Files
rocm-systems/ext-tuner/example/nccl/tuner.h
T
Sylvain Jeaugey 6aae379278 2.24.3-1
Network user buffer support for collectives
 * Leverage user buffer registration to achieve zero-copy
   inter-node communications for Ring, NVLS and Collnet

Add RAS subsystem
 * Create a RAS thread keeping track of all NCCL communicators.
 * Add a ncclras tool contacting the RAS thread and getting a
   report.

Add fp8 support
 * Add support for e5m2 and e4m3 8-bit floating point operations.
 * Use Tree/PAT algorithms when possible for better numerical
   stability.

Add NIC fusion
 * Add a NET API to ask the network plugin to fuse a set of
   interfaces together.
 * Fuse multiple NICs under the same PCI switch as a single,
   larger NIC.

Socket connection failure retry
 * Retry in case of socket connection failure (unreachable host)
 * Avoid "Software caused connection abort" errors on retries

QP connection failure retry
 * Retry in case of IB QP connection failure during ibv_modify_qp.

NET API improvements
 * Allow plugins to force a flush in case data and completion
   ordering is not guaranteed.
 * Indicate when completion is not needed (e.g. for the LL128
   protocol), allowing plugins to skip generating a completion.
 * Allow for full offload of allgather operations when using one
   GPU per node.

NCCL_ALGO/NCCL_PROTO strict enforcement
 * Extend NCCL_ALGO/NCCL_PROTO syntax to be able to specify
   ALGO/PROTO filters for each collective operation.
 * Strictly enforce the ALGO/PROTO filters, no longer fall back
   on the ring algorithm when the filtering leaves no option and
   error out instead.

Enable CUMEM host allocations
 * Use cumem functions for host memory allocation by default.

Improved profiler plugin API
 * Avoid dependencies with NCCL includes.
 * Add information on whether the buffer is registered or not

Adjust PAT tuning
 * Improve transition between PAT and ring at scale.

Fix hangs when running with different CPU architectures
 * Detect when we use a mix of GPU architectures
 * Ensure Algo/Proto decisions are made based on that unified
   state.

Fix FD leak in UDS
 * Fix a leak when mapping buffers intra-node with cumem IPCs.

Fix crash when mixing buffer registration and graph buffer registration.
 * Separate local and graph registration to avoid crashes when we free
   buffers.

Fix user buffer registration with dmabuf
 * Make ncclSend/ncclRecv communication with buffer registration functional
   on network plugins relying on dmabuf for buffer registration.

Fix crash in IB code caused by uninitialized fields.

Fix non-blocking ncclSend/ncclRecv
 * Fix case where ncclSend/ncclRecv would return ncclSuccess in non-blocking
   mode even though the operation was not enqueued onto the stream.
 * Issue #1495

Various compiler tweaks and fixes
 * PR #758

Fix typo in ncclTopoPrintGraph
 * Issue #1468
2025-01-07 02:01:15 -08:00

98 líneas
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
// - 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;
typedef ncclTuner_v4_t ncclTuner_t;
#define NCCL_TUNER_PLUGIN_SYMBOL "ncclTunerPlugin_v4"
#endif