[PATCH] D68360: PR41162 Implement LKK remainder and divisibility algorithms [urem]

[Tim Gymnich via Phabricator via llvm-commits]

TG908 marked an inline comment as done.
TG908 added inline comments.


================
Comment at: llvm/test/CodeGen/X86/urem-lkk.ll:110
+
+define void @urem_loop(i32 %x) {
+entry:
----------------
xbolva00 wrote:
> This loop test  we dont need I think.
> 
> If you want to leave it, please regenerate CHECKs.
The loop test was meant to demonstrate that lkk is beneficial on aarch64 even though one single rem operation emits more instructions than the old approach. In a loop the loading of constants only happens once so there overall performance with lkk is better than without.  I will remove this since this was only a test.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68360/new/

https://reviews.llvm.org/D68360