platform/core/ml/nnfw.git
5 years agoImplement SQRT op in PACL (#3418)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 14 Nov 2018 01:27:24 +0000 (06:57 +0530)]
Implement SQRT op in PACL (#3418)

This patch implements SQRT op in PACL.
Related issue: #3341

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdd optimize_for_inference script into tflkit (#3546)
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 14 Nov 2018 00:46:35 +0000 (09:46 +0900)]
Add optimize_for_inference script into tflkit (#3546)

* Add optimize_for_inference script into tflkit

optimize_for_inference tool optimizes a TensorFlow GraphDef for inference.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Add detail information to README.md

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years agoAdd NNAPI delegation for SQRT_EX (#3422)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 13 Nov 2018 09:43:02 +0000 (15:13 +0530)]
Add NNAPI delegation for SQRT_EX (#3422)

This patch adds NNAPI delegation for SQRT_EX

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years ago[neurun] Remove Planner implementation (#3560)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 13 Nov 2018 09:34:26 +0000 (18:34 +0900)]
[neurun] Remove Planner implementation (#3560)

Now that we are able to have uniform planning procedure for all Nodes,
We do not need Planner class anymore. The planning procedure is now
unified and moved to `compilation.cc` but Planner class is left for
assertion checks which will be renamed as `OperationAsserter` later.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoMismatch in generated test files for NOT_EQUAL_EX (#3550)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 13 Nov 2018 07:55:14 +0000 (13:25 +0530)]
Mismatch in generated test files for NOT_EQUAL_EX (#3550)

This patches the mismatch in the GTest files for NOT_EQUAL_EX.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdd tflite_convert scripts into tflkit (#3544)
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 13 Nov 2018 01:51:24 +0000 (10:51 +0900)]
Add tflite_convert scripts into tflkit (#3544)

* Add tflite_convert scripts into tflkit

tflite_convert tool will convert a TensorFlow GraphDef into TfLite model.

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Add check routine for bazel

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Change the PB_PATH to GRAPHDEF_PATH and add detail usages

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Add detail usage to README.md

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Fixed wrong exitcode

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
5 years ago[neurun] Add const iterate method to Linear (#3547)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 13 Nov 2018 01:51:04 +0000 (10:51 +0900)]
[neurun] Add const iterate method to Linear (#3547)

Add const iterate method to Linear

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years ago[neurun] Revise IStageGenerator (#3536)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 12 Nov 2018 04:12:55 +0000 (13:12 +0900)]
[neurun] Revise IStageGenerator (#3536)

* [neurun] Revise IStageGenerator

Revise IStageGenerator to be a NodeVisitor. This will make it possible
to unify Planner implementation.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Pass Stage as const reference

6 years agoUse pre-built acl by environment variable (#3533)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 12 Nov 2018 02:06:02 +0000 (11:06 +0900)]
Use pre-built acl by environment variable (#3533)

* Use pre-built acl by environment variable

When environment variable EXT_ACL_FOLDER is set, use pre-built acl binary

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Fix if-else syntax in Makefile

6 years agoAdding testcases for NotEqual Op (#3516)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Fri, 9 Nov 2018 07:50:55 +0000 (13:20 +0530)]
Adding testcases for NotEqual Op (#3516)

This commit adds Gtest testcases for NotEqual op.
Related issues: #3335,#3337

Signed-off-by: Siva Sai <siva.sai@samsung.com>
6 years agoConfigure parallel execution job count (#3531)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 9 Nov 2018 06:50:12 +0000 (15:50 +0900)]
Configure parallel execution job count (#3531)

User can configure parallel execution job count using NPROCS environment variable
- Reduce local compilation overhead when doing multiple job
- Protect excessive CI processor consumtion by one job

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoCreate tflkit directory (#3438)
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 9 Nov 2018 05:20:39 +0000 (14:20 +0900)]
Create tflkit directory (#3438)

* Create tflite_easytool directory

This directory is created to make it easier to run frequently used tools in scripts.
Now, it has two functions:
- Summraize PB model
- Summraize TfLite model

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Change the directory name to tflkit

Also changes the relative path to absolute path

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Add Prerequires and TF tool guideline

