File size: 4,824 Bytes
d2ab3a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
import os
import sys
import tempfile
import torch
import torch.distributed as dist
import torch.nn as nn
import torch.optim as optim
import torch.multiprocessing as mp

from torch.nn.parallel import DistributedDataParallel as DDP



def setup(rank, world_size):
    # os.environ['MASTER_ADDR'] = 'localhost'
    # os.environ['MASTER_PORT'] = '12355'
    print(os.environ['MASTER_ADDR'])
    print(os.environ['MASTER_PORT'])

    # initialize the process group
    dist.init_process_group("gloo", rank=rank, world_size=world_size)

def cleanup():
    dist.destroy_process_group()


# ``` python
class ToyModel(nn.Module):
    def __init__(self):
        super(ToyModel, self).__init__()
        self.net1 = nn.Linear(10, 10)
        self.relu = nn.ReLU()
        self.net2 = nn.Linear(10, 5)

    def forward(self, x):
        return self.net2(self.relu(self.net1(x)))


def demo_basic(rank, world_size):
    print(f"Running basic DDP example on rank {rank}.")
    setup(rank, world_size)

    # create model and move it to GPU with id rank
    
    print("Start creating model")
    model = ToyModel().to(rank)
    ddp_model = DDP(model, device_ids=[rank])

    print("Model created")
    print("Start creating loss function")
    loss_fn = nn.MSELoss()
    print("Loss function created")
    print("Start creating optimizer")
    optimizer = optim.SGD(ddp_model.parameters(), lr=0.001)

    optimizer.zero_grad()
    outputs = ddp_model(torch.randn(20, 10))
    labels = torch.randn(20, 5).to(rank)
    loss_fn(outputs, labels).backward()
    optimizer.step()

    cleanup()
    print(f"Finished running basic DDP example on rank {rank}.")


def run_demo(demo_fn, world_size):
    mp.spawn(demo_fn,
             args=(world_size,),
             nprocs=world_size,
             join=True)

# ``` python
def demo_checkpoint(rank, world_size):
    print(f"Running DDP checkpoint example on rank {rank}.")
    setup(rank, world_size)

    model = ToyModel().to(rank)
    ddp_model = DDP(model, device_ids=[rank])


    CHECKPOINT_PATH = tempfile.gettempdir() + "/model.checkpoint"
    if rank == 0:
        # All processes should see same parameters as they all start from same
        # random parameters and gradients are synchronized in backward passes.
        # Therefore, saving it in one process is sufficient.
        torch.save(ddp_model.state_dict(), CHECKPOINT_PATH)

    # Use a barrier() to make sure that process 1 loads the model after process
    # 0 saves it.
    dist.barrier()
    # configure map_location properly
    map_location = {'cuda:%d' % 0: 'cuda:%d' % rank}
    ddp_model.load_state_dict(
        torch.load(CHECKPOINT_PATH, map_location=map_location, weights_only=True))

    loss_fn = nn.MSELoss()
    optimizer = optim.SGD(ddp_model.parameters(), lr=0.001)

    optimizer.zero_grad()
    outputs = ddp_model(torch.randn(20, 10))
    labels = torch.randn(20, 5).to(rank)

    loss_fn(outputs, labels).backward()
    optimizer.step()

    # Not necessary to use a dist.barrier() to guard the file deletion below
    # as the AllReduce ops in the backward pass of DDP already served as
    # a synchronization.

    if rank == 0:
        os.remove(CHECKPOINT_PATH)

    cleanup()
    print(f"Finished running DDP checkpoint example on rank {rank}.")
    

## Combining DDP with Model Parallelism


# ``` python
class ToyMpModel(nn.Module):
    def __init__(self, dev0, dev1):
        super(ToyMpModel, self).__init__()
        self.dev0 = dev0
        self.dev1 = dev1
        self.net1 = torch.nn.Linear(10, 10).to(dev0)
        self.relu = torch.nn.ReLU()
        self.net2 = torch.nn.Linear(10, 5).to(dev1)

    def forward(self, x):
        x = x.to(self.dev0)
        x = self.relu(self.net1(x))
        x = x.to(self.dev1)
        return self.net2(x)


# ``` python
def demo_model_parallel(rank, world_size):
    print(f"Running DDP with model parallel example on rank {rank}.")
    setup(rank, world_size)

    # setup mp_model and devices for this process
    dev0 = rank * 2
    dev1 = rank * 2 + 1
    mp_model = ToyMpModel(dev0, dev1)
    ddp_mp_model = DDP(mp_model)

    loss_fn = nn.MSELoss()
    optimizer = optim.SGD(ddp_mp_model.parameters(), lr=0.001)

    optimizer.zero_grad()
    # outputs will be on dev1
    outputs = ddp_mp_model(torch.randn(20, 10))
    labels = torch.randn(20, 5).to(dev1)
    loss_fn(outputs, labels).backward()
    optimizer.step()

    cleanup()
    print(f"Finished running DDP with model parallel example on rank {rank}.")


if __name__ == "__main__":
    n_gpus = torch.cuda.device_count()
    assert n_gpus >= 2, f"Requires at least 2 GPUs to run, but got {n_gpus}"
    world_size = n_gpus
    run_demo(demo_basic, world_size)
    # run_demo(demo_checkpoint, world_size)
    # world_size = n_gpus//2
    # run_demo(demo_model_parallel, world_size)