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

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

Browse Source
This commit is contained in:
BertanDogancay
2025-06-20 07:53:59 -05:00
parent 12315c259a 8171af656b
commit aaf023976a
136 changed files with 8510 additions and 5421 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ext-net/example/nccl/net.h
+11 -2
View File
@@ -2,14 +2,15 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_H_
#define NCCL_NET_H_
#ifndef NET_H_
#define NET_H_
#include <stdint.h>
#include <stdlib.h>
#include "common.h"
#include "err.h"
#include "net_device.h"
#define NCCL_NET_HANDLE_MAXSIZE 128
#define NCCL_MAX_NET_SIZE_BYTES (1*1024*1024*1024*1024L) //1TB
@@ -22,6 +23,9 @@
// 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"
#include "net_v7.h"
@@ -31,4 +35,9 @@
#include "net_v3.h"
#include "net_v2.h"
typedef ncclNet_v10_t ncclNet_t;
typedef ncclNetProperties_v10_t ncclNetProperties_t;
typedef ncclNetVDeviceProps_v10_t ncclNetVDeviceProps_t;
typedef ncclNetCommConfig_v10_t ncclNetCommConfig_t;
#endif // end include guard
ext-net/example/nccl/net_device.h
+2 -1
View File
@@ -26,6 +26,7 @@ typedef struct {
typedef ncclNetDeviceHandle_v7_t ncclNetDeviceHandle_v8_t;
typedef ncclNetDeviceHandle_v8_t ncclNetDeviceHandle_v9_t;
typedef ncclNetDeviceHandle_v9_t ncclNetDeviceHandle_t;
typedef ncclNetDeviceHandle_v9_t ncclNetDeviceHandle_v10_t;
typedef ncclNetDeviceHandle_v10_t ncclNetDeviceHandle_t;
#endif
ext-net/example/nccl/net_v10.h
+101
View File
@@ -0,0 +1,101 @@
/*
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NET_V10_H_
#define NET_V10_H_
#define NCCL_NET_MAX_DEVS_PER_NIC_V10 4
typedef struct {
int ndevs;
int devs[NCCL_NET_MAX_DEVS_PER_NIC_V10];
} ncclNetVDeviceProps_v10_t;
#define NCCL_NET_TRAFFIC_CLASS_UNDEF -1
typedef struct {
// Plugin-specific TC value
int trafficClass;
} ncclNetCommConfig_v10_t;
typedef struct {
char* name; // Used mostly for logging.
char* pciPath; // Path to the PCI device in /sys.
uint64_t guid; // Unique identifier for the NIC chip. Important for
// cards with multiple PCI functions (Physical or virtual).
int ptrSupport; // [NCCL_PTR_HOST|NCCL_PTR_CUDA|NCCL_PTR_DMABUF]
int regIsGlobal; // regMr is not tied to a particular comm
int forceFlush; // Force a flush on receives
int speed; // Port speed in Mbps.
int port; // Port number.
float latency; // Network latency
int maxComms; // Maximum number of comms we can create
int maxRecvs; // Maximum number of grouped receives.
ncclNetDeviceType netDeviceType; // Network offload type
int netDeviceVersion; // Version number for network offload
ncclNetVDeviceProps_v10_t vProps;
size_t maxP2pBytes; // Max transfer size for point-to-point operations
size_t maxCollBytes; // Max transfer size for collective operations
} ncclNetProperties_v10_t;
typedef struct {
// Name of the network (mainly for logs)
const char* name;
// Initialize the network.
ncclResult_t (*init)(ncclDebugLogger_t logFunction, ncclProfilerCallback_t profFunction);
// Return the number of adapters.
ncclResult_t (*devices)(int* ndev);
// Get various device properties.
ncclResult_t (*getProperties)(int dev, ncclNetProperties_v10_t* props);
// Create a receiving object and provide a handle to connect to it. The
// handle can be up to NCCL_NET_HANDLE_MAXSIZE bytes and will be exchanged
// between ranks to create a connection.
ncclResult_t (*listen)(int dev, void* handle, void** listenComm);
// Connect to a handle and return a sending comm object for that peer.
// This call must not block for the connection to be established, and instead
// should return successfully with sendComm == NULL with the expectation that
// it will be called again until sendComm != NULL.
// If *sendDevComm points to a valid object, then NCCL is requesting device offload for this connection
ncclResult_t (*connect)(int dev, ncclNetCommConfig_v10_t* config, void* handle, void** sendComm, ncclNetDeviceHandle_v10_t** sendDevComm);
// Finalize connection establishment after remote peer has called connect.
// This call must not block for the connection to be established, and instead
// should return successfully with recvComm == NULL with the expectation that
// it will be called again until recvComm != NULL.
// If *recvDevComm points to a valid object, then NCCL is requesting device offload for this connection
ncclResult_t (*accept)(void* listenComm, void** recvComm, ncclNetDeviceHandle_v10_t** recvDevComm);
// Register/Deregister memory. Comm can be either a sendComm or a recvComm.
// Type is either NCCL_PTR_HOST or NCCL_PTR_CUDA.
ncclResult_t (*regMr)(void* comm, void* data, size_t size, int type, void** mhandle);
/* DMA-BUF support */
ncclResult_t (*regMrDmaBuf)(void* comm, void* data, size_t size, int type, uint64_t offset, int fd, void** mhandle);
ncclResult_t (*deregMr)(void* comm, void* mhandle);
// Asynchronous send to a peer.