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
* Add additional description for prerequires

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
6 years ago[neurun] Default implementation for NodeVisitor (#3530)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 9 Nov 2018 03:34:47 +0000 (12:34 +0900)]
[neurun] Default implementation for NodeVisitor (#3530)

Implement default implementation for NodeVisitor which is just doing
nothing.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoEnable concat elimination on acl backend (#3528)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 08:55:29 +0000 (17:55 +0900)]
Enable concat elimination on acl backend (#3528)

Enable concat elimination on acl backend
Change config and remove assertion block

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Remove IInitializerGenerator (#3525)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 8 Nov 2018 08:16:57 +0000 (17:16 +0900)]
[neurun] Remove IInitializerGenerator (#3525)

Remove IInitializerGenerator and its implementations. We do not need
this backend API anymore.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoAdd comment for tensorflow_max_ex (#3526)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 08:16:17 +0000 (17:16 +0900)]
Add comment for tensorflow_max_ex (#3526)

Add comment for tensorflow_max_ex in NeuralNetworksEx.h

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoFix typo in nnapi delegate (#3527)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 08:15:49 +0000 (17:15 +0900)]
Fix typo in nnapi delegate (#3527)

Fix typo in nnapi delegate: v1.11 -> v1.12

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Apply IMemoryPlanner to backend/cpu (#3517)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 8 Nov 2018 07:48:44 +0000 (16:48 +0900)]
[neurun] Apply IMemoryPlanner to backend/cpu (#3517)

Now IMemoryPlanner and Allocator plays the role of IMemoryAllocator.
This commits includes some fixing for bugs to apply on backend/cpu.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
6 years agoUpdate tensorflow to v1.12 (#3486)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 07:12:55 +0000 (16:12 +0900)]
Update tensorflow to v1.12 (#3486)

* Update external package

- Update external package version
- Update cmake to build tflite
- Add gitignore for new external code

* Update library to support tflite

- Update nnapi delegate
- Update NeuralNetworksShim.h for new API
- Fix cmake for new files in updated tensorflow
- Workaround: Introduce OBS_BUILD flag to avoid gbs build fail

* Update neurun CPU kernel

- Update neurun CPU kernel to call updated tflite interpreter kernel
- Add build option -fPIC for updated tflite kernel

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoRegister subtensor info to tensor builder (#3519)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 06:49:08 +0000 (15:49 +0900)]
Register subtensor info to tensor builder (#3519)

Register subtensor info to tensor builder if
- Tensor is subtensor of other tensor
- Backend support subtensor allocation

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoCheck external directory exists (#3522)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 06:40:53 +0000 (15:40 +0900)]
Check external directory exists (#3522)

Check external directory exists and download if directory does not exist

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoFix run_benchmark.sh typo(MODLES->MODELS) (#3523)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 05:12:20 +0000 (14:12 +0900)]
Fix run_benchmark.sh typo(MODLES->MODELS) (#3523)

- Fix run_benchmark.sh typo( MODLES -> MODELS )

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
6 years agoFix CI benchmark failure (#3520)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 04:08:02 +0000 (13:08 +0900)]
Fix CI benchmark failure (#3520)

CI benchmark job fails since it does not reflect model path
change. This commit sets the proper model path.

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
6 years agoConcat elimination in codegen (#3518)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 02:44:39 +0000 (11:44 +0900)]
Concat elimination in codegen (#3518)

Concat elimination in codegen: check output tensor is parent of inputs and do nothing if true

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoBuild subtensor in acl TensorBuilder (#3513)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 01:56:03 +0000 (10:56 +0900)]
Build subtensor in acl TensorBuilder (#3513)

* Build subtensor in acl TensorBuilder

Build subtensor in acl TensorBuilder
Change to public function in Convert.cc

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Remove deprecated declaration

* Remove diff by space line

6 years ago[neurun] Remove InitializerGenerator dependency (#3508)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 8 Nov 2018 01:11:02 +0000 (10:11 +0900)]
[neurun] Remove InitializerGenerator dependency (#3508)

Remove all InitializerGenerator dependent code since we now have
ConstantInitializer for this purpose.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoIntroduce subtensor allocation check API (#3510)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 8 Nov 2018 01:10:32 +0000 (10:10 +0900)]
Introduce subtensor allocation check API (#3510)

