test harness.
-! { dg-additional-options "-cpp -DACC_DEVICE_TYPE_host" }
+! { dg-additional-options "-cpp" }
! TODO: Have to disable the acc_on_device builtin for we want to test
! the libgomp library function? The command line option
! '-fno-builtin-acc_on_device' is valid for C/C++/ObjC/ObjC++ but not
@@ -12,7 +11,9 @@
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
!Host via offloading fallback mode.
@@ -20,7 +21,9 @@
!$ACC PARALLEL IF(.FALSE.)
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
!$ACC END PARALLEL
@@ -31,7 +34,17 @@
!$ACC PARALLEL
IF (ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
IF (ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_host_nonshm
+ IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#else
+ IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#endif
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_nvidia
+ IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#else
+ IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#endif
!$ACC END PARALLEL
#endif
@@ -1,5 +1,4 @@
-! TODO: Remove -DACC_DEVICE_TYPE_host once that is set by the test harness.
-! { dg-additional-options "-cpp -DACC_DEVICE_TYPE_host" }
+! { dg-additional-options "-cpp" }
! TODO: Have to disable the acc_on_device builtin for we want to test
! the libgomp library function? The command line option
! '-fno-builtin-acc_on_device' is valid for C/C++/ObjC/ObjC++ but not
@@ -12,7 +11,9 @@
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
!Host via offloading fallback mode.
@@ -20,7 +21,9 @@
!$ACC PARALLEL IF(.FALSE.)
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
IF (ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+ IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
!$ACC END PARALLEL
@@ -31,7 +34,17 @@
!$ACC PARALLEL
IF (ACC_ON_DEVICE (ACC_DEVICE_NONE)) CALL ABORT
IF (ACC_ON_DEVICE (ACC_DEVICE_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_host_nonshm
+ IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#else
+ IF (ACC_ON_DEVICE (ACC_DEVICE_HOST_NONSHM)) CALL ABORT
+#endif
IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NOT_HOST)) CALL ABORT
+#if ACC_DEVICE_TYPE_nvidia
+ IF (.NOT. ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#else
+ IF (ACC_ON_DEVICE (ACC_DEVICE_NVIDIA)) CALL ABORT
+#endif
!$ACC END PARALLEL
#endif
@@ -21,7 +21,8 @@ set quadmath_library_path "../libquadmath/.libs"
dg-init
# Turn on OpenACC.
-lappend ALWAYS_CFLAGS "additional_flags=-fopenacc"
+# XXX (TEMPORARY): Remove the -flto once that's properly integrated.
+lappend ALWAYS_CFLAGS "additional_flags=-fopenacc -flto"
if { $blddir != "" } {
set lang_source_re {^.*\.[fF](|90|95|03|08)$}
@@ -65,10 +66,41 @@ if { $lang_test_file_found } {
append ld_library_path [gcc-set-multilib-library-path $GCC_UNDER_TEST]
set_ld_library_path_env_vars
- # For Fortran we're doing torture testing, as Fortran has far more tests
- # with arrays etc. that testing just -O0 or -O2 is insufficient, that is
- # typically not the case for C/C++.
- gfortran-dg-runtest $tests "" ""
+ # Todo: get list of accelerators from configure options --enable-accelerator.
+ set accels { "nvidia" "host_nonshm" }
+
+ # Run on host (or fallback) accelerator.
+ lappend accels "host"
+
+ # Test OpenACC with available accelerators.
+ foreach accel $accels {
+ set tagopt "-DACC_DEVICE_TYPE_$accel=1"
+
+ # Todo: Determine shared memory or not using run-time test.
+ switch $accel {
+ host {
+ set acc_mem_shared 1
+ }
+ host_nonshm {
+ set acc_mem_shared 0
+ }
+ nvidia {
+ set acc_mem_shared 0
+ }
+ default {
+ set acc_mem_shared 0
+ }
+ }
+ set tagopt "$tagopt -DACC_MEM_SHARED=$acc_mem_shared"
+
+ # Todo: Verify that this works for both local and remote testing.
+ setenv ACC_DEVICE_TYPE $accel
+
+ # For Fortran we're doing torture testing, as Fortran has far more tests
+ # with arrays etc. that testing just -O0 or -O2 is insufficient, that is
+ # typically not the case for C/C++.
