# \[RFC\] TensorIR: A schedulable IR for TVM

**URL:** <https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872>\
**Category:** RFC\
**Created:** [September 10, 2020, 4:42pm UTC](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872 "2020-09-10T16:42:18Z")\
**Posts on this page:** 1\
**Showing post:** 17

<div class="post-metadata">

**Author:** ![comaniac](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/comaniac/32/899_2.png) [@comaniac](https://discuss.tvm.apache.org/u/comaniac)\
**Post date:** [September 12, 2020, 1:55am UTC](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872/17 "2020-09-12T01:55:15Z")

</div>

So the scenario is like you can choose to use TE or TIR to write a compute, but if you choose TE, you have to first lower it to TIR and then add schedule primitives?

IIUC, it seems to me that this is nontrivial, because TIR was not written by human and you may need to first print it out to figure out how to schedule it. It sounds more straightforward to keep TE schedule as syntactic sugar. At least you can get the sense about how the schedule looks like by tracing the Python code.

---

_[View the full topic](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872)._