[llvm] r199978 - [AArch64 NEON] Fix a bug in implementing register copy bwtween FPR16.

[Kevin Qin]

Author: kevinqin
Date: Fri Jan 24 01:53:04 2014
New Revision: 199978

URL: http://llvm.org/viewvc/llvm-project?rev=199978&view=rev
Log:
[AArch64 NEON] Fix a bug in implementing register copy bwtween FPR16.

Modified:
    llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp
    llvm/trunk/test/CodeGen/AArch64/neon-copy.ll

Modified: llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp?rev=199978&r1=199977&r2=199978&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp Fri Jan 24 01:53:04 2014
@@ -135,9 +135,9 @@ void AArch64InstrInfo::copyPhysReg(Machi
   } else if (AArch64::FPR16RegClass.contains(DestReg, SrcReg)) {
     // The copy of two FPR16 registers is implemented by the copy of two FPR32
     const TargetRegisterInfo *TRI = &getRegisterInfo();
-    unsigned Dst = TRI->getMatchingSuperReg(SrcReg, AArch64::sub_16,
+    unsigned Dst = TRI->getMatchingSuperReg(DestReg, AArch64::sub_16,
                                             &AArch64::FPR32RegClass);
-    unsigned Src = TRI->getMatchingSuperReg(DestReg, AArch64::sub_16,
+    unsigned Src = TRI->getMatchingSuperReg(SrcReg, AArch64::sub_16,
                                             &AArch64::FPR32RegClass);
     BuildMI(MBB, I, DL, get(AArch64::FMOVss), Dst)
       .addReg(Src);

Modified: llvm/trunk/test/CodeGen/AArch64/neon-copy.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AArch64/neon-copy.ll?rev=199978&r1=199977&r2=199978&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AArch64/neon-copy.ll (original)
+++ llvm/trunk/test/CodeGen/AArch64/neon-copy.ll Fri Jan 24 01:53:04 2014
@@ -1262,4 +1262,15 @@ entry:
   %vecext1 = extractelement <1 x i64> %y, i32 0
   %vecinit2 = insertelement <2 x i64> %vecinit, i64 %vecext1, i32 1
   ret <2 x i64> %vecinit2
-}
\ No newline at end of file
+}
+
+declare <1 x i16> @llvm.aarch64.neon.vsqadd.v1i16(<1 x i16>, <1 x i16>)
+
+define <1 x i16> @test_copy_FPR16_FPR16(<1 x i16> %a, <1 x i16> %b) {
+; CHECK-LABEL: test_copy_FPR16_FPR16:
+; CHECK: usqadd h1, h0
+; CHECK-NEXT: fmov s0, s1
+entry:
+  %vsqadd2.i = call <1 x i16> @llvm.aarch64.neon.vsqadd.v1i16(<1 x i16> %b, <1 x i16> %a)
+  ret <1 x i16> %vsqadd2.i
+}