NCCL 2.4.6-1
Added detection of IBM/Power NVLink bridge device.
Add NUMA support to PCI distance calculations.
Added NCCL_IGNORE_CPU_AFFINITY env var.
Fix memory leaks; GithubIssue#180
Compiler warning fix; GithubIssue#178
Replace non-standard variable length arrays. GithubIssue#171
Fix Tree+Shared Memory crash. GithubPR#185
Fix LL cleanup hang during long running DL jobs.
Fix NCCL_RINGS environment variable handling.
Added extra checks to catch repeat calls to ncclCommDestroy() GithubIssue#191
Improve bootstrap socket connection reliability at scale.
Fix hostname hashing issue. GithubIssue#187
Code cleanup to rename all non device files from *.cu to *.cc
[ROCm/rccl commit: f40ce73e89]
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2015-2018, NVIDIA CORPORATION. All rights reserved.
|
||||
* Copyright (c) 2015-2019, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
@@ -24,7 +24,7 @@ extern int ncclDebugLevel;
|
||||
extern uint64_t ncclDebugMask;
|
||||
extern pthread_mutex_t ncclDebugOutputLock;
|
||||
extern FILE *ncclDebugFile;
|
||||
extern ncclResult_t getHostName(char* hostname, int maxlen);
|
||||
extern ncclResult_t getHostName(char* hostname, int maxlen, const char delim);
|
||||
extern ncclResult_t getNvmlDevice(int cudaDev, int *nvmlDev);
|
||||
|
||||
extern void ncclDebugLog(ncclDebugLogLevel level, unsigned long flags, const char *filefunc, int line, const char *fmt, ...);
|
||||
@@ -108,7 +108,7 @@ static inline void initDebug() {
|
||||
break;
|
||||
case 'h': // %h = hostname
|
||||
char hostname[1024];
|
||||
getHostName(hostname, 1024);
|
||||
getHostName(hostname, 1024, '.');
|
||||
dfn += snprintf(dfn, PATH_MAX, "%s", hostname);
|
||||
break;
|
||||
case 'p': // %p = pid
|
||||
|
||||
Reference in New Issue
Block a user