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

Cudnn Batch-normalization not working with cudnn-v4 #60

Closed
zchen0211 opened this issue Sep 9, 2016 · 2 comments
Closed

Cudnn Batch-normalization not working with cudnn-v4 #60

zchen0211 opened this issue Sep 9, 2016 · 2 comments
Labels
Bug

Comments

@zchen0211
Copy link
Contributor

Hi,

I tried make-test with cudnn v4. The batch-normalization reports "segmentation fault" problem when I make test.

The Cudnn-v5 version works without problems. (Maybe cudnn-v5 suggested?)
@qingqing01
Copy link
Contributor

Thanks for your feedback. We suggest to use cudnn-v5 or cudnn-v5.1. And I will fix it. Thanks!

@qingqing01
Copy link
Contributor

We have fixed this problem, the code is #71

@qingqing01 qingqing01 added the Bug label Oct 25, 2016
zhhsplendid pushed a commit to zhhsplendid/Paddle that referenced this issue Sep 25, 2019
@shanyi15
Merge pull request PaddlePaddle#60 from tink2123/api_doc
d16c5ca 
update develop api_doc according paddle repo
@DemoMoon DemoMoon mentioned this issue Mar 24, 2021
Closed
thisjiang pushed a commit to thisjiang/Paddle that referenced this issue Oct 28, 2021
@Superjomn
Merge pull request PaddlePaddle#60 from Superjomn/fea/support-header-…
54a1d24 
…output

support header file output
gglin001 pushed a commit to graphcore/Paddle-fork that referenced this issue Dec 8, 2021
@XBWGC
fix ~IpuBackend() quit error (PaddlePaddle#60)
ff4ba95
wangxicoding pushed a commit to wangxicoding/Paddle that referenced this issue Dec 9, 2021
@kinghuin
Add msra_ner eval scripts (PaddlePaddle#60)
34f98a8 
* add msra_ner eval

* add yapf disable
zhoutianzi666 pushed a commit to zhoutianzi666/Paddle that referenced this issue May 23, 2022
@jiweibo
Merge pull request PaddlePaddle#60 from jiweibo/windows_cpu_demo
9efa922 
add windows cpu doc.
danleifeng pushed a commit to danleifeng/Paddle that referenced this issue Jul 7, 2022
@qingshui
Optimize graph loading and sample loading performance (PaddlePaddle#60)
33f3c9b 
* Optimize graph loading and sample loading performance，gpu load graph from 172s to 124s, cpu load graph from 92s to 45s
AnnaTrainingG pushed a commit to AnnaTrainingG/Paddle that referenced this issue Sep 19, 2022
@qingqing01
Add Copyright (PaddlePaddle#60)
9020cf3
zmxdream added a commit to zmxdream/Paddle that referenced this issue Oct 21, 2022
@zmxdream
add get func (PaddlePaddle#60)
a27936c
zmxdream added a commit to zmxdream/Paddle that referenced this issue Oct 26, 2022
@zmxdream
Revert "add get func (PaddlePaddle#60)"
62dc501 
This reverts commit a27936c.
zmxdream pushed a commit to zmxdream/Paddle that referenced this issue Oct 10, 2023
@qingshui @zmxdream
Merge pull request PaddlePaddle#60 from laipaang/masked_data_norm
f1f9ce0 
add a new op: masked_data_norm
AnnaTrainingG pushed a commit to AnnaTrainingG/Paddle that referenced this issue Dec 6, 2023
@tridao
Merge pull request PaddlePaddle#60 from 201419/patch-1
1d0b41b 
fix typo in function mha_fwd
NKNaN pushed a commit to NKNaN/Paddle that referenced this issue Mar 3, 2024
Merge branch 'gangliao-master'
f6efaf4 
Should fix PaddlePaddle#60
feifei-111 added a commit to feifei-111/Paddle that referenced this issue Mar 12, 2024
@feifei-111
Cinn trivalop fuse (PaddlePaddle#60)
185f288
Aurelius84 pushed a commit that referenced this issue Mar 26, 2024
@2742195759 @tc20042008
@feifei-111 @jiahy0825 @Fridge003
[CINN / PIR] Cinn trivalop fuse (#62088)
fec0b3d 
* implement FuseFilteredStmtPatterns

* update

* split trivial op into a single file.

