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/transport.h

@@ -28,7 +28,6 @@ extern struct ncclTransport netTransport;
 extern struct ncclTransport collNetTransport;
 
 extern struct ncclTransport* ncclTransports[];
-
 // Forward declarations
 struct ncclRing;
 struct ncclConnector;
@@ -115,16 +114,16 @@ struct ncclTransport {
 };
 
 ncclResult_t ncclTransportP2pConnect(struct ncclComm* comm, int channelId, int nrecv, int* peerRecv, int nsend, int* peerSend, int connIndex);
-ncclResult_t ncclTransportP2pSetup(struct ncclComm* comm, struct ncclTopoGraph* graph, int connIndex, int* highestTransportType=NULL);
+ncclResult_t ncclTransportP2pSetup(struct ncclComm* comm, struct ncclTopoGraph* graph, int connIndex);
 ncclResult_t ncclTransportCheckP2pType(struct ncclComm* comm, bool* intraNodeP2pSupport, bool* directMode);
 
 ncclResult_t ncclNvlsInit(struct ncclComm* comm);
 ncclResult_t ncclNvlsSetup(struct ncclComm* comm, struct ncclComm* parent);
 ncclResult_t ncclNvlsBufferSetup(struct ncclComm* comm);
 ncclResult_t ncclNvlsTreeConnect(struct ncclComm* comm);
-ncclResult_t ncclNvlsGraphRegisterBuffer(struct ncclComm *comm, const void *sendbuff, void *recvbuff, size_t sendbuffSize, size_t recvbuffSize, bool *outRegBufUsed, void **outRegBufSend, void **outRegBufRecv, struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue, int* nCleanupQueueElts);
-ncclResult_t ncclNvlsLocalRegisterBuffer(struct ncclComm *comm, const void *sendbuff, void *recvbuff, size_t sendbuffSize, size_t recvbuffSize, bool *outRegBufUsed, void **outRegBufSend, void **outRegBufRecv);
-ncclResult_t ncclNvlsDeregBuffer(CUmemGenericAllocationHandle *mcHandler, CUdeviceptr ptr, int dev, size_t size);
+ncclResult_t ncclNvlsGraphRegisterBuffer(struct ncclComm *comm, const void *sendbuff, void *recvbuff, size_t sendbuffSize, size_t recvbuffSize, int *outRegBufUsed, void **outRegBufSend, void **outRegBufRecv, struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue, int* nCleanupQueueElts);
+ncclResult_t ncclNvlsLocalRegisterBuffer(struct ncclComm *comm, const void *sendbuff, void *recvbuff, size_t sendbuffSize, size_t recvbuffSize, int *outRegBufUsed, void **outRegBufSend, void **outRegBufRecv);
+ncclResult_t ncclNvlsDeregBuffer(struct ncclComm* comm, CUmemGenericAllocationHandle *mcHandler, CUdeviceptr ptr, int dev, size_t size);
 ncclResult_t ncclNvlsFree(struct ncclComm* comm);
 
 enum { collNetRecv=0, collNetSend=1 };
@@ -143,4 +142,13 @@ ncclResult_t ncclCollNetSetup(ncclComm_t comm, ncclComm_t parent, struct ncclTop
 ncclResult_t ncclCollNetChainBufferSetup(ncclComm_t comm);
 ncclResult_t ncclCollNetDirectBufferSetup(ncclComm_t comm);
 
+ncclResult_t ncclNetDeregBuffer(struct ncclComm* comm, struct ncclProxyConnector* proxyConn, void* handle);
+ncclResult_t ncclNetLocalRegisterBuffer(ncclComm* comm, const void* userbuff, size_t buffSize, struct ncclConnector** peerConns, int nPeers, int* outRegBufFlag, void** outHandle);
+ncclResult_t ncclNetGraphRegisterBuffer(ncclComm* comm, const void* userbuff, size_t buffSize, struct ncclConnector** peerConns, int nPeers, int* outRegBufFlag, void** outHandle, struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue, int* nCleanupQueueElts);
+
+ncclResult_t ncclRegisterP2pIpcBuffer(struct ncclComm* comm, void* userbuff, size_t size, int peerRank, int* regFlag, void** regAddr, struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue);
+ncclResult_t ncclRegisterP2pNetBuffer(struct ncclComm* comm, void* userbuff, size_t size, struct ncclConnector* conn, int* regFlag, void** handle, struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue);
+ncclResult_t ncclRegisterCollBuffers(struct ncclComm* comm, struct ncclTaskColl* info, void* outRegBufSend[NCCL_MAX_LOCAL_RANKS], void* outRegBufRecv[NCCL_MAX_LOCAL_RANKS], struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue, bool* regNeedConnect);
+ncclResult_t ncclRegisterCollNvlsBuffers(struct ncclComm* comm, struct ncclTaskColl* info, void* outRegBufSend[NCCL_MAX_LOCAL_RANKS], void* outRegBufRecv[NCCL_MAX_LOCAL_RANKS], struct ncclIntruQueue<struct ncclCommCallback, &ncclCommCallback::next>* cleanupQueue, bool* regNeedConnect);
+
 #endif