+ gfortran-dg-runtest $tests "$tagopt" ""
+ }
}
# All done.
@@ -1,3 +1,13 @@
use openacc
+if (acc_get_num_devices (acc_device_host) .ne. 1) call abort
+call acc_set_device_type (acc_device_host)
+if (acc_get_device_type () .ne. acc_device_host) call abort
+call acc_set_device_num (0, acc_device_host)
+if (acc_get_device_num (acc_device_host) .ne. 0) call abort
+call acc_shutdown (acc_device_host)
+
+call acc_init (acc_device_host)
+call acc_shutdown (acc_device_host)
+
end
new file mode 100644
@@ -0,0 +1,82 @@
+! { dg-do run }
+
+program main
+ implicit none
+ include "openacc_lib.h"
+
+ integer, target :: a_3d_i(10, 10, 10)
+ complex a_3d_c(10, 10, 10)
+ real a_3d_r(10, 10, 10)
+
+ integer i, j, k
+ complex c
+ real r
+ integer, parameter :: i_size = sizeof (i)
+ integer, parameter :: c_size = sizeof (c)
+ integer, parameter :: r_size = sizeof (r)
+
+ if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+ call acc_init (acc_device_nvidia)
+
+ call set3d (.FALSE., a_3d_i, a_3d_c, a_3d_r)
+
+ call acc_copyin (a_3d_i)
+ call acc_copyin (a_3d_c)
+ call acc_copyin (a_3d_r)
+
+ if (acc_is_present (a_3d_i) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r) .neqv. .TRUE.) call abort
+
+ do i = 1, 10
+ do j = 1, 10
+ do k = 1, 10
+ if (acc_is_present (a_3d_i(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r(i, j, k), i_size) .neqv. .TRUE.) call abort
+ end do
+ end do
+ end do
+
+ call acc_shutdown (acc_device_nvidia)
+
+contains
+
+ subroutine set3d (clear, a_i, a_c, a_r)
+ logical clear
+ integer, dimension (:,:,:), intent (inout) :: a_i
+ complex, dimension (:,:,:), intent (inout) :: a_c
+ real, dimension (:,:,:), intent (inout) :: a_r
+
+ integer i, j, k
+ integer lb1, ub1, lb2, ub2, lb3, ub3
+
+ lb1 = lbound (a_i, 1)
+ ub1 = ubound (a_i, 1)
+
+ lb2 = lbound (a_i, 2)
+ ub2 = ubound (a_i, 2)
+
+ lb3 = lbound (a_i, 3)
+ ub3 = ubound (a_i, 3)
+
+ do i = lb1, ub1
+ do j = lb2, ub2
+ do k = lb3, ub3
+ if (clear) then
+ a_i(i, j, k) = 0
+ a_c(i, j, k) = cmplx (0.0, 0.0)
+ a_r(i, j, k) = 0.0
+ else
+ a_i(i, j, k) = i
+ a_c(i, j, k) = cmplx (i, j)
+ a_r(i, j, k) = i
+ end if
+ end do
+ end do
+ end do
+
+ end subroutine
+
+end program
new file mode 100644
@@ -0,0 +1,82 @@
+! { dg-do run }
+
+program main
+ implicit none
+ include "openacc_lib.h"
+
+ integer, target :: a_3d_i(10, 10, 10)
+ complex a_3d_c(10, 10, 10)
+ real a_3d_r(10, 10, 10)
+
+ integer i, j, k
+ complex c
+ real r
+ integer, parameter :: i_size = sizeof (i)
+ integer, parameter :: c_size = sizeof (c)
+ integer, parameter :: r_size = sizeof (r)
+
+ if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+ call acc_init (acc_device_nvidia)
+
+ call set3d (.FALSE., a_3d_i, a_3d_c, a_3d_r)
+
+ call acc_copyin (a_3d_i)
+ call acc_copyin (a_3d_c)
+ call acc_copyin (a_3d_r)
+
+ if (acc_is_present (a_3d_i) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r) .neqv. .TRUE.) call abort
+
+ do i = 1, 10
