Merge remote-tracking branch 'nccl/master' into develop
[ROCm/rccl commit: 08a7be231b]
This commit is contained in:
BertanDogancay
@@ -29,10 +29,9 @@
|
||||
#define NCCL_NET_MAX_REQUESTS 32
|
||||
|
||||
// Max number of ncclNet objects which can live in the same process
|
||||
#define NCCL_NET_MAX_PLUGINS 3
|
||||
|
||||
// NCCL core profiler callback for network defined events instrumentation
|
||||
typedef ncclResult_t (*ncclProfilerCallback_t)(void** eHandle, int type, void* pHandle, int64_t pluginId, void* extData);
|
||||
#ifndef NCCL_NET_MAX_PLUGINS
|
||||
#define NCCL_NET_MAX_PLUGINS 16
|
||||
#endif
|
||||
|
||||
#include "net/net_v10.h"
|
||||
#include "net/net_v9.h"
|
||||
|
||||
@@ -19,43 +19,53 @@ enum {
|
||||
};
|
||||
|
||||
typedef enum {
|
||||
ncclProfilerProxyOpSendPosted,
|
||||
ncclProfilerProxyOpSendRemFifoWait,
|
||||
ncclProfilerProxyOpSendTransmitted,
|
||||
ncclProfilerProxyOpSendDone,
|
||||
ncclProfilerProxyOpRecvPosted,
|
||||
ncclProfilerProxyOpRecvReceived,
|
||||
ncclProfilerProxyOpRecvTransmitted,
|
||||
ncclProfilerProxyOpRecvDone,
|
||||
ncclProfilerProxyOpSendPosted = 0, // deprecated in v4
|
||||
ncclProfilerProxyOpSendRemFifoWait = 1, // deprecated in v4
|
||||
ncclProfilerProxyOpSendTransmitted = 2, // deprecated in v4
|
||||
ncclProfilerProxyOpSendDone = 3, // deprecated in v4
|
||||
ncclProfilerProxyOpRecvPosted = 4, // deprecated in v4
|
||||
ncclProfilerProxyOpRecvReceived = 5, // deprecated in v4
|
||||
ncclProfilerProxyOpRecvTransmitted = 6, // deprecated in v4
|
||||
ncclProfilerProxyOpRecvDone = 7, // deprecated in v4
|
||||
ncclProfilerProxyOpInProgress_v4 = 19,
|
||||
|
||||
/* Legacy proxy profiler states */
|
||||
ncclProfilerProxyStepSendGPUWait,
|
||||
ncclProfilerProxyStepSendWait,
|
||||
ncclProfilerProxyStepRecvWait,
|
||||
ncclProfilerProxyStepRecvFlushWait,
|
||||
ncclProfilerProxyStepRecvGPUWait,
|
||||
ncclProfilerProxyStepSendGPUWait = 8,
|
||||
ncclProfilerProxyStepSendPeerWait_v4 = 20,
|
||||
ncclProfilerProxyStepSendWait = 9,
|
||||
ncclProfilerProxyStepRecvWait = 10,
|
||||
ncclProfilerProxyStepRecvFlushWait = 11,
|
||||
ncclProfilerProxyStepRecvGPUWait = 12,
|
||||
|
||||
/* Legacy proxy control states */
|
||||
ncclProfilerProxyCtrlIdle,
|
||||
ncclProfilerProxyCtrlActive,
|
||||
ncclProfilerProxyCtrlSleep,
|
||||
ncclProfilerProxyCtrlWakeup,
|
||||
ncclProfilerProxyCtrlAppend,
|
||||
ncclProfilerProxyCtrlAppendEnd,
|
||||
ncclProfilerProxyCtrlIdle = 13,
|
||||
ncclProfilerProxyCtrlActive = 14,
|
||||
ncclProfilerProxyCtrlSleep = 15,
|
||||
ncclProfilerProxyCtrlWakeup = 16,
|
||||
ncclProfilerProxyCtrlAppend = 17,
|
||||
ncclProfilerProxyCtrlAppendEnd = 18,
|
||||
|
||||
/* Network defined event states */
|
||||
ncclProfilerNetPluginUpdate = 21,
|
||||
|
||||
/* Kernel event states */
|
||||
ncclProfilerKernelChStop = 22,
|
||||
} ncclProfilerEventState_t;
|
||||
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v1_t;
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v2_t;
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v3_t;
|
||||
typedef ncclProfilerEventState_t ncclProfilerEventState_v4_t;
|
||||
|
||||
#include <cstdint>
|
||||
#include "profiler/profiler_v4.h"
|
||||
#include "profiler/profiler_v3.h"
|
||||
#include "profiler/profiler_v2.h"
|
||||
#include "profiler/profiler_v1.h"
|
||||
|
||||
typedef ncclProfiler_v3_t ncclProfiler_t;
|
||||
typedef ncclProfilerEventDescr_v3_t ncclProfilerEventDescr_t;
|
||||
typedef ncclProfilerEventStateArgs_v3_t ncclProfilerEventStateArgs_t;
|
||||
typedef ncclProfiler_v4_t ncclProfiler_t;
|
||||
typedef ncclProfilerEventDescr_v4_t ncclProfilerEventDescr_t;
|
||||
typedef ncclProfilerEventStateArgs_v4_t ncclProfilerEventStateArgs_t;
|
||||
|
||||
#define NCCL_PROFILER_NET_VER_BITS (16)
|
||||
#define NCCL_PROFILER_NET_VER_MASK (~0U >> NCCL_PROFILER_NET_VER_BITS)
|
||||
|
||||
@@ -0,0 +1,123 @@
|
||||
/*************************************************************************
|
||||
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
||||
*
|
||||
* See LICENSE.txt for license information
|
||||
************************************************************************/
|
||||
|
||||
#ifndef PROFILER_V4_H_
|
||||
#define PROFILER_V4_H_
|
||||
|
||||
typedef struct {
|
||||
uint8_t type; // event type descriptor: ncclProfileColl, ...
