13 Commits (fb578fdecd18a183ae2914a2990fe7f674501f4e)
| Author | SHA1 | Message | Date |
|---|---|---|---|
raver119
|
320924278d
|
Legacy API changes (#441)
* initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * another initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * another initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * one more initial commit Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next step Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Refactored buffer() and shapeInfo() methods usage with NDArray class. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt Graph class methods to use const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt choose op to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt where op shape method to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt lstsq op to use constant empty shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt matrix_diag_part op shape routine to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt determinant ops to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt mean_pairwssqerr_loss ops to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt shape methods for loss ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt log_loss op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt shape methods for ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt dilation2d ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted deconv2d ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted dynamicRNN op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods for ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods for lstm layer ops. Signed-off-by: shugeo <sgazeos@gmail.com> * few updates Signed-off-by: raver119@gmail.com <raver119@gmail.com> * first cuda tweak Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Adopt constant shapes for sconv2d ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt constant shapes for gru ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt constant shapes with shape methods for segment ops and so on. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted constant shapes with unsorted_segment_* ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted constant shapes with gamma op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods of reduce_stddev ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape methods for reduce_* ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt shape method for squeeze op. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt strided_slice shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored concat op shape method to adopt constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted shape method for mirror_pad op. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted split op shape method. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted tile ops shape methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Added const cast for mkldnn routines handles. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored logSoftMaxForVector_ routine to conform with proper data and shape pointer casts. Signed-off-by: shugeo <sgazeos@gmail.com> * Cosmetic changes to proper usage of constant pointers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored a couple shape comparators for strides and addBias helpers to proper use data pointers with inplace option. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored depthToSpace helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored histogram helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored im2col helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored gather and gatherND helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage on percentile helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed gather shape with helpers and range buffer usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with space to depth helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage and constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with LUP decomposition> Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored onehot_ helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pad and prefix to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactoed softmax helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed space to batch helpers to use buffers properly. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed stack and split helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with sparse to dense helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with mindistance_ helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with tile helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed constant shape usage with legacy pairwise bool ops. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored a couple of methods to adopt constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed broadcasting with constant shape." Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const usage with inplace reverse and constant shapes with legacy reduction. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored legacy ops with const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored sort to adopt constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected sort for constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed constant shape usage with special methods. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored Context to conform with constant shape usage. Signed-off-by: shugeo <sgazeos@gmail.com> * CUDA broadcasting headers Signed-off-by: raver119@gmail.com <raver119@gmail.com> * pairwise/indexreduce/random headers Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Refactored native ops to adopt constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * legacy reduce3/scalar headers Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Corrected pullRow signature and tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected routines to proper use of constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored tests to use constant shapes properly. