Merge remote-tracking branch 'nccl/master' into develop
[ROCm/rccl commit: aaf023976a]
This commit is contained in:
BertanDogancay
@@ -0,0 +1,60 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NCCL_NET_H_
|
||||
#define NCCL_NET_H_
|
||||
|
||||
#include "nccl.h"
|
||||
#include "nccl_common.h"
|
||||
#include "net_device.h"
|
||||
#include <stdint.h>
|
||||
|
||||
#define NCCL_NET_HANDLE_MAXSIZE 128
|
||||
//Maximum value NCCL can accept for maxP2pBytes and maxCollBytes net properties
|
||||
#define NCCL_MAX_NET_SIZE_BYTES (1*1024*1024*1024*1024L)
|
||||
#define NCCL_NET_OPTIONAL_RECV_COMPLETION 0x1
|
||||
|
||||
#define MAX_NET_SIZE (1024*1024*1024L) // Rather than send INT_MAX which is 2G-1, send a power of two.
|
||||
#define MAX_COLLNET_SIZE (512*1024*1024L) //Set for initial collent plugins when size was not dynamically queried
|
||||
|
||||
#define NCCL_PTR_HOST 0x1
|
||||
#define NCCL_PTR_CUDA 0x2
|
||||
#define NCCL_PTR_DMABUF 0x4
|
||||
|
||||
// Maximum number of requests per comm object
|
||||
#define NCCL_NET_MAX_REQUESTS 32
|
||||
|
||||
// Max number of ncclNet objects which can live in the same process
|
||||
#define NCCL_NET_MAX_PLUGINS 3
|
||||
|
||||
// NCCL core profiler callback for network defined events instrumentation
|
||||
typedef ncclResult_t (*ncclProfilerCallback_t)(void** eHandle, int type, void* pHandle, int64_t pluginId, void* extData);
|
||||
|
||||
#include "net/net_v10.h"
|
||||
#include "net/net_v9.h"
|
||||
#include "net/net_v8.h"
|
||||
#include "net/net_v7.h"
|
||||
#include "net/net_v6.h"
|
||||
|
||||
typedef ncclNet_v10_t ncclNet_t;
|
||||
typedef ncclCollNet_v10_t ncclCollNet_t;
|
||||
typedef ncclNetSGE_v10_t ncclNetSGE_t;
|
||||
typedef ncclNetProperties_v10_t ncclNetProperties_t;
|
||||
typedef ncclNetVDeviceProps_v10_t ncclNetVDeviceProps_t;
|
||||
typedef ncclNetCommConfig_v10_t ncclNetCommConfig_t;
|
||||
|
||||
#define NCCL_NET_MAX_DEVS_PER_NIC NCCL_NET_MAX_DEVS_PER_NIC_V10
|
||||
|
||||
#define NCCL_NET_PLUGIN_SYMBOL ncclNetPlugin_v10
|
||||
#define NCCL_COLLNET_PLUGIN_SYMBOL ncclCollNetPlugin_v10
|
||||
|
||||
// context passed from RCCL lib to n/w plugin
|
||||
typedef struct {
|
||||
// channel id
|
||||
uint32_t chId;
|
||||
} ncclNet_ctxt_t;
|
||||
|
||||
#endif // end include guard
|
||||
@@ -0,0 +1,69 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NCCL_PROFILER_H_
|
||||
#define NCCL_PROFILER_H_
|
||||
|
||||
enum {
|
||||
ncclProfileGroup = (1 << 0), // group event type
|
||||
ncclProfileColl = (1 << 1), // host collective call event type
|
||||
ncclProfileP2p = (1 << 2), // host point-to-point call event type
|
||||
ncclProfileProxyOp = (1 << 3), // proxy operation event type
|
||||
ncclProfileProxyStep = (1 << 4), // proxy step event type
|
||||
ncclProfileProxyCtrl = (1 << 5), // proxy control event type
|
||||
ncclProfileKernelCh = (1 << 6), // kernel channel event type
|
||||
ncclProfileNetPlugin = (1 << 7), // network plugin-defined, events
|
||||
};
|
||||
|
||||
typedef enum {
|
||||
ncclProfilerProxyOpSendPosted,
|
||||
ncclProfilerProxyOpSendRemFifoWait,
|
||||
ncclProfilerProxyOpSendTransmitted,
|
||||
ncclProfilerProxyOpSendDone,
|
||||
ncclProfilerProxyOpRecvPosted,
|
||||
ncclProfilerProxyOpRecvReceived,
|
||||
ncclProfilerProxyOpRecvTransmitted,
|
||||
ncclProfilerProxyOpRecvDone,
|
||||
|
||||
/* Legacy proxy profiler states */
|
||||
ncclProfilerProxyStepSendGPUWait,
|
||||
ncclProfilerProxyStepSendWait,
|
||||
ncclProfilerProxyStepRecvWait,
|
||||
ncclProfilerProxyStepRecvFlushWait,
|
||||
ncclProfilerProxyStepRecvGPUWait,
|
||||
|
||||
/* Legacy proxy control states */
|
||||
ncclProfilerProxyCtrlIdle,
|
||||
ncclProfilerProxyCtrlActive,
|
||||
ncclProfilerProxyCtrlSleep,
|
||||
ncclProfilerProxyCtrlWakeup,
|
||||
ncclProfilerProxyCtrlAppend,
|
||||
ncclProfilerProxyCtrlAppendEnd,
|
||||
} ncclProfilerEventState_t;
|
||||
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v1_t;
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v2_t;
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v3_t;
|
||||
|
||||
#include <cstdint>
|
||||
#include "profiler/profiler_v3.h"
|
||||
#include "profiler/profiler_v2.h"
|
||||
#include "profiler/profiler_v1.h"
|
||||
|
||||
typedef ncclProfiler_v3_t ncclProfiler_t;
|
||||
typedef ncclProfilerEventDescr_v3_t ncclProfilerEventDescr_t;
|
||||
typedef ncclProfilerEventStateArgs_v3_t ncclProfilerEventStateArgs_t;
|
||||
|
||||
#define NCCL_PROFILER_NET_VER_BITS (16)
|
||||
#define NCCL_PROFILER_NET_VER_MASK (~0U >> NCCL_PROFILER_NET_VER_BITS)
|
||||
#define NCCL_PROFILER_NET_TYPE_MASK (~0U << NCCL_PROFILER_NET_VER_BITS)
|
||||
|
||||
typedef enum {
|
||||
NCCL_PROFILER_NET_TYPE_IB = (1U << NCCL_PROFILER_NET_VER_BITS),
|
||||
NCCL_PROFILER_NET_TYPE_SOCK = (2U << NCCL_PROFILER_NET_VER_BITS),
|
||||
} ncclProfilerNetType;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,22 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved.
