- 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()

* [ConvertLayout] Support QNN ops.

* Changing layouts to C.

* Fixing dilation.

* Empty commit.

Co-authored-by: Ubuntu <ubuntu@ip-172-31-53-55.us-west-2.compute.internal>

* add missing upcast to avgpool

* add avg pool test

Change-Id: I015b2c66a50b64d0eb2e9efe336f6c18ea1fdc67

* [CODEGEN][OPENCL] Explicitly cast min/max operands

* retrigger CI

* refactor relay python

* revert relay/ir/*.py to relay

* Address comments

* remove direct access to analysis and transform namespace

* update docs for dilation 2d

* dilation2d compute

* dilation2d register

* dilation2d rel compute

* dilation2d strategy

* dilation2d attrs

* dilation2d generic schedule

* dilation2d tf frontend support

* dilation2d tf frontend test case

* dilation2d test cases

* pylint fixes

* add exception for cuda target

* Update docstring

* Update docstring

* change rates to dilations

* removed unused param

* merge master

* Update nn.py

* Update nn.py

* [TFLITE]DepthToSpace and SpaceToDepth op parser support

* DepthToSpace and SpaceToDepth testcases

* Review comments fixed

* Use dummy func when no lowered_funcs exists in Relay mod

* Dummy func -> CSourceModule with empty code str

* Added comments describing the empty CSouceModule

* Always import external modules w/o assertions

* Use CSourceModule as a fallback for LLVMModule

* Changed cond for target == llvm

* Create an empty LLVM module w/o using dummy func

* Avoid using IR str concat to create LLVM module

* Improved comments for codegen.LLVMModuleCreate

* Satisfy the linter for LLVMModuleCreate

* add stub for nd impl

* refactored indices compute

* refactored divide step

* remove unused variables, add doc

* fix lint

* add relay op def

* add python registration

* refactor topi test

* update relay tests, but test result is weird

* workaround for weird bug

* add relay adaptive pool 3d test

* add topi tests

* update doc for 3d

* typo fix

* fix lint

* add more tests including NDHWC

No changes seem to be needed to _fused_batch_norm. It just works.

* [TESTS] Triage the testcases to fit the naming convention of the new namespaces

* Remove multiple usage of system lib to avoid test problems