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored legacy ops tests to use constant shapes properly. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored buffer usage with NDArray tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed native ops tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed special concat routine. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with test. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed buffer usage with a test. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored TAD.h and tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored calcStrides* routines to use constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed miscelaneous errors with constant shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * NativeOps const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Corrected definitions for declared functions. Signed-off-by: shugeo <sgazeos@gmail.com> * NativeOps const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * few more const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed const shapes with shape routines. Signed-off-by: shugeo <sgazeos@gmail.com> * few more const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed shape method for broadcastable case. Signed-off-by: shugeo <sgazeos@gmail.com> * few more const changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * xw_plus_b BP shape fn restored Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed signatures with broadcasting. Signed-off-by: shugeo <sgazeos@gmail.com> * Repaired backprops shape methods for a set of operations. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored broadcast bool for cuda. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored methods for 3 args with const qualifier. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed a couple of kernel signatures for broadcasting. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernels signatures for const buffers and shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pairwise methods to persistent buffers and shapes usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt const to buffers and shapes with kernels. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopt const to buffers and shapes with scalar kernels. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored indexreduce kernels signatures to use const buffers and shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pairwise kernels to adopt cons shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored pairwise bool kernels to adopt cons shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored random special ops to conform with const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored native ops to conform with const shapes and buffers under cuda platform. Signed-off-by: shugeo <sgazeos@gmail.com> * Cosmetical changes only. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shapes and buffers error. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected start pos routine. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored methods to conform with const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored helpers to use proper methods instead. Signed-off-by: shugeo <sgazeos@gmail.com> * bunch of changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next bunch of changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * next bunch of changes Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Fixed execScalar declaration. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed execScalar declaration. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected const shape cases with sort and so on. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shapes for sort. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored kernel declarations to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernels declarations to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected kernel declarations to adopt const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernels declarations to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed segment helpers kernels declarations and so on to adopt const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shape usage with segment and solve helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed kernel declaration with adjustWeight helper. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed cuda implementations for constant shape helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted const shape usage with kernels. Signed-off-by: shugeo <sgazeos@gmail.com> * Adopted top_k kernels to use const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Corrected kernels declarations to adopt const shapes with helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored NDArray definitions to adopt const shapes and buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shapes with image suppression helpers. Signed-off-by: shugeo <sgazeos@gmail.com> * Slight improvement with buffers. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored buffer usage. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored buffer usage with tests. Signed-off-by: shugeo <sgazeos@gmail.com> * Fixed const shape usage with definitions. Signed-off-by: shugeo <sgazeos@gmail.com> * minor updates on cpu side Signed-off-by: raver119@gmail.com <raver119@gmail.com> * Refactored const shape usage with ConstantDescritor and native ops with cuda platform. Signed-off-by: shugeo <sgazeos@gmail.com> * Refactored tear and tile kernels to adopt with const shapes. Signed-off-by: shugeo <sgazeos@gmail.com> * softmax_loop fix Signed-off-by: raver119 <raver119@gmail.com> * update missing signature Signed-off-by: raver119@gmail.com <raver119@gmail.com> * softmax again Signed-off-by: raver119@gmail.com <raver119@gmail.com> * few more missing consts Signed-off-by: raver119 <raver119@gmail.com> * new methods updated Signed-off-by: raver119@gmail.com <raver119@gmail.com> Co-authored-by: shugeo <sgazeos@gmail.com> |
