Commit Graph

311 Commits (63fa3c2ef3c4e5e33cdb99bb4804997b40ad4590)

Author SHA1 Message Date
raver119 63fa3c2ef3
libnd4j polishing (#273)
* initial set of include changes

Signed-off-by: raver119 <raver119@gmail.com>

* one more tweak

Signed-off-by: raver119 <raver119@gmail.com>

* few more rearrangements

Signed-off-by: raver119 <raver119@gmail.com>

* few more rearrangements

Signed-off-by: raver119 <raver119@gmail.com>

* few more rearrangements

Signed-off-by: raver119 <raver119@gmail.com>

* cuda includes rearrangements

Signed-off-by: raver119 <raver119@gmail.com>

* java update

Signed-off-by: raver119 <raver119@gmail.com>

* = namespace changed to sd
- few CMake variables renamed with SD_ prefix

Signed-off-by: raver119 <raver119@gmail.com>

* java update

Signed-off-by: raver119 <raver119@gmail.com>

* LoopKind minor fix

Signed-off-by: raver119 <raver119@gmail.com>

* few more changes

Signed-off-by: raver119 <raver119@gmail.com>

* few more changes

Signed-off-by: raver119 <raver119@gmail.com>

* few more changes

Signed-off-by: raver119 <raver119@gmail.com>

* sanitizer is optional now

Signed-off-by: raver119 <raver119@gmail.com>

* dev tests updated

Signed-off-by: raver119 <raver119@gmail.com>

* few more changes

Signed-off-by: raver119 <raver119@gmail.com>

* last update

Signed-off-by: raver119 <raver119@gmail.com>

* java update

Signed-off-by: raver119 <raver119@gmail.com>
2020-03-02 12:49:41 +03:00
Oleh f116f53d61
Loops auto-vectorization problem fix (#277)
* libnd4j cast loop types

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j more type castination added to loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j sync casting types of iterated variable in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j more loops reviewed for vectorization problem fix

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fixed several typos

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j several more files reviewed to fix auto-vectorization problem in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j merge master and reviewed more files to fix auto-vectorization problem in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j several type casting added in broadcasting that were missed, fixed mac builds

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j double check all files and fix several more places in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fixed builds

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j revert changes for lup.cpp

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j more files reviewed for auto-vectorization problem fix

Signed-off-by: Oleg <oleg.semeniv@gmail.com>
2020-02-28 17:04:45 +03:00
raver119 5332ace32b
better inplace exec with FastPath (#280)
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-28 12:06:30 +03:00
shugeo 330a69d4e2
Shugeo solve ls (#203)
* lstsq op. Initial commit.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Least squares linear problem solve op (lstsq). Cpu draft implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed shape routine and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added test for lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Rectification for lstsq op implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Corrected test to avoid numerical inconsistensy.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added prints for check computing.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Corrected tests to use evalueate facility instead.

Signed-off-by: shugeo <sgazeos@gmail.com>

* CPU implementation of MatrixSolveLs op and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added cuda implementation for helpers with lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored tests for lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added processing for empty inputs.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Merged tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored lstsq op for fast case.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed test.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed some issues with solve.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed lstsq op to avoid erros.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added kernel for giagonal factor

Signed-off-by: shugeo <sgazeos@gmail.com>

* lstsq wrapper and triangular_solve fixed

* Added proper processing empty inputs and test.

Signed-off-by: shugeo <sgazeos@gmail.com>

* SequenceMask test

* Build fixed

* Added proper processing of empty inputs with solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Mapping added

* Added check of input shapes with solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added a couple of tests for lstsq op and minor changes with cuda helper for one.'

Signed-off-by: shugeo <sgazeos@gmail.com>

* Tests on

* Refactored test for lstsq op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed test

* Added another approach for lstsq op aka solve_ls.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Finished cpu part for solve_ls op helpers.

* Added helper for low triangular matrix inversion.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored alternate solve_ls cpu implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Removed alternate approach for solve_ls op. Added multithreading with matrix inversion.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Assert fixed

* Refactored multithreading for inverse matricies.

