Conversation
Plz refer to https://github.com/coredac/dataflow/blob/b493f50bef66977cc01637bfd4f40b895718812f/test/neura/interpreter/lower_and_interpret_subf.mlir#L35
|
|
@tancheng Hi, I have add the interpreter.mlir and the multi_ops.mlir, but I am confused how the multi_ops works |
Sorry, I just meant have a test including both sub and mul.
You mean you don't understand something? or it doesn't work on your side? |
| @@ -29,22 +29,14 @@ | |||
| // GOLDEN: 7.0 | |||
There was a problem hiding this comment.
May need change 7.0 to 63.0.
| %arg0 = arith.constant 9.0 : f32 | ||
| %cst = arith.constant 2.0 : f32 | ||
| %0 = arith.subf %arg0, %cst : f32 | ||
| %1 = arith.mulf %arg0, %0 : f32 |
There was a problem hiding this comment.
You may need to provide the lowering from Arith to Neura. Currently, you only enable LLVM to Neura.
add arith to neura for fmul
Hello, I have added the fmul for interpreter, let me know if I miss something.