|
Oleh
|
c3223dbc7a
|
Improve ResultSet usage in libnd4j (#281)
* libnd4j profiling DeclarableOp and Tests by replacing return ResultSet pointer by instance Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j profiling semantic change in tests cases Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j some corrections to make new ResultSet semantic works, fixed one test Signed-off-by: Oleg <oleg.semeniv@gmail.com> * libnd4j more tests fixes Signed-off-by: Oleg <oleg.semeniv@gmail.com> * - correct copy and move assignment operators of ResultSet class Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com> |
|
|
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> |
|
|
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> |
|
|
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> |
|
|
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> |
|
Yurii Shyrma
|
5d9b2a16e5 |
Shyrma temp (#131)
* - specifying template instantiation for certain types in float16 and bloat16 Signed-off-by: Yurii <iuriish@yahoo.com> * - polishing bfloat16 and float16 member functions template specialization Signed-off-by: Yurii <iuriish@yahoo.com> * - rewrite and overload array +-*/ scalar and scalar +-*/ arr in NDAray class Signed-off-by: Yurii <iuriish@yahoo.com> * - make corrections which have to do with and rvalue lvalue conversions Signed-off-by: Yurii <iuriish@yahoo.com> * - provide move semantic in NDArray operators array +-/* array Signed-off-by: Yurii <iuriish@yahoo.com> * float16/bfloat16 tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more tweak Signed-off-by: raver119 <raver119@gmail.com> * - make float16 and bfloat16 to compile successfully on cuda Signed-off-by: Yurii <iuriish@yahoo.com> * - do not use resources of view-like arrays when move semantics is applied Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of pointers in signatures NDArray methods 1 Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of signature of NDArray::dup method Signed-off-by: Yurii <iuriish@yahoo.com> * - correction of signature of NDArray::reduceAlongDimension method Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyIndexReduce and applyTrueBroadcast methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyReduce3 and varianceAlongDimension methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::tensorsAlongDimension and diagonal methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::allTensorsAlongDimension Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::reduceAlongDimension 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyTransform 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyPairwiseTransform 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyBroadcast 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyTrueBroadcast 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::applyScalar and applyScalarArr Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::lambda methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::reduce3 methods 2 Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of following NDArray methods: add/sub/mul/div row/column and fillAsTriangular Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::tileToShape methods Signed-off-by: Yurii <iuriish@yahoo.com> * - signature correction of NDArray::isShapeSameStrict method Signed-off-by: Yurii <iuriish@yahoo.com> * minor corrections in tests Signed-off-by: Yurii <iuriish@yahoo.com> * - replace reduce op in batchnorm mkldnn Signed-off-by: Yurii <iuriish@yahoo.com> * - add explicit templates instantiations for operator+(NDArray&&. const scalar) Signed-off-by: Yurii <iuriish@yahoo.com> * - corrections of casts in float16/bfloat16 Signed-off-by: Yurii <iuriish@yahoo.com> * - provide move semantics in following NDArray methods: transform, applyTrueBroadcast, transpose, reshape, permute Signed-off-by: Yurii <iuriish@yahoo.com> * - get rid of input array A duplicate in svd cuda op Signed-off-by: Yurii <iuriish@yahoo.com> * - avoid available bug in svd cuda API Signed-off-by: Yurii <iuriish@yahoo.com> * - add temporary global memory buffer in svd cuda when calcUV = false and m != n Signed-off-by: Yurii <iuriish@yahoo.com> * - remove test with blfoat16 type for betainC Signed-off-by: Yurii <iuriish@yahoo.com> * - resolve conflicts after master has been merged in Signed-off-by: Yurii <iuriish@yahoo.com> * - changed type of affected input array in fused_batch_norm Signed-off-by: Yurii <iuriish@yahoo.com> * - add several explicit type castings Signed-off-by: Yurii <iuriish@yahoo.com> * - add ND4J_EXPORT to operators Signed-off-by: Yurii <iuriish@yahoo.com> * - add explicit template types in instantiations of template arithm operators of NDArray class Signed-off-by: Yurii <iuriish@yahoo.com> * - one more test fix Signed-off-by: Yurii <iuriish@yahoo.com> Co-authored-by: raver119 <raver119@gmail.com> |
|
|
raver119
|
ee5d25caa9 |
cuda broadcast exec fix
Signed-off-by: raver119 <raver119@gmail.com> |
|
|
raver119
|
ae7933a428 |
cpu truebroadcast fix
Signed-off-by: raver119 <raver119@gmail.com> |
|
|
raver119
|
25b3cd9b80
|
[WIP] CUDA tests (#95)
* one more CI test Signed-off-by: raver119 <raver119@gmail.com> * export additional symbols Signed-off-by: raver119 <raver119@gmail.com> * few more tweaks Signed-off-by: raver119 <raver119@gmail.com> * one more tweak for linux Signed-off-by: raver119 <raver119@gmail.com> * fix dtype in few tests Signed-off-by: raver119 <raver119@gmail.com> * missing sync and memset in couple of tests Signed-off-by: raver119 <raver119@gmail.com> * copy step for libnd4j cuda Signed-off-by: raver119 <raver119@gmail.com> * no-op on empty for adjust hue/contrast/saturation Signed-off-by: raver119 <raver119@gmail.com> * CUDA_VERBOSE Off Signed-off-by: raver119 <raver119@gmail.com> * BroadcastBool fix + few tests Signed-off-by: raver119 <raver119@gmail.com> * trigger jenkins Signed-off-by: raver119 <raver119@gmail.com> * trigger jenkins Signed-off-by: raver119 <raver119@gmail.com> * - ignore couple of warnings - remove redundant compiler options Signed-off-by: raver119 <raver119@gmail.com> |