Signed-off-by: shugeo <sgazeos@gmail.com>

Co-authored-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
2020-02-28 11:37:26 +03:00
raver119 358c650b62 one micro fix
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-27 19:28:26 +03:00
raver119 31e3a2f7a5
transparent conversion to FastPath execution within Graph (#278)
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-27 16:10:38 +03:00
Oleh b4575d11e9
Loops auto-vectorization problem fix (#274)
* libnd4j cast loop types

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j more type castination added to loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j sync casting types of iterated variable in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j more loops reviewed for vectorization problem fix

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fixed several typos

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j several more files reviewed to fix auto-vectorization problem in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j merge master and reviewed more files to fix auto-vectorization problem in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j several type casting added in broadcasting that were missed, fixed mac builds

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j double check all files and fix several more places in loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fixed builds

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j revert changes for lup.cpp

Signed-off-by: Oleg <oleg.semeniv@gmail.com>
2020-02-26 21:12:19 +03:00
raver119 5c806d2fb5
reshape tweak (#275)
* - expand dims tweak
- reshape memcpy

Signed-off-by: raver119 <raver119@gmail.com>

* validation fix

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-26 14:05:32 +03:00
Oleh b686368b82
Refactoring split operation (#266)
* libnd4j moved split operation implementation to helpers before special case adding

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j minor fixes for general split operation move, merge master

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libndj4 split cpu implementation

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* - provide cuda helper for split op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - minor correction

Signed-off-by: Yurii <iuriish@yahoo.com>

* - minor correction 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* libnd4j moved split implementation from specials to split.cpp

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j update loopkind selections for 3D, 4D and 5D cases

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j removed unnecessary BUILD_SINGLE_TEMPLATE

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-02-26 10:20:39 +03:00
raver119 cf67c7165a nano fix
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-25 15:20:51 +03:00
raver119 f6442b6724
few minor tweaks (#272)
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-25 11:13:23 +03:00
raver119 241ed05c64
VariableSpace uses unordered maps as well (#270)
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-24 21:58:23 +03:00
Oleh f0706b21aa
Split operation improvement (#262)
* libnd4j moved split operation implementation to helpers before special case adding

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j minor fixes for general split operation move, merge master

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libndj4 split cpu implementation

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* - provide cuda helper for split op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - minor correction

Signed-off-by: Yurii <iuriish@yahoo.com>

* - minor correction 2

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
Co-authored-by: raver119 <raver119@gmail.com>
2020-02-24 08:22:41 +03:00
shugeo 1bb3ae4b03
Shugeo unordered map (#256)
* Refactored usage of std::map to std::unordered_map instead.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Eliminated crash with wrong ShapeDescriptor hash.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Eliminated crash with TadDescriptor hash.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored Stash hash.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored hashes.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored TadDescriptor hash and top_k mapping.

* Refactored hashes for ShapeDescriptor and TadDescriptor classes.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored hash for ConstantDescriptor and ShapeDescriptor classes.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed map using with cuda platform.

Signed-off-by: shugeo <sgazeos@gmail.com>

* - few rearrangements for hash functions
- shared openblas allowed

Signed-off-by: raver119 <raver119@gmail.com>

* exports

Signed-off-by: raver119 <raver119@gmail.com>

* exports

Signed-off-by: raver119 <raver119@gmail.com>

* Stash reverted to std::map

Signed-off-by: raver119@gmail.com <raver119@gmail.com>

* Added additional test.

Signed-off-by: shugeo <sgazeos@gmail.com>

* different maps for different compilers

Signed-off-by: raver119 <raver119@gmail.com>

* missing include

Signed-off-by: raver119 <raver119@gmail.com>

* fix the leak

Signed-off-by: raver119 <raver119@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-02-24 07:51:01 +03:00
raver119 e78be14cc1
arm fix (#260)
* range check for scalar_int

Signed-off-by: raver119 <raver119@gmail.com>

* no simd

Signed-off-by: raver119 <raver119@gmail.com>

* no ops

Signed-off-by: raver119 <raver119@gmail.com>

* cyclic shift?

