* add 4 dim softmax

* update for NHWC layout

* remove layout param from softmax

* fix typo

* minor fix to pool

support axis=1 ndims=5 softmax.

add softmax axis

* few fix for softmax

* fix typo

* add more doc

* minor doc fix

* fix upsampling output shape

* fix lint

* cleanup softmax

* minor fix

* raise exception instead of assert, handles negative axis

* check axis after axis transformation

* [PASS] Prepare storage rewrite for unified buffer

* more comments

* conv2d schedules for Intel CPU (AVX2 & AVX512)

* fix lint

* remove override register

* [PASS] Enable StorageRewrite before virtual thread lowering

* update

* fix testcase

[TOPI][GL] OpenGL topi.

* add peak test

* fix error for lanes=16

* update doc

* fix names

* fix names

* Fixed namespacing issues in schedules

* Fixed compile error

* Try fix cpp topi test

* move cpp test to another stage

* update

* Added +x permission to task_cpp_topi.sh. Added C++ topi tests to Jenkinsfile

* Fixed test_topi_math.py

* Minor style fix

* modified schedule_dataflow_rewrite.cc to fix losing tensor problem

* modified schedule_dataflow_rewrite.cc for lint scan

* modified schedule_dataflow_rewrite.cc for lint scan

* using tensor's value_index to index output of stage op

* repare address offset for different kinds of dtype

* bc

* aaa

* aaaaa

* repare address for different dtypes

* remove nonsense files

* add whitespace of line 581

* use base alloc elem_type

* enhance the testcast of basic buffer is 64bits,32bits,16bits,8bits

* use extends[0]->type() as dtype of offset

* clear program writes

* enhance inject_copy_intin to support of pragma stmt with no loops

* fix cpplint errors

* fix cpplint error of !

* enhance detectLinearEquation to support with no loop vars

* fix cpplint errors

* Fix bugs with C++ TOPI flatten and relu

* Added regression tests. Fixed typo in CMakeLists.txt. Fixed topi cpp import removed.

* Fix Vulkan Build, add tanh to llvm instrinsic, fix halideIR

* fix llvm tanh

* [TOPI] Add compute for more operators

* Remove device except llvm

* Address comments

* Remove matmul compute

* Add outtype to boolean operator

* Address coments

* TOPI C++ bugfixes

* Fix lint

* [BACKEND] Vulkan Runtime and SPIRV Codegen

* fix doc

* Update HalideIR commit to include TVM_STATIC_IR_FUNCTOR_REGISTER

* Fix HalideIR to point to the right commit

* Add missing using to C++ TOPI nn.h

* Update HalideIR to include compiler error fix

* Fixed error where broadcast_to fails if shape is tuple of IntImm

* Change get_const_int to support int as input

* fix #802, create cache based on sugar tensor

* [Pass] Improve storage rewrite

* fix ci

* fix comment

* fix comment

* Update workspace_pool.cc

* Update workspace_pool.cc

* fix opengl to OpenGL/gl3.h for APPLE

* use glfw3 to include gl.h header

* Ported injective schedules to C++. Added some elementwise ops.

* Fix lint errors

* Added reduction ops and schedules

* Fix lint errors

* Fix lint errors

* Fix lint errors

* Added transform ops

* Fix lint errors

* Fix lint errors

* Added softmax, log_softmax, leaky_relu and flatten ops.
Fixed issue where TVM_DECLARE_INTRIN_UNARY used the PureExtern flag
instead of PureIntrinsic.
Added softmax CUDA schedule.

* Fix lint

* Fix lint

* Added binary_dense, batch_norm_inference, dense, dilate, scale_shift_*,
global_pool and pool ops.
Extended pad to allow specifying pad_value.
Fixed issue where pad would throw if padding was zero in all dimensions.

* Fix lint

* Fix lint

* Added CUDA schedules for dense, pool and global_pool

* Added extern schedules for generic and CUDA

* Fix lint

* Added x86 binary schedules

* Fix lint

* Added rocm dense schedule. Added rocBLAS and cuBLAS support to dense ops

* Added pow ops. Added x86 default and injective schedules

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix indent

* Removed schedules directory

* Changed left_shift, right_shift to operators. Changed pad_value in pad() to remove pointer usage

* Fixed usage of pad in nn/pooling.h. Fixed declaration of operator>>

* Fixed comments for shift operators

* Added comments to utility functions

* Added TOPI C++ library, exporting broadcast_add op

* Fix lint

* Share libinfo.py with TVM

* Fix lint

* Add other broadcast ops

* Fix lint

* Fix imports in topi

* Fix lib names

* Fixed build issue where windows builds don't apply correct definitions

* Removed TVM_EXPORTS from topi library

* Attempted CI build fix

* Add topi lib to tvm_multilib

* Fix Jenkinsfile

* Added TOPI build target to Makefile

* Fix nn op namespaces.

* Fix lint

* Renamed TOPI lib to libtvm_topi

* Removed _ffi/base.py

* Remove _ffi from topi, now shared with tvm.

* Make libtvm_topi loading optional

* Fix compiler warnings

* Fix lint

* Fix lint

* Fix lint

* Fix build error by making new libs argument to Target optional

* Added C++ Target type interop. Added registration of remaining C++ ops and schedules. Added test of broadcast ops

* Fix lint

* Fix lint

* Fix compile error

* Fix compiler warnings

* Fix compiler warnings

* Fixed int vector interop. Fixed argmin incorrectly invoking argmax. Fixed corner case in default schedules of attempting to fuse 0 length axes. Added tests for reduce ops.

* Refactored reduce builders

* Fixed typos in topi.cc. Added basic test.

* Fixed padding size error. Added dense, dilate, pooling tests

* Fixed issue where clip would output a different dtype to the input. Added split_sections op to cover the other mode of the python split op. Added tests.

* Changed extension type numbers to avoid clash with NNVM

* Fix lint

* Fix compiler warnings

* Removed use of std::vector from the public TOPI API

* Fix lint

* Add TOPI C++ tests to CI

* Fixed detail namespacing. Improved comments.

* when there is no intrin func, using body for initialization. For issue 714.

* Refine code per review comments, and add a test case.

* Fix lint issues.

* Re-organize the tensorize test cases, and add a new case for none-reset
mode.

* Fix a typo.

* Delete the unit case because merged it into test_schedule_tensorize.py already.

* always use new tensor in its stage when rewrite for cache read

* revert previous changes to sync up with master

* support using the ptr with an original offset

* update test case and fix CI error

* OpenGL texture is always 1024 x nrows.

* Address review comments.