Skip to content
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

Jump to bottom

Print the reminder for the illegal memory error in the AutoBatchSize under tf #4283

Merged
merged 3 commits into from
Oct 31, 2024
Merged

Print the reminder for the illegal memory error in the AutoBatchSize under tf #4283

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7aefed5
move the illegal memory reminder from base class AutoBatchSize to the…
Yi-FanLi Oct 30, 2024
94b2d41
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Oct 30, 2024
5870a93
only show the reminder when GPU is used
Yi-FanLi Oct 30, 2024
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
16 changes: 16 additions & 0 deletions deepmd/tf/utils/batch_size.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,6 @@
# SPDX-License-Identifier: LGPL-3.0-or-later
import os

from packaging.version import (
Version,
)
Expand All @@ -11,9 +13,23 @@
OutOfMemoryError,
)
from deepmd.utils.batch_size import AutoBatchSize as AutoBatchSizeBase
from deepmd.utils.batch_size import (
log,
)


class AutoBatchSize(AutoBatchSizeBase):
def __init__(self, initial_batch_size: int = 1024, factor: float = 2.0) -> None:
super().__init__(initial_batch_size, factor)
njzjz marked this conversation as resolved.
Show resolved Hide resolved
DP_INFER_BATCH_SIZE = int(os.environ.get("DP_INFER_BATCH_SIZE", 0))
if not DP_INFER_BATCH_SIZE > 0:
if self.is_gpu_available():
log.info(
"If you encounter the error 'an illegal memory access was encountered', this may be due to a TensorFlow issue. "
"To avoid this, set the environment variable DP_INFER_BATCH_SIZE to a smaller value than the last adjusted batch size. "
"The environment variable DP_INFER_BATCH_SIZE controls the inference batch size (nframes * natoms). "
)

def is_gpu_available(self) -> bool:
"""Check if GPU is available.

Expand Down
5 changes: 0 additions & 5 deletions deepmd/utils/batch_size.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,11 +61,6 @@ def __init__(self, initial_batch_size: int = 1024, factor: float = 2.0) -> None:
self.maximum_working_batch_size = initial_batch_size
if self.is_gpu_available():
self.minimal_not_working_batch_size = 2**31
log.info(
"If you encounter the error 'an illegal memory access was encountered', this may be due to a TensorFlow issue. "
"To avoid this, set the environment variable DP_INFER_BATCH_SIZE to a smaller value than the last adjusted batch size. "
"The environment variable DP_INFER_BATCH_SIZE controls the inference batch size (nframes * natoms). "
)
else:
self.minimal_not_working_batch_size = (
self.maximum_working_batch_size + 1
Expand Down