Signed-off-by: raver119 <raver119@gmail.com>

* left split

Signed-off-by: raver119 <raver119@gmail.com>

* left split

Signed-off-by: raver119 <raver119@gmail.com>

* rot ops unrolled templates

Signed-off-by: raver119 <raver119@gmail.com>

* no rotl/rotr for uint64

Signed-off-by: raver119 <raver119@gmail.com>

* no rotl/rotr for uint64 2

Signed-off-by: raver119 <raver119@gmail.com>

* no rotl/rotr for uint64 3

Signed-off-by: raver119 <raver119@gmail.com>

* ARM_BUILD declared

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-21 14:31:00 +03:00
Oleh 0748c7e7c2
Oleh broadcast4d (#257)
* libnd4j raw implementation of native broadcast for special cases

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fixed bugs for special case of 4D loop broadcast, add some tests, need more testing and discussion

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j added 3D and 5D cases support and tests, need testing with different orders

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j correctd case selection for broadcast 3,4,5D loops, fixed several places for more stable behavior, clean up

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j minor corrections to avoid some risks in strides selection, added tests and rename some variables

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j optimize usage the stride selection for all loops in separate ShapeUtils method copyCertainStridesFromShapeInfo, merge master

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j remove per request several tests for 3D, 4D and 5D broadcast loops

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j removed some loac changes that had not been sync with serve playground, turn on new loops usage
2020-02-21 07:46:05 +03:00
Yurii Shyrma f7a9190407
profiling of concat op (both cuda and cpu) (#151)
* - profiling of concat op (both cuda and cpu)

Signed-off-by: Yurii <iuriish@yahoo.com>

* better comparison for large concat

Signed-off-by: raver119 <raver119@gmail.com>

* - further improving of concat op

Signed-off-by: Yurii <iuriish@yahoo.com>

* some loggin

Signed-off-by: raver119 <raver119@gmail.com>

* - add possibility to verify presence of trailing unities in shape and set strides/ews correspondingly
- restrict second simple case in concat op to c order only

Signed-off-by: Yurii <iuriish@yahoo.com>

* - move concat op to specials_single.cpp file

Signed-off-by: Yurii <iuriish@yahoo.com>

* - get rid of second concat op declaration in transforms.cpp file

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-02-20 21:19:01 +03:00
raver119 215641ea9e
Minor improvements (#255)
* static increments in loops

Signed-off-by: raver119 <raver119@gmail.com>

* specials and concat split into separate units

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-20 11:43:26 +03:00
Yurii Shyrma c5193ecb81
Shyrma gather (#254)
* - profiling gather op for aurora

Signed-off-by: Yurii <iuriish@yahoo.com>

* - include contiguous memcpy in gather op

Signed-off-by: Yurii <iuriish@yahoo.com>
2020-02-19 09:35:52 +03:00
Abdelrauf 72f9cda019
Added missing bfloat16 (#252)
Signed-off-by: AbdelRauf <rauf@konduit.ai>
2020-02-18 17:01:43 +03:00
Yurii Shyrma 22c7aa9acf
Shyrma mkl matmul (#250)
* - provide matmul code based on mkl api

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct typo in mkl matmul op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - take into account empty arrays in mkl matmul op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - fix bug in mkl matmul and group all matmul tests in one file

Signed-off-by: Yurii <iuriish@yahoo.com>
2020-02-18 08:58:01 +03:00
raver119 2698fbf541
Broadcast perf improvements (#248)
* broadcast as scalar edge case

Signed-off-by: raver119 <raver119@gmail.com>

* missing return

Signed-off-by: raver119 <raver119@gmail.com>

* few fixes

Signed-off-by: raver119 <raver119@gmail.com>

* one more fix

Signed-off-by: raver119 <raver119@gmail.com>

* no need for lambdas

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-17 16:25:09 +03:00
raver119 f9d51b7278
More compilation units (#246)
* weird edge case

