Sylvain Jeaugey
f9c3dc251e
Add local user buffer registration for NVLink SHARP. Add tuning plugin support. Increase net API to v7 to allow for device-side packet reordering; remove support for v4 plugins. Add support for RoCE ECE. Add support for C2C links. Better detect SHM allocation failures to avoid crash with Bus Error. Fix missing thread unlocks in bootstrap (Fixes #936). Disable network flush by default on H100. Move device code from src/collectives/device to src/device.
42 строки
1.1 KiB
C++
42 строки
1.1 KiB
C++
/*************************************************************************
|
|
* Copyright (c) 2015-2021, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#ifndef NCCL_CORE_H_
|
|
#define NCCL_CORE_H_
|
|
|
|
#include <pthread.h>
|
|
#include <unistd.h>
|
|
#include <stdlib.h>
|
|
#include <stdint.h>
|
|
#include <algorithm> // For std::min/std::max
|
|
#include "nccl.h"
|
|
|
|
#ifdef PROFAPI
|
|
#define NCCL_API(ret, func, args...) \
|
|
__attribute__ ((visibility("default"))) \
|
|
__attribute__ ((alias(#func))) \
|
|
ret p##func (args); \
|
|
extern "C" \
|
|
__attribute__ ((visibility("default"))) \
|
|
__attribute__ ((weak)) \
|
|
ret func(args)
|
|
#else
|
|
#define NCCL_API(ret, func, args...) \
|
|
extern "C" \
|
|
__attribute__ ((visibility("default"))) \
|
|
ret func(args)
|
|
#endif // end PROFAPI
|
|
|
|
#include "debug.h"
|
|
#include "checks.h"
|
|
#include "cudawrap.h"
|
|
#include "alloc.h"
|
|
#include "utils.h"
|
|
#include "param.h"
|
|
#include "nvtx.h"
|
|
|
|
#endif // end include guard
|