|
||||
* Copyright (c) 2023, Meta Platforms, Inc. and affiliates.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NCCL_TUNER_H_
|
||||
#define NCCL_TUNER_H_
|
||||
|
||||
#include "nccl.h"
|
||||
#include "nccl_common.h"
|
||||
|
||||
#include "tuner/tuner_v4.h"
|
||||
#include "tuner/tuner_v3.h"
|
||||
#include "tuner/tuner_v2.h"
|
||||
|
||||
typedef ncclTuner_v4_t ncclTuner_t;
|
||||
|
||||
#define NCCL_TUNER_PLUGIN_SYMBOL "ncclTunerPlugin_v4"
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,158 @@
|
||||
/*
|
||||
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*/
|
||||
|
||||
#ifndef NET_V10_H_
|
||||
#define NET_V10_H_
|
||||
|
||||
#define NCCL_NET_MAX_DEVS_PER_NIC_V10 4
|
||||
|
||||
typedef struct {
|
||||
int ndevs;
|
||||
int devs[NCCL_NET_MAX_DEVS_PER_NIC_V10];
|
||||
} ncclNetVDeviceProps_v10_t;
|
||||
|
||||
#define NCCL_NET_TRAFFIC_CLASS_UNDEF -1
|
||||
|
||||
typedef struct {
|
||||
// Plugin-specific TC value
|
||||
int trafficClass;
|
||||
} ncclNetCommConfig_v10_t;
|
||||
|
||||
|
||||
typedef struct {
|
||||
char* name; // Used mostly for logging.
|
||||
char* pciPath; // Path to the PCI device in /sys.
|
||||
uint64_t guid; // Unique identifier for the NIC chip. Important for
|
||||
// cards with multiple PCI functions (Physical or virtual).
|
||||
int ptrSupport; // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
|
||||
int regIsGlobal; // regMr is not tied to a particular comm
|
||||
int forceFlush; // Force a flush on receives
|
||||
int speed; // Port speed in Mbps.
|
||||
int port; // Port number.
|
||||
float latency; // Network latency
|
||||
int maxComms; // Maximum number of comms we can create
|
||||
int maxRecvs; // Maximum number of grouped receives.
|
||||
ncclNetDeviceType netDeviceType; // Network offload type
|
||||
int netDeviceVersion; // Version number for network offload
|
||||
ncclNetVDeviceProps_v10_t vProps;
|
||||
size_t maxP2pBytes; // Max transfer size for point-to-point operations
|
||||
size_t maxCollBytes; // Max transfer size for collective operations
|
||||
} ncclNetProperties_v10_t;
|
||||
|
||||
typedef struct {
|
||||
// Name of the network (mainly for logs)
|
||||
const char* name;
|
||||
// Initialize the network.
|
||||
ncclResult_t (*init)(ncclDebugLogger_t logFunction, ncclProfilerCallback_t profFunction);
|
||||
// Return the number of adapters.
|
||||
ncclResult_t (*devices)(int* ndev);
|
||||
// Get various device properties.
|
||||
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v10_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.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with sendComm == NULL with the expectation that
|
||||
// it will be called again until sendComm != NULL.
|
||||
// If *sendDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*connect)(int dev, ncclNetCommConfig_v10_t* config, void* handle, void** sendComm, ncclNetDeviceHandle_v10_t** sendDevComm);
|
||||
// Finalize connection establishment after remote peer has called connect.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with recvComm == NULL with the expectation that
|
||||
// it will be called again until recvComm != NULL.
|
||||
// If *recvDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*accept)(void* listenComm, void** recvComm, ncclNetDeviceHandle_v10_t** recvDevComm);
|
||||
// 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, size_t size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, 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, size_t size, int tag, void* mhandle, void* phandle, 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, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** phandles, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
|
||||
// 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* sizes);
|
||||
// Close and free send/recv comm objects
|
||||
ncclResult_t (*closeSend)(void* sendComm);
|
||||
ncclResult_t (*closeRecv)(void* recvComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
|
||||
// Copy the given mhandle to a dptr in a format usable by this plugin's device code
|
||||
ncclResult_t (*getDeviceMr)(void* comm, void* mhandle, void** dptr_mhandle);
|
||||
|
||||
// Notify the plugin that a recv has completed by the device
|
||||
ncclResult_t (*irecvConsumed)(void* recvComm, int n, void* request);
|
||||
|
||||
// Virtual NIC APIs. makeVDevice will create a virtual NIC given the specified properties, and tell the caller
|
||||
// what index this new vNIC exists at
|
||||
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v10_t* props);
|
||||
} ncclNet_v10_t;
|
||||
|
||||
typedef struct {
|
||||
void* mhandle;
|
||||
void* address;
|
||||
size_t size;
|
||||
} ncclNetSGE_v10_t;
|
||||
|
||||
typedef struct {
|
||||
// Name of the collective network (mainly for logs)
|
||||
const char* name;
|
||||
// Initialize the collective network.
|
||||
ncclResult_t (*init)(ncclDebugLogger_t logFunction);
|
||||
// Return the number of adapters capable of doing collective operations.
|
||||
// If ndev returns 0, all other functions might be set to NULL.
|
||||
ncclResult_t (*devices)(int* ndev);
|
||||
// Get various device properties.
|
||||
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v10_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 connections.
|
||||
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
|
||||
// Create a group for collective operations. handles have been created
|
||||
// using listen() above. rank indicates caller's rank in the collective network.
|
||||
ncclResult_t (*connect)(void* handles[], int nranks, int rank, void* listenComm, void** collComm);
|
||||
// Returns whether a reduction operation on a data type is supported.
|
||||
// 1 for supported, 0 otherwise.
|
||||
ncclResult_t (*reduceSupport)(ncclDataType_t dataType, ncclRedOp_t redOp, int* supported);
|
||||
// Register/Deregister memory. Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
|
||||
ncclResult_t (*regMr)(void* collComm, void* data, size_t size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
|
||||
ncclResult_t (*deregMr)(void* collComm, void* mhandle);
|
||||
// Performs an asynchronous allreduce operation on the collective group.
|
||||
// May return request == NULL if the call cannot be performed (or would block).