Signed-off-by: raver119 <raver119@gmail.com>

* weird edge case

Signed-off-by: raver119 <raver119@gmail.com>

* get rid of it

Signed-off-by: raver119 <raver119@gmail.com>

* crop and resize reorganized

Signed-off-by: raver119 <raver119@gmail.com>

* restore test

Signed-off-by: raver119 <raver119@gmail.com>

* remove unwanted unit refs in cmale

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-17 10:23:05 +03:00
Yurii Shyrma 011c272fde
Shyrma transpose (#244)
* - provide contiguous strides for ouput in transpose op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide contiguous strides for output in permute op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - take into account empty shapes properly in transpose/permute op

Signed-off-by: Yurii <iuriish@yahoo.com>
2020-02-17 08:04:28 +03:00
raver119 9e3c1b02b1
Perf improvements (#242)
* initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* meh

Signed-off-by: raver119 <raver119@gmail.com>

* better ExpandDims impl

Signed-off-by: raver119 <raver119@gmail.com>

* better Squeeze impl

Signed-off-by: raver119 <raver119@gmail.com>

* better Softmax impl

Signed-off-by: raver119 <raver119@gmail.com>

* one test disabled

Signed-off-by: raver119 <raver119@gmail.com>

* more accurate impl

Signed-off-by: raver119 <raver119@gmail.com>

* - GraphProfiler now prints full shapeInfo instead of shape
- softmax typo fix

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-14 16:20:31 +03:00
Oleh 6e6289b6b9
Oleh bert multiply true broad cast (#239)
* libnd4j trueBroadcast rank 3 row implementation of special case

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j rule clarify for second special case for all tests pass

* libnd4j parallel_tad loop switch on in special case

* libnd4j more general case for special case 2, need additional testing

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j more general case for trueBroadcast special cases added

* libnd4j minor corrections and clean up

* libnd4j one more minor fix

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fixed check point to support all Y common vector representations in first special case for trueBroadcast

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-02-14 12:04:38 +03:00
raver119 3de3cd8277
R119 tests (#238)
* one small test

Signed-off-by: raver119 <raver119@gmail.com>

* one small test

Signed-off-by: raver119 <raver119@gmail.com>

* bert test

Signed-off-by: raver119 <raver119@gmail.com>

* Graph FlowPath fix

Signed-off-by: raver119 <raver119@gmail.com>

* - GraphProfiler tweaks
- NodeProfile now includes shapes

Signed-off-by: raver119 <raver119@gmail.com>

* RELU_layer inplace tweak

Signed-off-by: raver119 <raver119@gmail.com>

* meh

Signed-off-by: raver119 <raver119@gmail.com>

* identity tweaks

Signed-off-by: raver119 <raver119@gmail.com>

* bert result validation

Signed-off-by: raver119 <raver119@gmail.com>

* - bunch of Shape ops have inplace exec forbidden now
- Legacy ops have inplace exec disabled by default now

Signed-off-by: raver119 <raver119@gmail.com>

* ffast-math enabled

Signed-off-by: raver119 <raver119@gmail.com>

* ffast-math enabled

Signed-off-by: raver119 <raver119@gmail.com>

* allow some legacy ops to be inplace

Signed-off-by: raver119 <raver119@gmail.com>

* disable -fast_math

Signed-off-by: raver119 <raver119@gmail.com>

* disable expensive test for cuda

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-13 20:59:35 +03:00
Yurii Shyrma fe47f52896
Oleh tenzor mmul (#231)
* Libnd4j: TensorMMul backprop op #8174, raw implementation

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 merge master and some corrections

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 algorithm update, need testing, sync with  master

* Libnd4j: TensorMMul backprop op #8174 fixed incorrect B axes calculation

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 optimize axes identification and fix bug of indeces overlapping, added first test. need testing with different shapes

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 some fixes and improvements need more testing

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 fixed order of matrix multiply

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 fixed issue of incorrect axes definition, add tests based on TF, need additional testing for case dLdC not equal 1

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 fixed scalar case add test

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 fixed bp algorithm, axes definition, need some mode testing with different orders combination f,c; c,f f,f and add some checks for inputs