|
|
raver119
|
6de00bf75f
|
[WIP] Weekly update of repo (#8390)
* [WIP] Fix compilation after nd4j changes (#37) * Fix compilation. * Some tests fixed * Disable tests temporarily. * Restored test * Tests restored. * Test restored. * [WIP] perf tests (#40) * special maxpool test Signed-off-by: raver119 <raver119@gmail.com> * special maxpool test Signed-off-by: raver119 <raver119@gmail.com> * Shyrma bnorm bp (#41) Batchnorm backprop mkldnn * Add SameDiff memory reuse memory manager (array cache) (#39) * Attention op comments Signed-off-by: AlexDBlack <blacka101@gmail.com> * ArrayCacheMemoryMgr - first pass Signed-off-by: AlexDBlack <blacka101@gmail.com> * Tweak array cache for use with SameDiff identity arrays Signed-off-by: AlexDBlack <blacka101@gmail.com> * ArrayCacheMemoryMgr javadoc and properly get max memory Signed-off-by: AlexDBlack <blacka101@gmail.com> * LRU cache policy + add tests Signed-off-by: AlexDBlack <blacka101@gmail.com> * Fixes Signed-off-by: AlexDBlack <blacka101@gmail.com> * Resize arrays internally if required for ArrayCacheMemoryMgr Signed-off-by: AlexDBlack <blacka101@gmail.com> * Test improvement Signed-off-by: AlexDBlack <blacka101@gmail.com> * Small polish Signed-off-by: AlexDBlack <blacka101@gmail.com> * SameDiff op runtime benchmarking listener (#42) Signed-off-by: AlexDBlack <blacka101@gmail.com> * INLINE_LOOPS for windows Signed-off-by: raver119 <raver119@gmail.com> * [WIP] ThreadPool (#8) This PR removes OpenMP use in 95% of cases |
|
Alex Black
|
68ea5f3688
|
Dev branch merge: dev_20190606 (#7904)
* correct logsoftmax looss (#2) * Small SameDiff listener fix (#4) * Various fixes (#6) * #7839 Fix for asXMatrix and tests * #7866 EmbeddingSequenceLayer dtype fix + test * #7856 SameDiff save/load stream methods * #7859 RegressionEvaluation rank 4 fix + tests + axis configuration * EvaluationBinary 3d/4d * More evaluation 3d/4d tests * #7847 Evaluation empty checks * Small test ifx * #7848 Fix median edge case * Improve DL4J samediff layer tests * [WIP] FastText wrapper implemented (#8) * FastText implemented * Some fixes * Fix shapes for wordsNearest * Validation of input vectors * Fixes * Fixed test * Thread tagged * Some tweaks * setContextClassLoader for DeallocatorServiceThread * Numpy format tests (#1) * Various fixes (#11) * #7852 SameDiff gather fix * #7892 SameDiff placeholder to constant conversion * #7890 validate input rank for MLN/CG init methods * Fix broken permute shape calculation * Permute and gather fixes * Tests * #7850 LogSumExp fix + test * Handful of test fixes * Empty arrays with non-scalar shapes (#10) * minor rearrangements for lambdas * empty tensors with non-scalar shapes * numpy empty tensors with non-scalar shapes * few more empty tweaks * Small fixes * conv3d signature update * micro fix in batchnorm mkldnn * Import fixes * Fix * MKL-DNN update * Small fill fix * fill with empty input + test * Fixes * Small error improvement * Fix * one special test * couple of fixes for lstm * Rewrite TFGraphMapper.getNDArrayFromTensor to be maintainable and less error prone * Fixes * FP16 * Unsigned * BFloat16 * Fill op - empty tweaks * - couple of fixes for empty arrays construction - stack updated * strided slice fix * one transform test * provide method for reducing shapeInfo in case of input array is empty * Fixed reduceAlongDimensions to use empty input properly. * couple of broadcast tests * couple of tests broadcast tests + tweak to make them pass * add check of non-empty to methods producing sub-arrays * Fixed reshapeC with zeros in shape. * complete empty check in reduce_... legacy ops * Concat and cumsum/prod * Tweak to empty shape inference on import * add empty check to the rest of reduce legacy ops * one more test * correct typo in evalReduceShapeInfoEmpty * Added tests for reduce_* ops to tests with zero shapes. * few more tests for empty reductions * Fixed strided_slice op with empty case and tests. * one more empty reduction test * Fixed strided_slice test. * add empty check to NDArray::reshapei * infOrMax * empty min/max with infinity tests * made unstack working correctly with empty arrays * few IndexReduce tests + tweaks for empty shapes * add test for empty concat * few tests fixed * Validation fix for reductions on empty shapes * Reverse fix * Reduction shape calc fixes * SameDiff.generateOutputVariable: don't use shape function to determine number of outputs * Range fix * - NDArray constructor updated for scalars/empty arrays - few tests fixed * More fixes * Empty creator fixes * concat fix * concat fix * TF import tests: allow 'both all NaN' and 'both all inf' to pass * Slice, zero fraction, and reshape fixes * transpose, gather * Zero fraction * scalar cast fix * Empty reduction axis support * few more tests fixed * Fixed input checks conforming with TF for concat op and tests. * few tests fixed * matmul scalar shape fix * Fixed checkout for data type and scalarity with concat to allow non-empty scalars with vector concats. * broadcast bool fix * few more tests * few more tests * correct evalReduceShapeInfoEmpty * argmax/argmin + tests * one more empty edge case + one more test * argmax/argmin/realdiv_bp tweaks * empty reshape test + fix * Helper fixes * Small fixes * Gather test fix * Gather test fix * Small fixes * reduce scalar zero values * scalar mean workaround * Remove debug code * along dim mean workaround * one more test * - equalsTo() tweak for empty arrays - one more test * broadcast tweaks |
|
skymindops
|
b5f0ec072f | Eclipse Migration Initial Commit |