|
||||
ncclResult_t (*iallreduce)(void* collComm, void* sendData, void* recvData, size_t count,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp, void* sendMhandle, void* recvMhandle, void** request);
|
||||
ncclResult_t (*iallgather)(void* collComm, void* sendData, int nRecvParts, ncclNetSGE_v10_t* recvParts,
|
||||
size_t bytesPerRank, size_t windowOffset, size_t windowBytes,
|
||||
void* sendMhandle, void** request);
|
||||
ncclResult_t (*ireducescatter)(void* collComm, int nSendParts, ncclNetSGE_v10_t* sendParts, void* recvData,
|
||||
size_t bytesPerRank, size_t windowOffset, size_t windowBytes,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp,
|
||||
void* recvMhandle, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* collComm, void* data, int size, void* mhandle, void** request);
|
||||
// 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 collective comm objects
|
||||
ncclResult_t (*closeColl)(void* collComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
|
||||
// Create a virtual NIC given the specified properties, which can be accessed at device index d
|
||||
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v10_t* props);
|
||||
} ncclCollNet_v10_t;
|
||||
|
||||
#endif // end include guard
|
||||
@@ -0,0 +1,113 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_V6_H_
|
||||
#define NET_V6_H_
|
||||
|
||||
#define NCCL_NET_MAX_REQUESTS_V6 8
|
||||
|
||||
// v6 struct for backwards compatibility
|
||||
typedef struct {
|
||||
char* name; // Used mostly for logging.
|
||||
char* pciPath; // Path to the PCI device in /sys.
|
||||
uint64_t guid; // Unique identifier for the NIC chip. Important for
|
||||
// cards with multiple PCI functions (Physical or virtual).
|
||||
int ptrSupport; // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
|
||||
int speed; // Port speed in Mbps.
|
||||
int port; // Port number.
|
||||
float latency; // Network latency
|
||||
int maxComms; // Maximum number of comms we can create
|
||||
int maxRecvs; // Maximum number of grouped receives.
|
||||
} ncclNetProperties_v6_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_v6_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.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with sendComm == NULL with the expectation that
|
||||
// it will be called again until sendComm != NULL.
|
||||
ncclResult_t (*connect)(int dev, void* handle, void** sendComm);
|
||||
// Finalize connection establishment after remote peer has called connect.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with recvComm == NULL with the expectation that
|
||||
// it will be called again until recvComm != NULL.
|
||||
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);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, 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, int tag, 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, int n, void** data, int* sizes, int* tags, void** mhandles, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
|
||||
// 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* sizes);
|
||||
// Close and free send/recv comm objects
|
||||
ncclResult_t (*closeSend)(void* sendComm);
|
||||
ncclResult_t (*closeRecv)(void* recvComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
} ncclNet_v6_t;
|
||||
|
||||
typedef struct {
|
||||
// Name of the collective network (mainly for logs)
|
||||
const char* name;
|
||||
// Initialize the collective network.
|
||||
ncclResult_t (*init)(ncclDebugLogger_t logFunction);
|
||||
// Return the number of adapters capable of doing collective operations.
|
||||
// If ndev returns 0, all other functions might be set to NULL.
|
||||
ncclResult_t (*devices)(int* ndev);
|
||||
// Get various device properties.
|
||||
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v6_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 connections.
|
||||
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
|
||||
// Create a group for collective operations. handles have been created
|
||||
// using listen() above. rank indicates caller's rank in the collective network.
|
||||
ncclResult_t (*connect)(void* handles[], int nranks, int rank, void* listenComm, void** collComm);
|
||||
// Returns whether a reduction operation on a data type is supported.
|
||||
// 1 for supported, 0 otherwise.
|
||||
ncclResult_t (*reduceSupport)(ncclDataType_t dataType, ncclRedOp_t redOp, int* supported);
|
||||
// Register/Deregister memory. Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
|
||||
ncclResult_t (*regMr)(void* collComm, void* data, int size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
|
||||
ncclResult_t (*deregMr)(void* collComm, void* mhandle);
|
||||
// Performs an asynchronous allreduce operation on the collective group.
|
||||
// May return request == NULL if the call cannot be performed (or would block).
|
||||
ncclResult_t (*iallreduce)(void* collComm, void* sendData, void* recvData, int count,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp, void* sendMhandle, void* recvMhandle, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* collComm, void* data, int size, void* mhandle, void** request);
|
||||
// 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 collective comm objects
|
||||
ncclResult_t (*closeColl)(void* collComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
} ncclCollNet_v6_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,120 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_V7_H_
|
||||
#define NET_V7_H_
|
||||
|
||||
typedef struct {
|
||||
char* name; // Used mostly for logging.
|
||||
char* pciPath; // Path to the PCI device in /sys.
|
||||
uint64_t guid; // Unique identifier for the NIC chip. Important for
|
||||
// cards with multiple PCI functions (Physical or virtual).
|
||||
int ptrSupport; // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
|
||||
int speed; // Port speed in Mbps.
|
||||
int port; // Port number.
|
||||
float latency; // Network latency
|
||||
int maxComms; // Maximum number of comms we can create
|
||||
int maxRecvs; // Maximum number of grouped receives.
|
||||
ncclNetDeviceType netDeviceType; // Network offload type
|
||||
int netDeviceVersion; // Version number for network offload
|
||||
} ncclNetProperties_v7_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_v7_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.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with sendComm == NULL with the expectation that
|
||||
// it will be called again until sendComm != NULL.
|
||||
// If *sendDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*connect)(int dev, void* handle, void** sendComm, ncclNetDeviceHandle_v7_t** sendDevComm);
|
||||
// Finalize connection establishment after remote peer has called connect.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with recvComm == NULL with the expectation that
|
||||
// it will be called again until recvComm != NULL.
|
||||
// If *recvDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*accept)(void* listenComm, void** recvComm, ncclNetDeviceHandle_v7_t** recvDevComm);
|
||||
// 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);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, 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, int tag, 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, int n, void** data, int* sizes, int* tags, void** mhandles, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
|
||||
// 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* sizes);
|
||||
// Close and free send/recv comm objects
|
||||
ncclResult_t (*closeSend)(void* sendComm);
|
||||
ncclResult_t (*closeRecv)(void* recvComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
|
||||
// Copy the given mhandle to a dptr in a format usable by this plugin's device code
|
||||
ncclResult_t (*getDeviceMr)(void* comm, void* mhandle, void** dptr_mhandle);
|
||||
|
||||
// Notify the plugin that a recv has completed by the device
|
||||
ncclResult_t (*irecvConsumed)(void* recvComm, int n, void* request);
|
||||
} ncclNet_v7_t;
|
||||
|
||||
typedef struct {
|
||||
// Name of the collective network (mainly for logs)
|
||||
const char* name;
|
||||
// Initialize the collective network.
|
||||
ncclResult_t (*init)(ncclDebugLogger_t logFunction);
|
||||
// Return the number of adapters capable of doing collective operations.
|
||||
// If ndev returns 0, all other functions might be set to NULL.
|
||||
ncclResult_t (*devices)(int* ndev);
|
||||
// Get various device properties.
|
||||
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v7_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 connections.
|
||||
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
|
||||
// Create a group for collective operations. handles have been created
|
||||
// using listen() above. rank indicates caller's rank in the collective network.
