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

Update ext-profiler example

Browse Source 
Sync ext-profiler example with 2.26.2.


[ROCm/rccl commit: 145e67e707]
This commit is contained in:
Giuseppe Congiu
2025-04-09 09:02:40 -07:00
committed by Sylvain Jeaugey
parent 59f0bf79c5
commit ef77e8d4b0
13 changed files with 621 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rccl/ext-profiler/example/nccl/net_ib_v1.h
+34
View File
@@ -0,0 +1,34 @@
/*************************************************************************
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
#ifndef NET_IB_V1_H_
#define NET_IB_V1_H_
#define NCCL_PROFILER_NET_IB_VER 1
enum {
ncclProfileQp = (1 << 0),
};
// The data structure version is encoded in the plugin identifier bitmask and
// passed to NCCL core through the profiler callback. NCCL copies the plugin
// identifier in the event descriptor before calling the profiler startEvent
// function. The profiler should inspect the plugin id to find out the source
// plugin as well as the version of the event struct
typedef struct {
uint8_t type; // event type (plugin defined)
union {
struct {
int device; // network device id
uint64_t wr_id; // work request id
int opcode; // ibv opcode
int qpNum; // QP number
size_t length; // work request data length
} qp;
};
} ncclProfilerNetIbDescr_v1_t;
#endif
projects/rccl/ext-profiler/example/nccl/net_socket_v1.h
+32
View File
@@ -0,0 +1,32 @@
/*************************************************************************
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
#ifndef NET_SOCKET_V1_H_
#define NET_SOCKET_V1_H_
#define NCCL_PROFILER_NET_SOCKET_VER 1
enum {
ncclProfileSocket = (1 << 0),
};
// The data structure version is encoded in the plugin identifier bitmask and
// passed to NCCL core through the profiler callback. NCCL copies the plugin
// identifier in the event descriptor before calling the profiler startEvent
// function. The profiler should inspect the plugin id to find out the source
// plugin as well as the version of the event struct
typedef struct {
uint8_t type; // event type (plugin defined)
union {
struct {
int fd;
int op;
size_t length;
} sock;
};
} ncclProfilerNetSockDescr_v1_t;
#endif
projects/rccl/ext-profiler/example/nccl/profiler.h
+49 -2
View File
@@ -4,8 +4,8 @@
* See LICENSE.txt for license information
************************************************************************/
#ifndef NCCL_PROFILER_H_
#define NCCL_PROFILER_H_
#ifndef PROFILER_H_
#define PROFILER_H_
#include <stdint.h>
#include <stdlib.h>
@@ -13,7 +13,54 @@
#include "common.h"
#include "err.h"
enum {
ncclProfileGroup = (1 << 0), // group event type
ncclProfileColl = (1 << 1), // host collective call event type
ncclProfileP2p = (1 << 2), // host point-to-point call event type
ncclProfileProxyOp = (1 << 3), // proxy operation event type
ncclProfileProxyStep = (1 << 4), // proxy step event type
ncclProfileProxyCtrl = (1 << 5), // proxy control event type
ncclProfileKernelCh = (1 << 6), // kernel channel event type
ncclProfileNetPlugin = (1 << 7), // network plugin-defined, events
};
typedef enum {
ncclProfilerProxyOpSendPosted,
ncclProfilerProxyOpSendRemFifoWait,
ncclProfilerProxyOpSendTransmitted,
ncclProfilerProxyOpSendDone,
ncclProfilerProxyOpRecvPosted,
ncclProfilerProxyOpRecvReceived,
ncclProfilerProxyOpRecvTransmitted,
ncclProfilerProxyOpRecvDone,
/* Legacy proxy profiler states */
ncclProfilerProxyStepSendGPUWait,
ncclProfilerProxyStepSendWait,
ncclProfilerProxyStepRecvWait,
ncclProfilerProxyStepRecvFlushWait,
ncclProfilerProxyStepRecvGPUWait,
/* Legacy proxy control states */
ncclProfilerProxyCtrlIdle,
ncclProfilerProxyCtrlActive,
ncclProfilerProxyCtrlSleep,
ncclProfilerProxyCtrlWakeup,
ncclProfilerProxyCtrlAppend,
ncclProfilerProxyCtrlAppendEnd,
} ncclProfilerEventState_t;
typedef ncclProfilerEventState_t ncclProfilerEventState_v1_t;
typedef ncclProfilerEventState_t ncclProfilerEventState_v2_t;
typedef ncclProfilerEventState_t ncclProfilerEventState_v3_t;
#include "profiler_v3.h"
#include "profiler_v2.h"
#include "profiler_v1.h"
#include "profiler_net.h"
typedef ncclProfiler_v3_t ncclProfiler_t;
typedef ncclProfilerEventDescr_v3_t ncclProfilerEventDescr_t;
typedef ncclProfilerEventStateArgs_v3_t ncclProfilerEventStateArgs_t;
#endif // end include guard
projects/rccl/ext-profiler/example/nccl/profiler_net.h
+22
View File
@@ -0,0 +1,22 @@
/*************************************************************************
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
#ifndef PROFILER_NET_H_
#define PROFILER_NET_H_
#define NCCL_PROFILER_NET_VER_BITS (16)
#define NCCL_PROFILER_NET_VER_MASK (~0U >> NCCL_PROFILER_NET_VER_BITS)
#define NCCL_PROFILER_NET_TYPE_MASK (~0U << NCCL_PROFILER_NET_VER_BITS)
typedef enum {
NCCL_PROFILER_NET_TYPE_IB = (1U << NCCL_PROFILER_NET_VER_BITS),