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 some checks and corrections added tests, exists the problem with different input orders support A-f B-c and A-f B-f

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* Libnd4j: TensorMMul backprop op #8174 sync master

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* - correct bug in MmulHelper::tensorDot(a, b, c, axes_a, axes_b,permutForC)

Signed-off-by: Yurii <iuriish@yahoo.com>

* Libnd4j: TensorMMul backprop op #8174 code clean up and refactoring

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* - add check for linspase ordered permutations in ShapeUtils::evalShapeForTensorDot

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide additional code in shape::reshape stuff in order to reduce amount of allocation/copy operations during reshaping procedure

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on problem of wrong shape evaluation during permute/reshape procedures

Signed-off-by: Yurii <iuriish@yahoo.com>

* - still looking for bug reason in reshape/permute stuff

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct bug in transform cuda native ops

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct bug in NDArray::assign

Signed-off-by: Yurii <iuriish@yahoo.com>

* - remove old shape::reshape stuff

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add possibility to disable copy of old buffer to new buffer during reshape operation in NDArray class

Signed-off-by: Yurii <iuriish@yahoo.com>

* - correct bug in tensorDot which had to do with wrong pointers assigments

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: Oleh <oleg.semeniv@gmail.com>
2020-02-13 20:33:54 +03:00
shugeo f0c684020f
Shugeo resize area fix4 (#229)
* Fixed a couple of issues with resize_area op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added additional test for alternate params for resize_area testing.

Signed-off-by: shugeo <sgazeos@gmail.com>
2020-02-12 19:02:42 +03:00
Oleh 11cb561045
Oleh true broadcast opt (#234)
* libnd4j trueBroadcast special case

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j fix trueBroadcast special case

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j special case of TrueBroadcastHelper

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* libnd4j trueBroadCast special case and test

* libnd4j minor changes sync with master

* libnd4j changes to TrueBroadcastHelper.hpp per require

Signed-off-by: Oleg <oleg.semeniv@gmail.com>
2020-02-12 14:12:17 +03:00
raver119 237c137166 few more smaller compilation units (#226)
Signed-off-by: raver119 <raver119@gmail.com>
2020-02-10 10:57:18 +03:00
raver119 8a0d5e3b97
Compilation units (#224)
* - TrueBroadcastHelper split into multiple compilation units
- legacy gemm.cpp disabled

Signed-off-by: raver119 <raver119@gmail.com>

* - IndexReduce int32/int64 split into multiple compilation units

Signed-off-by: raver119 <raver119@gmail.com>

* - Reduce3 ops split into multiple compilation units

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-09 19:48:32 +03:00
Abdelrauf bead656feb
Initial performance improvement for Bias Add and etc #8556 (#217)
* Initial  performance improvement for Bias Add, loop coords helpers and increment aligned parallel threading

Signed-off-by: AbdelRauf <rauf@konduit.ai>

* One more test for Rauf

Signed-off-by: raver119 <raver119@gmail.com>

* disable couple of perf tests

Signed-off-by: raver119 <raver119@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-02-08 15:31:30 +03:00
raver119 a0da5a9e47
Events removed from Java (#219)
* replace mutex with lock_guards

Signed-off-by: raver119 <raver119@gmail.com>

* Events ditched from Java CUDA logic

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-07 12:34:55 +03:00
Yurii Shyrma 948646b32d
Shyrma mkl test (#211)
* - provide nhwc format in mkl conv ops

Signed-off-by: Yurii <iuriish@yahoo.com>

* - corrections in mkl conv3d

Signed-off-by: Yurii <iuriish@yahoo.com>

* - corrections in mkl batchnorm

Signed-off-by: Yurii <iuriish@yahoo.com>

* - corrections in mkl maxpooling2d

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add format format_tag::any to outputs in mkl conv ops

Signed-off-by: Yurii <iuriish@yahoo.com>

* - complete corrections in mkl conv ops

Signed-off-by: Yurii <iuriish@yahoo.com>

* - add test for comparison of execution speeds of mkl conv2d op with different weights format

