mindspore-ci-bot
50542793c8
!12077 optimize gpu backend logger
From: @wilfchen
Reviewed-by: @cristoval,@limingqi107
Signed-off-by: @limingqi107
5 years ago
wilfChen
58196f1faf
modify gpu backend logger
5 years ago
zuochuanyong
3fa26683ac
nlp perf(Pynative): change memory sync mode from synchronous to asynchronous in SyncHostToDevice
5 years ago
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)
```
5 years ago
lizhenyu
6649153c49
add input data type check for ps cache mode
5 years ago
limingqi107
366f3e668d
optimize the memory alloc error info
5 years ago
mindspore-ci-bot
4364abc7ee
!11798 Support RunOpsInGraph on CPU&GPU in pynative mode
From: @HulkTang
Reviewed-by:
Signed-off-by:
5 years ago
lizhenyu
f17534af08
ps cache support sparse
5 years ago
tanghuikang
6f2cd92aba
Support RunOpsInGraph on CPU&GPU in pynative mode
5 years ago
mindspore-ci-bot
03f88c6f44
!11271 Fix the bug of step_trace cannot get the step_trace_point name in callback scene
From: @gzhcv
Reviewed-by: @ouwenchang,@lilongfei15
Signed-off-by: @lilongfei15
5 years ago
mindspore-ci-bot
d8323b5d51
!11342 Support device memeory profiling
From: @yanghaitao1
Reviewed-by: @wangyue01,@lilongfei15
Signed-off-by: @lilongfei15
5 years ago
yuchaojie
1932d87a26
update some op's attr name
5 years ago
yanghaitao1
8d147deb07
profiler memory
5 years ago
gzhcv
ce66e8cf4e
Fix the bug of step_trace cannot get the step_trace_point name in callback scene
5 years ago
chujinjin
ade9a82c2b
fix device memory leak
5 years ago
mindspore-ci-bot
59d2affa97
!10021 Fixed double stutter issue at the end of step for debugger
From: @adelshafiei
Reviewed-by: @john_tzanakakis,@wangyue01
Signed-off-by: @wangyue01
5 years ago
caifubi
4aecf539e9
Fix GPU sync stream Segmentation fault
5 years ago
John Tzanakakis
b291861e85
LoadTensors was using a 4-byte size field instead of an 8-byte size field
don't load tensors if the type is none
5 years ago
ZPaC
bf793cd1a4
Return false if Recv node is not found in gpu_stream_assign.cc
5 years ago
lizhenyu
1f99cd7d86
ps cache data process thread support exit when exceptions occur
5 years ago
Adel Shafiei
1d795a4f9d
Fixed the double stutter problem at the end of step for debugger
5 years ago
mindspore-ci-bot
726a4b2e8f
!9665 fix the bug of step_trace incorrect content in inference scene
From: @gzhcv
Reviewed-by:
Signed-off-by:
5 years ago
mindspore-ci-bot
bccf04d36c
!8378 [MD][GPU] minddata device_que push optimizer
From: @xiefangqi
Reviewed-by:
Signed-off-by:
5 years ago
xiefangqi
ae36071fc8
add push opt logic
5 years ago
limingqi107
72a584b7c7
gpu all-reduce memory alloc fixed
5 years ago
gzhcv
de3a653c57
fix the bug of step_trace incorrect content in inference scene
5 years ago
lizhenyu
e3f7ae61db
add ps cache manager
5 years ago
mindspore-ci-bot
2799b6d35f
!9683 [Debugger] Performance and state improvements
From: @harsh1995
Reviewed-by: @john_tzanakakis,@wenkai_dist
Signed-off-by: @wenkai_dist
5 years ago
Harshvardhan Gupta
dd0084c52b
improve perf, keep consistent tensor state, fix recheck, check weights at step end
5 years ago
limingqi107
a5f57ce8a0
add ps cache
5 years ago
mindspore-ci-bot
a84f2d812a
!8989 [PyNative]Optimize performance of Resnet50
From: @jojobugfree
Reviewed-by: @jjfeing,@chujinjin
Signed-off-by: @chujinjin
5 years ago
mindspore-ci-bot
1a5dd4a711
!9390 Pynative support dynamic op run in gpu
From: @joylvliang
Reviewed-by: @chujinjin,@jjfeing
Signed-off-by: @chujinjin
5 years ago
mindspore-ci-bot
95573571f0
!9511 Codedex change for tensor_loader
From: @liangzhibo
Reviewed-by:
Signed-off-by:
5 years ago
lvliang
8984cc9c03
pynative-support-dynamic-op-run-in-gpu
5 years ago
caifubi
3033ae295c
Create Tensor for assignadd input in Optimizer
5 years ago
l00591931
1d1cab986d
Codedex change for tensor_loader
5 years ago
VectorSL
6c6e2e5478
add trace for gpu error/excpt log
5 years ago
mindspore-ci-bot
125940314f
!9256 remove gil release in gpu runtime
From: @kisnwang
Reviewed-by: @jjfeing,@chujinjin
Signed-off-by: @chujinjin
5 years ago
mindspore-ci-bot
b22294e808
!9088 fix some bugs about gatherd and gatherdgrad over several new test scens
From: @yuan_shen_zhou
Reviewed-by:
Signed-off-by:
5 years ago
kswang
0ad5357ce7
add longrunning for runop
5 years ago
ZPaC
ea69c905e0
Fix GPU stream assign bug.
5 years ago
zhouyuanshen
8ab5b06fb1
add more dtypes support for gatherdgrad and other bugfix
5 years ago
Adel Shafiei
a322184057
debugger backend compability support
5 years ago
gzhcv
dead0bbf80
fix the bug of index out of range in step trace feature
5 years ago
lizhenyu
6f6a0dfd7a
[bug_fix]GPU distributed training occur core dump when memory is not enough
5 years ago
ZPaC
db3a2d60cb
GPU supports p2p nccl interfaces
5 years ago
gzhcv
3d6c1fc5f6
fix the bug of step_trace
5 years ago
mindspore-ci-bot
418c8b5e3f
!8550 add gpu step trace
From: @gzhcv
Reviewed-by:
Signed-off-by:
5 years ago
gzhcv
6f6b56bfe1
add gpu step_trace
5 years ago
mindspore-ci-bot
a3066105d5
!7081 Mindspore debugger supporting multigraph
From: @lichen_101010
Reviewed-by:
Signed-off-by:
5 years ago