aboutsummaryrefslogtreecommitdiff
path: root/libgomp/oacc-init.c
diff options
context:
space:
mode:
authorMaciej W. Rozycki <macro@codesourcery.com>2019-12-22 19:54:09 +0000
committerFrederik Harwath <frederik@gcc.gnu.org>2019-12-22 19:54:09 +0000
commit6c84c8bf9b29ce89f5d263c1fa3630896fcb23f4 (patch)
tree0e15cf12a4c3396702ed004deabe3c86ea7ac18e /libgomp/oacc-init.c
parentedadb8adc3563bf782e4781bf3be6425af566368 (diff)
downloadgcc-6c84c8bf9b29ce89f5d263c1fa3630896fcb23f4.zip
gcc-6c84c8bf9b29ce89f5d263c1fa3630896fcb23f4.tar.gz
gcc-6c84c8bf9b29ce89f5d263c1fa3630896fcb23f4.tar.bz2
Add OpenACC 2.6 `acc_get_property' support
Add generic support for the OpenACC 2.6 `acc_get_property' and `acc_get_property_string' routines, as well as full handlers for the host and the NVPTX offload targets and minimal handlers for the HSA, Intel MIC, and AMD GCN offload targets. Included are C/C++ and Fortran tests that, in particular, print the property values for acc_property_vendor, acc_property_memory, acc_property_free_memory, acc_property_name, and acc_property_driver. The output looks as follows: Vendor: GNU Name: GOMP Total memory: 0 Free memory: 0 Driver: 1.0 with the host driver (where the memory related properties are not supported for the host device and yield 0, conforming to the standard) and output like: Vendor: Nvidia Total memory: 12651462656 Free memory: 12202737664 Name: TITAN V Driver: CUDA Driver 9.1 with the NVPTX driver. 2019-12-22 Maciej W. Rozycki <macro@codesourcery.com> Frederik Harwath <frederik@codesourcery.com> Thomas Schwinge <tschwinge@codesourcery.com> include/ * gomp-constants.h (gomp_device_property): New enum. libgomp/ * libgomp.h (gomp_device_descr): Add `get_property_func' member. * libgomp-plugin.h (gomp_device_property_value): New union. (gomp_device_property_value): New prototype. * openacc.h (acc_device_t): Add `acc_device_current' enumeration constant. (acc_device_property_t): New enum. (acc_get_property, acc_get_property_string): New prototypes. * oacc-init.c (acc_get_device_type): Also assert that result is not `acc_device_current'. (get_property_any, acc_get_property, acc_get_property_string): New functions. * openacc.f90 (openacc_kinds): Add `acc_device_current' and `acc_property_memory', `acc_property_free_memory', `acc_property_name', `acc_property_vendor' and `acc_property_driver' constants. Add `acc_device_property' data type. (openacc_internal): Add `acc_get_property' and `acc_get_property_string' interfaces. Add `acc_get_property_h', `acc_get_property_string_h', `acc_get_property_l' and `acc_get_property_string_l'. * oacc-host.c (host_get_property): New function. (host_dispatch): Wire it. * target.c (gomp_load_plugin_for_device): Handle `get_property'. * libgomp.map (OACC_2.6): Add `acc_get_property', `acc_get_property_h_', `acc_get_property_string' and `acc_get_property_string_h_' symbols. * libgomp.texi (OpenACC Runtime Library Routines): Add `acc_get_property'. (acc_get_property): New node. * plugin/plugin-gcn.c (GOMP_OFFLOAD_get_property): New function (stub). * plugin/plugin-hsa.c (GOMP_OFFLOAD_get_property): New function. * plugin/plugin-nvptx.c (CUDA_CALLS): Add `cuDeviceGetName', `cuDeviceTotalMem', `cuDriverGetVersion' and `cuMemGetInfo' calls. (GOMP_OFFLOAD_get_property): New function. (struct ptx_device): Add new field "name". (cuda_driver_version_s): Add new static variable ... (nvptx_init): ... and init from here. * testsuite/libgomp.oacc-c-c++-common/acc_get_property.c: New test. * testsuite/libgomp.oacc-c-c++-common/acc_get_property-2.c: New test. * testsuite/libgomp.oacc-c-c++-common/acc_get_property-3.c: New test. * testsuite/libgomp.oacc-c-c++-common/acc_get_property-aux.c: New file with test helper functions. * testsuite/libgomp.oacc-fortran/acc_get_property.f90: New test. liboffloadmic/ * plugin/libgomp-plugin-intelmic.cpp (GOMP_OFFLOAD_get_property): New function. Reviewed-by: Thomas Schwinge <thomas@codesourcery.com> Co-Authored-By: Frederik Harwath <frederik@codesourcery.com> Co-Authored-By: Thomas Schwinge <tschwinge@codesourcery.com> From-SVN: r279710
Diffstat (limited to 'libgomp/oacc-init.c')
-rw-r--r--libgomp/oacc-init.c63
1 files changed, 62 insertions, 1 deletions
diff --git a/libgomp/oacc-init.c b/libgomp/oacc-init.c
index dd88b58..487a2cc 100644
--- a/libgomp/oacc-init.c
+++ b/libgomp/oacc-init.c
@@ -670,7 +670,8 @@ acc_get_device_type (void)
}
assert (res != acc_device_default
- && res != acc_device_not_host);
+ && res != acc_device_not_host
+ && res != acc_device_current);
return res;
}
@@ -759,6 +760,66 @@ acc_set_device_num (int ord, acc_device_t d)
ialias (acc_set_device_num)
+static union gomp_device_property_value
+get_property_any (int ord, acc_device_t d, acc_device_property_t prop)
+{
+ goacc_lazy_initialize ();
+ struct goacc_thread *thr = goacc_thread ();
+
+ if (d == acc_device_current && thr && thr->dev)
+ return thr->dev->get_property_func (thr->dev->target_id, prop);
+
+ gomp_mutex_lock (&acc_device_lock);
+
+ struct gomp_device_descr *dev = resolve_device (d, true);
+
+ int num_devices = dev->get_num_devices_func ();
+
+ if (num_devices <= 0 || ord >= num_devices)
+ acc_dev_num_out_of_range (d, ord, num_devices);
+
+ dev += ord;
+
+ gomp_mutex_lock (&dev->lock);
+ if (dev->state == GOMP_DEVICE_UNINITIALIZED)
+ gomp_init_device (dev);
+ gomp_mutex_unlock (&dev->lock);
+
+ gomp_mutex_unlock (&acc_device_lock);
+
+ assert (dev);
+
+ return dev->get_property_func (dev->target_id, prop);
+}
+
+size_t
+acc_get_property (int ord, acc_device_t d, acc_device_property_t prop)
+{
+ if (!known_device_type_p (d))
+ unknown_device_type_error(d);
+
+ if (prop & GOMP_DEVICE_PROPERTY_STRING_MASK)
+ return 0;
+ else
+ return get_property_any (ord, d, prop).val;
+}
+
+ialias (acc_get_property)
+
+const char *
+acc_get_property_string (int ord, acc_device_t d, acc_device_property_t prop)
+{
+ if (!known_device_type_p (d))
+ unknown_device_type_error(d);
+
+ if (prop & GOMP_DEVICE_PROPERTY_STRING_MASK)
+ return get_property_any (ord, d, prop).ptr;
+ else
+ return NULL;
+}
+
+ialias (acc_get_property_string)
+
/* For -O and higher, the compiler always attempts to expand acc_on_device, but
if the user disables the builtin, or calls it via a pointer, we'll need this
version.