[llvm] r201061 - [AArch64]Implement the copy of two FPR8 registers by using FMOVss of two FPR32 registers in copyPhysReg.

[Hao Liu]

Author: haoliu
Date: Sun Feb  9 21:16:22 2014
New Revision: 201061

URL: http://llvm.org/viewvc/llvm-project?rev=201061&view=rev
Log:
[AArch64]Implement the copy of two FPR8 registers by using FMOVss of two FPR32 registers in copyPhysReg.

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=201061&r1=201060&r2=201061&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64InstrInfo.cpp Sun Feb  9 21:16:22 2014
@@ -132,6 +132,16 @@ void AArch64InstrInfo::copyPhysReg(Machi
         .addImm(16);
       return;
     }
+  } else if (AArch64::FPR8RegClass.contains(DestReg, SrcReg)) {
+    // The copy of two FPR8 registers is implemented by the copy of two FPR32
+    const TargetRegisterInfo *TRI = &getRegisterInfo();
+    unsigned Dst = TRI->getMatchingSuperReg(DestReg, AArch64::sub_8,
+                                            &AArch64::FPR32RegClass);
+    unsigned Src = TRI->getMatchingSuperReg(SrcReg, AArch64::sub_8,
+                                            &AArch64::FPR32RegClass);
+    BuildMI(MBB, I, DL, get(AArch64::FMOVss), Dst)
+      .addReg(Src);
+    return;
   } 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();

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=201061&r1=201060&r2=201061&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/AArch64/neon-copy.ll (original)
+++ llvm/trunk/test/CodeGen/AArch64/neon-copy.ll Sun Feb  9 21:16:22 2014
@@ -1291,6 +1291,19 @@ entry:
   ret <2 x i64> %vecinit2
 }
 
+declare <1 x i8> @llvm.aarch64.neon.vsqadd.v1i8(<1 x i8>, <1 x i8>)
+
+; This case tests the copy of two FPR8 registers, which is implemented by fmov
+; of two FPR32 registers.
+define <1 x i8> @test_copy_FPR8_FPR8(<1 x i8> %a, <1 x i8> %b) {
+; CHECK-LABEL: test_copy_FPR8_FPR8:
+; CHECK: usqadd b1, b0
+; CHECK-NEXT: fmov s0, s1
+entry:
+ %vsqadd2.i = call <1 x i8> @llvm.aarch64.neon.vsqadd.v1i8(<1 x i8> %b, <1 x i8> %a)
+ ret <1 x i8> %vsqadd2.i
+}
+
 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) {