Signed-off-by: Yurii <iuriish@yahoo.com>

* - take into account order f in mkl conv ops

Signed-off-by: Yurii <iuriish@yahoo.com>
2020-02-06 21:12:54 +03:00
shugeo 5ae40f6e38
Shugeo sequence mask fix2 (#216)
* Fixed sequence_mask op and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Cuda fix for sequence_mask op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed sequence_mask op for both platforms and tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed solve and triangular_solve for more than 2D for adjoint cases.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added adjoint solve test again.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added a set of tests for triangual_solve and generic solve ops.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added a pair tests for triangular_solve

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added tests for triangular_solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>
2020-02-06 21:06:50 +03:00
raver119 5d28e6143d
OpContext handling (#214)
* nano tweaks

Signed-off-by: raver119 <raver119@gmail.com>

* OpContext tweaks

Signed-off-by: raver119 <raver119@gmail.com>

* OpContext deallocators

Signed-off-by: raver119 <raver119@gmail.com>

* get rid of few mkldnn safety checks

Signed-off-by: raver119 <raver119@gmail.com>

* databuffer setSpecial fix

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-05 07:27:24 +03:00
shugeo 41ff907bc6
Shugeo solve linear (#191)
* linear equations systems solve op. Initial commit.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed compiling issues.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Linear equations systems solve. The next stage commit.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added test for linear equations systems solve operation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added additional test and fixed lower matrix retrievance.

* Implementation for solve of the systems of linear equations."

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored permutation generation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added restore for permutations batched with cuda helper for solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Finished cuda implementation for solve op helpers.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored cpu helpers for solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fix gtest output on Windows

* Fixed issue with permutation matrix for cuda implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed issue with permutation matrix for cpu implementation.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Eliminated waste comments.

Signed-off-by: shugeo <sgazeos@gmail.com>

* LinearSolve added

* Mapping added

* Javadoc added

* Refactored implementation of triangular_solve helpers and tests for solve matrix equations generally.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added a test for solve op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Solve test added

* Fix for TF import

Co-authored-by: Serhii Shepel <9946053+sshepel@users.noreply.github.com>
Co-authored-by: raver119 <raver119@gmail.com>
Co-authored-by: Alexander Stoyakin <alexander.stoyakin@gmail.com>
2020-02-04 08:59:11 +03:00
raver119 9bb5798cac
Null arrays fix (#208)
* don't skip null arrays

Signed-off-by: raver119 <raver119@gmail.com>

* one test tweak

Signed-off-by: raver119 <raver119@gmail.com>
2020-02-02 23:14:00 +03:00
Oleh d52e67209e
Oleh convert (#200)
* StringUtils for utf convertor raw implementation of all possible combinations, need to be add counter of bytes per symbol for any type and add api to call convertors and store data

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor more corrections to support convertors

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor some corrections and bug fixes, need review to discuss how to add multi-threading

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 some corrections to move to multi-threading, add one test need discussion data inputs/outputs array presentation, need discussion the way of multi-threading

* StringUtils for utf convertor #8613 tests added some corrections to optimize build

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 some corrections and code clean up

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 code clean up and optimize usage, need update ndarray factory before replace std usage

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 some staff to integrate converters into NDArrayFactory, update tests and add some functionality

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 minor corrections and bug fix before discussion

* StringUtils for utf convertor #8613 some fixes and tets

* StringUtils for utf convertor #8613 some more staff to support different unicode

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 fix linking bug

* StringUtils for utf convertor #8613 corrected several tests as defaults for string ndarray changed

* StringUtils for utf convertor #8613 replace some incorrect implementation, revert some test changes, need sync before testing

* StringUtils for utf convertor #8613 fixed several thing that were badly implemented yesterday, need optimization, testing (before testing have to be add support of u32 and u16 buffer visualization)

* StringUtils for utf convertor #8613 fixed to support u16 and u32, and convertor in ndarray, fix buffer print, etc

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 merge master and sync with server

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 some correction for string cast, need print check only asci support