+ do j = 1, 10
+ do k = 1, 10
+ if (acc_is_present (a_3d_i(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r(i, j, k), i_size) .neqv. .TRUE.) call abort
+ end do
+ end do
+ end do
+
+ call acc_shutdown (acc_device_nvidia)
+
+contains
+
+ subroutine set3d (clear, a_i, a_c, a_r)
+ logical clear
+ integer, dimension (:,:,:), intent (inout) :: a_i
+ complex, dimension (:,:,:), intent (inout) :: a_c
+ real, dimension (:,:,:), intent (inout) :: a_r
+
+ integer i, j, k
+ integer lb1, ub1, lb2, ub2, lb3, ub3
+
+ lb1 = lbound (a_i, 1)
+ ub1 = ubound (a_i, 1)
+
+ lb2 = lbound (a_i, 2)
+ ub2 = ubound (a_i, 2)
+
+ lb3 = lbound (a_i, 3)
+ ub3 = ubound (a_i, 3)
+
+ do i = lb1, ub1
+ do j = lb2, ub2
+ do k = lb3, ub3
+ if (clear) then
+ a_i(i, j, k) = 0
+ a_c(i, j, k) = cmplx (0.0, 0.0)
+ a_r(i, j, k) = 0.0
+ else
+ a_i(i, j, k) = i
+ a_c(i, j, k) = cmplx (i, j)
+ a_r(i, j, k) = i
+ end if
+ end do
+ end do
+ end do
+
+ end subroutine
+
+end program
@@ -1,3 +1,13 @@
USE OPENACC
+ IF (ACC_GET_NUM_DEVICES (ACC_DEVICE_HOST) .NE. 1) CALL ABORT
+ CALL ACC_SET_DEVICE_TYPE (ACC_DEVICE_HOST)
+ IF (ACC_GET_DEVICE_TYPE () .NE. ACC_DEVICE_HOST) CALL ABORT
+ CALL ACC_SET_DEVICE_NUM (0, ACC_DEVICE_HOST)
+ IF (ACC_GET_DEVICE_NUM (ACC_DEVICE_HOST) .NE. 0) CALL ABORT
+ CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
+ CALL ACC_INIT (ACC_DEVICE_HOST)
+ CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
END
@@ -1,3 +1,13 @@
INCLUDE "openacc_lib.h"
+ IF (ACC_GET_NUM_DEVICES (ACC_DEVICE_HOST) .NE. 1) CALL ABORT
+ CALL ACC_SET_DEVICE_TYPE (ACC_DEVICE_HOST)
+ IF (ACC_GET_DEVICE_TYPE () .NE. ACC_DEVICE_HOST) CALL ABORT
+ CALL ACC_SET_DEVICE_NUM (0, ACC_DEVICE_HOST)
+ IF (ACC_GET_DEVICE_NUM (ACC_DEVICE_HOST) .NE. 0) CALL ABORT
+ CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
+ CALL ACC_INIT (ACC_DEVICE_HOST)
+ CALL ACC_SHUTDOWN (ACC_DEVICE_HOST)
+
END
new file mode 100644
@@ -0,0 +1,35 @@
+! { dg-do run }
+
+program main
+ use openacc
+ implicit none
+
+ integer n
+
+ if (acc_get_num_devices (acc_device_host) .ne. 1) call abort
+
+ if (acc_get_num_devices (acc_device_none) .ne. 0) call abort
+
+ call acc_init (acc_device_host)
+
+ if (acc_get_device_type () .ne. acc_device_host) call abort
+
+ call acc_set_device_type (acc_device_host)
+
+ if (acc_get_device_type () .ne. acc_device_host) call abort
+
+ n = 0
+
+ call acc_set_device_num (n, acc_device_host)
+
+ if (acc_get_device_num (acc_device_host) .ne. 0) call abort
+
+ if (.NOT. acc_async_test (n) ) call abort
+
+ call acc_wait (n)
+
+ call acc_wait_all ()
+
+ call acc_shutdown (acc_device_host)
+
+end program
new file mode 100644
@@ -0,0 +1,31 @@
+! { dg-do run }
+
+program main
+ use openacc
+ implicit none
+
+ integer n
+
+ if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+ call acc_init (acc_device_nvidia)
+
+ n = 0
+
+ call acc_set_device_num (n, acc_device_nvidia)
+
+ if (acc_get_device_num (acc_device_nvidia) .ne. 0) call abort
