Hi,
While studying, I found out that there was something wrong.
It seems to be showing the wrong result.
Code is fine, but result is not proper.
How do I fix it?
https://pytorch.org/tutorials/intermediate/model_parallel_tutorial.html
Speed Up by Pipelining Inputs
in “GETTING STARTED WITH DISTRIBUTED DATA PARALLEL”
class PipelineParallelResNet50(ModelParallelResNet50):
def __init__(self, split_size=20, *args, **kwargs):
super(PipelineParallelResNet50, self).__init__(*args, **kwargs)
self.split_size = split_size
def forward(self, x):
splits = iter(x.split(self.split_size, dim=0))
s_next = next(splits)
s_prev = self.seq1(s_next).to('cuda:1')
ret = []
for s_next in splits:
# A. s_prev runs on cuda:1
s_prev = self.seq2(s_prev)
ret.append(self.fc(s_prev.view(s_prev.size(0), -1)))
# B. s_next runs on cuda:0, which can run concurrently with A
s_prev = self.seq1(s_next).to('cuda:1')
s_prev = self.seq2(s_prev)
ret.append(self.fc(s_prev.view(s_prev.size(0), -1)))
return torch.cat(ret)
setup = "model = PipelineParallelResNet50()"
pp_run_times = timeit.repeat(
stmt, setup, number=1, repeat=num_repeat, globals=globals())
pp_mean, pp_std = np.mean(pp_run_times), np.std(pp_run_times)
plot([mp_mean, rn_mean, pp_mean],
[mp_std, rn_std, pp_std],
['Model Parallel', 'Single GPU', 'Pipelining Model Parallel'],
'mp_vs_rn_vs_pp.png')
