@jdavies-huawei Agree it would be better to have a section dedicated to
threads. I just posted an issue/bug to the github
https://github.com/dmlc/tvm/issues/3052, resolving which shall help developers
understand the concept of threads better.
---
[Visit
Topic](https://discuss.tvm.ai/t/di
Since many of us have run into the same issue, I’d suggest we document this
limitation. This affects tensorisor too. There does not seem to be a simple fix
for this due to the use of simple ranges. We can use a simpler example if you
have one.
---
[Visit
Topic](https://discuss.tvm.ai/t/d
`PassUpDomain` can also be conservative in some cases. This can be illustrated
with the following test case.
```
import tvm
import numpy as np
M = 64
N = 64
B = tvm.compute((M, N), lambda i, j: i+j, name='B')
C = tvm.compute(
(M, N),
lambda i, j: B[i,j],
name='C'
)
s = tvm.creat
Sure. Thanks for including me in the doc! Glad to help.
I can send you the raw file for the IterVar diagram which can be edited with
http://draw.io, if you want it.
---
[Visit
Topic](https://discuss.tvm.ai/t/discuss-contributing-new-docs-for-inferbound/2151/8)
to respond.
You are recei
@jdavies-huawei Thanks for creating this document. This is great. I just went
through the same exercise so to understand the InferBound and my notes are not
nearly as comprehensive as yours.
Following are some diffs, which I hope shall be useful to you.
### Suggested change 1
The following
