提交 · c09c4a15d104aec3bbaebc540fb9a4e62152980f · PaddlePaddle / Paddle-Lite

27 3月, 2020 2 次提交
- Y
  [LITE][OPENCL] Fix elemMul/instanceNorm kernel of opencl (#3272) · c09c4a15
  由 Yuan Shuai 提交于 3月 27, 2020
```
* [LITE][OPENCL] fix elemul kernel of opencl. test=develop

* fix instanceNorm of opencl. test=develop

* add more info about cl device info. test=develop
```
  c09c4a15
- M
  
  fix segment fault bug, test=develop (#3282) · e3cf724e
  由 mapingshuo 提交于 3月 27, 2020
  
  e3cf724e
24 3月, 2020 3 次提交
- C
  
  Support gnustl, replace string funcs with ours, test=develop (#3263) · 5ffdfeda
  由 cc 提交于 3月 24, 2020
  
  5ffdfeda
- X
  
  [LITE][OPENCL][Image]support multi batch conv2d 3x3 5x5 7x7 ,open lws,test=develop (#3258) · 73ca2e00
  由 xiebaiyuan 提交于 3月 24, 2020
  
  73ca2e00
- X
  [LITE][OPENCL][Image]optimise conv2d 5x5 7x7,test=develop (#3253) · 71d01cfb
  由 xiebaiyuan 提交于 3月 24, 2020
```
* [LITE][OPENCL][Image]optimise conv2d 5x5 7x7,test=develop

* [LITE][OPENCL][Image]optimise conv2d 5x5 7x7,test=develop

* [LITE][OPENCL][Image]optimise conv2d 5x5 7x7,test=develop
```
  71d01cfb
23 3月, 2020 3 次提交
- H
  [arm]improve sgemv profile (#3241) · 1c5b0583
  由 HappyAngel 提交于 3月 23, 2020
```
* fxi ff, test=develop

* delete bgr_flip, test=develop
```
  1c5b0583
- X
  
  feat: add elementwise_grad op (#3246) · 6d7e40a9
  由 xiaogang 提交于 3月 23, 2020
  
  6d7e40a9
- Z
  
  [NPU] cache om-models by inputs shape (#3242) · 0b753607
  由 zhupengyang 提交于 3月 23, 2020
  
  0b753607
22 3月, 2020 1 次提交

[LITE][OPENCL][PROFILE] Enhance precision profile & Clean opencl code (#3227) · 5b2a618f

由 Yuan Shuai 提交于 3月 22, 2020

* [LITE][OPENCL] clean code for opencl. test=develop

* [LITE][PROFILER] Enhance Precision Profiler. test=develop

* delete useless var in profiler. test=develop

* add ocl header. test=develop

5b2a618f

17 3月, 2020 1 次提交
- W
  For cuda compilation products and ci (#3152) · ca2481e6
  由 Wilber 提交于 3月 17, 2020
```
add cuda ci.

Organize cuda compilation products.
```
  ca2481e6
16 3月, 2020 2 次提交

[LITE][ARM] Comment armv7 cpu layout (#3196) · 6c7678ac

由 Yuan Shuai 提交于 3月 16, 2020

* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][ARM] comment assembly of layout armv7 cpu. test=develop

6c7678ac

M
add square op for arm kernel (#3169) · 8aaf3197
由 mapingshuo 提交于 3月 16, 2020
```
* add backend

* add kernel

* add grad kernel
```
8aaf3197

15 3月, 2020 2 次提交

[LITE][OPENCL] Add lws for opencl conv image kernel (#3191) · 23c56b1e

由 Yuan Shuai 提交于 3月 15, 2020

* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][OPENCL] fix opencl fc kernel. test=develop

* [LITE][OPENCL] add lws for opencl conv image kernel. test=develop

23c56b1e

[LITE][OPENCL] Fix fc opencl (#3190) · 0f110d69

由 Yuan Shuai 提交于 3月 15, 2020

* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][OPENCL] fix opencl fc kernel. test=develop

0f110d69

14 3月, 2020 5 次提交

[arm] improve conv3x3_dw performance with relu, relu6 and leakey relu (#3183) · efed01ad

由 HappyAngel 提交于 3月 14, 2020


* improve conv_dw profile with rel relu6 leakyrelu, test=develop

* add depthwise, test=develop

* fix ci error, test=develop

* fix cv demo print, test=develop

efed01ad

[ARM] improve sgemm performance with relu, relu6 and leakey relu, test=develop (#3181) · 5772d7ec

由 yiicy 提交于 3月 14, 2020

* [ARM] improve sgemm performance with relu, relu6 and leakey relu, test=develop

* [ARM] improve sgemm performance with relu, relu6 and leakey relu, test=develop

5772d7ec

[LITE][DEMO] Fix mobile light demo (#3180) · 2c05abda

由 Yuan Shuai 提交于 3月 14, 2020

* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][DEMO] fix input arg. test=develop

* fix shutdownlog for std::endl. test=develop

2c05abda

J

[Lite][OpenCL]Delete unused macro in depthwise_conv2d_kernel.cl. test=develop (#3176) · ccd0c558
由 Jiaying Zhao 提交于 3月 14, 2020

ccd0c558
Y
[LITE][OPENCL] Change fp32 fc to fp16's. test=develop (#3173) · dff59708
由 Yuan Shuai 提交于 3月 14, 2020
```
* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop

* fix act in conv3x3opt opencl kernel. test=develop
```
dff59708

