|
|
|
#!/usr/bin/env python
|
|
|
|
# -*- encoding: utf-8 -*-
|
|
|
|
import time
|
|
|
|
from .cuda import synchronize
|
|
|
|
|
|
|
|
|
|
|
|
class Timer:
|
|
|
|
'''
|
|
|
|
A timer object which helps to log the execution times, and provides different tools to assess the times.
|
|
|
|
'''
|
|
|
|
def __init__(self):
|
|
|
|
self._started = False
|
|
|
|
self._start_time = time.time()
|
|
|
|
self._elapsed = 0
|
|
|
|
self._history = []
|
|
|
|
|
|
|
|
@property
|
|
|
|
def has_history(self):
|
|
|
|
return len(self._history) != 0
|
|
|
|
|
|
|
|
def start(self):
|
|
|
|
'''Fisrtly synchronize cuda, reset the clock and then start the timer.
|
|
|
|
'''
|
|
|
|
self._elapsed = 0
|
|
|
|
synchronize()
|
|
|
|
self._start_time = time.time()
|
|
|
|
self._started = True
|
|
|
|
|
|
|
|
def stop(self, keep_in_history: bool = False):
|
|
|
|
'''Stop the timer and record the start-stop time interval.
|
|
|
|
:param keep_in_history: whether does it record into history each start-stop interval, defaults to False
|
|
|
|
:type keep_in_history: bool, optional
|
|
|
|
:return: start-stop interval
|
|
|
|
:rtype: int
|
|
|
|
'''
|
|
|
|
synchronize()
|
|
|
|
end_time = time.time()
|
|
|
|
elapsed = end_time - self._start_time
|
|
|
|
if keep_in_history:
|
|
|
|
self._history.append(elapsed)
|
|
|
|
self._elapsed = elapsed
|
|
|
|
self._started = False
|
|
|
|
return elapsed
|
|
|
|
|
|
|
|
def get_history_mean(self):
|
|
|
|
'''mean of all history start-stop time intervals.
|
|
|
|
:return: mean of time intervals
|
|
|
|
:rtype: int
|
|
|
|
'''
|
|
|
|
return sum(self._history) / len(self._history)
|
|
|
|
|
|
|
|
def get_history_sum(self):
|
|
|
|
'''add up all the start-stop time intervals.
|
|
|
|
:return: sum of time intervals
|
|
|
|
:rtype: int
|
|
|
|
'''
|
|
|
|
return sum(self._history)
|
|
|
|
|
|
|
|
def get_elapsed_time(self):
|
|
|
|
'''return the last start-stop time interval. *use it only when timer is not in progress*
|
|
|
|
:return: the last time interval
|
|
|
|
:rtype: int
|
|
|
|
'''
|
|
|
|
assert not self._started, 'Timer is still in progress'
|
|
|
|
return self._elapsed
|
|
|
|
|
|
|
|
def reset(self):
|
|
|
|
'''clear up the timer and its history
|
|
|
|
'''
|
|
|
|
self._history = []
|
|
|
|
self._started = False
|
|
|
|
self._elapsed = 0
|
|
|
|
|
|
|
|
|
|
|
|
class MultiTimer:
|
|
|
|
'''An object contains multiple timers
|
|
|
|
'''
|
|
|
|
|
|
|
|
def __init__(self, on: bool = True):
|
|
|
|
self._on = on
|
|
|
|
self._timers = dict()
|
|
|
|
|
|
|
|
def start(self, name: str):
|
|
|
|
'''Start namely one of the timers
|
|
|
|
:param name: timer's key
|
|
|
|
:type name: str
|
|
|
|
'''
|
|
|
|
if self._on:
|
|
|
|
if name not in self._timers:
|
|
|
|
self._timers[name] = Timer()
|
|
|
|
return self._timers[name].start()
|
|
|
|
|
|
|
|
def stop(self, name: str, keep_in_history: bool):
|
|
|
|
'''Stop namely one of the timers.