NCCL_PROFILER_NET_TYPE_SOCK = (2U << NCCL_PROFILER_NET_VER_BITS),
} ncclProfilerNetType;
#include "net_ib_v1.h"
#include "net_socket_v1.h"
#endif
projects/rccl/ext-profiler/example/nccl/profiler_v1.h
+12 -4
View File
@@ -4,8 +4,8 @@
* See LICENSE.txt for license information
************************************************************************/
#ifndef NCCL_PROFILER_V1_H_
#define NCCL_PROFILER_V1_H_
#ifndef PROFILER_V1_H_
#define PROFILER_V1_H_
#include <stdint.h>
@@ -59,8 +59,16 @@ typedef struct {
};
} ncclProfilerEventDescr_v1_t;
typedef ncclProfilerEventState_v2_t ncclProfilerEventState_v1_t;
typedef ncclProfilerEventStateArgs_v2_t ncclProfilerEventStateArgs_v1_t;
typedef union {
struct {
size_t transSize;
int steps;
} proxyOp;
struct {
int appendedProxyOps;
} proxyCtrl;
} ncclProfilerEventStateArgs_v1_t;
typedef struct {
const char* name;
projects/rccl/ext-profiler/example/nccl/profiler_v2.h
+2 -42
View File
@@ -4,20 +4,11 @@
* See LICENSE.txt for license information
************************************************************************/
#ifndef NCCL_PROFILER_V2_H_
#define NCCL_PROFILER_V2_H_
#ifndef PROFILER_V2_H_
#define PROFILER_V2_H_
#include <stdint.h>
enum {
ncclProfileGroup = (1 << 0), // group event type
ncclProfileColl = (1 << 1), // host collective call event type
ncclProfileP2p = (1 << 2), // host point-to-point call event type
ncclProfileProxyOp = (1 << 3), // proxy operation event type
ncclProfileProxyStep = (1 << 4), // proxy step event type
ncclProfileProxyCtrl = (1 << 5), // proxy control event type
};
typedef struct {
uint8_t type; // event type descriptor: ncclProfileColl, ...
void* parentObj; // pointer to the profiler parent object (for coll is the group)
@@ -65,32 +56,6 @@ typedef struct {
};
} ncclProfilerEventDescr_v2_t;
typedef enum {
ncclProfilerProxyOpSendPosted,
ncclProfilerProxyOpSendRemFifoWait,
ncclProfilerProxyOpSendTransmitted,
ncclProfilerProxyOpSendDone,
ncclProfilerProxyOpRecvPosted,
ncclProfilerProxyOpRecvReceived,
ncclProfilerProxyOpRecvTransmitted,
ncclProfilerProxyOpRecvDone,
/* Legacy proxy profiler states */
ncclProfilerProxyStepSendGPUWait,
ncclProfilerProxyStepSendWait,
ncclProfilerProxyStepRecvWait,
ncclProfilerProxyStepRecvFlushWait,
ncclProfilerProxyStepRecvGPUWait,
/* Legacy proxy control states */
ncclProfilerProxyCtrlIdle,
ncclProfilerProxyCtrlActive,
ncclProfilerProxyCtrlSleep,
ncclProfilerProxyCtrlWakeup,
ncclProfilerProxyCtrlAppend,
ncclProfilerProxyCtrlAppendEnd,
} ncclProfilerEventState_v2_t;
typedef union {
struct {
size_t transSize;
@@ -138,9 +103,4 @@ typedef struct {
ncclResult_t (*finalize)(void* context);
} ncclProfiler_v2_t;
typedef ncclProfilerEventDescr_v2_t ncclProfilerEventDescr_t;
typedef ncclProfilerEventState_v2_t ncclProfilerEventState_t;
typedef ncclProfilerEventStateArgs_v2_t ncclProfilerEventStateArgs_t;
typedef ncclProfiler_v2_t ncclProfiler_t;
#endif
projects/rccl/ext-profiler/example/nccl/profiler_v3.h
+119
View File
@@ -0,0 +1,119 @@
/*************************************************************************
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
*
* See LICENSE.txt for license information
************************************************************************/
#ifndef PROFILER_V3_H_
#define PROFILER_V3_H_
#include <stdint.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 {
const char* name;
uint64_t commHash;
uint64_t seqNumber;
const char* func;
void const* sendBuff;
void* recvBuff;
size_t count;
int root;
const char* datatype;
uint8_t nMaxChannels;
uint8_t nWarps;
const char* algo;
const char* proto;
} coll;
struct {
const char* name;
uint64_t commHash;
const char* func;
void* buff;
const char* datatype;
size_t count;
int peer;
} 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;
} kernelCh;
struct {
int64_t id;
void* data;
} netPlugin;
};
} ncclProfilerEventDescr_v3_t;
typedef union {
struct {
size_t transSize;
int steps;
} proxyOp;
struct {
int appendedProxyOps;
} proxyCtrl;
} ncclProfilerEventStateArgs_v3_t;
typedef struct {
const char* name;
// init - initialize the profiler plugin
// Input
// - context : opaque profiler context object for separating profiler behavior across comms
// Output
// - eActivationMask: bitmask of active events set by the plugin
ncclResult_t (*init)(void** context, int* eActivationMask);
// 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_v3_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_v3_t eState, ncclProfilerEventStateArgs_v3_t* eStateArgs);
// finalize - finalize the profiler plugin
// Input
// - context: opaque profiler context object
ncclResult_t (*finalize)(void* context);
} ncclProfiler_v3_t;
typedef ncclProfilerEventDescr_v3_t ncclProfilerEventDescr_t;
typedef ncclProfilerEventState_v3_t ncclProfilerEventState_t;
typedef ncclProfilerEventStateArgs_v3_t ncclProfilerEventStateArgs_t;
typedef ncclProfiler_v3_t ncclProfiler_t;
#endif