|
||||
ncclResult_t (*connect)(void* handles[], int nranks, int rank, void* listenComm, void** collComm);
|
||||
// Returns whether a reduction operation on a data type is supported.
|
||||
// 1 for supported, 0 otherwise.
|
||||
ncclResult_t (*reduceSupport)(ncclDataType_t dataType, ncclRedOp_t redOp, int* supported);
|
||||
// Register/Deregister memory. Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
|
||||
ncclResult_t (*regMr)(void* collComm, void* data, int size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
|
||||
ncclResult_t (*deregMr)(void* collComm, void* mhandle);
|
||||
// Performs an asynchronous allreduce operation on the collective group.
|
||||
// May return request == NULL if the call cannot be performed (or would block).
|
||||
ncclResult_t (*iallreduce)(void* collComm, void* sendData, void* recvData, int count,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp, void* sendMhandle, void* recvMhandle, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* collComm, void* data, int size, void* mhandle, void** request);
|
||||
// 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 collective comm objects
|
||||
ncclResult_t (*closeColl)(void* collComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
} ncclCollNet_v7_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,134 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_V8_H_
|
||||
#define NET_V8_H_
|
||||
|
||||
typedef struct {
|
||||
char* name; // Used mostly for logging.
|
||||
char* pciPath; // Path to the PCI device in /sys.
|
||||
uint64_t guid; // Unique identifier for the NIC chip. Important for
|
||||
// cards with multiple PCI functions (Physical or virtual).
|
||||
int ptrSupport; // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
|
||||
int regIsGlobal; // regMr is not tied to a particular comm
|
||||
int speed; // Port speed in Mbps.
|
||||
int port; // Port number.
|
||||
float latency; // Network latency
|
||||
int maxComms; // Maximum number of comms we can create
|
||||
int maxRecvs; // Maximum number of grouped receives.
|
||||
ncclNetDeviceType netDeviceType; // Network offload type
|
||||
int netDeviceVersion; // Version number for network offload
|
||||
} ncclNetProperties_v8_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_v8_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.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with sendComm == NULL with the expectation that
|
||||
// it will be called again until sendComm != NULL.
|
||||
// If *sendDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*connect)(int dev, void* handle, void** sendComm, ncclNetDeviceHandle_v8_t** sendDevComm);
|
||||
// Finalize connection establishment after remote peer has called connect.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with recvComm == NULL with the expectation that
|
||||
// it will be called again until recvComm != NULL.
|
||||
// If *recvDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*accept)(void* listenComm, void** recvComm, ncclNetDeviceHandle_v8_t** recvDevComm);
|
||||
// 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, size_t size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, 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, int tag, 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, int n, void** data, int* sizes, int* tags, void** mhandles, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
|
||||
// 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* sizes);
|
||||
// Close and free send/recv comm objects
|
||||
ncclResult_t (*closeSend)(void* sendComm);
|
||||
ncclResult_t (*closeRecv)(void* recvComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
|
||||
// Copy the given mhandle to a dptr in a format usable by this plugin's device code
|
||||
ncclResult_t (*getDeviceMr)(void* comm, void* mhandle, void** dptr_mhandle);
|
||||
|
||||
// Notify the plugin that a recv has completed by the device
|
||||
ncclResult_t (*irecvConsumed)(void* recvComm, int n, void* request);
|
||||
} ncclNet_v8_t;
|
||||
|
||||
typedef struct {
|
||||
void* mhandle;
|
||||
void* address;
|
||||
uint32_t size;
|
||||
} ncclNetSGE_v8_t;
|
||||
|
||||
typedef struct {
|
||||
// Name of the collective network (mainly for logs)
|
||||
const char* name;
|
||||
// Initialize the collective network.
|
||||
ncclResult_t (*init)(ncclDebugLogger_t logFunction);
|
||||
// Return the number of adapters capable of doing collective operations.
|
||||
// If ndev returns 0, all other functions might be set to NULL.
|
||||
ncclResult_t (*devices)(int* ndev);
|
||||
// Get various device properties.
|
||||
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v8_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 connections.
|
||||
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
|
||||
// Create a group for collective operations. handles have been created
|
||||
// using listen() above. rank indicates caller's rank in the collective network.
|
||||
ncclResult_t (*connect)(void* handles[], int nranks, int rank, void* listenComm, void** collComm);
|
||||
// Returns whether a reduction operation on a data type is supported.
|
||||
// 1 for supported, 0 otherwise.
|
||||
ncclResult_t (*reduceSupport)(ncclDataType_t dataType, ncclRedOp_t redOp, int* supported);
|
||||
// Register/Deregister memory. Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
|
||||
ncclResult_t (*regMr)(void* collComm, void* data, size_t size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
|
||||
ncclResult_t (*deregMr)(void* collComm, void* mhandle);
|
||||
// Performs an asynchronous allreduce operation on the collective group.
|
||||
// May return request == NULL if the call cannot be performed (or would block).
|
||||
ncclResult_t (*iallreduce)(void* collComm, void* sendData, void* recvData, int count,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp, void* sendMhandle, void* recvMhandle, void** request);
|
||||
ncclResult_t (*iallgather)(void* collComm, void* sendData, int nRecvParts, ncclNetSGE_v8_t* recvParts,
|
||||
size_t bytesPerRank, size_t windowOffset, size_t windowBytes,
|
||||
void* sendMhandle, void** request);
|
||||
ncclResult_t (*ireducescatter)(void* collComm, int nSendParts, ncclNetSGE_v8_t* sendParts, void* recvData,
|
||||
size_t bytesPerRank, size_t windowOffset, size_t windowBytes,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp,
|
||||
void* recvMhandle, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* collComm, void* data, int size, void* mhandle, void** request);
|
||||
// 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 collective comm objects
|
||||
ncclResult_t (*closeColl)(void* collComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
} ncclCollNet_v8_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,152 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_V9_H_
|
||||
#define NET_V9_H_
|
||||
|
||||
#define NCCL_NET_MAX_DEVS_PER_NIC_V9 4
|
||||
|
||||
typedef struct {
|
||||
int ndevs;
|
||||
int devs[NCCL_NET_MAX_DEVS_PER_NIC_V9];
|
||||
} ncclNetVDeviceProps_v9_t;
|
||||
|
||||
typedef struct {
|
||||
char* name; // Used mostly for logging.
|
||||
char* pciPath; // Path to the PCI device in /sys.
|
||||
uint64_t guid; // Unique identifier for the NIC chip. Important for
|
||||
// cards with multiple PCI functions (Physical or virtual).
|
||||
int ptrSupport; // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
|
||||
int regIsGlobal; // regMr is not tied to a particular comm
|
||||
int forceFlush; // Force a flush on receives
|
||||
int speed; // Port speed in Mbps.