Check API will be used in codegen

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Introduce MemoryPlanner and Allocator (#3511)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 8 Nov 2018 01:09:12 +0000 (10:09 +0900)]
[neurun] Introduce MemoryPlanner and Allocator (#3511)

Introduces IMemoryPlanner, BumpPlanner, FirstFitPlanner and
Allocator to replace IMemoryAllocator.
Current IMemoryAllocator has two roles, Planner and Allocator. This
commits separates IMemoryAllocator to the two classes. After this commit
lands, IMemoryAllocator will be removed soon.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
6 years agoOptimize the StridedSlice Kernel for performance improvement (#3230)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 7 Nov 2018 09:31:46 +0000 (18:31 +0900)]
Optimize the StridedSlice Kernel for performance improvement (#3230)

This commit optimizes the StridedSlice Kernel for performance inprovement.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years agoIntroducing NotEqual Op in runtime (#3485)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 7 Nov 2018 08:18:53 +0000 (13:48 +0530)]
Introducing NotEqual Op in runtime (#3485)

This commit introduces NotEqual op in runtime.
Related issues: #3335, #3337

Signed-off-by: Siva Sai <siva.sai@samsung.com>
6 years agoArgMinMax Implementation for ArgMin and ArgMax. (#3331)
PRAVEEN DORESWAMY NAIDU/System SW /SRI-Bangalore/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 08:17:28 +0000 (13:47 +0530)]
ArgMinMax Implementation for ArgMin and ArgMax. (#3331)

This change introduces the cpu kernel for the ArgMin and ArgMax
operations.

Signed-off-by: Praveen D N <praveen.dn@samsung.com>
6 years ago[neurun] Fix build break (#3507)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 7 Nov 2018 08:01:26 +0000 (17:01 +0900)]
[neurun] Fix build break (#3507)

Caused by #3426 and #3436 collision.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoUpdate framework test list (#3499)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 07:40:33 +0000 (16:40 +0900)]
Update framework test list (#3499)

Add more framework test for neurun
Change inception test: use simple module instead of full models

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoIntroduce subtensor map (#3493)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 07:17:33 +0000 (16:17 +0900)]
Introduce subtensor map (#3493)

- Introduce subtensor map in ACL tensor builder
- TensorBuilder::at() and TensorBuilder::tensorAt() can return subtensor

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Introduce ConstantInitializer (#3426)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 7 Nov 2018 07:02:25 +0000 (16:02 +0900)]
[neurun] Introduce ConstantInitializer (#3426)

* [neurun] Introduce ConstantInitializer

This commit introduces `ConstantIntializer` class that fills operand
objects with the constant values which were specified by
`ANeuralNetworksModel_setOperandValue`. Plus, this class replaces the
InitializerGenerator.

NOTE due to FullyConnected operation's implicit reshaping, it is
implemented with workarounds.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Add license

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoFix custom operator register macro (#3495)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 06:34:34 +0000 (15:34 +0900)]
Fix custom operator register macro (#3495)

Fix custom operator register macro for updated TfLiteRegistration field
- First 4 fields may not change
- Can adjust new fields before custom_name

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoEnable more model tests (#3497)
이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 06:34:20 +0000 (15:34 +0900)]
Enable more model tests (#3497)

The following tests are triggered on default on framework/verification
test :

- embedding lookup
- L2 normalization
- L2 pool
- Squeeze
- Tanh
- Transpose
- Logistic

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
6 years agoIntroduce namespace in runtime load helper (#3494)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 7 Nov 2018 06:18:40 +0000 (15:18 +0900)]
Introduce namespace in runtime load helper (#3494)

Introduce namespace in runtime load helper
Restore function name
It protects naming conflict with upstream tensorflow

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[model_parser] Hide instruction counts by verbose option (#3487)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 7 Nov 2018 03:12:34 +0000 (12:12 +0900)]
[model_parser] Hide instruction counts by verbose option (#3487)

Hides instruction counts by verbose option. Now -v or --verbose can skip
printing instruction counts. You can use this verbose option as follows
- With verbose level 0, prints only summary of tflite
- With verbose level 1(default), prints all like current default except for
instructions
- With verbose level 2, prints all like current default including for
instructions

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
6 years ago[neurun] Introduce FirstfitAllocator (#3458)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 6 Nov 2018 09:15:59 +0000 (18:15 +0900)]
[neurun] Introduce FirstfitAllocator (#3458)

* [neurun] Introduce FirstfitAllocator

Introduces FirstfitAllocator instead of BumpAllocator. This allocator
allocates a block for tensor at the first-fit offset.

