Skip to content

add the fmul into the intepreter#26

Closed
chz05 wants to merge 7 commits intomainfrom
interpreter_for_neura
Closed

add the fmul into the intepreter#26
chz05 wants to merge 7 commits intomainfrom
interpreter_for_neura

Conversation

@chz05
Copy link
Copy Markdown
Collaborator

@chz05 chz05 commented Jun 4, 2025

Hello, I have added the fmul for interpreter, let me know if I miss something.

@chz05 chz05 requested a review from tancheng June 4, 2025 21:39
@tancheng
Copy link
Copy Markdown
Contributor

tancheng commented Jun 4, 2025

Hello, I have added the fmul for interpreter, let me know if I miss something.

Plz refer to https://github.com/coredac/dataflow/blob/b493f50bef66977cc01637bfd4f40b895718812f/test/neura/interpreter/lower_and_interpret_subf.mlir#L35
or directly from llvm.ir: test/neura/interpreter/interpreter.mlir

  • add the fmul following the fsub to test
  • we can rename this lower_and_interpret_subf.mlir to multi_ops.mlir

@chz05
Copy link
Copy Markdown
Collaborator Author

chz05 commented Jun 5, 2025

@tancheng Hi, I have add the interpreter.mlir and the multi_ops.mlir, but I am confused how the multi_ops works

@tancheng
Copy link
Copy Markdown
Contributor

tancheng commented Jun 5, 2025

@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.

I am confused how the multi_ops works

You mean you don't understand something? or it doesn't work on your side?

@@ -29,22 +29,14 @@
// GOLDEN: 7.0
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You may need to provide the lowering from Arith to Neura. Currently, you only enable LLVM to Neura.

@chz05 chz05 closed this Sep 19, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants