Add Topologies for 16-GPU gfx942 SuperNode (#1417)

* Add Topologies for 16-GPU gfx942 SuperNode

- Add GigaIO topologies to tools/topo_expl for dev and testing
- Add GigaIO Columba 16 GPU romeModel and adjust topology
  matching algorithm in rome_models for 16 GPU system
- Fix bug which failed to match Rome Model when using subsets
  of system resources (i.e. ROCR_VISIBLE_DEVICES is set)
- Fixes for topo_expl

* Fix bug w/ 1H16P

[ROCm/rccl commit: a05329bd0d]

projects/rccl/tools/topo_expl/utils.cpp

@@ -224,9 +224,9 @@ void ncclDebugLog(ncclDebugLogLevel level, unsigned long flags, const char *file
 
 ncclResult_t ncclTopoGetSystem(const char* xmlTopoFile, struct ncclTopoSystem** system) {
   struct ncclXml* xml;
-  NCCLCHECK(ncclCalloc(&xml, 1));
+  NCCLCHECK(xmlAlloc(&xml, NCCL_GRAPH_XML_MAX_NODES));
   NCCLCHECK(ncclTopoGetXmlFromFile(xmlTopoFile, xml, 0));
-  NCCLCHECK(ncclTopoGetSystemFromXml(xml, system));
+  NCCLCHECK(ncclTopoGetSystemFromXml(xml, system, 0));
   free(xml);
   return ncclSuccess;
 }
@@ -1092,7 +1092,7 @@ ncclResult_t initTransportsRank_3(struct ncclComm* comm, struct allGatherInfo *a
 
   NCCLCHECKGOTO(ncclCalloc(&rings, nranks*MAXCHANNELS), ret, fail);
 
-  NCCLCHECKGOTO(ncclTopoPostset(comm, nodesFirstRank, nodesTreePatterns, allTopoRanks, rings, graphs, nc), ret, fail);
+  NCCLCHECKGOTO(ncclTopoPostset(comm, nodesFirstRank, nodesTreePatterns, allTopoRanks, rings, graphs, NULL, nc), ret, fail);
   if (comm->topo->treeDefined) NCCLCHECK(ncclTreeBasePostset(comm, &treeGraph));
 
   // AllGather3 - end
@@ -1358,3 +1358,11 @@ bool mscclForceEnabled() {
 ncclResult_t mscclSchedulerInit(ncclComm_t comm, int* numChannelsRequired) {
   return ncclSuccess;
 }
+
+uint64_t getHostHash(void) {
+  return 0xdeadbeef;
+}
+
+ncclResult_t bootstrapIntraNodeAllGather(void* commState, int *ranks, int rank, int nranks, void* allData, int size) {
+  return ncclSuccess;
+}