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

[xdoctest] reformat example code with google style in No. 203 - 211 #56473

Merged
merged 11 commits into from
Aug 23, 2023
Merged

[xdoctest] reformat example code with google style in No. 203 - 211 #56473

Show file tree
Hide file tree
Changes from 9 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
965ab78
203
Liyulingyue Aug 20, 2023
c1e7cc8
204
Liyulingyue Aug 20, 2023
967f419
205
Liyulingyue Aug 20, 2023
4494ec1
206
Liyulingyue Aug 20, 2023
bf1327f
207
Liyulingyue Aug 20, 2023
03526b1
208
Liyulingyue Aug 20, 2023
da8e922
209
Liyulingyue Aug 20, 2023
01bfc0b
210
Liyulingyue Aug 20, 2023
f5e315c
211
Liyulingyue Aug 20, 2023
97cd5a2
Update all_to_all.py
Liyulingyue Aug 21, 2023
1af0de5
Apply suggestions from code review
Liyulingyue Aug 21, 2023
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
31 changes: 16 additions & 15 deletions python/paddle/distributed/communication/stream/all_reduce.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,21 +92,22 @@ def all_reduce(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
local_rank = dist.get_rank()
data = None
if local_rank == 0:
data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
else:
data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
task = dist.stream.all_reduce(data, sync_op=False)
task.wait()
out = data
# [[5, 7, 9], [5, 7, 9]]
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> local_rank = dist.get_rank()
>>> data = None
>>> if local_rank == 0:
... data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
>>> else:
... data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
>>> task = dist.stream.all_reduce(data, sync_op=False)
>>> task.wait()
>>> out = data
>>> print(out)
[[5, 7, 9], [5, 7, 9]]
"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down
110 changes: 56 additions & 54 deletions python/paddle/distributed/communication/stream/all_to_all.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,23 +154,23 @@ def alltoall(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
out_tensor_list = []
if dist.get_rank() == 0:
data1 = paddle.to_tensor([[1, 2, 3], [4, 5, 6]])
data2 = paddle.to_tensor([[7, 8, 9], [10, 11, 12]])
else:
data1 = paddle.to_tensor([[13, 14, 15], [16, 17, 18]])
data2 = paddle.to_tensor([[19, 20, 21], [22, 23, 24]])
task = dist.stream.alltoall(out_tensor_list, [data1, data2], sync_op=False)
task.wait()
print(out_tensor_list)
# [[[1, 2, 3], [4, 5, 6]], [[13, 14, 15], [16, 17, 18]]] (2 GPUs, out for rank 0)
# [[[7, 8, 9], [10, 11, 12]], [[19, 20, 21], [22, 23, 24]]] (2 GPUs, out for rank 1)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> out_tensor_list = []
>>> if dist.get_rank() == 0:
... data1 = paddle.to_tensor([[1, 2, 3], [4, 5, 6]])
... data2 = paddle.to_tensor([[7, 8, 9], [10, 11, 12]])
>>> else:
... data1 = paddle.to_tensor([[13, 14, 15], [16, 17, 18]])
... data2 = paddle.to_tensor([[19, 20, 21], [22, 23, 24]])
>>> task = dist.stream.alltoall(out_tensor_list, [data1, data2], sync_op=False)
>>> task.wait()
>>> print(out_tensor_list)
[[[1, 2, 3], [4, 5, 6]], [[13, 14, 15], [16, 17, 18]]] (2 GPUs, out for rank 0)
[[[7, 8, 9], [10, 11, 12]], [[19, 20, 21], [22, 23, 24]]] (2 GPUs, out for rank 1)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(2 GPUs, out for rank 0) 不应该出现在 print 里面吧 ～ 可以放到上面语句里面作为注释。

"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down Expand Up @@ -289,43 +289,45 @@ def alltoall_single(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
local_rank = dist.get_rank()

# case 1
output = paddle.empty([2], dtype="int64")
if local_rank == 0:
data = paddle.to_tensor([0, 1])
else:
data = paddle.to_tensor([2, 3])
task = dist.stream.alltoall_single(output, data, sync_op=False)
task.wait()
out = output.numpy()
# [0, 2] (2 GPUs, out for rank 0)
# [1, 3] (2 GPUs, out for rank 1)

