[PATCH] D142178: [X86] Change precision control to FP80 during u64->fp32 conversion on Windows.

Sat Feb 4 07:02:02 PST 2023

icedrocket added a comment.

I wrote some code to verify that u64 to f64 conversion using FILD+FADD with 53-bit precision is correct. I tested it with 100 billion cases and the results are: u64 to f32 conversion failed frequently, but u64 to f64 conversion does not failed.

F26352111: test-f64.rs <https://reviews.llvm.org/F26352111>
F26352131: test-f32.rs <https://reviews.llvm.org/F26352131>

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D142178/new/

https://reviews.llvm.org/D142178