2.21.5-1

Add support for IB SHARP 1PPN operation with user buffers.
Improve support for MNNVL, add NVLS support and multi-clique support.
 * Detect the NVLS clique through NVML
 * Exchange XML between peers in the same NVLS clique and fuse XMLs
   before creating the topology graph.
 * Rework bootstrap allgather algorithms to allow for large allgather
   operations intra-node (XML exchange).
Net/IB: add support for dynamic GID detection.
 * Automatically select RoCEv2/IPv4 interface by default. Allow to
   select IPv6 or even the network/mask.
Reduce NVLS memory usage.
 * Add stepSize as property of a connection to allow for different
   sizes on different peers; set it to 128K for NVLink SHARP.
Improve tuner loading
 * Look for more paths, be more consistent with the network device
   plugin.
 * Also search for tuner support inside the net plugin.
Improve tuner API
 * Add context to support multi-device per process.
Add magic number around comm object to detect comm corruption.
 * Add some basic check around communicators so that we can report a
   problem when a communicator gets corrupted or a wrong comm pointer
   is passed to NCCL.
Fix net/IB error path. Github PR #1164
Fix collnet rail mapping with split comm.
Fix packet reordering issue causing bootstrap mismatch
 * Use a different tag in ncclTransportP2pSetup for the connectInfo
   exchange and the following barrier.
Fix hang when crossNic is inconsistent between ranks.
Fix minCompCap/maxCompCap computation. Github issue #1184


[ROCm/rccl commit: ab2b89c4c3]

projects/rccl/src/include/proxy.h

@@ -33,7 +33,6 @@ union ncclProxyOpSpecifics {
 
 struct ncclProxyOp {
   struct ncclProxyConnection* connection;
-  void* buffer;
   ssize_t nbytes;
   uint64_t opCount;
   int root;
@@ -49,6 +48,11 @@ struct ncclProxyOp {
   uint8_t /*ncclPattern_t*/ pattern;
   uint8_t protocol;
   uint8_t reg;
+  // collnet buffer reg handles
+  void* sendMhandle;
+  void* recvMhandle;
+  uint8_t* sendbuff;
+  uint8_t* recvbuff;
 
   union ncclProxyOpSpecifics specifics;
 
@@ -58,8 +62,14 @@ struct ncclProxyOp {
 struct ncclProxySubArgs {
   struct ncclProxyConnection* connection;
   int reg;
-  void* buffer;
+  // p2p mhandle
   void* mhandle;
+  // collnet handles
+  void* sendMhandle;
+  void* recvMhandle;
+  uint8_t* sendbuff;
+  uint8_t* recvbuff;
+  size_t offset;
   int channelId;
   int nsteps;
   ssize_t nbytes;
@@ -88,6 +98,10 @@ struct ncclProxyArgs {
   int sliceSteps;
   int chunkSteps;
   int chunkSize;
+  size_t totalSendSize;
+  size_t totalRecvSize;
+  size_t sendSizePerRound;
+  size_t recvSizePerRound;
   uint8_t /*ncclDataType_t*/ dtype;
   uint8_t /*ncclDevRedOp_t*/ redOp;
   uint8_t /*ncclPattern_t*/ pattern;
@@ -302,6 +316,8 @@ enum ncclProxyMsgType {
   ncclProxyMsgAbort = 7,
   ncclProxyMsgStop = 8,
   ncclProxyMsgGetFd = 9, // cuMem API support (UDS)
+  ncclProxyMsgRegister = 10,
+  ncclProxyMsgDeregister = 11
 };
 
 // This function is called by a client of the proxy that needs to invoke any of the non-progress proxyOp types