+
+ if (acc_get_num_devices (acc_device_nvidia) .gt. 1) then
+
+ n = 1
+
+ call acc_set_device_num (n, acc_device_nvidia)
+
+ if (acc_get_device_num (acc_device_nvidia) .ne. 1) call abort
+
+ end if
+
+ call acc_shutdown (acc_device_nvidia)
+
+end program
new file mode 100644
@@ -0,0 +1,35 @@
+! { dg-do run }
+
+program main
+ implicit none
+ include "openacc_lib.h"
+
+ integer n
+
+ if (acc_get_num_devices (acc_device_host) .ne. 1) call abort
+
+ if (acc_get_num_devices (acc_device_none) .ne. 0) call abort
+
+ call acc_init (acc_device_host)
+
+ if (acc_get_device_type () .ne. acc_device_host) call abort
+
+ call acc_set_device_type (acc_device_host)
+
+ if (acc_get_device_type () .ne. acc_device_host) call abort
+
+ n = 0
+
+ call acc_set_device_num (n, acc_device_host)
+
+ if (acc_get_device_num (acc_device_host) .ne. 0) call abort
+
+ if (.NOT. acc_async_test (n) ) call abort
+
+ call acc_wait (n)
+
+ call acc_wait_all ()
+
+ call acc_shutdown (acc_device_host)
+
+end program
new file mode 100644
@@ -0,0 +1,31 @@
+! { dg-do run }
+
+program main
+ implicit none
+ include "openacc_lib.h"
+
+ integer n
+
+ if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+ call acc_init (acc_device_nvidia)
+
+ n = 0
+
+ call acc_set_device_num (n, acc_device_nvidia)
+
+ if (acc_get_device_num (acc_device_nvidia) .ne. 0) call abort
+
+ if (acc_get_num_devices (acc_device_nvidia) .gt. 1) then
+
+ n = 1
+
+ call acc_set_device_num (n, acc_device_nvidia)
+
+ if (acc_get_device_num (acc_device_nvidia) .ne. 1) call abort
+
+ end if
+
+ call acc_shutdown (acc_device_nvidia)
+
+end program
new file mode 100644
@@ -0,0 +1,83 @@
+! { dg-do run }
+
+program main
+ use openacc
+ use iso_c_binding
+ implicit none
+
+ integer, target :: a_3d_i(10, 10, 10)
+ complex a_3d_c(10, 10, 10)
+ real a_3d_r(10, 10, 10)
+
+ integer i, j, k
+ complex c
+ real r
+ integer, parameter :: i_size = sizeof (i)
+ integer, parameter :: c_size = sizeof (c)
+ integer, parameter :: r_size = sizeof (r)
+
+ if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+ call acc_init (acc_device_nvidia)
+
+ call set3d (.FALSE., a_3d_i, a_3d_c, a_3d_r)
+
+ call acc_copyin (a_3d_i)
+ call acc_copyin (a_3d_c)
+ call acc_copyin (a_3d_r)
+
+ if (acc_is_present (a_3d_i) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r) .neqv. .TRUE.) call abort
+
+ do i = 1, 10
+ do j = 1, 10
+ do k = 1, 10
+ if (acc_is_present (a_3d_i(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r(i, j, k), i_size) .neqv. .TRUE.) call abort
+ end do
+ end do
+ end do
+
+ call acc_shutdown (acc_device_nvidia)
+
+contains
+
+ subroutine set3d (clear, a_i, a_c, a_r)
+ logical clear
+ integer, dimension (:,:,:), intent (inout) :: a_i
+ complex, dimension (:,:,:), intent (inout) :: a_c
+ real, dimension (:,:,:), intent (inout) :: a_r
+
+ integer i, j, k
+ integer lb1, ub1, lb2, ub2, lb3, ub3
+
+ lb1 = lbound (a_i, 1)
+ ub1 = ubound (a_i, 1)
