AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2.9.9-1

Browse Source 
Fix crash when setting NCCL_MAX_P2P_NCHANNELS below nchannels.
Fix hang during sendrecv dynamic NVB connection establishment on
cubemesh topologies.
Add environment variable to only use SHARP on communicators beyond
a given number of ranks.
Add debug subsystem to trace memory allocations.
Fix compilation with TRACE=1. (Issue #505)
This commit is contained in:
Sylvain Jeaugey
2021-05-11 18:16:30 -07:00
parent ca8485b0d0
commit 3fec2fa5ee
14 changed files with 142 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/include/nccl_net.h
+2 -2
View File
@@ -1,5 +1,5 @@
/*************************************************************************
* Copyright (c) 2017-2020, NVIDIA CORPORATION. All rights reserved.
* Copyright (c) 2017-2021, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
@@ -19,7 +19,7 @@
#define NCCL_NET_MAX_REQUESTS 8
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=1, NCCL_COLL=2, NCCL_P2P=4, NCCL_SHM=8, NCCL_NET=16, NCCL_GRAPH=32, NCCL_TUNING=64, NCCL_ENV=128, NCCL_ALL=~0} ncclDebugLogSubSys;
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_ALL=~0} ncclDebugLogSubSys;
typedef void (*ncclDebugLogger_t)(ncclDebugLogLevel level, unsigned long flags, const char *file, int line, const char *fmt, ...);