SWDEV-299893 - Set preferred node affinity

Set affinity to the closest node of the current GPU. This reduces
the latency to fetch kernel args since device would query the CPU cache
of core which did the dispatch. This behavior is controlled with
AMD_CPU_AFFINITY env var(disabled by default)

Change-Id: I65afba62cb818ea25a311b88d1c0dd5c51330292

rocclr/device/rocm/rocdevice.cpp

@@ -170,7 +170,8 @@ Device::Device(hsa_agent_t bkendDevice)
     , queuePool_(QueuePriority::Total)
     , coopHostcallBuffer_(nullptr)
     , queueWithCUMaskPool_(QueuePriority::Total)
-    , numOfVgpus_(0) {
+    , numOfVgpus_(0)
+    , preferred_numa_node_(0) {
   group_segment_.handle = 0;
   system_segment_.handle = 0;
   system_coarse_segment_.handle = 0;
@@ -194,7 +195,7 @@ void Device::setupCpuAgent() {
       }
     }
   }
-
+  preferred_numa_node_ = index;
   cpu_agent_ = cpu_agents_[index].agent;
   system_segment_ = cpu_agents_[index].fine_grain_pool;
   system_coarse_segment_ = cpu_agents_[index].coarse_grain_pool;