* support dim-0 tensor in topi ops

revert transform

* revert

* add target.libs to target str representation

* integrate cudnn into topi cuda

* append target.libs to target.options

* add extern schedule for miopen

* fix comment

* optionally dispatch to miopen from topi

* fix lint

* check if current target is None

* use generic dispatch for rocm conv2d

* fix lint

* fix workspace bug

* remove blank line

* remove blank line

* remove blank line

* add x86_64 target

* add binary dense operator

* rebase

* improve schedule

* remove x86 target

* improve schedule

* fist working miopen support

* do FindFwdAlgo during build time

* fix lint

* update doc string

* import topi after checking if rocm is enabled

* add miopen namespace

* fixed descriptor overwrite bug

* add use_miopen option

* fix lint

* better miopen option handling

* fix typo

* fix options handling

* [CODEGEN] update codegen for vector operation

* update comment, fix for metal

* Make duplicated function name checker working

* Fix dependency checking problem for reducer condition (#712); add test

* Fix dependency checking problem for reducer condition (#712); add test

* Specify R to be computed inlined

During tensorize, call Simplify on algorithm and intrinsic definitions before CanonicalSimplify. This will prevent a number of false tensorize mismatches. (#718)

thanks, this we can use this solution for now 

* 1) removed non-determinism from CanonicalSimplify
2) added couple of testcases for CanonicalSimplify

* Use IRDeepCompare instead of comparison of string representation

* Give a warning (instead of fatal error) when two "ComExprEntry"s are equal

* Simplify expressions early on

* fixed lint errors

* 1) Refactored some parts of the unrolling code into their own methods so we can reuse unrolling functionality in other parts of the code. E.g., to explicitly unroll loops with count of 1 when they are programmatically created.
2) Reorder based on top operator before resorting to pointers, which causes non-determinism.

* Fixed lint errors

* Use long long for platforms where long is 32 bits (like windows).

* Make sure scalar chars are signed.

* Re-add NOLINT marker.

* [CODEGEN] add fp16 and fp64 enable pragma for opencl

* fix style

* Port build_module.py to C++

* Fix lint errors

* Fix more lint errors

* Fix more lint errors

* Fix more lint errors

* Fix build error

* Implemented style fixes

* Fix lint errors

* Added function to construct target from string
lower now returns array

* Fix lint error

* Implemented review changes - style & Target options -> std::vector

* Fixed lint, argument alignment and added unit test

* Changed test to target LLVM, fixed sign compare warnings

* Reverted unit test to CUDA, changed Jenkinsfile to enable GPU for C++ tests

* Slight change to Jenkinsfile

* Changed build_module test from CUDA to LLVM

* Added function var() to construct a Var instance.
Changed implementation of LLVMEnabled()

* Reverted Jenkinsfile

* [CI] Enable llvm in CPU test

* fix llvm

* Support rank-0 tensor

* fix lint

* [RANDOM] Init contrib.random library

* [RANDOM] Add uniform

* [RANDOM] Fix lint

* [RANDOM] Add comments and tests

* [RANDOM] Fix lint

* [CUDA] Enable int64

* [PYTHON] Fix rpc tutorial with opencl

* OK

* update

Change the parameter 'C' name

In unroll_loop.cc the parameter name is "auto_max_depth", but in ir_pass.h the parameter name is "auto_min_depth"

* [RPC][JVM] Remove binary dist gradle from repo

* fix header

* [PASS] Allow compact checking when strides is available

* remove assert compact

Readability.

* [PASS/SETUP] Fix minior issues

* fix lint

* mps

* update

* scheduler tweaked for super resolution perf

* conv2d_transpose schedule error fixed

* nnvm issue #239 fixed

some host opencl runtime may at cpu mode, but remote

client opencl runtime at gpu mode, compat it