# \[TVM Scheduling\] Split factors missmatch to original extent

**URL:** <https://discuss.tvm.apache.org/t/tvm-scheduling-split-factors-missmatch-to-original-extent/2982>\
**Category:** Questions\
**Created:** [June 18, 2019, 2:58pm UTC](https://discuss.tvm.apache.org/t/tvm-scheduling-split-factors-missmatch-to-original-extent/2982 "2019-06-18T14:58:34Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![aca88](https://discuss.tvm.apache.org/letter_avatar_proxy/v4/letter/a/ed8c4c/32.png) [@aca88](https://discuss.tvm.apache.org/u/aca88)\
**Post date:** [June 21, 2019, 10:00am UTC](https://discuss.tvm.apache.org/t/tvm-scheduling-split-factors-missmatch-to-original-extent/2982/2 "2019-06-21T10:00:40Z")

</div>

I guess some of my problem arises from wanting to generate code which will be static analysable

- What I mean by this (sorry if this isnt the correct terminology) is to generate code which will have resolved all the different paths of the execution.

I have looked into some of the VTA code and I guess that the rely on the VTARuntime being called inside of the compiled module which is capable of resolving (dynamically) all the paths.  
Would this be the “preferred way” to do this?  
Any comments?@tqchen @zhiics @eqy @xqdan

---

_[View the full topic](https://discuss.tvm.apache.org/t/tvm-scheduling-split-factors-missmatch-to-original-extent/2982)._