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Revise allocate() of FirstfitAllocator

- Adds comment for description of allocate()
- Removes inner lambda allocateBlock() in allocate()

* Change the name from Firstfit to FirstFit

* Fix typo

* Adds comment for _alloc_table

6 years agoIntroduce a enum class declaration for reduce operations. (#3461)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 6 Nov 2018 08:50:30 +0000 (17:50 +0900)]
Introduce a enum class declaration for reduce operations. (#3461)

This commit introduces a enum declaration for reduce operations.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years agoIntroduce registerSubTensorInfo (#3474)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 6 Nov 2018 02:48:23 +0000 (11:48 +0900)]
Introduce registerSubTensorInfo (#3474)

Introduce registerTensorInfo to register subtensor information (not used yet)
Backend allocator will use this info for allocation

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoIntroducing NotEqual op in NeuralNetworksEx (#3473)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 6 Nov 2018 02:30:37 +0000 (08:00 +0530)]
Introducing NotEqual op in NeuralNetworksEx (#3473)

This commit introduces NotEqual op in NeuralNetworksEx.h
Related issues: #3335, #3337

Signed-off-by: Siva Sai <siva.sai@samsung.com>
6 years agoAdd CL kernel call for Transpose op from runtime (#3470)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 6 Nov 2018 01:05:23 +0000 (06:35 +0530)]
Add CL kernel call for Transpose op from runtime (#3470)

This patch adds cl kernel call for transpose op from PACL.

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoUpdating comment to create more formal equation (#3466)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 6 Nov 2018 00:42:06 +0000 (06:12 +0530)]
Updating comment to create more formal equation (#3466)

This patch will updates comment for sqrt so as to remove x and y and to
have more formal equation.

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoEnable broadcast support for Equal_Ex op (#3431)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 6 Nov 2018 00:41:53 +0000 (06:11 +0530)]
Enable broadcast support for Equal_Ex op (#3431)

This patch enables broadcast support for Equal_Ex op.
Related issue: #3295.

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years agoCorrection of comments by adding shape info in NeuralNetworksEx.h (#3463)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 6 Nov 2018 00:41:18 +0000 (06:11 +0530)]
Correction of comments by adding shape info in NeuralNetworksEx.h (#3463)

This patch will add correction in comments by adding shape info in NeuralNetworksEx.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoDefining CAST_EX in NeuralNetworksEx.h (#3424)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 6 Nov 2018 00:41:03 +0000 (06:11 +0530)]
Defining CAST_EX in NeuralNetworksEx.h (#3424)

This patch defines CAST_EX in NeuralNetworksEx.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoDefining RSQRT_EX in NeuralNetworksEx.h (#3415)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 5 Nov 2018 08:39:08 +0000 (14:09 +0530)]
Defining RSQRT_EX in NeuralNetworksEx.h (#3415)

This patch defines RSQRT_EX in NeuralNetworksEx.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoIntroduce registerTensorInfo (#3467)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 5 Nov 2018 08:01:56 +0000 (17:01 +0900)]
Introduce registerTensorInfo (#3467)

Introduce registerTensorInfo to
- Divide tensor info register and use-def notify
- Prepare subtensor information register

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoFix build failure on neuurun (#3468)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 5 Nov 2018 07:43:03 +0000 (16:43 +0900)]
Fix build failure on neuurun (#3468)

Fix build failure on neurun by operator structure change

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Structural changes for ops (#3436)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 5 Nov 2018 07:14:35 +0000 (12:44 +0530)]
[neurun] Structural changes for ops (#3436)