# case 2
size = dist.get_world_size()
output = paddle.empty([(local_rank + 1) * size, size], dtype='float32')
if local_rank == 0:
data = paddle.to_tensor([[0., 0.], [0., 0.], [0., 0.]])
else:
data = paddle.to_tensor([[1., 1.], [1., 1.], [1., 1.]])
out_split_sizes = [local_rank + 1 for i in range(size)]
in_split_sizes = [i + 1 for i in range(size)]
task = dist.stream.alltoall_single(output,
data,
out_split_sizes,
in_split_sizes,
sync_op=False)
task.wait()
out = output.numpy()
# [[0., 0.], [1., 1.]] (2 GPUs, out for rank 0)
# [[0., 0.], [0., 0.], [1., 1.], [1., 1.]] (2 GPUs, out for rank 1)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> local_rank = dist.get_rank()

>>> # case 1
>>> output = paddle.empty([2], dtype="int64")
>>> if local_rank == 0:
... data = paddle.to_tensor([0, 1])
>>> else:
... data = paddle.to_tensor([2, 3])
>>> task = dist.stream.alltoall_single(output, data, sync_op=False)
>>> task.wait()
>>> out = output.numpy()
>>> print(out)
[0, 2] (2 GPUs, out for rank 0)
[1, 3] (2 GPUs, out for rank 1)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

同上


>>> # case 2
>>> size = dist.get_world_size()
>>> output = paddle.empty([(local_rank + 1) * size, size], dtype='float32')
>>> if local_rank == 0:
... data = paddle.to_tensor([[0., 0.], [0., 0.], [0., 0.]])
>>> else:
... data = paddle.to_tensor([[1., 1.], [1., 1.], [1., 1.]])
>>> out_split_sizes = [local_rank + 1 for i in range(size)]
>>> in_split_sizes = [i + 1 for i in range(size)]
>>> task = dist.stream.alltoall_single(output,
... data,
... out_split_sizes,
... in_split_sizes,
... sync_op=False)
>>> task.wait()
>>> out = output.numpy()
>>> print(out)
[[0., 0.], [1., 1.]] (2 GPUs, out for rank 0)
[[0., 0.], [0., 0.], [1., 1.], [1., 1.]] (2 GPUs, out for rank 1)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

同上

"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down
29 changes: 15 additions & 14 deletions python/paddle/distributed/communication/stream/broadcast.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,20 +94,21 @@ def broadcast(tensor, src, group=None, sync_op=True, use_calc_stream=False):
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
local_rank = dist.get_rank()
if local_rank == 0:
data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
else:
data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
task = dist.stream.broadcast(data, src=1, sync_op=False)
task.wait()
out = data.numpy()
# [[1, 2, 3], [1, 2, 3]] (2 GPUs)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> local_rank = dist.get_rank()
>>> if local_rank == 0:
... data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
>>> else:
... data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
>>> task = dist.stream.broadcast(data, src=1, sync_op=False)
>>> task.wait()
>>> out = data.numpy()
>>> print(out)
[[1, 2, 3], [1, 2, 3]] (2 GPUs)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

同上

"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down
30 changes: 15 additions & 15 deletions python/paddle/distributed/communication/stream/gather.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,21 +80,21 @@ def gather(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
gather_list = []
if dist.get_rank() == 0:
data = paddle.to_tensor([1, 2, 3])
dist.stream.gather(data, gather_list, dst=0)
else:
data = paddle.to_tensor([4, 5, 6])
dist.stream.gather(data1, gather_list, dst=0)
print(gather_list)
# [[1, 2, 3], [4, 5, 6]] (2 GPUs, out for rank 0)
# [] (2 GPUs, out for rank 1)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> gather_list = []
>>> if dist.get_rank() == 0:
... data = paddle.to_tensor([1, 2, 3])
... dist.stream.gather(data, gather_list, dst=0)
>>> else:
... data = paddle.to_tensor([4, 5, 6])
... dist.stream.gather(data1, gather_list, dst=0)
>>> print(gather_list)
[[1, 2, 3], [4, 5, 6]] (2 GPUs, out for rank 0)
[] (2 GPUs, out for rank 1)
"""

