Rashika Kheria
93840e7476
NCCL Net v4 supports a maximum handle size of 64 bytes whereas the ext-net example header files set it for NCCL Net v3. Since, `aws-ofi-nccl` plugin plans to follow the example header files, fix it here. Signed-off-by: Rashika Kheria <rashika@amazon.com>
51 lines
2.3 KiB
C
51 lines
2.3 KiB
C
/*
|
|
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
|
*/
|
|
|
|
#ifndef NCCL_NET_V3_H_
|
|
#define NCCL_NET_V3_H_
|
|
|
|
#define NCCL_NET_MAX_REQUESTS_V3 16
|
|
|
|
typedef ncclNetProperties_v4_t ncclNetProperties_v3_t;
|
|
typedef struct {
|
|
// Name of the network (mainly for logs)
|
|
const char* name;
|
|
// Initialize the network.
|
|
ncclResult_t (*init)(ncclDebugLogger_t logFunction);
|
|
// Return the number of adapters.
|
|
ncclResult_t (*devices)(int* ndev);
|
|
// Get various device properties.
|
|
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v3_t* props);
|
|
// Create a receiving object and provide a handle to connect to it. The
|
|
// handle can be up to NCCL_NET_HANDLE_MAXSIZE bytes and will be exchanged
|
|
// between ranks to create a connection.
|
|
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
|
|
// Connect to a handle and return a sending comm object for that peer.
|
|
ncclResult_t (*connect)(int dev, void* handle, void** sendComm);
|
|
// Finalize connection establishment after remote peer has called connectHandle
|
|
ncclResult_t (*accept)(void* listenComm, void** recvComm);
|
|
// Register/Deregister memory. Comm can be either a sendComm or a recvComm.
|
|
// Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
|
|
ncclResult_t (*regMr)(void* comm, void* data, int size, int type, void** mhandle);
|
|
ncclResult_t (*deregMr)(void* comm, void* mhandle);
|
|
// Asynchronous send to a peer.
|
|
// May return request == NULL if the call cannot be performed (or would block)
|
|
ncclResult_t (*isend)(void* sendComm, void* data, int size, void* mhandle, void** request);
|
|
// Asynchronous recv from a peer.
|
|
// May return request == NULL if the call cannot be performed (or would block)
|
|
ncclResult_t (*irecv)(void* recvComm, void* data, int size, void* mhandle, void** request);
|
|
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
|
// visible to the GPU
|
|
ncclResult_t (*flush)(void* recvComm, void* data, int size, void* mhandle);
|
|
// Test whether a request is complete. If size is not NULL, it returns the
|
|
// number of bytes sent/received.
|
|
ncclResult_t (*test)(void* request, int* done, int* size);
|
|
// Close and free send/recv comm objects
|
|
ncclResult_t (*closeSend)(void* sendComm);
|
|
ncclResult_t (*closeRecv)(void* recvComm);
|
|
ncclResult_t (*closeListen)(void* listenComm);
|
|
} ncclNet_v3_t;
|
|
|
|
#endif // end include guard
|