This commit follows the discussions on #3250

Signed-off-by: Siva Sai <siva.sai@samsung.com>
6 years agoSupport ReduceMax kernel for cl up to 4-dimensions (#3340)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 5 Nov 2018 07:04:39 +0000 (16:04 +0900)]
Support ReduceMax kernel for cl up to 4-dimensions (#3340)

* Support ReduceMax kernel for cl up to 4-dimensions

This commit supports ReduceMax kernel for cl up to 4-dimensions.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
* Optimize ReduceMax Kernel for cl

This commit optimizes ReduceNMax kernel for cl.
  - Change calling kernel from at once kernel to call separated kernels multiple times.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years agoIntroduce backend config for subtensor (#3460)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 5 Nov 2018 05:58:51 +0000 (14:58 +0900)]
Introduce backend config for subtensor (#3460)

Introduce backend config for subtensor
CPU and ACL backend are not support subtensor yet

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoComment correction in CLBatchToSpaceND.h (#3313)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 5 Nov 2018 01:17:10 +0000 (06:47 +0530)]
Comment correction in CLBatchToSpaceND.h (#3313)

This patch will correct the doxygen comment for CLBatchToSpaceND.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years ago[neurun] Apply tensor lifetime-info(use-def) to Linear/TensorBuilder (#3409)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 5 Nov 2018 01:12:03 +0000 (10:12 +0900)]
[neurun] Apply tensor lifetime-info(use-def) to Linear/TensorBuilder (#3409)

* [neurun] Apply tensor lifetime-info(use-def) to memory allocation

Applies tensor lifetime-info(use-def) to memory allocation with revising
Linear and TensorBuilder.
- Introduce vassignTensors(virtually assign tensors) in Linear instead
  of markTensors
- Introduce assign(assign memory virtually)/unassign(unassign memory
  virtually) in TensorBuilder instead of mark

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
* Fix release build error

* Rename functions properly

Linear::vassignTensors -> planTensors
ITensorBuilder::assign -> notifyFirstUse
ITensorBuilder::unassign -> notifyLastUse

* Fix log

* Fix searching output first than input

6 years agoImplementation of Generic Permute CL Kernel (#3114)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 5 Nov 2018 01:11:09 +0000 (06:41 +0530)]
Implementation of Generic Permute CL Kernel (#3114)

This patch will add generic permute kernel supporting all permutations for nD Tensors
This kernel is required for Reshape and Transpose op

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoAdded test cases for Pack operation (#3399)
Vishal Keshav/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 5 Nov 2018 01:09:04 +0000 (06:39 +0530)]
Added test cases for Pack operation (#3399)

Test cases for 3D to 4D pack along 2 axises
Added test in skiplist of arm-linux, neuran and x86-linux

Signed-off-by: Vishal Keshav <vishal.k1@samsung.com>
6 years agoDefining NEG_EX in NeuralNetworksEx.h (#3417)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Fri, 2 Nov 2018 07:42:07 +0000 (13:12 +0530)]
Defining NEG_EX in NeuralNetworksEx.h (#3417)

This patch defines NEG_EX in NeuralNetworksEx.h
Related issue: #3347

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years agoDefining EXP_EX in NeuralNetworksEx.h (#3416)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Fri, 2 Nov 2018 06:27:10 +0000 (11:57 +0530)]
Defining EXP_EX in NeuralNetworksEx.h (#3416)

This patch defines EXP_EX in NeuralNetworksEx.h
Related issue: #3347

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years agoRemove deprecated coverity script (#3440)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Nov 2018 23:49:29 +0000 (08:49 +0900)]
Remove deprecated coverity script (#3440)

Remove deprecated coverity script (used nowhere)

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoRemove svace and coverity build script (#3439)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Nov 2018 08:21:17 +0000 (17:21 +0900)]
Remove svace and coverity build script (#3439)

Remove svace and coverity build script
- These scripts are not used in CI any more
- These scripts are not used by developer

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoRemove unnecessary headers from src/core/CL/kernels/* (#3375)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 1 Nov 2018 07:23:16 +0000 (12:53 +0530)]
Remove unnecessary headers from src/core/CL/kernels/* (#3375)

This patch will remove unnecessary headers from src/core/CL/kernels/* files

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoRevise script for docker image build (#3430)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Nov 2018 04:37:00 +0000 (13:37 +0900)]
Revise script for docker image build (#3430)

