junrushao1994 opened a new pull request, #11532:
URL: https://github.com/apache/tvm/pull/11532
This PR fixes an existing bug in TIR lowering where the TIR below triggers
an error:
```python
@T.prim_func
def func(a: T.Buffer[10, "bool"], b: T.Buffer[10, "bool"]) -> None:
T.func_attr({"global_symbol": "main", "tir.noalias": True})
for i in T.serial(10):
with T.block("b"):
vi = T.axis.spatial(10, i)
b[vi] = a[vi]
tvm.build(func, target="llvm")
```
The error message is:
```
File "/root/Projects/tvm-dev/src/tir/transforms/flatten_buffer.cc", line
173
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: store->buffer->dtype == DataType::Int(8) (bool vs. int8) :
Expected int8 backing array for boolean tensor
```
This PR fixes this behavior.
--
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]
