derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
86 lines
3.3 KiB
C
86 lines
3.3 KiB
C
/*************************************************************************
|
|
* Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* See LICENSE.txt for license information
|
|
************************************************************************/
|
|
|
|
#ifndef PROFILER_H_
|
|
#define PROFILER_H_
|
|
|
|
#include <stdint.h>
|
|
#include <stdlib.h>
|
|
|
|
#include "common.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
|
|
ncclProfileGroupApi = (1 << 8), // Group API events
|
|
ncclProfileCollApi = (1 << 9), // Collective API events
|
|
ncclProfileP2pApi = (1 << 10), // Point-to-Point API events
|
|
ncclProfileKernelLaunch = (1 << 11), // Kernel launch events
|
|
};
|
|
|
|
typedef enum {
|
|
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 = 8,
|
|
ncclProfilerProxyStepSendPeerWait_v4 = 20,
|
|
ncclProfilerProxyStepSendWait = 9,
|
|
ncclProfilerProxyStepRecvWait = 10,
|
|
ncclProfilerProxyStepRecvFlushWait = 11,
|
|
ncclProfilerProxyStepRecvGPUWait = 12,
|
|
|
|
/* Legacy proxy control states */
|
|
ncclProfilerProxyCtrlIdle = 13,
|
|
ncclProfilerProxyCtrlActive = 14,
|
|
ncclProfilerProxyCtrlSleep = 15,
|
|
ncclProfilerProxyCtrlWakeup = 16,
|
|
ncclProfilerProxyCtrlAppend = 17,
|
|
ncclProfilerProxyCtrlAppendEnd = 18,
|
|
|
|
/* Network defined events states */
|
|
ncclProfilerNetPluginUpdate = 21,
|
|
|
|
/* Kernel event states */
|
|
ncclProfilerKernelChStop = 22,
|
|
|
|
/* Group API States */
|
|
ncclProfilerEndGroupApiStart = 23,
|
|
ncclProfilerBeginGroupApiEnd = 24
|
|
} 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;
|
|
typedef ncclProfilerEventState_t ncclProfilerEventState_v5_t;
|
|
|
|
#include "profiler_v5.h"
|
|
#include "profiler_v4.h"
|
|
#include "profiler_v3.h"
|
|
#include "profiler_v2.h"
|
|
#include "profiler_v1.h"
|
|
#include "profiler_net.h"
|
|
|
|
typedef ncclProfiler_v5_t ncclProfiler_t;
|
|
typedef ncclProfilerEventDescr_v5_t ncclProfilerEventDescr_t;
|
|
typedef ncclProfilerEventStateArgs_v5_t ncclProfilerEventStateArgs_t;
|
|
|
|
#endif // end include guard
|