Revise script for docker image build
- Change script name
- Rename common.sh and move
- Set argument for docker image name and tizen build image
- Update documents

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoIntroduce SubTensorAnalyzer (#3410)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 1 Nov 2018 04:36:46 +0000 (13:36 +0900)]
Introduce SubTensorAnalyzer (#3410)

Introduce SubTensorAnalyzer and insert subtensor analyze phase in compilation

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Introduce iterate method for Context (#3425)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 31 Oct 2018 10:58:29 +0000 (19:58 +0900)]
[neurun] Introduce iterate method for Context (#3425)

Introduce `iterate` method for `codegen::operand::Context`.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoMove Graph::insertPermute to PermutationInsertionPass (#3408)
Дилшоджон Умронхонович Пошшоев/AI Tools Lab /SRR/Engineer/삼성전자 [Wed, 31 Oct 2018 10:03:50 +0000 (13:03 +0300)]
Move Graph::insertPermute to PermutationInsertionPass (#3408)

Since this method is used just in `PermutationInsertionPass` it's
reasonable to move into this class
Related issue is https://github.sec.samsung.net/STAR/nnfw/issues/3388

Signed-off-by: Poshshoev Dilshodzhon <d.poshshoev@samsung.com>
6 years agoDefining SQUARED_DIFFERENCE_EX in NeuralNetworksEx.h (#3413)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 09:55:07 +0000 (15:25 +0530)]
Defining SQUARED_DIFFERENCE_EX in NeuralNetworksEx.h (#3413)

This patch defines SQUARED_DIFFERENCE_EX in NeuralNetworksEx.h
Related issue: #3347

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years agoDefining EQUAL_EX in NeuralNetworksEx.h (#3354)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 09:28:06 +0000 (14:58 +0530)]
Defining EQUAL_EX in NeuralNetworksEx.h (#3354)

This patch defines EQUAL_EX in NeuralNetworksEx.h
Related issue: #3347

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years ago[neurun] Modification for Add op (#3414)
Siva Sai Vaddipati/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 08:51:13 +0000 (14:21 +0530)]
[neurun] Modification for Add op (#3414)

The changes made are aligned with the discussion in #3250

Signed-off-by: Siva Sai <siva.sai@samsung.com>
6 years agoIntroduce SQRT in PACL (#3412)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 08:08:18 +0000 (13:38 +0530)]
Introduce SQRT in PACL (#3412)

This patch introduces SQRT op in PACL
Related issue: #3341

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years agoIntroduce SQRT_EX in NeuralNetworksEx.h (#3400)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 06:00:09 +0000 (11:30 +0530)]
Introduce SQRT_EX in NeuralNetworksEx.h (#3400)

This patch includes SQRT_EX in NeuralNetworksEx.h
Related issue: #3341

Signed-off-by: prasannar <prasanna.r@samsung.com>
6 years agoRun benchmark for all tflite model under tests/framework (#3402)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 31 Oct 2018 05:50:48 +0000 (14:50 +0900)]
Run benchmark for all tflite model under tests/framework (#3402)

Related: #3397 #3264

Previously, run_benchmark_op.sh runs the tests in `benchmark_op_models.txt`.
- No one maintains the list.
- It contains only a few tests.
- If the location or folder name is changed, the list should be updated.

Now, run_benchmark_op.sh runs all tests under `tests/frameworks`.
- No one need to update whenever a new model is added/removed, location is changed....

This PR also removes

- option  `--frameworktest_list_file` option from `run_benchmark_op.sh`.
- benchmark_op_list.txt

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
6 years ago[neurun] Introduce OperationPass (#3403)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 31 Oct 2018 03:59:34 +0000 (12:59 +0900)]
[neurun] Introduce OperationPass (#3403)

Introduce `OperationPass` class which iterates over `operation::Node`s.
This is the same manner with `OperandPass`.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
6 years agoRemoving TODO for pool op (#3370)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 01:24:50 +0000 (06:54 +0530)]
Removing TODO for pool op (#3370)