|
||||
void* parentObj; // pointer to the profiler parent object (for coll is the group)
|
||||
int rank; // originating rank
|
||||
union {
|
||||
struct {
|
||||
uint64_t seqNumber;
|
||||
const char* func;
|
||||
void const* sendBuff;
|
||||
void* recvBuff;
|
||||
size_t count;
|
||||
int root;
|
||||
const char* datatype;
|
||||
uint8_t nChannels;
|
||||
uint8_t nWarps;
|
||||
const char* algo;
|
||||
const char* proto;
|
||||
} coll;
|
||||
|
||||
struct {
|
||||
const char* func;
|
||||
void* buff;
|
||||
const char* datatype;
|
||||
size_t count;
|
||||
int peer;
|
||||
uint8_t nChannels;
|
||||
} p2p;
|
||||
|
||||
struct {
|
||||
pid_t pid; // pid of the originating process
|
||||
uint8_t channelId; // channel id for this proxy operation
|
||||
int peer; // remote rank for send/recv
|
||||
int nSteps; // number of steps for this proxy operation
|
||||
int chunkSize; // amount of data transferred by this proxy operation
|
||||
int isSend;
|
||||
} proxyOp;
|
||||
|
||||
struct {
|
||||
int step;
|
||||
} proxyStep;
|
||||
|
||||
struct {
|
||||
uint8_t channelId;
|
||||
uint64_t pTimer; // start timestamp from GPU globaltimer
|
||||
} kernelCh;
|
||||
|
||||
struct {
|
||||
int64_t id;
|
||||
void* data;
|
||||
} netPlugin;
|
||||
};
|
||||
} ncclProfilerEventDescr_v4_t;
|
||||
|
||||
typedef union {
|
||||
struct {
|
||||
size_t transSize;
|
||||
} proxyStep;
|
||||
|
||||
struct {
|
||||
int appendedProxyOps;
|
||||
} proxyCtrl;
|
||||
|
||||
struct {
|
||||
void* data;
|
||||
} netPlugin;
|
||||
|
||||
struct {
|
||||
uint64_t pTimer;
|
||||
} kernelCh;
|
||||
} ncclProfilerEventStateArgs_v4_t;
|
||||
|
||||
typedef struct {
|
||||
const char* name;
|
||||
|
||||
// init - initialize the profiler plugin
|
||||
// Input
|
||||
// - context : opaque profiler context object for separating profiler behavior across comms
|
||||
// - commName : user assigned communicator name
|
||||
// - commHash : communicator id
|
||||
// - nNodes : number of nodes in communicator
|
||||
// - nranks : number of ranks in communicator
|
||||
// - rank : rank identifier in communicator
|
||||
// - logfn : logger function
|
||||
// Output
|
||||
// - eActivationMask: bitmask of active events set by the plugin
|
||||
ncclResult_t (*init)(void** context, int* eActivationMask, const char* commName, uint64_t commHash, int nNodes, int nranks, int rank, ncclDebugLogger_t logfn);
|
||||
|
||||
// startEvent - initialize and start a new event for the supplied event descriptor inside the eventset
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
// - eDescr : pointer to ncclProfilerEventDescr_t object
|
||||
// Output
|
||||
// - eHandle: return event handle for supplied event descriptor object
|
||||
ncclResult_t (*startEvent)(void* context, void** eHandle, ncclProfilerEventDescr_v4_t* eDescr);
|
||||
|
||||
// stopEvent - stop/finalize an event inside and event set
|
||||
// Input
|
||||
// - eHandle: handle to event object
|
||||
ncclResult_t (*stopEvent)(void* eHandle);
|
||||
|
||||
// recordEventState - record event state transitions and event attribute updates
|
||||
// Input
|
||||
// - eHandle : handle to event object created through startEvent
|
||||
// - eStateArgs: optional argument used to capture event attribute updates associated with the state transition
|
||||
// - eState : event state transition
|
||||
ncclResult_t (*recordEventState)(void* eHandle, ncclProfilerEventState_v4_t eState, ncclProfilerEventStateArgs_v4_t* eStateArgs);
|
||||
|
||||
// finalize - finalize the profiler plugin
|
||||
// Input
|
||||
// - context: opaque profiler context object
|
||||
ncclResult_t (*finalize)(void* context);
|
||||
} ncclProfiler_v4_t;
|
||||
|
||||
#endif
|
||||
Reference in New Issue
Block a user