Merge remote-tracking branch 'nccl/master' into develop

ext-net/example/nccl/common.h

@@ -7,9 +7,15 @@
 #ifndef COMMON_H_
 #define COMMON_H_
 
+#include <stdint.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=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, ...);
 
+enum { ncclProfilerNetEventStart = 0, ncclProfilerNetEventStop, ncclProfilerNetEventUpdate, ncclProfilerNetEventUpdateAndStop };
+
+typedef ncclResult_t (*ncclProfilerCallback_t)(void** eHandle, int type, void* phandle, int64_t pluginId, void* extData);
+
 #endif

ext-net/example/nccl/net.h

@@ -8,9 +8,9 @@
 #include <stdint.h>
 #include <stdlib.h>
 
-#include "common.h"
 #include "err.h"
 #include "net_device.h"
+#include "common.h"
 
 #define NCCL_NET_HANDLE_MAXSIZE 128
 #define NCCL_MAX_NET_SIZE_BYTES (1*1024*1024*1024*1024L) //1TB
@@ -23,8 +23,6 @@
 // Maximum number of requests per comm object
 #define NCCL_NET_MAX_REQUESTS 32
 
-typedef ncclResult_t (*ncclProfilerCallback_t)(void** eHandle, int type, void* phandle, int64_t pluginId, void* extData);
-
 #include "net_v10.h"
 #include "net_v9.h"
 #include "net_v8.h"