+
+ lb2 = lbound (a_i, 2)
+ ub2 = ubound (a_i, 2)
+
+ lb3 = lbound (a_i, 3)
+ ub3 = ubound (a_i, 3)
+
+ do i = lb1, ub1
+ do j = lb2, ub2
+ do k = lb3, ub3
+ if (clear) then
+ a_i(i, j, k) = 0
+ a_c(i, j, k) = cmplx (0.0, 0.0)
+ a_r(i, j, k) = 0.0
+ else
+ a_i(i, j, k) = i
+ a_c(i, j, k) = cmplx (i, j)
+ a_r(i, j, k) = i
+ end if
+ end do
+ end do
+ end do
+
+ end subroutine
+
+end program
new file mode 100644
@@ -0,0 +1,83 @@
+! { dg-do run }
+
+program main
+ use openacc
+ use iso_c_binding
+ implicit none
+
+ integer, target :: a_3d_i(10, 10, 10)
+ complex a_3d_c(10, 10, 10)
+ real a_3d_r(10, 10, 10)
+
+ integer i, j, k
+ complex c
+ real r
+ integer, parameter :: i_size = sizeof (i)
+ integer, parameter :: c_size = sizeof (c)
+ integer, parameter :: r_size = sizeof (r)
+
+ if (acc_get_num_devices (acc_device_nvidia) .eq. 0) call exit
+
+ call acc_init (acc_device_nvidia)
+
+ call set3d (.FALSE., a_3d_i, a_3d_c, a_3d_r)
+
+ call acc_copyin (a_3d_i)
+ call acc_copyin (a_3d_c)
+ call acc_copyin (a_3d_r)
+
+ if (acc_is_present (a_3d_i) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r) .neqv. .TRUE.) call abort
+
+ do i = 1, 10
+ do j = 1, 10
+ do k = 1, 10
+ if (acc_is_present (a_3d_i(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_c(i, j, k), i_size) .neqv. .TRUE.) call abort
+ if (acc_is_present (a_3d_r(i, j, k), i_size) .neqv. .TRUE.) call abort
+ end do
+ end do
+ end do
+
+ call acc_shutdown (acc_device_nvidia)
+
+contains
+
+ subroutine set3d (clear, a_i, a_c, a_r)
+ logical clear
+ integer, dimension (:,:,:), intent (inout) :: a_i
+ complex, dimension (:,:,:), intent (inout) :: a_c
+ real, dimension (:,:,:), intent (inout) :: a_r
+
+ integer i, j, k
+ integer lb1, ub1, lb2, ub2, lb3, ub3
+
+ lb1 = lbound (a_i, 1)
+ ub1 = ubound (a_i, 1)
+
+ lb2 = lbound (a_i, 2)
+ ub2 = ubound (a_i, 2)
+
+ lb3 = lbound (a_i, 3)
+ ub3 = ubound (a_i, 3)
+
+ do i = lb1, ub1
+ do j = lb2, ub2
+ do k = lb3, ub3
+ if (clear) then
+ a_i(i, j, k) = 0
+ a_c(i, j, k) = cmplx (0.0, 0.0)
+ a_r(i, j, k) = 0.0
+ else
+ a_i(i, j, k) = i
+ a_c(i, j, k) = cmplx (i, j)
+ a_r(i, j, k) = i
+ end if
+ end do
+ end do
+ end do
+
+ end subroutine
+
+end program
new file mode 100644
@@ -0,0 +1,97 @@
+program map
+ integer, parameter :: n = 20, c = 10
+ integer :: i, a(n), b(n)
+
+ a(:) = 0
+ b(:) = 0
+
+ ! COPY
+
+ !$acc parallel copy (a)
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ do i = 1, n
+ b(i) = i
+ end do
+
+ call check (a, b, n)
+
+ ! COPYOUT
+
+ a(:) = 0
+
+ !$acc parallel copyout (a)
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ do i = 1, n
+ if (a(i) .ne. b(i)) call abort
+ end do
+ call check (a, b, n)
+
+ ! COPYIN
+
+ a(:) = 0
+
+ !$acc parallel copyout (a) copyin (b)
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPY
+
+ !$acc parallel pcopy (a)
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPYOUT
+
+ a(:) = 0
+
+ !$acc parallel pcopyout (a)
