Sylvain Jeaugey
178b6b7590
Rework core for NVIDIA Trusted Computing * Compress work structs so that they are shared between channels * Utilize the full amount of kernel argument space permitted (4k) before resorting to work fifo. * Rework the task preprocessing phase. * Use a separate abortDevFlag which is kept in sync with abortFlag using cudaMemcpy operations. * Rename src/include/align.h to src/include/bitops.h Add lazy connection establishment for collective operations * Move buffer allocation and connection establishment to the first collective operation using that algorithm. * Accelerate init time and reduce memory usage. * Avoid allocating NVLS buffers if all calls are registered. * Compute algo/proto in ncclLaunchCollTasksInfo early on. * Connect peers in ncclCollPreconnectFunc if not connected already. * Also move shared buffer creation to the first send/recv call. Accelerate intra-node NVLink detection * Make each rank only detect NVLinks attached to its GPU. * Fuse XMLs to reconstruct the full NVLink topology Add init profiling to report time spend in different init phases. * Report timings of bootstrap, allgather, search, connect, etc. * Add new "PROFILE" category for NCCL_DEBUG_SUBSYS. Add support for PCI p2p on split PCI switches * Detect split PCI switches through a kernel module exposing switch information. * Update the topology XML and graph to add those inter-switch connections. Add cost estimation API * Add a new ncclGroupEndSimulate primitive to return the estimated time a group would take. Net/IB: Add separate traffic class for fifo messages * Add NCCL_IB_FIFO_TC to control the traffic class of fifo messages independently from NCCL_IB_TC. Merges PR #1194 Net/IB: Add support for IB router * Use flid instead of lid if subnets do not match * Warn if flid is 0 Optimizations and fixes for device network offload (unpack) * Double the default number of channels * Cache netDeviceType * Fix save/increment head logic to enable Tree support. Support ncclGroupStart/End for ncclCommAbort/Destroy * Allow Abort/Destroy to be called within a group when managing multiple GPUs with a single process. Improve Tuner API * Provide to the plugin the original cost table so that the plugin can leave unknown or disabled algo/proto combinations untouched. * Remove nvlsSupport and collnetSupport. Do not print version to stdout when using a debug file * Also print version from all processes with INFO debug level. Fixes issue #1271 Fix clang warnings in NVTX headers * Update NVTX headers to the latest version Fixes issue #1270 Disable port fusion in heterogeneous systems * Do not fuse ports if a mix of multi-port and single port are detected. Fix NVLS graphs search for dual NICs. * Fix NVLS graph search when we have more than one NIC per GPU. Fix crash with collnetDirect * Add separate graph search for collnetDirect, testing alltoall paths and working similarly to the NVLS search. Fix hang when nodes have different CPU types * Add the CPU type to the rank peer info. * Align all ranks on the CPU type after the first allgather. * Only use the aligned CPU type for all tuning operations. Fixes issue #1136 Fixes issue #1184 Fix performance of registered send/recv operations * Allow for single full size operations * Add INFO to confirm the registration of send/recv buffers. Move all sync ops to finalize stage * Ensure ncclCommDestroy is non-blocking if ncclCommFinalize has been called. Improve error reporting during SHM segment creation Improve support of various compilers Merges PR #1177 Merges PR #1228 Allow net and tuner plugins to be statically linked * Search for ncclNet or ncclTuner symbols in the main binary. Merges PR #979 Plugin examples includes cleanup * Harmonize err.h and common.h usage. * Add mixed plugin with both net and tuner.
96 lines
3.3 KiB
C
96 lines
3.3 KiB
C
/*************************************************************************
|
|
* 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 <stdint.h>
|
|
#include <stdlib.h>
|
|
|
|
#include "common.h"
|
|
#include "err.h"
|
|
|
|
#define NCCL_NUM_FUNCTIONS 5 // Send/Recv not included for now
|
|
typedef enum {
|
|
ncclFuncBroadcast = 0,
|
|
ncclFuncReduce = 1,
|
|
ncclFuncAllGather = 2,
|
|
ncclFuncReduceScatter = 3,
|
|
ncclFuncAllReduce = 4,
|
|
ncclFuncSendRecv = 5,
|
|
ncclFuncSend = 6,
|
|
ncclFuncRecv = 7,
|
|
ncclNumFuncs = 8
|
|
} ncclFunc_t;
|
|
|
|
#define NCCL_NUM_ALGORITHMS 6 // Tree/Ring/CollNet*
|
|
#define NCCL_ALGO_UNDEF -1
|
|
#define NCCL_ALGO_TREE 0
|
|
#define NCCL_ALGO_RING 1
|
|
#define NCCL_ALGO_COLLNET_DIRECT 2
|
|
#define NCCL_ALGO_COLLNET_CHAIN 3
|
|
#define NCCL_ALGO_NVLS 4
|
|
#define NCCL_ALGO_NVLS_TREE 5
|
|
|
|
#define NCCL_NUM_PROTOCOLS 3 // Simple/LL/LL128
|
|
#define NCCL_PROTO_UNDEF -1
|
|
#define NCCL_PROTO_LL 0
|
|
#define NCCL_PROTO_LL128 1
|
|
#define NCCL_PROTO_SIMPLE 2
|
|
|
|
#define NCCL_ALGO_PROTO_IGNORE -1.0
|
|
|
|
// 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;
|
|
|
|
typedef ncclTuner_v3_t ncclTuner_t;
|
|
|
|
#define NCCL_TUNER_PLUGIN_SYMBOL "ncclTunerPlugin_v3"
|
|
|
|
#endif
|