Make local RA smarter about reusing input register of a copy

as output.  Needed for (functional) correctness in inline asm,
and should be generally beneficial.  7361612.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95050 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/RegAllocLocal.cpp b/lib/CodeGen/RegAllocLocal.cpp
index 6a09bd981665f0172242705421cdbfe2be82a898..6a698dec863728167d53a3e34f3178eebbbb648c 100644 (file)
--- a/lib/CodeGen/RegAllocLocal.cpp
+++ b/lib/CodeGen/RegAllocLocal.cpp
@@ -764,8 +764,11 @@ void RALocal::AllocateBasicBlock(MachineBasicBlock &MBB) {
     // Determine whether this is a copy instruction.  The cases where the
     // source or destination are phys regs are handled specially.
     unsigned SrcCopyReg, DstCopyReg, SrcCopySubReg, DstCopySubReg;
+    unsigned SrcCopyPhysReg = 0U;
     bool isCopy = TII->isMoveInstr(*MI, SrcCopyReg, DstCopyReg, 
                                    SrcCopySubReg, DstCopySubReg);
+    if (isCopy && TargetRegisterInfo::isVirtualRegister(SrcCopyReg))
+      SrcCopyPhysReg = getVirt2PhysRegMapSlot(SrcCopyReg);
 
     // Loop over the implicit uses, making sure that they are at the head of the
     // use order list, so they don't get reallocated.
@@ -977,13 +980,24 @@ void RALocal::AllocateBasicBlock(MachineBasicBlock &MBB) {
 
         // If DestVirtReg already has a value, use it.
         if (!(DestPhysReg = getVirt2PhysRegMapSlot(DestVirtReg))) {
+          // If this is a copy try to reuse the input as the output;
+          // that will make the copy go away.
           // If this is a copy, the source reg is a phys reg, and
           // that reg is available, use that phys reg for DestPhysReg.
+          // If this is a copy, the source reg is a virtual reg, and
+          // the phys reg that was assigned to that virtual reg is now
+          // available, use that phys reg for DestPhysReg.  (If it's now
+          // available that means this was the last use of the source.)
           if (isCopy &&
               TargetRegisterInfo::isPhysicalRegister(SrcCopyReg) &&
               isPhysRegAvailable(SrcCopyReg)) {
             DestPhysReg = SrcCopyReg;
             assignVirtToPhysReg(DestVirtReg, DestPhysReg);
+          } else if (isCopy &&
+              TargetRegisterInfo::isVirtualRegister(SrcCopyReg) &&
+              SrcCopyPhysReg && isPhysRegAvailable(SrcCopyPhysReg)) {
+            DestPhysReg = SrcCopyPhysReg;
+            assignVirtToPhysReg(DestVirtReg, DestPhysReg);
           } else
             DestPhysReg = getReg(MBB, MI, DestVirtReg);
         }

diff --git a/test/CodeGen/PowerPC/2007-04-30-InlineAsmEarlyClobber.ll b/test/CodeGen/PowerPC/2007-04-30-InlineAsmEarlyClobber.ll
index c4ed1663a495bab92ec6ef50a597ecb584fd9723..d1d28ae15b0daaa633da1aa31904b8a52b4544fe 100644 (file)
--- a/test/CodeGen/PowerPC/2007-04-30-InlineAsmEarlyClobber.ll
+++ b/test/CodeGen/PowerPC/2007-04-30-InlineAsmEarlyClobber.ll
@@ -1,7 +1,7 @@
 ; RUN: llc < %s | grep {subfc r3,r5,r4}
 ; RUN: llc < %s | grep {subfze r4,r2}
-; RUN: llc < %s -regalloc=local | grep {subfc r5,r4,r3}
-; RUN: llc < %s -regalloc=local | grep {subfze r2,r2}
+; RUN: llc < %s -regalloc=local | grep {subfc r2,r5,r4}
+; RUN: llc < %s -regalloc=local | grep {subfze r3,r3}
 ; The first argument of subfc must not be the same as any other register.
 
 ; PR1357

diff --git a/test/CodeGen/X86/phys-reg-local-regalloc.ll b/test/CodeGen/X86/phys-reg-local-regalloc.ll
index e5e2d4bb230d5a03068bf1219d1f87fdbde70429..045841e7245b126c558c50a12e4c1880e2b76c9d 100644 (file)
--- a/test/CodeGen/X86/phys-reg-local-regalloc.ll
+++ b/test/CodeGen/X86/phys-reg-local-regalloc.ll
@@ -1,4 +1,6 @@
 ; RUN: llc < %s -march=x86 -mtriple=i386-apple-darwin9 -regalloc=local | FileCheck %s
+; RUN: llc -O0 < %s -march=x86 -mtriple=i386-apple-darwin9 -regalloc=local | FileCheck %s
+; CHECKed instructions should be the same with or without -O0.
 
 @.str = private constant [12 x i8] c"x + y = %i\0A\00", align 1 ; <[12 x i8]*> [#uses=1]