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPYIN
+
+ a(:) = 0
+
+ !$acc parallel pcopyout (a) pcopyin (b)
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+end program map
+
+subroutine check (a, b, n)
+ integer :: n, a(n), b(n)
+ integer :: i
+
+ do i = 1, n
+ if (a(i) .ne. b(i)) call abort
+ end do
+end subroutine check
new file mode 100644
@@ -0,0 +1,21 @@
+! PR middle-end/63247
+
+program test
+ implicit none
+
+ integer(kind=2) a(4)
+
+ a = 10;
+
+ !$acc parallel copy(a(2:4))
+ a(2) = 52
+ a(3) = 53
+ a(4) = 54
+ !$acc end parallel
+
+ if (a(1) .ne. 10) call abort
+ if (a(2) .ne. 52) call abort
+ if (a(3) .ne. 53) call abort
+ if (a(4) .ne. 54) call abort
+
+end program test
new file mode 100644
@@ -0,0 +1,229 @@
+! { dg-do run }
+
+program test
+ implicit none
+ integer, allocatable :: a1(:)
+ integer, allocatable :: b1(:)
+ integer, allocatable :: c1(:)
+ integer, allocatable :: b2(:,:)
+ integer, allocatable :: c3(:,:,:)
+
+ allocate (a1(5))
+ if (.not.allocated (a1)) call abort()
+
+ a1 = 10
+
+ !$acc parallel copy(a1(1:5))
+ a1(1) = 1
+ a1(2) = 2
+ a1(3) = 3
+ a1(4) = 4
+ a1(5) = 5
+ !$acc end parallel
+
+ if (a1(1) .ne. 1) call abort
+ if (a1(2) .ne. 2) call abort
+ if (a1(3) .ne. 3) call abort
+ if (a1(4) .ne. 4) call abort
+ if (a1(5) .ne. 5) call abort
+
+ deallocate(a1)
+
+ allocate (a1(0:4))
+ if (.not.allocated (a1)) call abort()
+
+ a1 = 10
+
+ !$acc parallel copy(a1(0:4))
+ a1(0) = 1
+ a1(1) = 2
+ a1(2) = 3
+ a1(3) = 4
+ a1(4) = 5
+ !$acc end parallel
+
+ if (a1(0) .ne. 1) call abort
+ if (a1(1) .ne. 2) call abort
+ if (a1(2) .ne. 3) call abort
+ if (a1(3) .ne. 4) call abort
+ if (a1(4) .ne. 5) call abort
+
+ deallocate(a1)
+
+ allocate (b2(5,5))
+ if (.not.allocated (b2)) call abort()
+
+ b2 = 11
+
+ !$acc parallel copy(b2(1:5,1:5))
+ b2(1,1) = 1
+ b2(2,2) = 2
+ b2(3,3) = 3
+ b2(4,4) = 4
+ b2(5,5) = 5
+ !$acc end parallel
+
+ if (b2(1,1) .ne. 1) call abort
+ if (b2(2,2) .ne. 2) call abort
+ if (b2(3,3) .ne. 3) call abort
+ if (b2(4,4) .ne. 4) call abort
+ if (b2(5,5) .ne. 5) call abort
+
+ deallocate(b2)
+
+ allocate (b2(0:4,0:4))
+ if (.not.allocated (b2)) call abort()
+
+ b2 = 11
+
+ !$acc parallel copy(b2(0:4,0:4))
+ b2(0,0) = 1
+ b2(1,1) = 2
+ b2(2,2) = 3
+ b2(3,3) = 4
+ b2(4,4) = 5
+ !$acc end parallel
+
+ if (b2(0,0) .ne. 1) call abort
+ if (b2(1,1) .ne. 2) call abort
+ if (b2(2,2) .ne. 3) call abort
+ if (b2(3,3) .ne. 4) call abort
+ if (b2(4,4) .ne. 5) call abort
+
+ deallocate(b2)
+
+ allocate (c3(5,5,5))
+ if (.not.allocated (c3)) call abort()
+
+ c3 = 12
+
+ !$acc parallel copy(c3(1:5,1:5,1:5))
+ c3(1,1,1) = 1
+ c3(2,2,2) = 2
+ c3(3,3,3) = 3
+ c3(4,4,4) = 4
+ c3(5,5,5) = 5
+ !$acc end parallel
+
+ if (c3(1,1,1) .ne. 1) call abort
+ if (c3(2,2,2) .ne. 2) call abort
+ if (c3(3,3,3) .ne. 3) call abort
+ if (c3(4,4,4) .ne. 4) call abort
+ if (c3(5,5,5) .ne. 5) call abort
+
+ deallocate(c3)
+
+ allocate (c3(0:4,0:4,0:4))
