Update Barrier_All and Sync_All APIs (#72)

* Fix deadlock in `rocshmem_ctx_wg_barrier_all` API in IPC conduit by adding per-context pSync buffers and context IDs
  - Added separate pSync buffers for each device context
  - Resolved deadlock when invoking barrier API (`rocshmem_ctx_wg_barrier_all`) concurrently from multiple contexts

* Update barrier_all functional tests for multi-context support

* Add thread, wavefront, and workgroup-level barrier_all APIs in IPC and RO conduits
  - Implemented barrier_all APIs at thread, wavefront, and workgroup granularity
  - Added support in both IPC and RO conduits
  - Updated functional tests to cover all `barrier_all` APIs

* Add thread, wavefront, and workgroup-level sync_all APIs in IPC and RO conduits
  - Implemented sync_all APIs for thread, wavefront, and workgroup scopes
  - Added support into both IPC and RO conduits
  - Added functional tests to cover all `sync_all` APIs

[ROCm/rocshmem commit: c652f58cef]

projects/rocshmem/tests/functional_tests/tester.cpp

@@ -43,10 +43,11 @@
 #include "random_access_tester.hpp"
 #include "shmem_ptr_tester.hpp"
 #include "signaling_operations_tester.hpp"
+#include "sync_all_tester.hpp"
 #include "sync_tester.hpp"
 #include "team_alltoall_tester.hpp"
-#include "team_broadcast_tester.hpp"
 #include "team_barrier_tester.hpp"
+#include "team_broadcast_tester.hpp"
 #include "team_ctx_infra_tester.hpp"
 #include "team_ctx_primitive_tester.hpp"
 #include "team_fcollect_tester.hpp"
@@ -317,6 +318,14 @@ std::vector<Tester*> Tester::create(TesterArguments args) {
       if (rank == 0) std::cout << "Barrier_All ###" << std::endl;
       testers.push_back(new BarrierAllTester(args));
       return testers;
+    case WAVEBarrierAllTestType:
+      if (rank == 0) std::cout << "WAVE Barrier_All ###" << std::endl;
+      testers.push_back(new BarrierAllTester(args));
+      return testers;
+    case WGBarrierAllTestType:
+      if (rank == 0) std::cout << "WG Barrier_All ###" << std::endl;
+      testers.push_back(new BarrierAllTester(args));
+      return testers;
     case TeamBarrierTestType:
       if (rank == 0) std::cout << "Team Barrier Test ###" << std::endl;
       testers.push_back(new TeamBarrierTester(args));
@@ -325,6 +334,14 @@ std::vector<Tester*> Tester::create(TesterArguments args) {
       if (rank == 0) std::cout << "SyncAll ###" << std::endl;
       testers.push_back(new SyncTester(args));
       return testers;
+    case WAVESyncAllTestType:
+      if (rank == 0) std::cout << "WAVE SyncAll ###" << std::endl;
+      testers.push_back(new SyncTester(args));
+      return testers;
+    case WGSyncAllTestType:
+      if (rank == 0) std::cout << "WG SyncAll ###" << std::endl;
+      testers.push_back(new SyncTester(args));
+      return testers;
     case SyncTestType:
       if (rank == 0) std::cout << "Sync ###" << std::endl;
       testers.push_back(new SyncTester(args));
@@ -510,7 +527,9 @@ bool Tester::peLaunchesKernel() {
                 (_type == TeamBroadcastTestType) || (_type == TeamCtxInfraTestType) ||
                 (_type == TeamAllToAllTestType) || (_type == TeamFCollectTestType) ||
                 (_type == PingPongTestType) || (_type == BarrierAllTestType) ||
+                (_type == WAVEBarrierAllTestType) || (_type == WGBarrierAllTestType) ||
                 (_type == SyncTestType) || (_type == SyncAllTestType) ||
+                (_type == WAVESyncAllTestType) || (_type == WGSyncAllTestType) ||
                 (_type == RandomAccessTestType) || (_type == PingAllTestType) ||
                 (_type == TeamBarrierTestType);