aboutsummaryrefslogtreecommitdiff
path: root/libgomp/plugin
diff options
context:
space:
mode:
authorMarcel Vollweiler <marcel@codesourcery.com>2022-12-06 05:42:46 -0800
committerMarcel Vollweiler <marcel@codesourcery.com>2022-12-06 06:03:50 -0800
commit81476bc4f4a20bcf3af7ac2548c2322d48499402 (patch)
tree05f4c4edec59886eab84c6e595023c03fdf5991e /libgomp/plugin
parent400d9fc1f04336118c3200e2af14a620e7ea1d95 (diff)
OpenMP: omp_get_max_teams, omp_set_num_teams, and omp_{gs}et_teams_thread_limit on offload devices
This patch adds support for omp_get_max_teams, omp_set_num_teams, and omp_{gs}et_teams_thread_limit on offload devices. That includes the usage of device-specific ICV values (specified as environment variables or changed on a device). In order to reuse device-specific ICV values, a copy back mechanism is implemented that copies ICV values back from device to the host. Additionally, a limitation of the number of teams on gcn offload devices is implemented. The number of teams is limited by twice the number of compute units (one team is executed on one compute unit). This avoids queueing unnessecary many teams and a corresponding allocation of large amounts of memory. Without that limitation the memory allocation for a large number of user-specified teams can result in an "memory access fault". A limitation of the number of teams is already also implemented for nvptx devices (see nvptx_adjust_launch_bounds in libgomp/plugin/plugin-nvptx.c). gcc/ChangeLog: * gimplify.cc (optimize_target_teams): Set initial num_teams_upper to "-2" instead of "1" for non-existing num_teams clause in order to disambiguate from the case of an existing num_teams clause with value 1. libgomp/ChangeLog: * config/gcn/icv-device.c (omp_get_teams_thread_limit): Added to allow processing of device-specific values. (omp_set_teams_thread_limit): Likewise. (ialias): Likewise. * config/nvptx/icv-device.c (omp_get_teams_thread_limit): Likewise. (omp_set_teams_thread_limit): Likewise. (ialias): Likewise. * icv-device.c (omp_get_teams_thread_limit): Likewise. (ialias): Likewise. (omp_set_teams_thread_limit): Likewise. * icv.c (omp_set_teams_thread_limit): Removed. (omp_get_teams_thread_limit): Likewise. (ialias): Likewise. * libgomp.texi: Updated documentation for nvptx and gcn corresponding to the limitation of the number of teams. * plugin/plugin-gcn.c (limit_teams): New helper function that limits the number of teams by twice the number of compute units. (parse_target_attributes): Limit the number of teams on gcn offload devices. * target.c (get_gomp_offload_icvs): Added teams_thread_limit_var handling. (gomp_load_image_to_device): Added a size check for the ICVs struct variable. (gomp_copy_back_icvs): New function that is used in GOMP_target_ext to copy back the ICV values from device to host. (GOMP_target_ext): Update the number of teams and threads in the kernel args also considering device-specific values. * testsuite/libgomp.c-c++-common/icv-4.c: Fixed an error in the reading of OMP_TEAMS_THREAD_LIMIT from the environment. * testsuite/libgomp.c-c++-common/icv-5.c: Extended. * testsuite/libgomp.c-c++-common/icv-6.c: Extended. * testsuite/libgomp.c-c++-common/icv-7.c: Extended. * testsuite/libgomp.c-c++-common/icv-9.c: New test. * testsuite/libgomp.fortran/icv-5.f90: New test. * testsuite/libgomp.fortran/icv-6.f90: New test. gcc/testsuite/ChangeLog: * c-c++-common/gomp/target-teams-1.c: Adapt expected values for num_teams from "1" to "-2" in cases without num_teams clause. * g++.dg/gomp/target-teams-1.C: Likewise. * gfortran.dg/gomp/defaultmap-4.f90: Likewise. * gfortran.dg/gomp/defaultmap-5.f90: Likewise. * gfortran.dg/gomp/defaultmap-6.f90: Likewise.
Diffstat (limited to 'libgomp/plugin')
-rw-r--r--libgomp/plugin/plugin-gcn.c14
1 files changed, 13 insertions, 1 deletions
diff --git a/libgomp/plugin/plugin-gcn.c b/libgomp/plugin/plugin-gcn.c
index 99a700276aa..f9b8dda75d6 100644
--- a/libgomp/plugin/plugin-gcn.c
+++ b/libgomp/plugin/plugin-gcn.c
@@ -1150,6 +1150,18 @@ limit_worker_threads (int threads)
return threads;
}
+/* This sets the maximum number of teams to twice the number of GPU Compute
+ Units to avoid memory waste and corresponding memory access faults. */
+
+static int
+limit_teams (int teams, struct agent_info *agent)
+{
+ int max_teams = 2 * get_cu_count (agent);
+ if (teams > max_teams)
+ teams = max_teams;
+ return teams;
+}
+
/* Parse the target attributes INPUT provided by the compiler and return true
if we should run anything all. If INPUT is NULL, fill DEF with default
values, then store INPUT or DEF into *RESULT.
@@ -1194,7 +1206,7 @@ parse_target_attributes (void **input,
switch (id & GOMP_TARGET_ARG_ID_MASK)
{
case GOMP_TARGET_ARG_NUM_TEAMS:
- gcn_teams = val;
+ gcn_teams = limit_teams (val, agent);
break;
case GOMP_TARGET_ARG_THREAD_LIMIT:
gcn_threads = limit_worker_threads (val);