+ if (.not.allocated (c3)) call abort()
+
+ c3 = 12
+
+ !$acc parallel copy(c3(0:4,0:4,0:4))
+ c3(0,0,0) = 1
+ c3(1,1,1) = 2
+ c3(2,2,2) = 3
+ c3(3,3,3) = 4
+ c3(4,4,4) = 5
+ !$acc end parallel
+
+ if (c3(0,0,0) .ne. 1) call abort
+ if (c3(1,1,1) .ne. 2) call abort
+ if (c3(2,2,2) .ne. 3) call abort
+ if (c3(3,3,3) .ne. 4) call abort
+ if (c3(4,4,4) .ne. 5) call abort
+
+ deallocate(c3)
+
+ allocate (a1(5))
+ if (.not.allocated (a1)) call abort()
+
+ allocate (b1(5))
+ if (.not.allocated (b1)) call abort()
+
+ allocate (c1(5))
+ if (.not.allocated (c1)) call abort()
+
+ a1 = 10
+ b1 = 3
+ c1 = 7
+
+ !$acc parallel copyin(a1(1:5)) create(c1(1:5)) copyout(b1(1:5))
+ c1(1) = a1(1)
+ c1(2) = a1(2)
+ c1(3) = a1(3)
+ c1(4) = a1(4)
+ c1(5) = a1(5)
+
+ b1(1) = c1(1)
+ b1(2) = c1(2)
+ b1(3) = c1(3)
+ b1(4) = c1(4)
+ b1(5) = c1(5)
+ !$acc end parallel
+
+ if (b1(1) .ne. 10) call abort
+ if (b1(2) .ne. 10) call abort
+ if (b1(3) .ne. 10) call abort
+ if (b1(4) .ne. 10) call abort
+ if (b1(5) .ne. 10) call abort
+
+ deallocate(a1)
+ deallocate(b1)
+ deallocate(c1)
+
+ allocate (a1(0:4))
+ if (.not.allocated (a1)) call abort()
+
+ allocate (b1(0:4))
+ if (.not.allocated (b1)) call abort()
+
+ allocate (c1(0:4))
+ if (.not.allocated (c1)) call abort()
+
+ a1 = 10
+ b1 = 3
+ c1 = 7
+
+ !$acc parallel copyin(a1(0:4)) create(c1(0:4)) copyout(b1(0:4))
+ c1(0) = a1(0)
+ c1(1) = a1(1)
+ c1(2) = a1(2)
+ c1(3) = a1(3)
+ c1(4) = a1(4)
+
+ b1(0) = c1(0)
+ b1(1) = c1(1)
+ b1(2) = c1(2)
+ b1(3) = c1(3)
+ b1(4) = c1(4)
+ !$acc end parallel
+
+ if (b1(0) .ne. 10) call abort
+ if (b1(1) .ne. 10) call abort
+ if (b1(2) .ne. 10) call abort
+ if (b1(3) .ne. 10) call abort
+ if (b1(4) .ne. 10) call abort
+
+ deallocate(a1)
+ deallocate(b1)
+ deallocate(c1)
+
+ allocate (a1(5))
+ if (.not.allocated (a1)) call abort()
+
+ a1 = 10
+
+ !$acc parallel copy(a1(2:3))
+ a1(2) = 2
+ a1(3) = 3
+ !$acc end parallel
+
+ if (a1(1) .ne. 10) call abort
+ if (a1(2) .ne. 2) call abort
+ if (a1(3) .ne. 3) call abort
+ if (a1(4) .ne. 10) call abort
+ if (a1(5) .ne. 10) call abort
+
+ deallocate(a1)
+
+end program test
new file mode 100644
@@ -0,0 +1,97 @@
+program subarrays
+ integer, parameter :: n = 20, c = 10
+ integer :: i, a(n), b(n)
+
+ a(:) = 0
+ b(:) = 0
+
+ ! COPY
+
+ !$acc parallel copy (a(1:n))
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ do i = 1, n
+ b(i) = i
+ end do
+
+ call check (a, b, n)
+
+ ! COPYOUT
+
+ a(:) = 0
+
+ !$acc parallel copyout (a(1:n))
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ do i = 1, n
+ if (a(i) .ne. b(i)) call abort
+ end do
+ call check (a, b, n)
+
+ ! COPYIN
+
+ a(:) = 0
+
+ !$acc parallel copyout (a(1:n)) copyin (b(1:n))
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPY
+
+ !$acc parallel pcopy (a(1:n))
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPYOUT
+
+ a(:) = 0
+
+ !$acc parallel pcopyout (a(1:n))
