platform/core/ml/nnfw.git
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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

5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 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>
5 years agoRemove unused headers and functions (#3316)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 25 Oct 2018 07:33:37 +0000 (13:03 +0530)]
Remove unused headers and functions (#3316)

This patch will remove all unused headers and functions from following files:
CLActivationLayerExKernel.cpp
CLBatchToSpaceNDKernel.cpp
CLDepthToSpaceKernel.cpp
CLEqualKernel.cpp
CLGatherKernel.cpp
CLNegKernel.cpp
CLPixelWiseDivisionKernel.cpp
CLReduceMaxKernel.cpp
CLReduceSumKernel.cpp
CLReductionMeanKernel.cpp
CLSpaceToDepthKernel.cpp
CLSquaredDifferenceKernel.cpp
CLStridedSliceKernel.cpp

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoCheck invalid format-checker exit (#3327)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 25 Oct 2018 07:18:43 +0000 (16:18 +0900)]
Check invalid format-checker exit (#3327)

Check invalid format-checker exit and return fail

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoUpdate docker-shell and configuration (#3324)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 25 Oct 2018 04:27:07 +0000 (13:27 +0900)]
Update docker-shell and configuration (#3324)

* Update docker-shell and configuration

Update docker-shell

- Use docker.configuration

Update docker.configuration

- Change default docker image name
- Fix tab to space
- Fix setting DOCKER_VOLUMES variable
- Enable using environment file

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
* Update environment variable setting

Remove unused environment setting and add download server setting

5 years agoSetting missing quantization info (#3330)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 25 Oct 2018 04:25:44 +0000 (09:55 +0530)]
Setting missing quantization info (#3330)

This patch will pass scale and offset so as to set quantization info.
If required, this quantization info can be used by the operations

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoRemove unused shape variables from L2Pool (#3329)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 25 Oct 2018 00:46:21 +0000 (06:16 +0530)]
Remove unused shape variables from L2Pool (#3329)

This patch will remove the unused shape variable from L2Pool.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdd Generated Test for Testing broadcast DIV (#3296)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Thu, 25 Oct 2018 00:40:38 +0000 (06:10 +0530)]
Add Generated Test for Testing broadcast DIV (#3296)

This patch adds a generated test for testing broadcast DIV.
This consist of testing broadcast div with tensors of shape 4D & 2D.
Added GTest : div_broadcast_float_4D_2D_nnfw

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoFix python syntax error (#3326)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Thu, 25 Oct 2018 00:09:52 +0000 (09:09 +0900)]
Fix python syntax error (#3326)

Fix python syntax error in select_operator.py

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoChange misleading FATAL error message from nnapi_delegate (#3307)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 22:19:57 +0000 (03:49 +0530)]
Change misleading FATAL error message from nnapi_delegate (#3307)

This patch changes misleading FATAL error message from nnapi_delegate for ```BatchToSpaceND```

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoRemove unused build script (#3323)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Wed, 24 Oct 2018 11:09:21 +0000 (20:09 +0900)]
Remove unused build script (#3323)

Remove unused two build script
- docker_build_cross_arm_neurun.sh (can build neurun using env file)
- docker_build_cross_arm_ubuntu_without_aclbuild.sh

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoRemove passing pad gtest from skiplist (#3320)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 11:05:04 +0000 (16:35 +0530)]
Remove passing pad gtest from skiplist (#3320)

This patch will remove pad gtest from skiplist

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoUpdate `run_benchmark_op.sh` to enable neon properly (#3318)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 24 Oct 2018 11:03:30 +0000 (20:03 +0900)]
Update `run_benchmark_op.sh` to enable neon properly (#3318)

Related Issue: #3262

`run_benchmark_op.sh` was written in the era of legacy runtime.
Currently we uses pure acl runtime as default.
Thus, I updated the way of enabling neon, and the labels.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoUpdate assertions for BatchToSpaceND op in compile time. (#3286)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 11:03:02 +0000 (16:33 +0530)]
Update assertions for BatchToSpaceND op in compile time. (#3286)

This patch updates the assertions required for BatchToSpaceND at compile time in PACL.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoRemoving unused cstdint header from the runtime/CL/functions/CL* (#3311)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 09:51:14 +0000 (15:21 +0530)]
Removing unused cstdint header from the runtime/CL/functions/CL* (#3311)

