* OpenGL texture is always 1024 x nrows.

* Address review comments.

* 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

The compilation warning is fixed. 
src/runtime/graph/graph_runtime.cc:392:24: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
   CHECK(data_byte_size == size)
         ~~~~~~~~~~~~~~~^~~~
/mnt/D_DRIVE/work/nnvm_22_Jan/nnvm_latest/tvm/dmlc-core/include/dmlc/logging.h:109:9: note: in definition of macro ‘CHECK’
   if (!(x))                                                \
         ^

fix errors when running `python3 setup.py sdist bdist_wheel`

This compilation warning is fixed.
src/pass/inject_virtual_thread.cc:43:19: warning: ‘rw_mask’ may be used uninitialized in this function [-Wmaybe-uninitialized]
       if (rw_mask & 2) {
           ~~~~~~~~^~~

Basic WebGL Backend

* Support dump ir for each pass(#693)

* expose DumpIR

* fix comments

* fix comments

* fix upsampling output shape

* simplify expr in get_const_tuple

* Add Mali target support to tvm.target.create

* Add Mali target support in codegen

The type of parameter options should be a str list.

* add basic x86 schedules

* parallelize & vectorize batchnorm + relu

* fuse conv into bn + relu

* move rc loop to outer

* add nhwc conv

* change weight layout to hwcf

* conv + bn + relu fusion for nhwc conv

* fix conv_nhwc schedule when no fusion

* clean up default parallel schedules

* simplify elemwise parallel

* fix elemwise parallel for batch == 1

* update nhwc conv test

* fix and add comment

* fix lint

* remove redundant import

* remove default multithreading for some ops

* remove default multithreading for global pool

* add schedule for ARM Mali GPU

* fix lint

* fix lint

* support more argument type in depthwise_conv2d

* mark all pointer as 'restrict' & fix vector conversion for opencl

try to fix

fix

* [LLVM] Enable same target option in JITModule

* not set mcpu explicitly

* add upsampling cpu op

* add upsampling gpu schedule

* add doc for upsampling op

add more doc

* cleanup upsampling test

* add doc

* fix lint

* fix lint

* fix lint

* remove unused import

* remove skimage dependency

* remove skimage import

* remove schedule_upsampling

* small fixs on docs

* add IR output after parallelization

* [PASS] Improve loop partition to remove un-necessary warning.

* fix comment

* Improve opt_gemm tutorial

* Addressed comments

* [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

* [IRbuild]Support automatically Name Loop Variable in IRBuilder (#719)

    * add idx_num in class

* using typical index [i, j, k] first, then i_suffix

* keep inputs names

* fix lint

* improve comment of name

* fix lint

* [SCHEDULE]Improve bound deduce for loop partition (#743)

    * add divided checking when deducing

    * related testcase

* fix

* * transform LE and GE first
* remove is_equal
* modify testcase for edge cases checking

* * fix comment

* * fix lint

* * apply transformation form LT -> LE, GT -> GE

* * fix lint

* simplify code and testcase

* add negative co-efficient case

* More complicated cases

* add testcase

* simplify testcase

* comment case for now

* fix testcase

* [CODEGEN] use charp for voidp

* fx

* rocblas integration

* fix include

* fix lint

* 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