Sylvain Jeaugey
60240fec77
Add scalable init API
* Add new ncclCommInitRankScalable to allow for passing multiple
unique IDs to the init function.
* Spreads the load onto multiple bootstrap roots, allowing for
constant bootstrap time.
* Requires multiple ranks to create a unique ID, and the CPU-side
ID exchange code to call allgather[v] instead of broadcast.
Accelerate init bootstrap operations
* Reduce the number of calls to allgather.
* Allow roots to reply early to ranks when information is already
available.
* Add an option to use ncclNet instead of sockets to perform
bootstrap allgather operations.
Add PAT algorithms for Allgather and ReduceScatter
* Parallel Aggregated Trees, variation of Bruck algorithm.
* Logarithmic number of network steps for small sizes at scale.
* Only supports one rank per node at the moment.
Add support for registered buffers for intra-node communication.
* Allow registered user buffers to be accessed directly intra-node
* Avoids extra copies in algorithms which permit it, saving
memory bandwidth and helping with compute overlap.
Add profiler plugin API
* New plugin API for profiling
* Supports various levels of profiling, with a hierarchy.
Asynchronous graph allocation
* Make calls to cudaMalloc and cudaMemcpy during graph allocation
asynchronous.
* Significantly speeds up graph capture.
Use fatal IB asynchronous events to stop network operation
* Avoids many other error messages
* Only fatal errors are affected; potentially transient errors
(e.g. port down) do not cause an immediate stop.
Set P2P level to PXB on AMD CPUs when using more than 2 GPUs per node
* P2P would cause a significant performance degradation when using
many GPUs, and therefore many interleaved data flows.
* Disable P2P through the CPU when we have 3+ GPUs per node; keep it
enabled when we only have 2 GPUs.
Improve the init logs to report the real NCCL function.
* Make the log report ncclCommInitRank or ncclCommSplit, rather than
the generic ncclCommInitRankFunc.
Add a parameter to set the location of the user configuration file.
* Add NCCL_CONF_FILE environment variable to set where the user's
configuration file resides.
Increase default IB timeout
* Increase IB timeout value from 18 to 20.
* Should help avoid fatal errors on large RoCE systems.
Add new check for nvidia peermem
* On linux kernels 6.6+, /sys/kernel/mm/memory_peers is no longer
present; check for /sys/module/nvidia_peermem/version instead.
Fix old performance regression when mixing small and large operations.
* Improves distribution of work on channels.
Fix crash when NUMA IDs are equal to -1.
* Can happen when a NIC is a virtual NIC, or when linux doesn't
know which NUMA node a device is attached to
* Issue NVIDIA/nccl-tests#233
Fix tree graph search when NCCL_CROSS_NIC is set to 1.
* Would force NCCL to use the balanced_tree pattern, thereby
disabling LL128 on platforms with 1 GPU+1 NIC per PCI switch.
* Would also try to use alternate rings even though it was not
needed.
Compiler tweaks and fixes
* PR #1177
* PR #1228
Fix stack smash
* PR #1325
Fixes for multi-node NVLink + IB operation
Coverity fixes and comments.
[ROCm/rccl commit: 68b542363f]
97 lines
3.3 KiB
C
97 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 7 // 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_ALGO_PAT 6
|
|
|
|
#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
|