提交 · 8e8e8e66aba8b6ccb1737f24c8cf12fa74acd177 · 机器未来 / Paddle

23 10月, 2018 1 次提交
- T
  fix typo and warning in analyzer_resnet50_test · 316bc9bf
  由 Tao Luo 提交于 10月 23, 2018
```
test=develop
```
  316bc9bf
21 10月, 2018 4 次提交
- T
  MKLDNN conv + elementwise_add fusion: fixing formatting · aa35aaa1
  由 Tomasz Patejko 提交于 10月 20, 2018
```
test=develop
```
  aa35aaa1
- T
  MKLDNN conv + elementwise_add fusion: turn on residual connection pass when CAPI is used. · 16760946
  由 Tomasz Patejko 提交于 10月 16, 2018
```
test=develop
```
  16760946
- T
  refine fuse pattern and attr · 40f8456a
  由 tensor-tang 提交于 10月 21, 2018
```
test=develop
```
  40f8456a
- T
  
  add seqconv eltadd relu pass · 603ba5e0
  由 tensor-tang 提交于 10月 19, 2018
  
  603ba5e0
19 10月, 2018 9 次提交
- M
  Remove use mkldnn from config in resnet50 test · f9ca3181
  由 Michał Gallus 提交于 10月 19, 2018
```
test=develop
```
  f9ca3181
- M
  Enable MKLDNN in Resnet50Tester · 91e8fbac
  由 Michal Gallus 提交于 10月 12, 2018
```
test=develop
```
  91e8fbac
- M
  
  Conv+Bias fuse · 582f59c1
  由 Michal Gallus 提交于 10月 12, 2018
  
  582f59c1
- W
  
  add comment on the default first pass · e6f480ec
  由 Wojciech Uss 提交于 10月 18, 2018
  
  e6f480ec
- W
  
  remove redundant pass list · 2cf258e3
  由 Wojciech Uss 提交于 10月 18, 2018
  
  2cf258e3
- W
  add MKL-DNN placement pass · 5632019f
  由 Wojciech Uss 提交于 10月 17, 2018
```
This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926)
updated to use the mkldnn-placement-pass.

test=develop
```
  5632019f
- W
  do not enable MKL-DNN twice · 5083ec3a
  由 Wojciech Uss 提交于 10月 19, 2018
```
After the MKL-DNN placement pass there is no need to enable MKL-DNN
in operators via executor

test=develop
```
  5083ec3a
- W
  Add MKL-DNN placement pass (#13958) · c3b70aec
  由 Wojciech Uss 提交于 10月 19, 2018
```
* add MKL-DNN placement pass

This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926)
updated to use the mkldnn-placement-pass.

test=develop

* remove redundant pass list

* add comment on the default first pass

* fix test for conv+relu mkldnn fuse
```
  c3b70aec
- W
  add ifdef guard for MKL-DNN placement pass · 4a368a49
  由 Wojciech Uss 提交于 10月 19, 2018
```
test=develop
```
  4a368a49
18 10月, 2018 3 次提交
- S
  update · b77e4f49
  由 superjomn 提交于 10月 18, 2018
```
test=develop
```
  b77e4f49
- T
  fix analyzer_rnn2_test · ef098624
  由 Tao Luo 提交于 10月 18, 2018
```
test=develop
```
  ef098624
- T
  add profile_mkldnn test · e5b4643a
  由 Tao Luo 提交于 10月 18, 2018
```
test=develop
```
  e5b4643a
17 10月, 2018 4 次提交
- T
  add compare_mkldnn test · b8196843
  由 Tao Luo 提交于 10月 17, 2018
```
test=develop
```
  b8196843
- T
  add analysis_predictor in vis_demo · 6ea9d1b5
  由 Tao Luo 提交于 10月 17, 2018
```
test=develop
```
  6ea9d1b5
- T
  
  update with comments · b854d959
  由 Tao Luo 提交于 10月 17, 2018
  
  b854d959
- Y
  
  fix analysis predictor profile (#13896) · 6809238d
  由 Yan Chunwei 提交于 10月 17, 2018
  