* fix compiler complaints

* rename StmtIter to StmtPtr

* declare group_pattern.InferShardableAxes

* refine signature of group_pattern.InferShardableAxes

* move group_pattern.InferShardableAxes to group_pattern_util.InferShardableAxes

* implement group_pattern_util.InferShardableAxes

* add group_pattern_util.InferShardableAxesFromSink

* ReversedInferShardableAxes support sinks

* update op lower

* support multiple sinks in group_pattern_util.InferShardableAxes

* update

* fix link error

* update

* remove FusionOp to OpList

* update

* update

* update

* update

* declare group_pattern_util.h

* fix compiler complains

* declare group_pattern_util.ClusteringHelper

* refine signature of group_pattern_util.ClusterIntoGroupPatternsFromOpList

* update op lowr

* add todo

* minor refine by group_pattern_util.OpSet

* update

* update

* update (#57)

* update

* update

* Cinn trivalop fuse (#58)

* fix

* refactor StmtFusionHelper by OpTopo

* Complete: CreateReduceExpr function.

* update

* recursive done.

* update

* Cinn trivalop fuse (#59)

* clean all the TODO.

* update

* fix cluster

* remove unused OpTopo.downstream_disconnected_ops

* Cinn trivalop fuse (#60)

* fix compile rror

* update

* Cinn trivalop fuse (#61)

* add R + T skeleon

* add search utils.

* update

* Cinn trivalop fuse (#62)

* push

* update

* fix

* fix transformer

* fix

* Implement iterator vars fetching in ReduceOp

* small fix

* add GetOuterIterVars API

* fix

* fix compile complain

* modify GetOutputIters of TrivialOp

* remove dumplicate code in visit

* implement ClusterIntoGroupPatternsFromOpList

* Fix most error in trivial_op.cc.

* CreateReduceExpr is OK!

* fix

* add CheckIterEq

* implement group_pattern_util.ClusteringEngine and groupp_pattern_util.ClusteringPolicy

* SinkTrivialTransform OK!

* update

* fix init_tensor name problem.

* update

* fix compiler complains

* refactor ShardableAxesSignature by group_pattern.SoleOutputShardableAxes

* split trivial_op.cc

* update

* implement group_pattern_util.MakeShardableAxesSignature4ReduceOp

* update

* implement group_pattern_util.MakeEmptyShardableAxesSignature

* add helper class group_pattern_util.ShardableAxesProvider

* implement group_pattern_util.MakeShardableAxesSignature4BroadcastOp

* update

* update

* fix softmax error.!

* fix

* update

* merge

* fix

* Implement new OpMergeWithOp and add a relevant flag

* update

* update

* fix reduce_load error. add splitReduceTransform

* fix conflict

* update

* update

* update

* disable horizontal fusion

* fix

* Add some VLOG

* Fix group cluster bug (#71)

* fix

* fix dyshape

* fix

* init split cluster files

* update

* update

* update

* spliting

* update

* spliting

* spliting

* pattern utils

* update

* update

* clean cmake

* update

* update

* update

* fix clustering_engine

* fix fusion_helper

* update

* fix

* update

* update

* update

* update

* fix

* fix some erros

* update

* update

* fix split with num problem

* update

* fix

* fix static issues

* fix

* init split cluster files (#72)

* update

* update

* update

* update

* update

* update

* update

* update

* update

* split shardable axes provider (#73)

* update

* update

* fix broadcast (#75)

* update

* update

* fix

* fix code format

* fix code format

* remove unittest

* update

* update (#77)

* update

* update

* update

---------

Co-authored-by: tc20042008 <156998525+tc20042008@users.noreply.github.com>
Co-authored-by: feifei-111 <2364819892@qq.com>
Co-authored-by: jiahy0825 <jiahongyu@baidu.com>
Co-authored-by: zhangbaizhou <zhangbaizhou@baidu.com>
Co-authored-by: Baizhou Zhang <eddiezhang@pku.edu.cn>
co63oc pushed a commit to co63oc/Paddle that referenced this issue Mar 26, 2024
@2742195759 @tc20042008
@feifei-111 @jiahy0825 @Fridge003 @co63oc
[CINN / PIR] Cinn trivalop fuse (PaddlePaddle#62088)
7d58ad1 
* implement FuseFilteredStmtPatterns

* update

* split trivial op into a single file.

