2.20.3-1

Add support for alternating rings, allow for cross-nic rings without
cross-rail communication.
Add support for user buffer registration for network send/recv.
Optimize aggregated operations to better utilize all channels.
Add flattening for BCM PCI gen5 switches.
Add support for inter-node NVLink communication
Add support for port fusion in NET/IB.
Add support for ReduceScatter and AllGather using Collnet.
Update net API to v8.
Fix hang during A2A connection.


[ROCm/rccl commit: b6475625fb]

projects/rccl/src/include/nccl_common.h

@@ -13,7 +13,17 @@ typedef enum {NCCL_INIT=1, NCCL_COLL=2, NCCL_P2P=4, NCCL_SHM=8, NCCL_NET=16, NCC
 typedef void (*ncclDebugLogger_t)(ncclDebugLogLevel level, unsigned long flags, const char *file, int line, const char *fmt, ...);
 
 #define NCCL_NUM_FUNCTIONS 5 // Send/Recv not included for now
-typedef enum { ncclFuncBroadcast, ncclFuncReduce, ncclFuncAllGather, ncclFuncReduceScatter, ncclFuncAllReduce, ncclFuncSendRecv, ncclFuncSend, ncclFuncRecv, ncclNumFuncs} ncclFunc_t;
+typedef enum {
+  ncclFuncBroadcast = 0,
+  ncclFuncReduce = 1,
+  ncclFuncAllGather = 2,
+  ncclFuncReduceScatter = 3,
+  ncclFuncAllReduce = 4,
+  ncclFuncSendRecv = 5,
+  ncclFuncSend = 6,
+  ncclFuncRecv = 7,
+  ncclNumFuncs = 8
+} ncclFunc_t;
 
 #define NCCL_NUM_ALGORITHMS 6 // Tree/Ring/CollNet*
 #define NCCL_ALGO_UNDEF -1