Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
magicwindyyd
mindspore
提交
a486f113
M
mindspore
项目概览
magicwindyyd
/
mindspore
与 Fork 源项目一致
Fork自
MindSpore / mindspore
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
mindspore
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
a486f113
编写于
6月 18, 2020
作者:
M
mindspore-ci-bot
提交者:
Gitee
6月 18, 2020
浏览文件
操作
浏览文件
下载
差异文件
!2271 add dependency for HostAllGather and HostReduceScatter
Merge pull request !2271 from yihuaijie/master
上级
b32c7192
6e970d35
变更
1
显示空白变更内容
内联
并排
Showing
1 changed file
with
14 addition
and
0 deletion
+14
-0
mindspore/ops/operations/comm_ops.py
mindspore/ops/operations/comm_ops.py
+14
-0
未找到文件。
mindspore/ops/operations/comm_ops.py
浏览文件 @
a486f113
...
@@ -182,6 +182,9 @@ class HostAllGather(PrimitiveWithInfer):
...
@@ -182,6 +182,9 @@ class HostAllGather(PrimitiveWithInfer):
Note:
Note:
Tensor must have the same shape and format in all processes participating in the collective.
Tensor must have the same shape and format in all processes participating in the collective.
HostAllGather is a host-side operator, it depends on OpenMPI and must use build option -M on
to enable it. Using mpirun command to run it:
mpirun -output-filename log -merge-stderr-to-stdout -np 3 python test_host_all_gather.py
Args:
Args:
group (Union[tuple[int],list[int]]): The rand_ids of communication group to work on.
group (Union[tuple[int],list[int]]): The rand_ids of communication group to work on.
...
@@ -200,9 +203,13 @@ class HostAllGather(PrimitiveWithInfer):
...
@@ -200,9 +203,13 @@ class HostAllGather(PrimitiveWithInfer):
Examples:
Examples:
>>> import mindspore.nn as nn
>>> import mindspore.nn as nn
>>> import mindspore.context as context
>>> import mindspore.ops.operations as P
>>> import mindspore.ops.operations as P
>>> from mindspore import Tensor
>>> from mindspore import Tensor
>>>
>>>
>>> context.set_context(mode=context.GRAPH_MODE, device_target='CPU')
>>> context.set_mpi_config(enable_mpi=True)
>>>
>>> class Net(nn.Cell):
>>> class Net(nn.Cell):
>>> def __init__(self):
>>> def __init__(self):
>>> super(Net, self).__init__()
>>> super(Net, self).__init__()
...
@@ -308,6 +315,9 @@ class HostReduceScatter(PrimitiveWithInfer):
...
@@ -308,6 +315,9 @@ class HostReduceScatter(PrimitiveWithInfer):
Note:
Note:
Tensor must have the same shape and format in all processes participating in the collective.
Tensor must have the same shape and format in all processes participating in the collective.
HostReduceScatter is a host-side operator, it depends on OpenMPI and must use build option
-M on to enable it. Using mpirun command to run it:
mpirun -output-filename log -merge-stderr-to-stdout -np 3 python test_host_reduce_scatter.py
Args:
Args:
op (str): Specifies an operation used for element-wise reductions,
op (str): Specifies an operation used for element-wise reductions,
...
@@ -322,10 +332,14 @@ class HostReduceScatter(PrimitiveWithInfer):
...
@@ -322,10 +332,14 @@ class HostReduceScatter(PrimitiveWithInfer):
Examples:
Examples:
>>> import mindspore.nn as nn
>>> import mindspore.nn as nn
>>> import mindspore.context as context
>>> import mindspore.ops.operations as P
>>> import mindspore.ops.operations as P
>>> from mindspore import Tensor
>>> from mindspore import Tensor
>>> from mindspore.ops.operations.comm_ops import ReduceOp
>>> from mindspore.ops.operations.comm_ops import ReduceOp
>>>
>>>
>>> context.set_context(mode=context.GRAPH_MODE, device_target='CPU')
>>> context.set_mpi_config(enable_mpi=True)
>>>
>>> class Net(nn.Cell):
>>> class Net(nn.Cell):
>>> def __init__(self):
>>> def __init__(self):
>>> super(Net, self).__init__()
>>> super(Net, self).__init__()
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录