[llvm] 250812a - Remove a reference to rdar://problem/16473581

[Jon Roelofs via llvm-commits]

Author: Jon Roelofs
Date: 2023-08-09T16:09:27-07:00
New Revision: 250812abe7334c95d4bfb3738e3646cc7f216aa1

URL: https://github.com/llvm/llvm-project/commit/250812abe7334c95d4bfb3738e3646cc7f216aa1
DIFF: https://github.com/llvm/llvm-project/commit/250812abe7334c95d4bfb3738e3646cc7f216aa1.diff

LOG: Remove a reference to rdar://problem/16473581

Readers can git-blame and find the necessary context if absolutely needed.
Otherwise, the presence of the link doesn't provide much value.

Moral of the story: don't emit `movi.2d #0` on any target affected by this.

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp b/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
index 76f1cc782b2488..0dc32b618787d5 100644
--- a/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
+++ b/llvm/lib/Target/AArch64/AArch64AsmPrinter.cpp
@@ -1453,8 +1453,13 @@ void AArch64AsmPrinter::emitInstruction(const MachineInstr *MI) {
       return;
   }
   case AArch64::MOVIv2d_ns:
-    // If the target has <rdar://problem/16473581>, lower this
-    // instruction to movi.16b instead.
+    // It is generally beneficial to rewrite "fmov s0, wzr" to "movi d0, #0".
+    // as movi is more efficient across all cores. Newer cores can eliminate
+    // fmovs early and there is no 
diff erence with movi, but this not true for
+    // all implementations.
+    //
+    // The floating-point version doesn't quite work in rare cases on older
+    // CPUs, so on those targets we lower this instruction to movi.16b instead.
     if (STI->hasZeroCycleZeroingFPWorkaround() &&
         MI->getOperand(1).getImm() == 0) {
       MCInst TmpInst;