|
||||
int port; // Port number.
|
||||
float latency; // Network latency
|
||||
int maxComms; // Maximum number of comms we can create
|
||||
int maxRecvs; // Maximum number of grouped receives.
|
||||
ncclNetDeviceType netDeviceType; // Network offload type
|
||||
int netDeviceVersion; // Version number for network offload
|
||||
ncclNetVDeviceProps_v9_t vProps;
|
||||
size_t maxP2pBytes; // Max transfer size for point-to-point operations
|
||||
size_t maxCollBytes; // Max transfer size for collective operations
|
||||
} ncclNetProperties_v9_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_v9_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.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with sendComm == NULL with the expectation that
|
||||
// it will be called again until sendComm != NULL.
|
||||
// If *sendDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*connect)(int dev, void* handle, void** sendComm, ncclNetDeviceHandle_v9_t** sendDevComm);
|
||||
// Finalize connection establishment after remote peer has called connect.
|
||||
// This call must not block for the connection to be established, and instead
|
||||
// should return successfully with recvComm == NULL with the expectation that
|
||||
// it will be called again until recvComm != NULL.
|
||||
// If *recvDevComm points to a valid object, then NCCL is requesting device offload for this connection
|
||||
ncclResult_t (*accept)(void* listenComm, void** recvComm, ncclNetDeviceHandle_v9_t** recvDevComm);
|
||||
// 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, size_t size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, 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, size_t size, int tag, 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, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
|
||||
// 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* sizes);
|
||||
// Close and free send/recv comm objects
|
||||
ncclResult_t (*closeSend)(void* sendComm);
|
||||
ncclResult_t (*closeRecv)(void* recvComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
|
||||
// Copy the given mhandle to a dptr in a format usable by this plugin's device code
|
||||
ncclResult_t (*getDeviceMr)(void* comm, void* mhandle, void** dptr_mhandle);
|
||||
|
||||
// Notify the plugin that a recv has completed by the device
|
||||
ncclResult_t (*irecvConsumed)(void* recvComm, int n, void* request);
|
||||
|
||||
// Virtual NIC APIs. makeVDevice will create a virtual NIC given the specified properties, and tell the caller
|
||||
// what index this new vNIC exists at
|
||||
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v9_t* props);
|
||||
} ncclNet_v9_t;
|
||||
|
||||
typedef struct {
|
||||
void* mhandle;
|
||||
void* address;
|
||||
size_t size;
|
||||
} ncclNetSGE_v9_t;
|
||||
|
||||
typedef struct {
|
||||
// Name of the collective network (mainly for logs)
|
||||
const char* name;
|
||||
// Initialize the collective network.
|
||||
ncclResult_t (*init)(ncclDebugLogger_t logFunction);
|
||||
// Return the number of adapters capable of doing collective operations.
|
||||
// If ndev returns 0, all other functions might be set to NULL.
|
||||
ncclResult_t (*devices)(int* ndev);
|
||||
// Get various device properties.
|
||||
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v9_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 connections.
|
||||
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
|
||||
// Create a group for collective operations. handles have been created
|
||||
// using listen() above. rank indicates caller's rank in the collective network.
|
||||
ncclResult_t (*connect)(void* handles[], int nranks, int rank, void* listenComm, void** collComm);
|
||||
// Returns whether a reduction operation on a data type is supported.
|
||||
// 1 for supported, 0 otherwise.
|
||||
ncclResult_t (*reduceSupport)(ncclDataType_t dataType, ncclRedOp_t redOp, int* supported);
|
||||
// Register/Deregister memory. Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
|
||||
ncclResult_t (*regMr)(void* collComm, void* data, size_t size, int type, void** mhandle);
|
||||
/* DMA-BUF support */
|
||||
ncclResult_t (*regMrDmaBuf)(void* collComm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
|
||||
ncclResult_t (*deregMr)(void* collComm, void* mhandle);
|
||||
// Performs an asynchronous allreduce operation on the collective group.
|
||||
// May return request == NULL if the call cannot be performed (or would block).
|
||||
ncclResult_t (*iallreduce)(void* collComm, void* sendData, void* recvData, size_t count,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp, void* sendMhandle, void* recvMhandle, void** request);
|
||||
ncclResult_t (*iallgather)(void* collComm, void* sendData, int nRecvParts, ncclNetSGE_v9_t* recvParts,
|
||||
size_t bytesPerRank, size_t windowOffset, size_t windowBytes,
|
||||
void* sendMhandle, void** request);
|
||||
ncclResult_t (*ireducescatter)(void* collComm, int nSendParts, ncclNetSGE_v9_t* sendParts, void* recvData,
|
||||
size_t bytesPerRank, size_t windowOffset, size_t windowBytes,
|
||||
ncclDataType_t dataType, ncclRedOp_t redOp,
|
||||
void* recvMhandle, void** request);
|
||||
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
|
||||
// visible to the GPU
|
||||
ncclResult_t (*iflush)(void* collComm, void* data, int size, void* mhandle, void** request);
|
||||
// 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 collective comm objects
|
||||
ncclResult_t (*closeColl)(void* collComm);
|
||||
ncclResult_t (*closeListen)(void* listenComm);
|
||||
|
||||
// Create a virtual NIC given the specified properties, which can be accessed at device index d
|
||||
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v9_t* props);
|
||||
} ncclCollNet_v9_t;
|
||||
|
||||
#endif // end include guard
|
||||
@@ -0,0 +1,18 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024-2025, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NCCL_PLUGIN_H_
|
||||
#define NCCL_PLUGIN_H_
|
||||
|
||||
#include "nccl.h"
|
||||
|
||||
void* ncclOpenNetPluginLib(const char* name);
|
||||
void* ncclOpenTunerPluginLib(const char* name);
|
||||
void* ncclOpenProfilerPluginLib(const char* name);
|
||||
void* ncclGetNetPluginLib(void);
|
||||
ncclResult_t ncclClosePluginLib(void* handle);
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,13 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_IB_H_
|
||||
#define NET_IB_H_
|
||||
|
||||
#include "nccl_profiler.h"
|
||||
#include "net_ib_v1.h"
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,34 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_IB_V1_H_
|
||||
#define NET_IB_V1_H_
|
||||
|
||||
#define NCCL_PROFILER_NET_IB_VER 1
|
||||
|
||||
enum {
|
||||
ncclProfileQp = (1 << 0),
|
||||
};
|
||||
|
||||
// The data structure version is encoded in the plugin identifier bitmask and
|
||||
// passed to NCCL core through the profiler callback. NCCL copies the plugin
|
||||
// identifier in the event descriptor before calling the profiler startEvent
|
||||
// function. The profiler should inspect the plugin id to find out the source
|
||||
// plugin as well as the version of the event struct
|
||||
typedef struct {
|
||||
uint8_t type; // event type (plugin defined)
|
||||
union {
|
||||
struct {
|
||||
int device; // network device id
|
||||
uint64_t wr_id; // work request id
|
||||
int opcode; // ibv opcode
|
||||
int qpNum; // QP number
|
||||
size_t length; // work request data length
|
||||
} qp;
|
||||
};
|
||||
} ncclProfilerNetIbDescr_v1_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,13 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_SOCKET_H_
|
||||
#define NET_SOCKET_H_
|
||||
|
||||
#include "nccl_profiler.h"
|
||||
#include "net_socket_v1.h"
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,32 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef NET_SOCKET_V1_H_
|
||||
#define NET_SOCKET_V1_H_
|
||||
|
||||
#define NCCL_PROFILER_NET_SOCKET_VER 1
|
||||
|
||||
enum {
|
||||
ncclProfileSocket = (1 << 0),
|
||||
};
|
||||
|
||||
// The data structure version is encoded in the plugin identifier bitmask and
|
||||
// passed to NCCL core through the profiler callback. NCCL copies the plugin
|
||||
// identifier in the event descriptor before calling the profiler startEvent
|
||||
// function. The profiler should inspect the plugin id to find out the source
|
||||
// plugin as well as the version of the event struct
|
||||
typedef struct {
|
||||
uint8_t type; // event type (plugin defined)
|
||||
union {
|
||||
struct {
|
||||
int fd;
|
||||
int op;
|
||||
size_t length;
|
||||
} sock;
|
||||
};
|
||||
} ncclProfilerNetSockDescr_v1_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,107 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef PROFILER_V1_H_
|
||||
#define PROFILER_V1_H_
|
||||
|
||||
typedef struct {
|
||||
uint8_t type; // event type descriptor: ncclProfileColl, ...