This patch will remove TODO statement for max_pool and avg_pool

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoUse rpm macro instead of user define macro in spec file (#3406)
윤지영/동작제어Lab(SR)/Engineer/삼성전자 [Wed, 31 Oct 2018 01:22:27 +0000 (10:22 +0900)]
Use rpm macro instead of user define macro in spec file (#3406)

%{install_prefix} -> %{_prefix}
%{install_prefix}/lib -> %{_libdir}

Signed-off-by: Jiyoung Yun <jy910.yun@samsung.com>
6 years agoAdding Unpack Node (#3216)
Vishal Keshav/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 31 Oct 2018 01:01:43 +0000 (06:31 +0530)]
Adding Unpack Node (#3216)

Added unpack node in pure_arm_compute

Signed-off-by: Vishal Keshav <vishal.k1@samsung.com>
6 years agoIntroduce SubTensorInfo class (#3407)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Oct 2018 12:06:07 +0000 (21:06 +0900)]
Introduce SubTensorInfo class (#3407)

Introduce SubTensorInfo class to use at backend tensor allocation

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoIntroduce ParentInfo class (#3401)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Oct 2018 07:58:47 +0000 (16:58 +0900)]
Introduce ParentInfo class (#3401)

Introduce ParentInfo class to represent parent tensor information
Add field in neurun::graph::operand::Object for ParentInfo

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years ago[neurun] Revise MemoryAllocator (#3386)
김용섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 30 Oct 2018 06:07:18 +0000 (15:07 +0900)]
[neurun] Revise MemoryAllocator (#3386)

- MemoryBlock -> Block
- base_offset -> offset
- Remove mem_id concept
- Introduce graph::operand::Index instead of uint32_t
- Apply above changes to symbols of MemoryAllocator
- Apply above changes to tests of MemoryAllocator
- Append Logging

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
6 years agoRevise tizen build script (#3393)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 30 Oct 2018 06:05:17 +0000 (15:05 +0900)]
Revise tizen build script (#3393)

- Revise tizen cross build script
- Revise tizen gbs build script

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoRemoving ambigous/unused num_elem_processed_per_iteration variable (#3315)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 11:36:49 +0000 (17:06 +0530)]
Removing ambigous/unused num_elem_processed_per_iteration variable (#3315)

This patch will remove unused num_elem_processed_per_iteration variable from CLGatherKernel.cpp

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoRemoving extra header files included in topkv2 files (#3372)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 11:36:26 +0000 (17:06 +0530)]
Removing extra header files included in topkv2 files (#3372)

This patch will remove extra unnecessary headers in topkv2 op.
Also add CLScheduler.h which was getting included by CLArray
ClArray was including headers which were not required, hence it has been removed

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoAdd a generated test for HashTable_Lookup 4-D (#3381)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 29 Oct 2018 11:30:47 +0000 (20:30 +0900)]
Add a generated test for HashTable_Lookup 4-D (#3381)

This commit add a generated test for HashTable_Lookup 4-D.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years ago[neurun] Fix wrong ifdef guard (#3350)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 29 Oct 2018 11:29:43 +0000 (20:29 +0900)]
[neurun] Fix wrong ifdef guard (#3350)

This commit fixes ifdef guard in neurun.

Signed-off-by: sjsujinkim sjsujin.kim@samsung.com
6 years agoUpdate nnapi delegate for LRN (#3270)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 11:26:54 +0000 (16:56 +0530)]
Update nnapi delegate for LRN (#3270)

This patch will add nnapi delegation changes for LocalResponseNormalization.

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoAdd GeneratedTests of ReduceMax for 4-D (#3366)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 29 Oct 2018 06:33:15 +0000 (15:33 +0900)]
Add GeneratedTests of ReduceMax for 4-D (#3366)

This commit adds GeneratedTests of ReduceMax(TensorflowMax) for 4-D.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years agoRemove unnecessary headers from src/runtime/CL/functions/* (#3374)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 02:14:28 +0000 (07:44 +0530)]
Remove unnecessary headers from src/runtime/CL/functions/* (#3374)

This patch will remove unnecessary headers from src/runtime/CL/functions

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoRemove unnecessary headers from arm_compute/runtime/CL/* (#3373)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 02:14:13 +0000 (07:44 +0530)]
Remove unnecessary headers from arm_compute/runtime/CL/* (#3373)

This patch will remove unnecessary headers from arm_compute/runtime/CL files.

