zhoufeng
b7bc99debf
move head files to include
...
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2023-03-08 10:44:43 +08:00
wYann
cdd61d758a
fix some bugs of kernel object type selection
2023-01-17 20:52:53 +08:00
gaoyong10
9eacdb70c7
Mv GetOutputTensorNum to backend anf_runtime_.cc
2022-12-13 10:36:59 +08:00
jjfeing
82f04825f3
remove enum fusion type
2022-12-08 11:19:48 +08:00
lby
1aa76afba5
decoupling plugin and runtime
2022-07-20 10:48:18 +08:00
ckey_Dou
0f4901b3ed
shape function refactor:
2022-06-17 23:36:41 +08:00
gaoyong10
c2d67a1ba9
Fix multi collect output for construct of tuple-tuple-getitem
2022-04-22 17:22:14 +08:00
zhoufeng
f49b195c39
extract common as an independent shared library
...
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2022-02-26 10:55:51 +08:00
marui
d47e79b04c
Refactor ccsrc directories and CMakeLists files
2022-02-13 14:37:51 +08:00
dayschan
cbb84ff580
Move IsRealKernel and IsRealCNodeKernel from AnfAlgo to AnfUtils
...
the function IsOneOfPrimitive and IsOneOfPrimitiveCNode is useful,
we can move them into anf.cc
2021-11-09 14:34:21 +08:00
LaiYongqiang
898a48d6ea
fix fusion type
2021-07-13 10:44:50 +08:00
dingpeifei
87e41aaeee
IR operators of GPU and CPU are unified as batchnorm
2021-03-18 19:02:28 +08:00
He Wei
7d9a783993
[auto-monad] Support side-effects by auto-monad
...
The basic idea is: exploits data dependency to control the execution order
of side-effect operations, and keep the semantics of ANF unchanged.
The ControlDepend primitive is removed and there are two primitives added:
1. UpdateState:
```
a = Assign(para, value)
```
became:
```
a = Assign(para, value, u)
u = UpdateState(u, a)
```
2. Load:
```
x = Add(para, value)
```
became:
```
p = Load(para, u)
x = Add(p, value)
u = UpdateState(u, p)
```
2021-02-08 09:01:15 +08:00
mindspore-ci-bot
e897eb4c41
!11915 Change TensorAdd to Add, merge from r1.1 to master
...
From: @liangzhibo
Reviewed-by: @ginfung,@zh_qh
Signed-off-by: @zh_qh
2021-02-02 09:16:08 +08:00
l00591931
9ec100d069
Change TensorAdd to Add, from r1.1 to master
2021-02-01 17:53:52 +08:00
liubuyu
4a3cbda322
get cube size by dtype
2021-01-29 20:08:56 +08:00
Yi Huaijie
d7faa77b5e
support int64 shape
2020-11-05 21:15:49 +08:00
Wei Luning
c1c30a44f1
rename param_value -> param_info
2020-08-18 11:16:28 +08:00
Wei Luning
a05c38bb63
make python Parameter inherit from Tensor
2020-08-03 09:12:24 +08:00
WilliamLian
d10d1a17f0
spilt valuenode & parameter's tuple output to maketuple
2020-07-20 09:48:03 +08:00
He Wei
ee1510da41
Eliminate circular dependency between 'ir' and 'device/kernel'
2020-07-14 19:56:22 +08:00
liubuyu
43c79eb853
mindspore path adjust
2020-07-14 18:07:28 +08:00
He Wei
f337c6bc14
Decouple ParamValue from python
2020-07-09 16:16:22 +08:00
zhoufeng
1f8b00dff2
Fix empty graph dump ir
...
Signed-off-by: zhoufeng <zhoufeng54@huawei.com>
2020-07-04 14:26:52 +08:00
gong chen
a6dfa281ea
Init GraphKernel.
...
- It provides a unified style to express graph and kernel for user.
- It provides a unified IR to represent graph and kernel for developer.
- It breaks the boundary between graph and kernel.
- It provides more opportunities to do compile optimization.
2020-06-20 22:31:54 +08:00
leopz
40e15996b0
move default_param out of parameter and remove pybind11 in anf define
2020-05-19 19:11:12 +08:00
lianliguang
5d225f934f
change the padding strategy & refactor insert transdata
2020-04-14 12:57:40 +08:00
zhunaipan
930a1fb0a8
initial version
...
Signed-off-by: leonwanghui <leon.wanghui@huawei.com>
2020-03-27 22:54:54 +08:00