Sylvain Jeaugey
d97a32fac8
Add support for IB SHARP to NVLS (NVLink SHARP algorithm). Add NVLS+Tree algorithm. Add support for memory management using cuMem* functions. Use all NICs for Send/Receive operations on systems with more than one NIC per GPU (#804). Add ncclCommSplit primitive, with resource sharing option in config. Fix alltoallv hang (#788) Increase number of channels on H100 when we're not limited by NVLink. Improve error reporting in case of IB failure, printing local and remote ID (#779). Add build option to allow compilation against RDMA includes instead of dynamically loading IB verbs symbols (#802). Fix context creation for progress thread (#803). NET/IB: add option to use multiple QPs in round-robin mode. Fix tree performance issue when NVB is disabled on HCM topologies.
28 خطوط
775 B
C
28 خطوط
775 B
C
/*************************************************************************
|
|
* Copyright (c) 2016-2022, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#ifndef NCCL_INT_NET_H_
|
|
#define NCCL_INT_NET_H_
|
|
|
|
#include "nccl.h"
|
|
#include "nccl_net.h"
|
|
#include "comm.h"
|
|
#include "checks.h"
|
|
|
|
typedef char ncclNetHandle_t[NCCL_NET_HANDLE_MAXSIZE];
|
|
|
|
ncclResult_t ncclNetPluginInit();
|
|
ncclResult_t ncclNetInit(struct ncclComm* comm);
|
|
int ncclNetVersion(struct ncclComm* comm);
|
|
|
|
// Test whether the current GPU support GPU Direct RDMA.
|
|
ncclResult_t ncclGpuGdrSupport(struct ncclComm* comm, int* gdrSupport);
|
|
|
|
extern ncclNet_t ncclNetIb;
|
|
extern ncclNet_t ncclNetSocket;
|
|
|
|
#endif
|