  6809238d
16 10月, 2018 2 次提交
- T
  adjust demo_ci with fluid_inference_install_dir · a35e7f4b
  由 Tao Luo 提交于 10月 16, 2018
```
test=develop
```
  a35e7f4b
- T
  refine mkldnn test in analyzer_tests · bd774601
  由 Tao Luo 提交于 10月 16, 2018
```
test=develop
```
  bd774601
15 10月, 2018 3 次提交
- S
  update · 1cfd2b51
  由 superjomn 提交于 10月 15, 2018
```
test=develop
```
  1cfd2b51
- S
  update · 28459592
  由 superjomn 提交于 10月 15, 2018
```
test=develop
```
  28459592
- S
  update · e2bd40ca
  由 superjomn 提交于 10月 15, 2018
```
test=develop
```
  e2bd40ca
14 10月, 2018 1 次提交
- S
  update · 049fcbe1
  由 superjomn 提交于 10月 14, 2018
```
test=develop
```
  049fcbe1
13 10月, 2018 1 次提交
- S
  clean CreatePaddlePredictor · f5c0221c
  由 superjomn 提交于 10月 13, 2018
```
test=develop
```
  f5c0221c
12 10月, 2018 4 次提交
- N
  fix commets · 320c78e1
  由 nhzlx 提交于 10月 12, 2018
```
test=develop
```
  320c78e1
- N
  fix demo_ci bug in vis_demo.cc · efa5bac7
  由 nhzlx 提交于 10月 12, 2018
```
test=develop
```
  efa5bac7
- T
  fix default number of threads when inference with or without MKLDNN · dc5a7b90
  由 tensor-tang 提交于 10月 12, 2018
```
test=develop
```
  dc5a7b90
- N
  
  add op converter · 0cb88c34
  由 nhzlx 提交于 10月 11, 2018
  
  0cb88c34
11 10月, 2018 1 次提交
- T
  
  Revert "[MKLDNN] Pass: Fuse Conv + Bias" · 9b11a175
  由 Tao Luo 提交于 10月 11, 2018
  
  9b11a175
10 10月, 2018 2 次提交
- M
  Pass: Fuse Conv + Bias · 40b17be4
  由 Michal Gallus 提交于 10月 01, 2018
```
test=develop
```
  40b17be4
- N
  
  fix comments · d347ea68
  由 nhzlx 提交于 10月 10, 2018
  
  d347ea68
09 10月, 2018 3 次提交
- N
  
  add tensorrt api lib to paddle_fluid · f5690950
  由 nhzlx 提交于 10月 09, 2018
  
  f5690950
- T
  revert with_fast_math to ON · 84a55155
  由 Tao Luo 提交于 10月 09, 2018
```
test=develop
```
  84a55155
- D
  enhance isinf/isnan in tensor util, avoid copy back to cpu (#12688) · a46e30aa
  由 dzhwinter 提交于 10月 09, 2018
```
* "avoid copy back to cpu"

* "add infinity support"

* "fix ci"

* "add cpu macro"

* rerun ci; test=develop

* "fix api"
test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop
```
  a46e30aa
08 10月, 2018 2 次提交
- S
  conv bn fuse pass · 78f98294
  由 Sylwester Fraczek 提交于 9月 19, 2018
```
review fix

review from hshen14 fix

test=develop

fix error in broadcast and code cleanup

rename bias -> eltwise and added macro to shorten code

formatting
```
  78f98294
- T
  disable EIGEN_FAST_MATH and use_fast_math · 28889cae
  由 Tao Luo 提交于 10月 08, 2018
```
test=develop
```
  28889cae

机器未来 / Paddle 与 Fork 源项目一致

机器未来 / Paddle
与 Fork 源项目一致