* 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

Basic WebGL Backend

* Add Mali target support to tvm.target.create

* Add Mali target support in codegen

* [PASS] StorageRewrite Fold Inplace op storage when possible

* update comment to fix typos

* [SCHEDULE]enable partition const loop with build flag (#719)

    * enable partition loop with build flag

    * add a testcase, and modify LoopPartition related cases

*     * add document for split_const_loop

* 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

* Support rank-0 tensor

* fix lint

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

* [PASS/SETUP] Fix minior issues

* fix lint

* Support vector operations for AMD (llvm IR)

* fix whitespace

* update comments, docstring

* [RUNTIME] Enable ext_dev type for quick plugin of device

* [TEST] Update testcase to cover all computation

* [PASS] copy intrin

* update comment thanks to derisavi

* [ARITH] Improve detect linear equation

* fix doc

* [TEST] rfactor+ewise, cite rfactor paper

* include all authors via abbrv

* [TOPI] Add transpose

* fix lint

* [RPC] Include rpc session info into context

* add type checker in return converison

* [RUNTIME] Enable extension type to PackedFunc.

* More comments

* [SCHEDULE] Enahance cache_write to enable layout change.

* more tests

* [SCHEDULE][PASS] support storage_align of certain axis

* fix lint

* [DOCS][APP] Add Example for C++ deployment

* fix lint

* v2: runtime support for rocm

* fixed coding space errors

* removed kROCM from c_runtime_api.h

* [WIP] C++ topi contributions

Summary:
This diff implements C++ topi contributions for:
  - relu with parametrix threshold
  - pad with generic padBefore / padAfter specification
  - matmult with transposes
  - conv2d_nchw, conv2d_hwcn with runtime constant padding and strides
  - depthwise_conv2d_nchw with runtime constant padding and strides
  - group_conv2d_ngchw with runtime constant padding and strides
  - broadcast_to a broadcastable shape
  - broadcast_bop where bop is an usual binary op (+ - * / %)

Convolution padding is implemented using the pad operation.
To avoid extra memory consumption, it is generally recommended to inline the padding with the autoinliner.
Unfortunately in its current form the elemwise checks are too restrictive to allow inlining.
So this diff also proposes an extension to LHS injective (i.e. no reduction axis in the current IR design)

Test Plan:
Tested in C++ testsuite in a separate repository, I am looking for suggestions to quickly spin up some tests for tvm.

Reviewers: tqchen

Subscribers:

Tasks:

Tags:

Blame Revision:

* Review + Lint + GSG C++

* [RUNTIME][PASS] Allow declare vector type array

* fix bcast

* [BUFFER] Enable vload/store function in buffer

* ok