|
||||
void* parentObj; // pointer to the profiler parent object (for coll is the group)
|
||||
int rank; // originating rank
|
||||
union {
|
||||
struct {
|
||||
const char* name;
|
||||
uint64_t commHash;
|
||||
uint64_t seqNumber;
|
||||
uint8_t func;
|
||||
void const* sendBuff;
|
||||
void* recvBuff;
|
||||
size_t count;
|
||||
int root;
|
||||
uint8_t datatype;
|
||||
uint32_t op;
|
||||
size_t trafficBytes;
|
||||
uint8_t nMaxChannels;
|
||||
uint8_t nWarps;
|
||||
uint8_t algo;
|
||||
uint8_t proto;
|
||||
int isCollnet;
|
||||
int isNvls;
|
||||
} coll;
|
||||
|
||||
struct {
|
||||
const char* name;
|
||||
uint64_t commHash;
|
||||
uint8_t func;
|
||||
void* buff;
|
||||
uint8_t datatype;
|
||||
size_t count;
|
||||
int peer;
|
||||
} p2p;
|
||||
|
||||
struct {
|
||||
pid_t pid; // pid of the originating process
|
||||
uint8_t channelId; // channel id for this proxy operation
|
||||
int peer; // remote rank for send/recv
|
||||
int nSteps; // number of steps for this proxy operation
|
||||
int chunkSize; // amount of data transferred by this proxy operation
|
||||
int isSend;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int step;
|
||||
} proxyStep;
|
||||
};
|
||||
} ncclProfilerEventDescr_v1_t;
|
||||
|
||||
typedef union {
|
||||
struct {
|
||||
size_t transSize;
|
||||
int steps;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int appendedProxyOps;
|
||||
} proxyCtrl;
|
||||
} ncclProfilerEventStateArgs_v1_t;
|
||||
|
||||
typedef struct {
|
||||
const char* name;
|
||||
|
||||
// init - initialize the profiler plugin
|
||||
// Input
|
||||
// - context : opaque profiler context object for separating profiler behavior across comms
|
||||
// Output
|
||||
// - eActivationMask: bitmask of active events set by the plugin
|
||||
ncclResult_t (*init)(void** context, int* eActivationMask);
|
||||
|
||||
// startEvent - initialize and start a new event for the supplied event descriptor inside the eventset
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
// - eDescr : pointer to ncclProfilerEventDescr_t object
|
||||
// Output
|
||||
// - eHandle: return event handle for supplied event descriptor object
|
||||
ncclResult_t (*startEvent)(void* context, void** eHandle, ncclProfilerEventDescr_v1_t* eDescr);
|
||||
|
||||
// stopEvent - stop/finalize an event inside and event set
|
||||
// Input
|
||||
// - eHandle: handle to event object
|
||||
ncclResult_t (*stopEvent)(void* eHandle);
|
||||
|
||||
// recordEventState - record event state transitions and event attribute updates
|
||||
// Input
|
||||
// - eHandle : handle to event object created through startEvent
|
||||
// - eStateArgs: optional argument used to capture event attribute updates associated with the state transition
|
||||
// - eState : event state transition
|
||||
ncclResult_t (*recordEventState)(void* eHandle, ncclProfilerEventState_v1_t eState, ncclProfilerEventStateArgs_v1_t* eStateArgs);
|
||||
|
||||
// finalize - finalize the profiler plugin
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
ncclResult_t (*finalize)(void* context);
|
||||
} ncclProfiler_v1_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,104 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef PROFILER_V2_H_
|
||||
#define PROFILER_V2_H_
|
||||
|
||||
typedef struct {
|
||||
uint8_t type; // event type descriptor: ncclProfileColl, ...
