Ke Wen
e11238b302
Add new API for creating a reduction operation which multiplies the input by a rank-specific scalar before doing an inter-rank summation (see: ncclRedOpCreatePreMulSum). Improve CollNet (SHARP) performance of ncclAllReduce when captured in a CUDA Graph via user buffer registration. Add environment variable NCCL_NET_PLUGIN="<suffix>" to allow user to choose among multiple NCCL net plugins by substituting into "libnccl-net-<suffix>.so". Fix memory leak of NVB connections. Fix topology detection of IB Virtual Functions (SR-IOV).
41 строка
1.3 KiB
C++
41 строка
1.3 KiB
C++
/*************************************************************************
|
|
* Copyright (c) 2015-2019, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#ifndef NCCL_DEBUG_H_
|
|
#define NCCL_DEBUG_H_
|
|
|
|
#include "nccl_net.h"
|
|
#include <stdio.h>
|
|
#include <chrono>
|
|
|
|
#include <sys/syscall.h>
|
|
#include <limits.h>
|
|
#include <string.h>
|
|
#include <pthread.h>
|
|
|
|
extern int ncclDebugLevel;
|
|
extern uint64_t ncclDebugMask;
|
|
extern pthread_mutex_t ncclDebugOutputLock;
|
|
extern FILE *ncclDebugFile;
|
|
extern ncclResult_t getHostName(char* hostname, int maxlen, const char delim);
|
|
|
|
void ncclDebugLog(ncclDebugLogLevel level, unsigned long flags, const char *filefunc, int line, const char *fmt, ...) __attribute__ ((format (printf, 5, 6)));
|
|
|
|
// Let code temporarily downgrade WARN into INFO
|
|
extern thread_local int ncclDebugNoWarn;
|
|
|
|
#define WARN(...) ncclDebugLog(NCCL_LOG_WARN, NCCL_ALL, __FILE__, __LINE__, __VA_ARGS__)
|
|
#define INFO(FLAGS, ...) ncclDebugLog(NCCL_LOG_INFO, (FLAGS), __func__, __LINE__, __VA_ARGS__)
|
|
|
|
#ifdef ENABLE_TRACE
|
|
#define TRACE(FLAGS, ...) ncclDebugLog(NCCL_LOG_TRACE, (FLAGS), __func__, __LINE__, __VA_ARGS__)
|
|
extern std::chrono::high_resolution_clock::time_point ncclEpoch;
|
|
#else
|
|
#define TRACE(...)
|
|
#endif
|
|
|
|
#endif
|