13 3月, 2020 2 次提交
- J
  
  [Lite][OpenCL]Add conv2d_3x3_opt_kernel. test=develop (#3170) · 813123f5
  由 Jiaying Zhao 提交于 3月 13, 2020
  
  813123f5
- H
  【arm】resize nv12 bug (#3155) · 3c6d0896
  由 HappyAngel 提交于 3月 13, 2020
```
* fix clang v7 error
* change ut, test=develop
* fix conv ut, test=develop
```
  3c6d0896
11 3月, 2020 1 次提交
- Y
  [OPENCL] add pad2d image kernel and ut, test=develop (#3143) · c1487788
  由 yiicy 提交于 3月 11, 2020
```
add pad2d image kernel and ut
```
  c1487788
10 3月, 2020 2 次提交
- X
  【opencl】add dropout opencl kernel (#3141) · 8ad2bd2b
  由 xiaogang 提交于 3月 10, 2020
```
* feat: add dropout opencl kernel
```
  8ad2bd2b
- X
  [LITE][OPENCL] add slice kernel (#3126) · 5fcd97a6
  由 xiaogang 提交于 3月 10, 2020
```
* feat: add opencl elementwise_sub op & ut
```
  5fcd97a6
09 3月, 2020 4 次提交
- Y
  [OPENCL] add instance norm kernel and ut, test=develop (#3122) · 4d379957
  由 yiicy 提交于 3月 09, 2020
```
add instance norm kernel and ut
```
  4d379957
- H
  [arm] fix clang v7 bug (#3118) · 17d2a04a
  由 HappyAngel 提交于 3月 09, 2020
```
* set arm_lang default is off. test=develop

* fix resize error, test-develop
```
  17d2a04a
- X
  Opencl eltwisesub (#3116) · e13bde79
  由 xiaogang 提交于 3月 09, 2020
```
* feat: add opencl elementwise_sub op & ut
```
  e13bde79
- X
  
  [LITE][OPENCL][Image] opencl compatible with arm ,test=develop (#3120) · f7cf6a8c
  由 xiebaiyuan 提交于 3月 09, 2020
  
  f7cf6a8c
08 3月, 2020 1 次提交
- H
  [opencl] Add lrn OP (#3104) · cdde336e
  由 HappyAngel 提交于 3月 08, 2020
```
* add lrn op

* fix v7 build error, test=develop
```
  cdde336e
06 3月, 2020 3 次提交

【OpenCL】add bilinear_interp op (#3088) · d501487a

由 HappyAngel 提交于 3月 06, 2020



* fix

* fix format. test=develop

* fix format, test=develop

* fix resize error

* fix format. test=develop

* fix format, test=develop

* fix format

* note log(4) << x_image. test=develop

* note x_image printf. test=develop

d501487a

Z
[MLU] resnet50 supported on MLU,test=develop (#3087) · cc227f27
由 zhangshijin 提交于 3月 06, 2020
```
* [MLU] support resnet50 on MLU

* [MLU] support resnet50 on MLU
```
cc227f27

Develop nlp patch (#3059) · 8425c924

由 xiaogang 提交于 3月 06, 2020

* fix: fix nlp ops input and output type
* fix: add elementwise x_dims>y_dims case

8425c924

05 3月, 2020 1 次提交
- X
  
  [ARM] fix 5x5s2_int8 compute bug, test=develop (#3079) · 8f7ca24f
  由 xiaogang 提交于 3月 05, 2020
  
  8f7ca24f
04 3月, 2020 3 次提交

Z
scale support int32 input (#3065) · 6989f47f
由 zhupengyang 提交于 3月 04, 2020
```
* scale support int32 input
```
6989f47f
H
[opencl compile] add into build.sh (#3031) · dfcbfbdc
由 huzhiqiang 提交于 3月 04, 2020
```
* test=devellop

* add cl file into resulted lib test=develop

* test=develop

* test=develop
```
dfcbfbdc

[opencl] add grid_sampler op (#3075) · 50b9e85f

由 HappyAngel 提交于 3月 04, 2020


* add grid sampler

* reset act

* fix conflict and readme, test=develop

* fix ios v8 run error

* fix grid_sampler compute error. test=develop

* fix exp act run error, test=develop

* fix format, test=develop

50b9e85f

03 3月, 2020 2 次提交
- Y
  
  fix kernel of conv1x1, fc OOM in opencl buffer kernel. test=develop (#3062) · 312239cc
  由 Yuan Shuai 提交于 3月 03, 2020
  
  312239cc
- H
  [OpenCL]Add leakyRelu and tanh op (#3048) · 68581c6e
  由 HappyAngel 提交于 3月 03, 2020
```
* fix leakyrelu and tanh compute error, test=develop

* delete extra file, test=develop

* reset act

* fix conflict and readme, test=develop

* fix ios run error, test=develop
```
  68581c6e
02 3月, 2020 1 次提交

[LITE][OPENCL] Support video-sr feature using OpenCL FP16 Image (#3049) · 7bba07bf

由 Yuan Shuai 提交于 3月 02, 2020

* [LITE][OPENCL] Support video-sr feature using OpenCL FP16 Image. test=develop

* optimize image2d_to_buffer_with_post255. test=develop

* add def debug in cl kernel. test=develop

* remove conv image code in conv buffer. test=develop

7bba07bf

28 2月, 2020 1 次提交

add sequence_conv op and arm kernel (#3016) · c5d69591

由 mapingshuo 提交于 2月 28, 2020

* add sequence_conv op and arm kernel

* add test, test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* test=develop

* modify code style. test=develop

* fix ut, test=develop

* delete unused code, test=develop

c5d69591