|
||||
void* parentObj; // pointer to the profiler parent object (for coll is the group)
|
||||
int rank; // originating rank
|
||||
union {
|
||||
struct {
|
||||
const char* name;
|
||||
uint64_t commHash;
|
||||
uint64_t seqNumber;
|
||||
const char* func;
|
||||
void const* sendBuff;
|
||||
void* recvBuff;
|
||||
size_t count;
|
||||
int root;
|
||||
const char* datatype;
|
||||
size_t trafficBytes;
|
||||
uint8_t nMaxChannels;
|
||||
uint8_t nWarps;
|
||||
const char* algo;
|
||||
const char* proto;
|
||||
} coll;
|
||||
|
||||
struct {
|
||||
const char* name;
|
||||
uint64_t commHash;
|
||||
const char* func;
|
||||
void* buff;
|
||||
const char* datatype;
|
||||
size_t count;
|
||||
int peer;
|
||||
} p2p;
|
||||
|
||||
struct {
|
||||
pid_t pid; // pid of the originating process
|
||||
uint8_t channelId; // channel id for this proxy operation
|
||||
int peer; // remote rank for send/recv
|
||||
int nSteps; // number of steps for this proxy operation
|
||||
int chunkSize; // amount of data transferred by this proxy operation
|
||||
int isSend;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int step;
|
||||
} proxyStep;
|
||||
};
|
||||
} ncclProfilerEventDescr_v2_t;
|
||||
|
||||
typedef union {
|
||||
struct {
|
||||
size_t transSize;
|
||||
int steps;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int appendedProxyOps;
|
||||
} proxyCtrl;
|
||||
} ncclProfilerEventStateArgs_v2_t;
|
||||
|
||||
typedef struct {
|
||||
const char* name;
|
||||
|
||||
// init - initialize the profiler plugin
|
||||
// Input
|
||||
// - context : opaque profiler context object for separating profiler behavior across comms
|
||||
// Output
|
||||
// - eActivationMask: bitmask of active events set by the plugin
|
||||
ncclResult_t (*init)(void** context, int* eActivationMask);
|
||||
|
||||
// startEvent - initialize and start a new event for the supplied event descriptor inside the eventset
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
// - eDescr : pointer to ncclProfilerEventDescr_t object
|
||||
// Output
|
||||
// - eHandle: return event handle for supplied event descriptor object
|
||||
ncclResult_t (*startEvent)(void* context, void** eHandle, ncclProfilerEventDescr_v2_t* eDescr);
|
||||
|
||||
// stopEvent - stop/finalize an event inside and event set
|
||||
// Input
|
||||
// - eHandle: handle to event object
|
||||
ncclResult_t (*stopEvent)(void* eHandle);
|
||||
|
||||
// recordEventState - record event state transitions and event attribute updates
|
||||
// Input
|
||||
// - eHandle : handle to event object created through startEvent
|
||||
// - eStateArgs: optional argument used to capture event attribute updates associated with the state transition
|
||||
// - eState : event state transition
|
||||
ncclResult_t (*recordEventState)(void* eHandle, ncclProfilerEventState_v2_t eState, ncclProfilerEventStateArgs_v2_t* eStateArgs);
|
||||
|
||||
// finalize - finalize the profiler plugin
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
ncclResult_t (*finalize)(void* context);
|
||||
} ncclProfiler_v2_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,112 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef PROFILER_V3_H_
|
||||
#define PROFILER_V3_H_
|
||||
|
||||
typedef struct {
|
||||
uint8_t type; // event type descriptor: ncclProfileColl, ...
|
||||
void* parentObj; // pointer to the profiler parent object (for coll is the group)
|
||||
int rank; // originating rank
|
||||
union {
|
||||
struct {
|
||||
const char* name;
|
||||
uint64_t commHash;
|
||||
uint64_t seqNumber;
|
||||
const char* func;
|
||||
void const* sendBuff;
|
||||
void* recvBuff;
|
||||
size_t count;
|
||||
int root;
|
||||
const char* datatype;
|
||||
uint8_t nMaxChannels;
|
||||
uint8_t nWarps;
|
||||
const char* algo;
|
||||
const char* proto;
|
||||
} coll;
|
||||
|
||||
struct {
|
||||
const char* name;
|
||||
uint64_t commHash;
|
||||
const char* func;
|
||||
void* buff;
|
||||
const char* datatype;
|
||||
size_t count;
|
||||
int peer;
|
||||
} p2p;
|
||||
|
||||
struct {
|
||||
pid_t pid; // pid of the originating process
|
||||
uint8_t channelId; // channel id for this proxy operation
|
||||
int peer; // remote rank for send/recv
|
||||
int nSteps; // number of steps for this proxy operation
|
||||
int chunkSize; // amount of data transferred by this proxy operation
|
||||
int isSend;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int step;
|
||||
} proxyStep;
|
||||
|
||||
struct {
|
||||
uint8_t channelId;
|
||||
} kernelCh;
|
||||
|
||||
struct {
|
||||
int64_t id;
|
||||
void* data;
|
||||
} netPlugin;
|
||||
};
|
||||
} ncclProfilerEventDescr_v3_t;
|
||||
|
||||
typedef union {
|
||||
struct {
|
||||
size_t transSize;
|
||||
int steps;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int appendedProxyOps;
|
||||
} proxyCtrl;
|
||||
} ncclProfilerEventStateArgs_v3_t;
|
||||
|
||||
typedef struct {
|
||||
const char* name;
|
||||
|
||||
// init - initialize the profiler plugin
|
||||
// Input
|
||||
// - context : opaque profiler context object for separating profiler behavior across comms
|
||||
// Output
|
||||
// - eActivationMask: bitmask of active events set by the plugin
|
||||
ncclResult_t (*init)(void** context, int* eActivationMask);
|
||||
|
||||
// startEvent - initialize and start a new event for the supplied event descriptor inside the eventset
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
// - eDescr : pointer to ncclProfilerEventDescr_t object
|
||||
// Output
|
||||
// - eHandle: return event handle for supplied event descriptor object
|
||||
ncclResult_t (*startEvent)(void* context, void** eHandle, ncclProfilerEventDescr_v3_t* eDescr);
|
||||
|
||||
// stopEvent - stop/finalize an event inside and event set
|
||||
// Input
|
||||
// - eHandle: handle to event object
|
||||
ncclResult_t (*stopEvent)(void* eHandle);
|
||||
|
||||
// recordEventState - record event state transitions and event attribute updates
|
||||
// Input
|
||||
// - eHandle : handle to event object created through startEvent
|
||||
// - eStateArgs: optional argument used to capture event attribute updates associated with the state transition
|
||||
// - eState : event state transition
|
||||
ncclResult_t (*recordEventState)(void* eHandle, ncclProfilerEventState_v3_t eState, ncclProfilerEventStateArgs_v3_t* eStateArgs);
|
||||
|
||||
// finalize - finalize the profiler plugin
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
ncclResult_t (*finalize)(void* context);
|
||||
} ncclProfiler_v3_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,53 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved.
|
||||
* Copyright (c) 2023, Meta Platforms, Inc. and affiliates.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef TUNER_V2_H_
|
||||
#define TUNER_V2_H_
|
||||
|
||||
// API to be implemented by external tuner
|
||||
typedef struct {
|
||||
// Name of the tuner
|
||||
const char* name;
|
||||
|
||||
// Initializes tuner states.
|
||||
// Inputs:
|
||||
// - nRanks: number of ranks in current communicator. Each communicator initialize its own tuner.
|
||||
// - nNodes: number of nodes in current communicator.
|
||||
// - logFunction: a logFunction can be useful to integrate logging together with NCCL core.
|
||||
// Outputs:
|
||||
// - context: tuner context object
|
||||
ncclResult_t (*init)(size_t nRanks, size_t nNodes, ncclDebugLogger_t logFunction, void **context);
|
||||
|
||||
// Gets info (algo, protocol, number of ctas and threads) for a given collective.