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoRemove unnecessary headers from arm_compute/core/CL/* (#3371)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 02:13:28 +0000 (07:43 +0530)]
Remove unnecessary headers from arm_compute/core/CL/* (#3371)

This patch will remove unnecessary headers included in the following files:

arm_compute/core/CL/kernels/CLActivationLayerExKernel.h
arm_compute/core/CL/kernels/CLArithmeticSubtractionExKernel.h
arm_compute/core/CL/kernels/CLEqualKernel.h
arm_compute/core/CL/kernels/CLGatherKernel.h
arm_compute/core/CL/kernels/CLNegKernel.h
arm_compute/core/CL/kernels/CLPixelWiseDivisionKernel.h
arm_compute/core/CL/kernels/CLReduceMaxKernel.h
arm_compute/core/CL/kernels/CLReductionMeanKernel.h
arm_compute/core/CL/kernels/CLSquaredDifferenceKernel.h
arm_compute/core/CL/kernels/CLStridedSliceKernel.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoUpdating addStage function declaration of Iplanbuilder (#3355)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 02:10:59 +0000 (07:40 +0530)]
Updating addStage function declaration of Iplanbuilder (#3355)

This patch updates the declaration of addStage function of Iplanbuilder and it's associated comments.
Due to ambiguous 's' in doxygen comment, this change is made.

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoAllign comment to have same formatting (#3369)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 02:08:48 +0000 (07:38 +0530)]
Allign comment to have same formatting (#3369)

This patch will remove tab spaces and align the comment to have same formating style in same_padding function

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoSupport Padding accross all dimensions (#3305)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 29 Oct 2018 01:08:36 +0000 (06:38 +0530)]
Support Padding accross all dimensions (#3305)

This patch will provide support to pad accross all dimensions of input tensor

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoCorrecting and adding arm_compute assertions in CL core/kernel files (#3312)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Fri, 26 Oct 2018 08:26:16 +0000 (13:56 +0530)]
Correcting and adding arm_compute assertions in CL core/kernel files (#3312)

This patch will add more asertions required to be tested and corrects the wrong assertions that have been added.

Signed-off-by: shubham <shub98.gupta@samsung.com>
6 years agoRevise docker_build_cross_arm_ubuntu.sh (#3348)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Fri, 26 Oct 2018 00:39:36 +0000 (09:39 +0900)]
Revise docker_build_cross_arm_ubuntu.sh (#3348)

Revise docker_build_cross_arm_ubuntu.sh
- Remove using nnfw_docker file
- Use docker-run and docker-shell command

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoIntroduce ArgMax operation. (#3288)
PRAVEEN DORESWAMY NAIDU/System SW /SRI-Bangalore/Staff Engineer/삼성전자 [Thu, 25 Oct 2018 10:51:14 +0000 (16:21 +0530)]
Introduce ArgMax operation. (#3288)

This patch will introduce the ArgMax operation in NNFW.

Signed-off-by: Praveen D N <praveen.dn@samsung.com>
6 years ago[neurun] Fix Shape4D in LowerInfo order (#3339)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 25 Oct 2018 10:46:32 +0000 (19:46 +0900)]
[neurun] Fix Shape4D in LowerInfo order (#3339)

Fix Shape4D order bug (NHWC)

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
6 years agoFix padding bug of EmbeddingLookup (#3184)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 25 Oct 2018 10:42:59 +0000 (19:42 +0900)]
Fix padding bug of EmbeddingLookup (#3184)

This commit fixes padding bug of EmbeddingLookup.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years agoSupport HashtableLookup greater than 2 dimensions (#3210)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Thu, 25 Oct 2018 09:43:05 +0000 (18:43 +0900)]
Support HashtableLookup greater than 2 dimensions (#3210)

This commit supports HashtableLookup greater than 2 dimensions.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
6 years agoFix docker-shell command bug (#3336)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 25 Oct 2018 08:22:16 +0000 (17:22 +0900)]
Fix docker-shell command bug (#3336)

Need docker option -it for interactive

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>