You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
MLIR refers to the process of converting tensor to memref as "bufferization". This thread records the issues I found during constant tensor bufferization.
Relevant test case: test_compute_basic.py::test_copy
These two passes should bufferize the arith.constant operation and then remove bufferization.to_tensor operation. But after the first pass memref.tensor_store is marked as illegal. Therefore, we get this error:
`memref.tensor_store %cst, %0`:
failed to legalize operation `memref.tensor_store`
The text was updated successfully, but these errors were encountered:
MLIR refers to the process of converting tensor to memref as "bufferization". This thread records the issues I found during constant tensor bufferization.
Relevant test case:
test_compute_basic.py::test_copy
MLIR assembly:
We need to lower
tensor<10xi32>
to memref. The existing passes in MLIR doesn't seem to work with constant tensor andmemref.tensor_store
together:These two passes should bufferize the
arith.constant
operation and then removebufferization.to_tensor
operation. But after the first passmemref.tensor_store
is marked as illegal. Therefore, we get this error:The text was updated successfully, but these errors were encountered: