2.24.3-1

Network user buffer support for collectives
 * Leverage user buffer registration to achieve zero-copy
   inter-node communications for Ring, NVLS and Collnet

Add RAS subsystem
 * Create a RAS thread keeping track of all NCCL communicators.
 * Add a ncclras tool contacting the RAS thread and getting a
   report.

Add fp8 support
 * Add support for e5m2 and e4m3 8-bit floating point operations.
 * Use Tree/PAT algorithms when possible for better numerical
   stability.

Add NIC fusion
 * Add a NET API to ask the network plugin to fuse a set of
   interfaces together.
 * Fuse multiple NICs under the same PCI switch as a single,
   larger NIC.

Socket connection failure retry
 * Retry in case of socket connection failure (unreachable host)
 * Avoid "Software caused connection abort" errors on retries

QP connection failure retry
 * Retry in case of IB QP connection failure during ibv_modify_qp.

NET API improvements
 * Allow plugins to force a flush in case data and completion
   ordering is not guaranteed.
 * Indicate when completion is not needed (e.g. for the LL128
   protocol), allowing plugins to skip generating a completion.
 * Allow for full offload of allgather operations when using one
   GPU per node.

NCCL_ALGO/NCCL_PROTO strict enforcement
 * Extend NCCL_ALGO/NCCL_PROTO syntax to be able to specify
   ALGO/PROTO filters for each collective operation.
 * Strictly enforce the ALGO/PROTO filters, no longer fall back
   on the ring algorithm when the filtering leaves no option and
   error out instead.

Enable CUMEM host allocations
 * Use cumem functions for host memory allocation by default.

Improved profiler plugin API
 * Avoid dependencies with NCCL includes.
 * Add information on whether the buffer is registered or not

Adjust PAT tuning
 * Improve transition between PAT and ring at scale.

Fix hangs when running with different CPU architectures
 * Detect when we use a mix of GPU architectures
 * Ensure Algo/Proto decisions are made based on that unified
   state.

Fix FD leak in UDS
 * Fix a leak when mapping buffers intra-node with cumem IPCs.

Fix crash when mixing buffer registration and graph buffer registration.
 * Separate local and graph registration to avoid crashes when we free
   buffers.

Fix user buffer registration with dmabuf
 * Make ncclSend/ncclRecv communication with buffer registration functional
   on network plugins relying on dmabuf for buffer registration.

Fix crash in IB code caused by uninitialized fields.

Fix non-blocking ncclSend/ncclRecv
 * Fix case where ncclSend/ncclRecv would return ncclSuccess in non-blocking
   mode even though the operation was not enqueued onto the stream.
 * Issue #1495

Various compiler tweaks and fixes
 * PR #758

Fix typo in ncclTopoPrintGraph
 * Issue #1468

src/include/graph.h

@@ -19,7 +19,7 @@ ncclResult_t ncclTopoCudaPath(int cudaDev, char** path);
 
 struct ncclTopoSystem;
 // Build the topology
-ncclResult_t ncclTopoGetSystem(struct ncclComm* comm, struct ncclTopoSystem** system);
+ncclResult_t ncclTopoGetSystem(struct ncclComm* comm, struct ncclTopoSystem** system, const char* dumpXmlFile=NULL);
 ncclResult_t ncclTopoSortSystem(struct ncclTopoSystem* system);
 ncclResult_t ncclTopoPrint(struct ncclTopoSystem* system);
 
@@ -33,10 +33,11 @@ ncclResult_t ncclTopoComputeCommCPU(struct ncclComm* comm);
 
 // Query topology
 ncclResult_t ncclTopoGetNetDev(struct ncclComm* comm, int rank, struct ncclTopoGraph* graph, int channelId, int peerRank, int64_t* id, int* dev, int* proxyRank);
-ncclResult_t ncclTopoCheckP2p(struct ncclTopoSystem* system, int rank1, int rank2, int* p2p, int *read, int* intermediateRank);
+ncclResult_t ncclTopoCheckP2p(struct ncclComm* comm, struct ncclTopoSystem* system, int rank1, int rank2, int* p2p, int *read, int* intermediateRank);
 ncclResult_t ncclTopoCheckMNNVL(struct ncclTopoSystem* system, struct ncclPeerInfo* info1, struct ncclPeerInfo* info2, int* ret);
-ncclResult_t ncclTopoCheckGdr(struct ncclTopoSystem* topo, int64_t busId, int64_t netId, int read, int* useGdr);
-ncclResult_t ncclTopoNeedFlush(struct ncclTopoSystem* system, int64_t busId, int* flush);
+ncclResult_t ncclTopoCheckGdr(struct ncclTopoSystem* topo, int rank, int64_t netId, int read, int* useGdr);
+ncclResult_t ncclTopoNeedFlush(struct ncclComm* comm, int netDev, int rank, int* flush);
+ncclResult_t ncclTopoIsGdrAvail(struct ncclTopoSystem* system, int rank, bool *avail);
 ncclResult_t ncclTopoCheckNet(struct ncclTopoSystem* system, int rank1, int rank2, int* net);
 int ncclPxnDisable(struct ncclComm* comm);
 ncclResult_t ncclTopoGetPxnRanks(struct ncclComm* comm, int** intermediateRanks, int* nranks);
@@ -118,6 +119,6 @@ ncclResult_t ncclTopoPostset(struct ncclComm* comm, int* firstRanks, int* treePa
     struct ncclTopoRanks** allTopoRanks, int* rings, struct ncclTopoGraph** graphs, struct ncclComm* parent);
 
 ncclResult_t ncclTopoTuneModel(struct ncclComm* comm, int minCompCap, int maxCompCap, struct ncclTopoGraph** graphs);
-ncclResult_t ncclTopoGetAlgoTime(struct ncclComm* comm, int coll, int algorithm, int protocol, size_t nBytes, int numPipeOps, float* time, bool* backup=nullptr);
+ncclResult_t ncclTopoGetAlgoTime(struct ncclComm* comm, int coll, int algorithm, int protocol, size_t nBytes, int numPipeOps, float* time);
 
 #endif