Limit max channels for ring graph on single node Rome (#347)

* Limit max channels for ring graph on single node Rome
* Partially revert "Use non-temporal access for streaming data (#341)"

src/graph/search.cc

@@ -766,6 +766,10 @@ ncclResult_t ncclTopoCompute(ncclTopoSystem* system, struct ncclTopoGraph* graph
   }
   if (graph->nChannels) return ncclSuccess;
 
+  if ((graph->pattern == NCCL_TOPO_PATTERN_RING) && (system->type & RCCL_TOPO_4P2H_ROME) && (ngpus == system->nRanks)) {
+    // limit single node max channels when searching ring graph on Rome
+    graph->maxChannels = 2;
+  }
   if (ngpus == 1) if (graph->pattern != NCCL_TOPO_PATTERN_RING) graph->pattern = NCCL_TOPO_PATTERN_TREE;
 
 #if defined(__HIP_PLATFORM_HCC__) || defined(__HCC__) || defined(__HIPCC__)