This patch will remove cstdint header from runtime/CL/functions/CL* since it is not getting used.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdding function call to validate_arg in CLGatherKernel.cpp (#3314)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 09:10:50 +0000 (14:40 +0530)]
Adding function call to validate_arg in CLGatherKernel.cpp (#3314)

This patch will add function call to validate_arg which was defined but was not getting used.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoUtility function to get ACL_PermutationVector from Runtime_PV (#3128)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 08:31:10 +0000 (14:01 +0530)]
Utility function to get ACL_PermutationVector from Runtime_PV (#3128)

For issue #3022
This commit adds a function that converts the Permutation vector of the runtime into the Permutation Vector of ACL

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdd CL Kernel Calls for SpaceToDepth from runtime. (#3267)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 07:25:48 +0000 (12:55 +0530)]
Add CL Kernel Calls for SpaceToDepth from runtime. (#3267)

This patch adds CL Kernel Calls for SpaceToDepth from runtime

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoRemoving TODO comment for reshape (#3309)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 04:21:27 +0000 (09:51 +0530)]
Removing TODO comment for reshape (#3309)

This patch will remove TODO assert comment of reshape since that TODO is already implemented.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoFix typos in Shape.h's comment (#3317)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Wed, 24 Oct 2018 04:21:01 +0000 (13:21 +0900)]
Fix typos in Shape.h's comment (#3317)

I've found a lot of typos in Shape.h during reading code for SMP documentation.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoRemoving typo in comment for Squaredifference (#3310)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 01:34:33 +0000 (07:04 +0530)]
Removing typo in comment for Squaredifference (#3310)

This patch will remove the typing error for comment related to #define in SquareDifference op

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoRemove Passing gtest of max_pool and avg_pool from skiplist (#3302)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 01:21:50 +0000 (06:51 +0530)]
Remove Passing gtest of max_pool and avg_pool from skiplist (#3302)

This patch will remove passing gtest of max and avg pool from skiplist

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years ago[tfltool] Op selector for LRN (#3284)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 01:08:34 +0000 (06:38 +0530)]
[tfltool] Op selector for LRN (#3284)

This patch will provide support to select LRN op in select_operator.py

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoAdd if defined block and remove ambiguous comments from BatchToSpaceND CL kernel...
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Wed, 24 Oct 2018 01:08:13 +0000 (06:38 +0530)]
Add if defined block and remove ambiguous comments from BatchToSpaceND CL kernel (#3294)

This patch adds if defined block and removes ambiguous comment from BatchToSpaceND CL Kernel.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoAdding assertions block for SpaceToBatch layer (#3269)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 23 Oct 2018 13:21:42 +0000 (18:51 +0530)]
Adding assertions block for SpaceToBatch layer (#3269)

This patch will add assertions for SpaceToBatch layer in visit function to handle exceptions

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years ago[neurun] Add default generate method (#3293)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 23 Oct 2018 09:37:28 +0000 (18:37 +0900)]
[neurun] Add default generate method (#3293)

Add default generate method for all IInitalizerGenerator. It returns
an empty list - i.e. no-op. Also this makes `Planner::visit` methods
call the initializer generation so all of them are identical. Later,
Planner implementation will be unified.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years agoAdd GTests for Equal_Ex (#3030)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 23 Oct 2018 09:35:16 +0000 (15:05 +0530)]
Add GTests for Equal_Ex (#3030)

equal_ex_1D_float.mod.py for 1D Tensor Inputs.
    equal_ex_4D_float.mod.py for 4D Tensor Inputs.
    equal_ex_quant.mod.py for QUANT8 Inputs.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoFix build command script (#3299)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Tue, 23 Oct 2018 08:32:49 +0000 (17:32 +0900)]
Fix build command script (#3299)

Fix build command script
- configure: Add home, binary home option
- build-acl: Fix to build-acl before configure

By this, we can build
"[env-set] ./run build-acl & [env-set] ./run configure & ./run build & ./run install"

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoIntroduce ArgMax_EX in NeuralNetworkEx (#3207)
PRAVEEN DORESWAMY NAIDU/System SW /SRI-Bangalore/Staff Engineer/삼성전자 [Tue, 23 Oct 2018 07:48:20 +0000 (13:18 +0530)]
Introduce ArgMax_EX in NeuralNetworkEx (#3207)

Introducing ArgMax operation in NeuralNetworkEx.

