This patch eanble register coalescing to coalesce the following:

  %vreg2<def> = MOVi32imm 1; GPR32:%vreg2
  %W1<def> = COPY %vreg2; GPR32:%vreg2
into:
  %W1<def> = MOVi32imm 1
Patched by Lawrence Hu (lawrence@codeaurora.org)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243033 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AArch64/AArch64InstrInfo.cpp b/lib/Target/AArch64/AArch64InstrInfo.cpp
index f5b0c8b450a4803c98a22887142050a3791e8dfc..66b89366c2d23a42448718fd2f156045ce7683b6 100644 (file)
--- a/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -533,6 +533,14 @@ void AArch64InstrInfo::insertSelect(MachineBasicBlock &MBB,
       CC);
 }
 
+/// Returns true if a MOVi32imm or MOVi64imm can be expanded to an ORRxx.
+static bool canBeExpandedToORR(const MachineInstr *MI, unsigned BitSize) {
+  uint64_t Imm = MI->getOperand(1).getImm();
+  uint64_t UImm = Imm << (64 - BitSize) >> (64 - BitSize);
+  uint64_t Encoding;
+  return AArch64_AM::processLogicalImmediate(UImm, BitSize, Encoding);
+}
+
 // FIXME: this implementation should be micro-architecture dependent, so a
 // micro-architecture target hook should be introduced here in future.
 bool AArch64InstrInfo::isAsCheapAsAMove(const MachineInstr *MI) const {
@@ -573,6 +581,12 @@ bool AArch64InstrInfo::isAsCheapAsAMove(const MachineInstr *MI) const {
   case AArch64::ORRWrr:
   case AArch64::ORRXrr:
     return true;
+  // If MOVi32imm or MOVi64imm can be expanded into ORRWri or
+  // ORRXri, it is as cheap as MOV
+  case AArch64::MOVi32imm:
+    return canBeExpandedToORR(MI, 32);
+  case AArch64::MOVi64imm:
+    return canBeExpandedToORR(MI, 64);
   }
 
   llvm_unreachable("Unknown opcode to check as cheap as a move!");

diff --git a/test/CodeGen/AArch64/arm64-coalescing-MOVi32imm.ll b/test/CodeGen/AArch64/arm64-coalescing-MOVi32imm.ll
new file mode 100644 (file)
index 0000000..2adbcdf
--- /dev/null
+++ b/test/CodeGen/AArch64/arm64-coalescing-MOVi32imm.ll
@@ -0,0 +1,18 @@
+; RUN: llc < %s | FileCheck %s
+
+; CHECK:        orr     w0, wzr, #0x1
+; CHECK-NEXT :  bl      foo
+; CHECK-NEXT :  orr     w0, wzr, #0x1
+; CHECK-NEXT :  bl      foo
+
+target triple = "aarch64--linux-android"
+declare i32 @foo(i32)
+
+; Function Attrs: nounwind uwtable
+define i32 @main() {
+entry:
+  %call = tail call i32 @foo(i32 1)
+  %call1 = tail call i32 @foo(i32 1)
+  ret i32 0
+}
+