Issue: #

Brief Summary

🤖 Generated by Copilot at d754141

Refactored and improved the scalarize IR pass and applied it selectively to block-local storage (BLS) kernels. This enhances the performance and correctness of the BLS transformation and simplifies the compilation pipeline.

Walkthrough

🤖 Generated by Copilot at d754141

• Change the scalarize function to return a bool value indicating if the IR was modified (link, link)
• Move the scalarize function to a later stage in the compilation pipeline, after the offloading is done, and only apply it to offloaded kernels with BLS enabled (link, link)
• Check the return value of the scalarize function and call full_simplify or die only if the IR was modified (link, link)
• Add a helper function make_pass_printer to print the IR after each pass if the verbose flag is true (link)
• Call scalarize and full_simplify in the make_block_local_offload function to handle the case where the global pointer index is a tensor type stored in an alloca statement (link)
• Use the delayed_modifier_ as a return value of the run function for each IR pass class in scalarize.cpp, and avoid calling the modifier twice (link, link, link, link, link, link)
• Change the run function of the MergeExternalAndMatrixPtr class to return a bool value and make it consistent with other IR passes (link)