* fix compiler complaints

* rename StmtIter to StmtPtr

* declare group_pattern.InferShardableAxes

* refine signature of group_pattern.InferShardableAxes

* move group_pattern.InferShardableAxes to group_pattern_util.InferShardableAxes

* implement group_pattern_util.InferShardableAxes

* add group_pattern_util.InferShardableAxesFromSink

* ReversedInferShardableAxes support sinks

* update op lower

* support multiple sinks in group_pattern_util.InferShardableAxes

* update

* fix link error

* update

* remove FusionOp to OpList

* update

* update

* update

* update

* declare group_pattern_util.h

* fix compiler complains

* declare group_pattern_util.ClusteringHelper

* refine signature of group_pattern_util.ClusterIntoGroupPatternsFromOpList

* update op lowr

* add todo

* minor refine by group_pattern_util.OpSet

* update

* update

* update (PaddlePaddle#57)

* update

* update

* Cinn trivalop fuse (PaddlePaddle#58)

* fix

* refactor StmtFusionHelper by OpTopo

* Complete: CreateReduceExpr function.

* update

* recursive done.

* update

* Cinn trivalop fuse (PaddlePaddle#59)

* clean all the TODO.

* update

* fix cluster

* remove unused OpTopo.downstream_disconnected_ops

* Cinn trivalop fuse (PaddlePaddle#60)

* fix compile rror

* update

* Cinn trivalop fuse (PaddlePaddle#61)

* add R + T skeleon

* add search utils.

* update

* Cinn trivalop fuse (PaddlePaddle#62)

* push

* update

* fix

* fix transformer

* fix

* Implement iterator vars fetching in ReduceOp

* small fix

* add GetOuterIterVars API

* fix

* fix compile complain

* modify GetOutputIters of TrivialOp

* remove dumplicate code in visit

* implement ClusterIntoGroupPatternsFromOpList

* Fix most error in trivial_op.cc.

* CreateReduceExpr is OK!

* fix

* add CheckIterEq

* implement group_pattern_util.ClusteringEngine and groupp_pattern_util.ClusteringPolicy

* SinkTrivialTransform OK!

* update

* fix init_tensor name problem.

* update

* fix compiler complains

* refactor ShardableAxesSignature by group_pattern.SoleOutputShardableAxes

* split trivial_op.cc

* update

* implement group_pattern_util.MakeShardableAxesSignature4ReduceOp

* update

* implement group_pattern_util.MakeEmptyShardableAxesSignature

* add helper class group_pattern_util.ShardableAxesProvider

* implement group_pattern_util.MakeShardableAxesSignature4BroadcastOp

* update

* update

* fix softmax error.!

* fix

* update

* merge

* fix

* Implement new OpMergeWithOp and add a relevant flag

* update

* update

* fix reduce_load error. add splitReduceTransform

* fix conflict

* update

* update

* update

* disable horizontal fusion

* fix

* Add some VLOG

* Fix group cluster bug (PaddlePaddle#71)

* fix

* fix dyshape

* fix

* init split cluster files

* update

* update

* update

* spliting

* update

* spliting

* spliting

* pattern utils

* update

* update

* clean cmake

* update

* update

* update

* fix clustering_engine

* fix fusion_helper

* update

* fix

* update

* update

* update

* update

* fix

* fix some erros

* update

* update

* fix split with num problem

* update

* fix

* fix static issues

* fix

* init split cluster files (PaddlePaddle#72)

* update

* update

* update

* update

* update

* update

* update

* update

* update

* split shardable axes provider (PaddlePaddle#73)

* update

* update

* fix broadcast (PaddlePaddle#75)

* update

* update

* fix

* fix code format

* fix code format

* remove unittest

* update

* update (PaddlePaddle#77)

* update

* update

* update

---------

Co-authored-by: tc20042008 <156998525+tc20042008@users.noreply.github.com>
Co-authored-by: feifei-111 <2364819892@qq.com>
Co-authored-by: jiahy0825 <jiahongyu@baidu.com>
Co-authored-by: zhangbaizhou <zhangbaizhou@baidu.com>
Co-authored-by: Baizhou Zhang <eddiezhang@pku.edu.cn>
zmxdream pushed a commit to zmxdream/Paddle that referenced this issue Apr 2, 2024
@YaoCheng8667
Merge pull request PaddlePaddle#60 from YaoCheng8667/paddlebox-yc
dd20513 
modify interface for compress push
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Bug
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zchen0211 @qingqing01