|
||||
// Inputs:
|
||||
// - context: tuner context object
|
||||
// - collType: collective type , e.g., allreduce, allgather…
|
||||
// - nBytes: collective size in bytes
|
||||
// - collNetTypeSupport: whether collnet supports this type
|
||||
// - nvlsTypeSupport: whether nvlink sharp supports this time
|
||||
// - numPipeOps: number of operations in the group
|
||||
//
|
||||
// Outputs:
|
||||
// - algorithm: selected algorithm to be used for the given collective
|
||||
// - protocol: selected protocol to be used for the give collective
|
||||
// - nChannels: number of channels (hence SMs) to be used.
|
||||
//
|
||||
// If getCollInfo() does not return ncclSuccess, NCCL will fall back to the
|
||||
// default tuning for the given collective.
|
||||
// Also, the plugin is allowed to not set any output, or set only the
|
||||
// algorithm and protocol, but not only the algorithm or only the protocol.
|
||||
// Unset fields will be set automatically by NCCL.
|
||||
ncclResult_t (*getCollInfo)(void* context, ncclFunc_t collType, size_t nBytes,
|
||||
int collNetSupport, int nvlsSupport, int numPipeOps,
|
||||
int* algorithm, int* protocol, int* nChannels);
|
||||
|
||||
// Terminates the plugin and cleans up any resources that the plugin allocated.
|
||||
// context: tuner context object
|
||||
ncclResult_t (*destroy)(void* context);
|
||||
} ncclTuner_v2_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,55 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved.
|
||||
* Copyright (c) 2023, Meta Platforms, Inc. and affiliates.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef TUNER_V3_H_
|
||||
#define TUNER_V3_H_
|
||||
|
||||
// API to be implemented by external tuner
|
||||
typedef struct {
|
||||
// Name of the tuner
|
||||
const char* name;
|
||||
|
||||
// Initializes tuner states.
|
||||
// Inputs:
|
||||
// - nRanks: number of ranks in current communicator. Each communicator initialize its own tuner.
|
||||
// - nNodes: number of nodes in current communicator.
|
||||
// - logFunction: a logFunction can be useful to integrate logging together with NCCL core.
|
||||
// Outputs:
|
||||
// - context: tuner context object
|
||||
ncclResult_t (*init)(size_t nRanks, size_t nNodes, ncclDebugLogger_t logFunction, void **context);
|
||||
|
||||
// Gets info (algo, protocol, number of ctas and threads) for a given collective.
|
||||
// Inputs:
|
||||
// - context: tuner context object
|
||||
// - collType: collective type , e.g., allreduce, allgather…
|
||||
// - nBytes: collective size in bytes
|
||||
// - numPipeOps: number of operations in the group
|
||||
// - numAlgo: number of algorithms in collCostTable
|
||||
// - numProto: number of protocols in collCostTable
|
||||
//
|
||||
// Outputs:
|
||||
// - nChannels: number of channels (hence SMs) to be used.
|
||||
//
|
||||
// InOut:
|
||||
// - collCostTable: collective cost table, generated by NCCL core, containing algo|proto|time entries for collType.
|
||||
// NCCL core sets ignored algo/proto cost table entries to -1.0 (NCCL_ALGO_PROTO_IGNORE).
|
||||
//
|
||||
// If getCollInfo() does not return ncclSuccess, NCCL will fall back to the
|
||||
// default tuning for the given collective.
|
||||
// Also, the plugin is allowed to not set any output, or set only the
|
||||
// algorithm and protocol, but not only the algorithm or only the protocol.
|
||||
// Unset fields will be set automatically by NCCL.
|
||||
ncclResult_t (*getCollInfo)(void* context, ncclFunc_t collType, size_t nBytes,
|
||||
int numPipeOps, float** collCostTable, int numAlgo, int numProto,
|
||||
int* nChannels);
|
||||
|
||||
// Terminates the plugin and cleans up any resources that the plugin allocated.
|
||||
// context: tuner context object
|
||||
ncclResult_t (*destroy)(void* context);
|
||||
} ncclTuner_v3_t;
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,56 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2023, NVIDIA CORPORATION. All rights reserved.
|
||||
* Copyright (c) 2023, Meta Platforms, Inc. and affiliates.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef TUNER_V4_H_
|
||||
#define TUNER_V4_H_
|
||||
|
||||
// API to be implemented by external tuner
|
||||
typedef struct {
|
||||
// Name of the tuner
|
||||
const char* name;
|
||||
|
||||
// Initializes tuner states.
|
||||
// Inputs:
|
||||
// - nRanks: number of ranks in current communicator. Each communicator initialize its own tuner.
|
||||
// - nNodes: number of nodes in current communicator.
|
||||
// - logFunction: a logFunction can be useful to integrate logging together with NCCL core.
|
||||
// Outputs:
|
||||
// - context: tuner context object
|
||||
ncclResult_t (*init)(size_t nRanks, size_t nNodes, ncclDebugLogger_t logFunction, void **context);
|
||||
|
||||
// Gets info (algo, protocol, number of ctas and threads) for a given collective.
|
||||
// Inputs:
|
||||
// - context: tuner context object
|
||||
// - collType: collective type , e.g., allreduce, allgather…
|
||||
// - nBytes: collective size in bytes
|
||||
// - numPipeOps: number of operations in the group
|
||||
// - numAlgo: number of algorithms in collCostTable
|
||||
// - numProto: number of protocols in collCostTable
|
||||
// - regBuff: can register user buffer
|
||||
//
|
||||
// Outputs:
|
||||
// - nChannels: number of channels (hence SMs) to be used.
|
||||
//
|
||||
// InOut:
|
||||
// - collCostTable: collective cost table, generated by NCCL core, containing algo|proto|time entries for collType.
|
||||
// NCCL core sets ignored algo/proto cost table entries to -1.0 (NCCL_ALGO_PROTO_IGNORE).
|
||||
//
|
||||
// If getCollInfo() does not return ncclSuccess, NCCL will fall back to the
|
||||
// default tuning for the given collective.
|
||||
// Also, the plugin is allowed to not set any output, or set only the
|
||||
// algorithm and protocol, but not only the algorithm or only the protocol.
|
||||
// Unset fields will be set automatically by NCCL.
|
||||
ncclResult_t (*getCollInfo)(void* context, ncclFunc_t collType, size_t nBytes,
|
||||
int numPipeOps, float** collCostTable, int numAlgo, int numProto,
|
||||
int regBuff, int* nChannels);
|
||||
|
||||
// Terminates the plugin and cleans up any resources that the plugin allocated.
|
||||
// context: tuner context object
|
||||
ncclResult_t (*destroy)(void* context);
|
||||
} ncclTuner_v4_t;
|
||||
|
||||
#endif
|
||||
Reference in New Issue
Block a user