[llvm] [AArch64] Keep floating-point conversion in SIMD (PR #147707)

David Sherwood via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 10 02:21:47 PDT 2025


https://github.com/david-arm commented:

The intent of the PR makes sense to me and it's nice to see it using the higher throughput versions of fcvtzs, etc. I just had a few comments about possibly improving the patterns - let me know what you think!

https://github.com/llvm/llvm-project/pull/147707


More information about the llvm-commits mailing list