assert (
Expand Down
31 changes: 16 additions & 15 deletions python/paddle/distributed/communication/stream/recv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,21 +81,22 @@ def recv(tensor, src=0, group=None, sync_op=True, use_calc_stream=False):
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
local_rank = dist.get_rank()
if local_rank == 0:
data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
task = dist.stream.send(data, dst=1, sync_op=False)
else:
data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
task = dist.stream.recv(data, src=0, sync_op=False)
task.wait()
out = data.numpy()
# [[4, 5, 6], [4, 5, 6]] (2 GPUs)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> local_rank = dist.get_rank()
>>> if local_rank == 0:
... data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
... task = dist.stream.send(data, dst=1, sync_op=False)
>>> else:
... data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
... task = dist.stream.recv(data, src=0, sync_op=False)
>>> task.wait()
>>> out = data.numpy()
>>> print(out)
[[4, 5, 6], [4, 5, 6]] (2 GPUs)
"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down
31 changes: 16 additions & 15 deletions python/paddle/distributed/communication/stream/reduce.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,21 +107,22 @@ def reduce(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
local_rank = dist.get_rank()
if local_rank == 0:
data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
else:
data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
task = dist.stream.reduce(data, dst=0, sync_op=False)
task.wait()
out = data.numpy()
# [[5, 7, 9], [5, 7, 9]] (2 GPUs, out for rank 0)
# [[1, 2, 3], [1, 2, 3]] (2 GPUs, out for rank 1)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> local_rank = dist.get_rank()
>>> if local_rank == 0:
... data = paddle.to_tensor([[4, 5, 6], [4, 5, 6]])
>>> else:
... data = paddle.to_tensor([[1, 2, 3], [1, 2, 3]])
>>> task = dist.stream.reduce(data, dst=0, sync_op=False)
>>> task.wait()
>>> out = data.numpy()
>>> print(out)
[[5, 7, 9], [5, 7, 9]] (2 GPUs, out for rank 0)
[[1, 2, 3], [1, 2, 3]] (2 GPUs, out for rank 1)
"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down
64 changes: 33 additions & 31 deletions python/paddle/distributed/communication/stream/reduce_scatter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,21 +134,22 @@ def reduce_scatter(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
if dist.get_rank() == 0:
data1 = paddle.to_tensor([0, 1])
data2 = paddle.to_tensor([2, 3])
else:
data1 = paddle.to_tensor([4, 5])
data2 = paddle.to_tensor([6, 7])
dist.stream.reduce_scatter(data1, [data1, data2])
out = data1.numpy()
# [4, 6] (2 GPUs, out for rank 0)
# [8, 10] (2 GPUs, out for rank 1)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> if dist.get_rank() == 0:
... data1 = paddle.to_tensor([0, 1])
... data2 = paddle.to_tensor([2, 3])
>>> else:
... data1 = paddle.to_tensor([4, 5])
... data2 = paddle.to_tensor([6, 7])
>>> dist.stream.reduce_scatter(data1, [data1, data2])
>>> out = data1.numpy()
>>> print(out)
[4, 6] (2 GPUs, out for rank 0)
[8, 10] (2 GPUs, out for rank 1)
"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down Expand Up @@ -218,22 +219,23 @@ def _reduce_scatter_base(
Examples:
.. code-block:: python

# required: distributed
import paddle
import paddle.distributed as dist

dist.init_parallel_env()
if dist.get_rank() == 0:
data1 = paddle.to_tensor([7, 8, 9])
data2 = paddle.to_tensor([10, 11, 12])
dist.stream.scatter(data1, src=1)
else:
data1 = paddle.to_tensor([1, 2, 3])
data2 = paddle.to_tensor([4, 5, 6])
dist.stream.scatter(data1, [data1, data2], src=1)
out = data1.numpy()
# [1, 2, 3] (2 GPUs, out for rank 0)
# [4, 5, 6] (2 GPUs, out for rank 1)
>>> # doctest: +REQUIRES(env: DISTRIBUTED)
>>> import paddle
>>> import paddle.distributed as dist

>>> dist.init_parallel_env()
>>> if dist.get_rank() == 0:
... data1 = paddle.to_tensor([7, 8, 9])
... data2 = paddle.to_tensor([10, 11, 12])
... dist.stream.scatter(data1, src=1)
>>> else:
... data1 = paddle.to_tensor([1, 2, 3])
... data2 = paddle.to_tensor([4, 5, 6])
... dist.stream.scatter(data1, [data1, data2], src=1)
>>> out = data1.numpy()
>>> print(out)
[1, 2, 3] (2 GPUs, out for rank 0)
[4, 5, 6] (2 GPUs, out for rank 1)
"""
if _warn_cur_rank_not_in_group(group):
return
Expand Down
Loading