* [Strategy][ARM CPU] Low the plevel of contrib spatial pack of depthwise convolution

* address comments

* [TE][Schedule] Duplicate likely nodes removed

* [1] Test case added

* [2] Lint error fixed

* [3] Review comments handled

* [4] Review comments handled

* [Torch] Add support for max_pool1d

* add test

* fix line-too-long

* remove wrapper class

* Fix conv2d conversion for group conv

* add more comment for clarification

* [REFACTOR][TIR] Introduce PrimFuncPass.

- Introduce PrimFuncPass
- Convert one pass to the unified Pass API.

* Address comments

* Fix comments

* save

* gradient.rly

* fix

* NOT WORKING: gradient cell pass

* test gradient pass

* fixed basic call ops

* more tests

* fix bug

* transform calls to one ones_like zero zero_like

* maintenance stuff

* fix linting

* linting

* linting

* throw default

* remove unrelated changes

* import gradent.rly in pass

* comment

* linting

* remove changes to test files

* move gradient_cell.cc to transforms

* revert change

* update files with new commits

* type

* wrapper function to main outermost function type

* fix linting

* fix unsigned and signed int comparison

* review

* GetConstructor definition in module and change op comparison

* update node instantiations

* increase code readability

Co-authored-by: Marisa Kirisame <lolisa@marisa.moe>

Existing test cases cover this fix. In addition I have added an assert to make sure that the data_min is always less than equal to data_max.

* add argsort_nms_thrust

* consider valid count in thrust nms sort

* make thrust optional

* typo

* typo

* fix pylint

* address some of the comments

* address more comments

* fix lint

* address more comments

* address more comments

* relay Node::make to constructor

* patternwildcard

* Address comments

* Improve TF control flow major logic

* Pass mod into operator convert function

* Fix LoopBound

* Add more control flow tests

* Add two test cases for stridedslice

* Fix docstring

* Fix lint

* Fix import

* Fix test assert

* Minor fix conv3d

* Add more comments

* Fix for dilation2d

* Change newly added atan

* Change newly added unravel

[Bugfix] Fixed bug where shifting by out-of-bounds value results in no compute code being emitted. (#5115)

* Fixed bug where shifting by out-of-bounds RHS values results in LLVM to codegen nothing. Added regression testcase

* Updated testcase to be more precise.

* Fixed testcase

* isfinite doc update

* isfinit expr

* isfinit expr

* isfinite schedule reg

* isfinite python binding

* isfinite python binding

* relay register isfinite

* isfinite type relation

* intrin isfinite

* topi isfinite

* testcase topi isfinite

* tf frontend isfinite

* tf frontend isfinite testcase

* test case relay isfinite

* small fixes

* test forward tf isfinite

* test cases injective for cuda

* remove float16 test case

* add support for isinf

* remove unwanted import

* fix conflict

* first cut unravel_index

* merge fixes

* change rates to dilations

* unravel_index op relay, topi, mxnet, tf

* doc changes

* small changes

* remove empty unravel and argwhere attrs

* remove empty unravel and argwhere attrs

* [DOCS] Cleanup docs before rebuild

* Ask doxygen to generate svg to minimize the file size

- This allows to emit vectorized loads/stores
  for CUDA math intrinsics.

- A few intrinsics should be lowered as CUDAMath not CUDAFastMath ones.

- Fixed the code block identation.

* Fix up the final pieces

* Tweak build.rs

* [DOCS] include a tarball of docs during deployment

* [DOCS] Add a short security faq

* [KERAS]Conv3d support added

* Keras conv3d testcase added

* Update relay docs

* any -> py:func

* make clean

* add Atan/Atan2 op

* fix bug and testing

* bind constant to subgraphs

* con -> constant

* fix CompilerAttrs

* retrigger ci

* [TOPI][OP] Use Thrust sort for argsort and topk

The current GPU sort implementation (odd-even transposition sort) is too slow
when the number of elements is large.  This PR introduces Thrust implementation
of sort which is much faster.

Note that this change requires CMake 3.8 or later since we have to use nvcc to
compile a thrust code.

* cmake: make CUDA optional

* allow .cu file to be into the repository

* pylint fix and cleanup

* require cmake 3.8 only when thrust is enabled

* fix nvcc compiler error when passing -pthread

* add missing include

* add USE_THRUST option in config.cmake

* retrigger CI

* retrigger CI

* Temporary fix to the stack overflow issue in autotvm task extraction

* fix lint

* fix graph tuner test

As part of the unified IR refactor.
This PR refactors the target codegen to use IRModule containing tir::PrimFuncs.

In order to break the refactor into several steps without breaking the codebase,
we built an conversion pass to convert Array<LoweredFunc> into IRModule.

The follow-up refactors will gradually move the passes covered by IRModule up
until we cover all the passes. Then we can remove the additional redundant
concepts such as LoweredFunc.

* fix minor lint issue

* add conv3d and adaptive avg pool3d conversion with test

* fix max pool handling

* add batch norm 3d test

* add resnet 3d test

* add more conv3d test

* clean up batch norm test

* add note on disabling inception v3 test

* add more tests

* add more tests

* fix names

* [DOC] Add doc for Relay op strategy

* update

* address more comments

* update

* update

* [Relay][Frontend][ONNX] operator support: NonZero

* update

* Solve the build fail

* solve the build fail

* Replace ctx_list with tvm.cpu()