SWDEV-549309 - Ensure that the kernel is issued to a stream that is ass… (#552)

* SWDEV-549309 - Ensure that the kernel is issued to a stream that is associated to the current device

* SWDEV-549309 - Ensure that the kernel is issued to a stream that is associated to the current device in atomic tests

* SWDEV-549309 - Added fix for Unit_hipMallocFromPoolAsync_Multidevice_Concurrent test

* SWDEV-549309 - Added fix for Unit_hipMemcpyPeerAsync_Positive_Default

* SWDEV-549309 - Added fix for Unit_hipStreamAttachMemAsync_Positive_AttachGlobal and Unit_hipGetProcAddress_GraphAPIs_AddMemsetMemcpyNodes

[ROCm/hip-tests commit: d21a95cea8]

projects/hip-tests/catch/unit/atomics/arithmetic_common.hh

@@ -446,6 +446,7 @@ void TestCore(const TestParams& p) {
 
  // Launch Kernel
   for (auto i = 0u; i < p.num_devices; ++i) {
+    HIP_CHECK(hipSetDevice(i));
     for (auto j = 0u; j < p.kernel_count; ++j) {
       const auto& stream = streams[i * p.kernel_count + j].stream();
       const auto old_vals = old_vals_devs[i].ptr() + j * p.ThreadCount();

projects/hip-tests/catch/unit/atomics/bitwise_common.hh

@@ -272,6 +272,7 @@ void TestCore(const TestParams& p) {
   }
   // Launch Kernel and get back old vals
   for (auto i = 0u; i < p.num_devices; ++i) {
+    HIP_CHECK(hipSetDevice(i));
     for (auto j = 0u; j < p.kernel_count; ++j) {
       const auto& stream = streams[i * p.kernel_count + j].stream();
       const auto old_vals = old_vals_devs[i].ptr() + j * p.ThreadCount();

projects/hip-tests/catch/unit/atomics/min_max_common.hh

@@ -302,6 +302,7 @@ void TestCore(const TestParams& p) {
 
   // Launch kernel
   for (auto i = 0u; i < p.num_devices; ++i) {
+    HIP_CHECK(hipSetDevice(i));
     for (auto j = 0u; j < p.kernel_count; ++j) {
       const auto& stream = streams[i * p.kernel_count + j].stream();
       const auto old_vals = old_vals_devs[i].ptr() + j * p.ThreadCount();