Signed-off-by: Praveen D N <praveen.dn@samsung.com>
5 years ago[neurun] Rename OperandConstraint generators (#3291)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 23 Oct 2018 03:03:43 +0000 (12:03 +0900)]
[neurun] Rename OperandConstraint generators (#3291)

This commit renames OperandConstraint static generator methods to be
natural.

Resolve #3239

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[neurun] Add missed license to newly added files (#3290)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 23 Oct 2018 01:39:30 +0000 (10:39 +0900)]
[neurun] Add missed license to newly added files (#3290)

This commit adds missed license to newly added files.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoAdd restrictions and comments for several operations applying reducing (#3280)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Tue, 23 Oct 2018 00:51:37 +0000 (09:51 +0900)]
Add restrictions and comments for several operations applying reducing (#3280)

This commit adds restrictions and comments for several operations applying reducing.

- Restrictions
  In case of that input rank is 4 and output rank is not 4, supports reducing height and width or reducing depth.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>
5 years agoPAD op in PACL as CPU Fallback (#2857)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Tue, 23 Oct 2018 00:09:55 +0000 (05:39 +0530)]
PAD op in PACL as CPU Fallback (#2857)

This patch will add PAD op in PACL as CPU version

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoSupport scalar type for operand rank larger than 0 (#3281)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 22 Oct 2018 09:16:19 +0000 (18:16 +0900)]
Support scalar type for operand rank larger than 0 (#3281)

Support scalar type for operand rank larger than 0
Operand rank can be changed to 1 ~ 4 for broadcast operation

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoRemove conflict helper comments in FeatureLoggingLayer.h (#3282)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 22 Oct 2018 08:12:48 +0000 (17:12 +0900)]
Remove conflict helper comments in FeatureLoggingLayer.h (#3282)

This commit removes conflict helper comments in `FeatureLoggingLayer.h`

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoAdd missed comment in asARMComputeCoordinates function (#3268)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 22 Oct 2018 06:34:01 +0000 (12:04 +0530)]
Add missed comment in asARMComputeCoordinates function (#3268)

This patch will add missed comments for asARMComputeCoordinates function in Cast.h

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years ago[neurun] Change bg color managing and colors in DotDumper (#3257)
김수진/동작제어Lab(SR)/Engineer/삼성전자 [Mon, 22 Oct 2018 06:32:14 +0000 (15:32 +0900)]
[neurun] Change bg color managing and colors in DotDumper (#3257)

close : #3241

This commit changes bg color managing and color scheme in DotDumper.

Signed-off-by: sjsujinkim <sjsujin.kim@samsung.com>
5 years agoAdd missing Apache License to PACK op. (#3277)
Prasanna R/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 22 Oct 2018 05:49:41 +0000 (11:19 +0530)]
Add missing Apache License to PACK op. (#3277)

This patch adds apache license to PACK op.

Signed-off-by: prasannar <prasanna.r@samsung.com>
5 years agoPatch to remove unused shape variables (#3271)
Shubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 [Mon, 22 Oct 2018 04:53:27 +0000 (10:23 +0530)]
Patch to remove unused shape variables (#3271)

This patch will remove unused shape variables.

Signed-off-by: shubham <shub98.gupta@samsung.com>
5 years agoCheck url for external source download (#3275)
오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 [Mon, 22 Oct 2018 02:50:51 +0000 (11:50 +0900)]
Check url for external source download (#3275)

Check url for external source download
If download url is not matched, download again

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
5 years agoFix line-break automatically in format-checker.sh (#3256)
이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 [Mon, 22 Oct 2018 01:12:22 +0000 (10:12 +0900)]
Fix line-break automatically in format-checker.sh (#3256)

- CRLF, CR style line break are fixed automatically.
 : Diff can be found in format.patch

- Missed double-quote is added.
It caused the output string printed in one line without "\n".

- Removed `function` keyword that remained.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
5 years agoRemove modelgen tool (#3263)
이한종/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 19 Oct 2018 08:47:38 +0000 (17:47 +0900)]
Remove modelgen tool (#3263)

Remove modelgen tool since it can be done with tflchef from nncc.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
5 years ago[Coverage] Remove codes for CPU from CLStridedSlice (#3238)
장지섭/동작제어Lab(SR)/Engineer/삼성전자 [Fri, 19 Oct 2018 07:21:28 +0000 (16:21 +0900)]
[Coverage] Remove codes for CPU from CLStridedSlice (#3238)

This commit Removes codes for CPU from CLStridedSlice.

Signed-off-by: jiseob.jang <jiseob.jang@samsung.com>