areusch commented on code in PR #87: URL: https://github.com/apache/tvm-rfcs/pull/87#discussion_r946216309
########## rfcs/0070-introducing-decl-buffer.md: ########## @@ -146,9 +146,36 @@ Specifically, the updated flow of buffer flattening using `DeclBuffer` will be: with flattened indices. ## TVM script updates +* New statement `T.decl_buffer` will be introduced. It has the same interface as `T.buffer_decl`. +```python +def decl_buffer( + shape: Sequence[Union[PrimExpr, int]], + dtype: str = "float32", + data: Var = None, Review Comment: ok, but in the example above (line 135) you have: ``` A_flattened = T.decl_buffer(A.data, (256,), "float32") ``` this says to me that: - `shape` == `A.data` - `dtype` == `(256,)` - `data` == `"float32"` could you keep the RFC consistent? -- 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: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