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 merge master, remove copies and add cast, need test, refactoring according review and clean up

* StringUtils for utf convertor #8613 fixed cast and copy issues

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 fixed cuda and update tests

* StringUtils for utf convertor #8613 integration into NdArray, fix several tests for build pass, refactoring, etc

* - avoid ambiguity of NDArray ctrs overloading in some tests

Signed-off-by: Yurii <iuriish@yahoo.com>

* StringUtils for utf convertor #8613 NDArray string constructors added, updated NDArrayFactory, refactoring unicode and tests, etc

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 fixed cuda build and test, refactoring and void* added to some functions

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613  void* integration, removed copy operation, refactoring, added tests for NDArray string constructors, etc

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 several more fixes, improvements and updates

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 master merge, code clean up and optimization before review

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 minor fixes string element size define

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 revert last changes as mistake

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 fixed NDArray constructor build problem, remove order from string factory, fixed order use for factory via project, added catch of incorrect sync in cast of arrays to data types, fixed e method for strings, etc

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 added javacpp hack, added multi-threading, minor corrections in license agreement

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

* StringUtils for utf convertor #8613 windows builds fix, as "sting" is not treated as utf8

Signed-off-by: Oleg <oleg.semeniv@gmail.com>

Co-authored-by: Yurii Shyrma <iuriish@yahoo.com>
2020-01-31 16:30:49 +03:00
raver119 1ab86d1306
Range op data type (#204)
* - range op now accepts dargs
- dargs now can be in signature

Signed-off-by: raver119 <raver119@gmail.com>

* range dtype java side

Signed-off-by: raver119 <raver119@gmail.com>

* linspace fix

Signed-off-by: raver119 <raver119@gmail.com>

* lin_space fix for scalar outputs

Signed-off-by: raver119 <raver119@gmail.com>
2020-01-31 10:45:40 +03:00
Abdelrauf d39ca6d488
ElementWiseStride==1 cases for legacy random ops (#202)
Signed-off-by: AbdelRauf <rauf@konduit.ai>
2020-01-31 08:57:31 +03:00
raver119 5d98cfcf47
Configurable DataType for ops (#201)
* initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* - one more test for OneHot with dtype
- one more signature in Nd4j

Signed-off-by: raver119 <raver119@gmail.com>

* ones_as/zeros_as now accept dtype

Signed-off-by: raver119 <raver119@gmail.com>

* one more test

Signed-off-by: raver119 <raver119@gmail.com>

* - more updates for configurable data types
- ones_as/zeros_as java side + tests

Signed-off-by: raver119 <raver119@gmail.com>

* few c++ tests fixed

Signed-off-by: raver119 <raver119@gmail.com>

* few more changes around DArgs

Signed-off-by: raver119 <raver119@gmail.com>
2020-01-30 18:46:12 +03:00
raver119 ba961c7601
DataTypes & FlatBuffers (#197)
* flatbuffers version upgrade

Signed-off-by: raver119 <raver119@gmail.com>

* flatbuffers version upgrade java side

Signed-off-by: raver119 <raver119@gmail.com>

* flatbuffers dependency version upgrade java side

Signed-off-by: raver119 <raver119@gmail.com>

* MKLDNN version upgrade

Signed-off-by: raver119 <raver119@gmail.com>

* DArgs first pass

Signed-off-by: raver119 <raver119@gmail.com>

* signatures first pass

Signed-off-by: raver119 <raver119@gmail.com>

* signatures second pass

Signed-off-by: raver119 <raver119@gmail.com>

* signatures third pass

Signed-off-by: raver119 <raver119@gmail.com>

* signatures third pass

Signed-off-by: raver119 <raver119@gmail.com>

* signatures fourth pass

Signed-off-by: raver119 <raver119@gmail.com>

* signatures fifth pass

Signed-off-by: raver119 <raver119@gmail.com>

* flatbuffers UI version upgrade java side

Signed-off-by: raver119 <raver119@gmail.com>

* flatbuffers ui update

Signed-off-by: raver119 <raver119@gmail.com>

* flatbuffers downgrade

Signed-off-by: raver119 <raver119@gmail.com>

* flatbuffers downgrade java side

Signed-off-by: raver119 <raver119@gmail.com>
2020-01-30 10:07:24 +03:00
Yurii Shyrma 7a7ee4b021 Shyrma cudnn (#192)
* - implementation of cudnn batchnorm_bp op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing and fixing bugs in batchnorm_bp based on cudnn api

Signed-off-by: Yurii <iuriish@yahoo.com>

* - move pooling mkl code and delete some unnecessary files

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implementation and testing cudnn pooling2d ops (avg/max, ff/bp)

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implementation and testing cudnn pooling 3d (ff/bp) ops

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide ff step in case of cudnn maxpool3d_bp op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - remove half type from set of supported types in mkl dpethwise conv op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - bring back cudaStreamSynchronize in batchnorm and pooling cudnn ops

Signed-off-by: Yurii <iuriish@yahoo.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-01-28 18:23:07 +03:00
raver119 531a72fabd
execution mode (#183)
* initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* execution mode java side

Signed-off-by: raver119 <raver119@gmail.com>

* meh

Signed-off-by: raver119 <raver119@gmail.com>

* move exec mode to ContextPrototype

Signed-off-by: raver119 <raver119@gmail.com>

* copyrights

Signed-off-by: raver119 <raver119@gmail.com>
2020-01-27 10:00:07 +03:00
shugeo 99a54829c2 Shugeo resize area fix2 (#181)
* Added test for issue with resize_area op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Added a pair of tests for resize_are op.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Refactored resize_area kernel to avoid shared memory overflow.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Eliminated prints with tests.

Signed-off-by: shugeo <sgazeos@gmail.com>

* ignore bad test

Signed-off-by: raver119 <raver119@gmail.com>

* Fixed test with resize_area.

Signed-off-by: shugeo <sgazeos@gmail.com>

* Fixed test for float constants.

Signed-off-by: shugeo <sgazeos@gmail.com>

Co-authored-by: raver119 <raver119@gmail.com>
2020-01-24 20:55:25 +03:00
raver119 f14e4beeb5 missing countOut for GPU
Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 15:37:24 +03:00
raver119 5d69069177
[WIP] Memory limits (#167)
* initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* one more initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* additional initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* subsequent initial commit

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit testing

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit per device

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit per group

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit for cuda

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit for cuda + few missed lines

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit for cuda + missed includes

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit for cuda + one more missed include

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit shouldn't count host mem as dev0 in cuda

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit that tracks HOST group limits for CUDA

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit with some Environment changes

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit with more Environment changes

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit with maxMasterThreads fix

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit with maxMasterThreads fix

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit without maxMasterThreads exception

Signed-off-by: raver119 <raver119@gmail.com>

* initial commit without Nd4jULong in Environment

Signed-off-by: raver119 <raver119@gmail.com>

* add sleep and more iterations for OOM cases

Signed-off-by: raver119 <raver119@gmail.com>

* limits propagation from java side

Signed-off-by: raver119 <raver119@gmail.com>

* - consume ErrorCode every time
- one test for memory limits

Signed-off-by: raver119 <raver119@gmail.com>

* unordered_map

Signed-off-by: raver119 <raver119@gmail.com>

* unordered_map

Signed-off-by: raver119 <raver119@gmail.com>

* unordered_map

Signed-off-by: raver119 <raver119@gmail.com>

* RSub op mapping fixed

Signed-off-by: raver119 <raver119@gmail.com>

* typo fixed

Signed-off-by: raver119 <raver119@gmail.com>

* one bad test fixed

Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 10:11:09 +03:00
raver119 256c9d20b0
alloc check for RNG (#179)
* missing alloc validation in RandomGenerator for CUDA

Signed-off-by: raver119 <raver119@gmail.com>

* set error message if rng alloc failed

Signed-off-by: raver119 <raver119@gmail.com>

* check for error code during RNG creation in java

Signed-off-by: raver119 <raver119@gmail.com>
2020-01-23 09:51:02 +03:00