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPYIN
+
+ a(:) = 0
+
+ !$acc parallel pcopyout (a(1:n)) pcopyin (b(1:n))
+ !$acc loop
+ do i = 1, n
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+end program subarrays
+
+subroutine check (a, b, n)
+ integer :: n, a(n), b(n)
+ integer :: i
+
+ do i = 1, n
+ if (a(i) .ne. b(i)) call abort
+ end do
+end subroutine check
new file mode 100644
@@ -0,0 +1,100 @@
+program subarrays
+ integer, parameter :: n = 20, c = 10, low = 5, high = 10
+ integer :: i, a(n), b(n)
+
+ a(:) = 0
+ b(:) = 0
+
+ ! COPY
+
+ !$acc parallel copy (a(low:high))
+ !$acc loop
+ do i = low, high
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ do i = low, high
+ b(i) = i
+ end do
+
+ call check (a, b, n)
+
+ ! COPYOUT
+
+ a(:) = 0
+
+ !$acc parallel copyout (a(low:high))
+ !$acc loop
+ do i = low, high
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ do i = low, high
+ if (a(i) .ne. b(i)) call abort
+ end do
+ call check (a, b, n)
+
+ ! COPYIN
+
+ a(:) = 0
+
+ !$acc parallel copyout (a(low:high)) copyin (b(low:high))
+ !$acc loop
+ do i = low, high
+ a(i) = b(i)
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPY
+
+ a(:) = 0
+
+ !$acc parallel pcopy (a(low:high))
+ !$acc loop
+ do i = low, high
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPYOUT
+
+ a(:) = 0
+
+ !$acc parallel pcopyout (a(low:high))
+ !$acc loop
+ do i = low, high
+ a(i) = i
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+
+ ! PRESENT_OR_COPYIN
+
+ a(:) = 0
+
+ !$acc parallel pcopyout (a(low:high)) &
+ !$acc & pcopyin (b(low:high))
+ !$acc loop
+ do i = low, high
+ a(i) = b(i)
+ end do
+ !$acc end parallel
+
+ call check (a, b, n)
+end program subarrays
+
+subroutine check (a, b, n)
+ integer :: n, a(n), b(n)
+ integer :: i
+
+ do i = 1, n
+ if (a(i) .ne. b(i)) call abort
+ end do
+end subroutine check
--
1.7.10.4
This is an updated version of the patch: https://gcc.gnu.org/ml/gcc-patches/2014-09/msg02025.html but against gomp4 branch instead of mainline. Some tests have been updated a little since the last patch. OK to apply (to the gomp4 branch)? Thanks, Julian ChangeLog xxxx-xx-xx James Norris <jnorris@codesourcery.com> Thomas Schwinge <thomas@codesourcery.com> Tom de Vries <tom@codesourcery.com> Cesar Philippidis <cesar@codesourcery.com> libgomp/ * testsuite/Makefile.in: Regenerated. * testsuite/lib/libgomp.exp (check_effective_target_openacc_nvidia_accel_present) (check_effective_target_openacc_nvidia_accel_selected): New functions. * testsuite/libgomp.oacc-fortran/fortran.exp: New exp file. * testsuite/libgomp.oacc-fortran/*.f: New tests. * testsuite/libgomp.oacc-fortran/*.f90: Likewise. * testsuite/libgomp.oacc-c/c.exp: New exp file. * testsuite/libgomp.oacc-c/subr.ptx: New file. * testsuite/libgomp.oacc-c/subr.cu: New file. * testsuite/libgomp.oacc-c/timer.h: New file. * testsuite/libgomp.oacc-c/*.c: New tests. * testsuite/libgomp.oacc-c++/c++.exp: New exp file.