// May return request == NULL if the call cannot be performed (or would block)
ncclResult_t (*isend)(void* sendComm, void* data, size_t size, int tag, void* mhandle, void* phandle, void** request);
// Asynchronous recv from a peer.
// May return request == NULL if the call cannot be performed (or would block)
ncclResult_t (*irecv)(void* recvComm, int n, void** data, size_t* sizes, int* tags, void** mhandles, void** phandles, void** request);
// Perform a flush/fence to make sure all data received with NCCL_PTR_CUDA is
// visible to the GPU
ncclResult_t (*iflush)(void* recvComm, int n, void** data, int* sizes, void** mhandles, void** request);
// Test whether a request is complete. If size is not NULL, it returns the
// number of bytes sent/received.
ncclResult_t (*test)(void* request, int* done, int* sizes);
// Close and free send/recv comm objects
ncclResult_t (*closeSend)(void* sendComm);
ncclResult_t (*closeRecv)(void* recvComm);
ncclResult_t (*closeListen)(void* listenComm);
// Copy the given mhandle to a dptr in a format usable by this plugin's device code
ncclResult_t (*getDeviceMr)(void* comm, void* mhandle, void** dptr_mhandle);
// Notify the plugin that a recv has completed by the device
ncclResult_t (*irecvConsumed)(void* recvComm, int n, void* request);
// Virtual NIC APIs. makeVDevice will create a virtual NIC given the specified properties, and tell the caller
// what index this new vNIC exists at
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v10_t* props);
} ncclNet_v10_t;
#endif // end include guard
ext-net/example/nccl/net_v2.h
+2 -2
View File
@@ -2,8 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V2_H_
#define NCCL_NET_V2_H_
#ifndef NET_V2_H_
#define NET_V2_H_
typedef struct {
// Name of the network (mainly for logs)
ext-net/example/nccl/net_v3.h
+2 -2
View File
@@ -2,8 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V3_H_
#define NCCL_NET_V3_H_
#ifndef NET_V3_H_
#define NET_V3_H_
#define NCCL_NET_MAX_REQUESTS_V3 16
ext-net/example/nccl/net_v4.h
+2 -2
View File
@@ -2,8 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V4_H_
#define NCCL_NET_V4_H_
#ifndef NET_V4_H_
#define NET_V4_H_
#define NCCL_NET_HANDLE_MAXSIZE_V4 64
ext-net/example/nccl/net_v5.h
+2 -2
View File
@@ -2,8 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V5_H_
#define NCCL_NET_V5_H_
#ifndef NET_V5_H_
#define NET_V5_H_
typedef ncclNetProperties_v6_t ncclNetProperties_v5_t;
typedef struct {
ext-net/example/nccl/net_v6.h
+2 -4
View File
@@ -2,10 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V6_H_
#define NCCL_NET_V6_H_
#define NCCL_NET_MAX_REQUESTS_V6 8
#ifndef NET_V6_H_
#define NET_V6_H_
typedef struct {
char* name; // Used mostly for logging.
ext-net/example/nccl/net_v7.h
+2 -4
View File
@@ -2,10 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V7_H_
#define NCCL_NET_V7_H_
#include "net_device.h"
#ifndef NET_V7_H_
#define NET_V7_H_
typedef struct {
char* name; // Used mostly for logging.
ext-net/example/nccl/net_v8.h
+2 -4
View File
@@ -2,10 +2,8 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V8_H_
#define NCCL_NET_V8_H_
#include "net_device.h"
#ifndef NET_V8_H_
#define NET_V8_H_
typedef struct {
char* name; // Used mostly for logging.
ext-net/example/nccl/net_v9.h
+3 -9
View File
@@ -2,18 +2,14 @@
* Copyright (c) 2017-2022, NVIDIA CORPORATION. All rights reserved.
*/
#ifndef NCCL_NET_V9_H_
#define NCCL_NET_V9_H_
#include "net_device.h"
#ifndef NET_V9_H_
#define NET_V9_H_
#define NCCL_NET_MAX_DEVS_PER_NIC_V9 4
#define NCCL_NET_MAX_DEVS_PER_NIC NCCL_NET_MAX_DEVS_PER_NIC_V9
typedef struct {
int ndevs;
int devs[NCCL_NET_MAX_DEVS_PER_NIC_V9];
} ncclNetVDeviceProps_v9_t;
typedef ncclNetVDeviceProps_v9_t ncclNetVDeviceProps_t;
typedef struct {
char* name; // Used mostly for logging.
@@ -35,8 +31,6 @@ typedef struct {
size_t maxCollBytes; // Max transfer size for collective operations
} ncclNetProperties_v9_t;
typedef ncclNetProperties_v9_t ncclNetProperties_t;
typedef struct {
// Name of the network (mainly for logs)
const char* name;
@@ -93,7 +87,7 @@ typedef struct {
// Virtual NIC APIs. makeVDevice will create a virtual NIC given the specified properties, and tell the caller
// what index this new vNIC exists at
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_t* props);
ncclResult_t (*makeVDevice)(int* d, ncclNetVDeviceProps_v9_t* props);
} ncclNet_v9_t;
#endif // end include guard