Sylvain Jeaugey
6aae379278
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
72 rader
1.7 KiB
C
72 rader
1.7 KiB
C
/*************************************************************************
|
|
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#ifndef NCCL_DEBUG_H_
|
|
#define NCCL_DEBUG_H_
|
|
|
|
typedef enum {
|
|
NCCL_LOG_NONE = 0,
|
|
NCCL_LOG_VERSION = 1,
|
|
NCCL_LOG_WARN = 2,
|
|
NCCL_LOG_INFO = 3,
|
|
NCCL_LOG_ABORT = 4,
|
|
NCCL_LOG_TRACE = 5
|
|
} ncclDebugLogLevel;
|
|
|
|
typedef enum {
|
|
NCCL_INIT = 0x1,
|
|
NCCL_COLL = 0x2,
|
|
NCCL_P2P = 0x4,
|
|
NCCL_SHM = 0x8,
|
|
NCCL_NET = 0x10,
|
|
NCCL_GRAPH = 0x20,
|
|
NCCL_TUNING = 0x40,
|
|
NCCL_ENV = 0x80,
|
|
NCCL_ALLOC = 0x100,
|
|
NCCL_CALL = 0x200,
|
|
NCCL_PROXY = 0x400,
|
|
NCCL_NVLS = 0x800,
|
|
NCCL_BOOTSTRAP = 0x1000,
|
|
NCCL_REG = 0x2000,
|
|
NCCL_PROFILE = 0x4000,
|
|
NCCL_RAS = 0x8000,
|
|
NCCL_ALL = ~0
|
|
} ncclDebugLogSubSys;
|
|
|
|
typedef void (*ncclDebugLogger_t)(ncclDebugLogLevel level, unsigned long flags, const char *file, int line, const char *fmt, ...);
|
|
|
|
#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
|
|
#endif
|