|
|
|
|
:param name: timer's key
|
|
|
|
:param keep_in_history: whether does it record into history each start-stop interval
|
|
|
|
:type keep_in_history: bool
|
|
|
|
'''
|
|
|
|
if self._on:
|
|
|
|
return self._timers[name].stop(keep_in_history)
|
|
|
|
else:
|
|
|
|
return None
|
|
|
|
|
|
|
|
def get_timer(self, name):
|
|
|
|
'''Get timer by its name (from multitimer)
|
|
|
|
:param name: timer's key
|
|
|
|
:return: timer with the name you give correctly
|
|
|
|
:rtype: Timer
|
|
|
|
'''
|
|
|
|
return self._timers[name]
|
|
|
|
|
|
|
|
def reset(self, name=None):
|
|
|
|
'''Reset timers.
|
|
|
|
:param name: if name is designated, the named timer will be reset and others will not, defaults to None
|
|
|
|
'''
|
|
|
|
if self._on:
|
|
|
|
if name is not None:
|
|
|
|
self._timers[name].reset()
|
|
|
|
else:
|
|
|
|
for timer in self._timers:
|
|
|
|
timer.reset()
|
|
|
|
|
|
|
|
def is_on(self):
|
|
|
|
return self._on
|
|
|
|
|
|
|
|
def set_status(self, mode: bool):
|
|
|
|
self._on = mode
|
|
|
|
|
|
|
|
def __iter__(self):
|
|
|
|
for name, timer in self._timers.items():
|
Develop/experiments (#59)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
* Split conv2d, class token, positional embedding in 2d, Fix random number in ddp
Fix convergence in cifar10, Imagenet1000
* Integrate 1d tensor parallel in Colossal-AI (#39)
* fixed 1D and 2D convergence (#38)
* optimized 2D operations
* fixed 1D ViT convergence problem
* Feature/ddp (#49)
* remove redundancy func in setup (#19) (#20)
* use env to control the language of doc (#24) (#25)
* Support TP-compatible Torch AMP and Update trainer API (#27)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
* add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29)
* add explanation for ViT example (#35) (#36)
* support torch ddp
* fix loss accumulation
* add log for ddp
* change seed
* modify timing hook
Co-authored-by: Frank Lee <somerlee.9@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
* Feature/pipeline (#40)
* remove redundancy func in setup (#19) (#20)
* use env to control the language of doc (#24) (#25)
* Support TP-compatible Torch AMP and Update trainer API (#27)
* Add gradient accumulation, fix lr scheduler
* fix FP16 optimizer and adapted torch amp with tensor parallel (#18)
* fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes
* fixed trainer
* Revert "fixed trainer"
This reverts commit 2e0b0b76990e8d4e337add483d878c0f61cf5097.
* improved consistency between trainer, engine and schedule (#23)
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
* add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29)
* add explanation for ViT example (#35) (#36)
* optimize communication of pipeline parallel
* fix grad clip for pipeline
Co-authored-by: Frank Lee <somerlee.9@gmail.com>
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
* optimized 3d layer to fix slow computation ; tested imagenet performance with 3d; reworked lr_scheduler config definition; fixed launch args; fixed some printing issues; simplified apis of 3d layers (#51)
* Update 2.5d layer code to get a similar accuracy on imagenet-1k dataset
* update api for better usability (#58)
update api for better usability
Co-authored-by: 1SAA <c2h214748@gmail.com>
Co-authored-by: ver217 <lhx0217@gmail.com>
Co-authored-by: puck_WCR <46049915+WANG-CR@users.noreply.github.com>
Co-authored-by: binmakeswell <binmakeswell@gmail.com>
Co-authored-by: アマデウス <kurisusnowdeng@users.noreply.github.com>
Co-authored-by: BoxiangW <45734921+BoxiangW@users.noreply.github.com>
3 years ago
|
|
|
yield name, timer
|