Files
Arm Patinyasakdikul 54194a17c3 Added ERROR message class to handle fatal error messages. (#2002)
* Added ERROR message class to handle fatal error messages.

New ERROR message class will print the message in all debug level,
including none.

Change some of the fatal error message to be in ERROR instead of WARN.

Added new error handler function to print out more meaningful error
message in the future.

* Added CHANGELOG entry.

* Update CHANGELOG.md

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

* Change to no longer reuse NONE as ERROR. ERROR is now a separated class.

* Update CHANGELOG.md

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

---------

Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>

[ROCm/rccl commit: 1ce83d5cc0]
2025-10-30 16:14:20 -05:00

16 строки
851 B
C

/*************************************************************************
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
#ifndef COMMON_H_
#define COMMON_H_
typedef enum {NCCL_LOG_NONE=0, NCCL_LOG_ERROR=1, NCCL_LOG_VERSION=2, NCCL_LOG_WARN=3, NCCL_LOG_INFO=4, NCCL_LOG_ABORT=5, NCCL_LOG_TRACE=6} ncclDebugLogLevel;
typedef enum {NCCL_INIT=1, NCCL_COLL=2, NCCL_P2P=4, NCCL_SHM=8, NCCL_NET=16, NCCL_GRAPH=32, NCCL_TUNING=64, NCCL_ENV=128, NCCL_ALLOC=256, NCCL_CALL=512, NCCL_PROXY=1024, NCCL_NVLS=2048, NCCL_BOOTSTRAP=4096, NCCL_REG=8192, NCCL_ALL=~0} ncclDebugLogSubSys;
typedef void (*ncclDebugLogger_t)(ncclDebugLogLevel level, unsigned long flags, const char *file, int line, const char *fmt, ...);
#endif