cxx122 opened a new issue, #12374:
URL: https://github.com/apache/tvm/issues/12374
```
tensor_0 = te.placeholder([5], dtype="int8", name="TENSOR_0")
tensor_1 = te.compute([5], lambda lcg:te.truncdiv(te.min_value("int64"),
tensor_0[lcg]), name ="TENSOR_1")
```
### Expected behavior
```
int32
int64
```
### Actual behavior
```
int32
int64
Floating point exception (core dumped)
```
### Environment
Operating System: Ubuntu 18.04, TVM version: tag0.9.0 [d361585]
### Steps to reproduce
```
import os
import numpy as np
import tvm
from tvm import te, auto_scheduler, topi
import tvm.testing
print("int32")
tensor_0 = te.placeholder([5], dtype="int8", name="TENSOR_0")
tensor_1 = te.compute([5], lambda lcg:te.truncdiv(te.min_value("int32"),
tensor_0[lcg]), name ="TENSOR_1")
s = te.create_schedule(tensor_1.op)
tensor_list = [tensor_0,tensor_1]
tvm.lower(s, tensor_list, simple_mode=True)
print("int64")
tensor_0 = te.placeholder([5], dtype="int8", name="TENSOR_0")
tensor_1 = te.compute([5], lambda lcg:te.truncdiv(te.min_value("int64"),
tensor_0[lcg]), name ="TENSOR_1")
s = te.create_schedule(tensor_1.op)
tensor_list = [tensor_0,tensor_1]
tvm.lower(s, tensor_list, simple_mode=True)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
