Skip to content

Add a option to move embedding lookup after sparse data dist in FusedSDD #3345

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Add a option to move embedding lookup after sparse data dist in FusedSDD #3345

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions torchrec/distributed/train_pipeline/train_pipelines.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -964,6 +964,7 @@ def __init__(
] = None,
strict: bool = False,
emb_lookup_stream: str = "data_dist", # new, current, data_dist (default)
embedding_lookup_after_data_dist: bool = False,
) -> None:
super().__init__(
model=model,
Expand All @@ -975,6 +976,8 @@ def __init__(
pipeline_postproc=pipeline_postproc,
custom_model_fwd=custom_model_fwd,
)
self._embedding_lookup_after_data_dist = embedding_lookup_after_data_dist

if emb_lookup_stream == "new":
self._emb_lookup_stream: Optional[torch.Stream] = (
(torch.get_device_module(device).Stream())
Expand Down Expand Up @@ -1046,8 +1049,9 @@ def progress(self, dataloader_iter: Iterator[In]) -> Out:
self._set_module_context(self.contexts[0])

# start embedding_lookup so it can overlap with previous optimizer
# pyre-ignore [6]
self.start_embedding_lookup(self.batches[0], self.contexts[0])
if not self._embedding_lookup_after_data_dist:
# pyre-ignore [6]
self.start_embedding_lookup(self.batches[0], self.contexts[0])

if self._model.training:
with record_function("## zero_grad ##"):
Expand All @@ -1064,6 +1068,10 @@ def progress(self, dataloader_iter: Iterator[In]) -> Out:
# batch i+2: load data and copy to gpu, the dataload iter will first exhaust here
self.enqueue_batch(dataloader_iter)

if self._embedding_lookup_after_data_dist:
# pyre-ignore [6]
self.start_embedding_lookup(self.batches[0], self.contexts[0])

# forward
with record_function(f"## forward {self.contexts[0].index} ##"):
losses, output = self._model_fwd(self.batches[0])
Expand Down
Loading