[SystemZ] Use BRCT and BRCTG to eliminate add-&-compare sequences

This patch just uses a peephole test for "add; compare; branch" sequences
within a single block.  The IR optimizers already convert loops to
decrement-and-branch-on-nonzero form in some cases, so even this
simplistic test triggers many times during a clang bootstrap and
projects/test-suite run.  It looks like there are still cases where we
need to more strongly prefer branches on nonzero though.  E.g. I saw a
case where a loop that started out with a check for 0 ended up with a
check for -1.  I'll try to look at that sometime.

I ended up adding the Reference class because MachineInstr::readsRegister()
doesn't check for subregisters (by design, as far as I could tell).

llvm-svn: 187723

1 files changed, 31 insertions, 0 deletions

diff --git a/llvm/lib/Target/SystemZ/SystemZLongBranch.cpp b/llvm/lib/Target/SystemZ/SystemZLongBranch.cpp
index c5c4cab6afd..114f74e14ac 100644
--- a/llvm/lib/Target/SystemZ/SystemZLongBranch.cpp
+++ b/llvm/lib/Target/SystemZ/SystemZLongBranch.cpp
@@ -148,6 +148,7 @@ namespace {
     bool mustRelaxBranch(const TerminatorInfo &Terminator, uint64_t Address);
     bool mustRelaxABranch();
     void setWorstCaseAddresses();
+    void splitBranchOnCount(MachineInstr *MI, unsigned AddOpcode);
     void splitCompareBranch(MachineInstr *MI, unsigned CompareOpcode);
     void relaxBranch(TerminatorInfo &Terminator);
     void relaxBranches();
@@ -218,6 +219,11 @@ TerminatorInfo SystemZLongBranch::describeTerminator(MachineInstr *MI) {
       // Relaxes to BRCL, which is 2 bytes longer.
       Terminator.ExtraRelaxSize = 2;
       break;
+    case SystemZ::BRCT:
+    case SystemZ::BRCTG:
+      // Relaxes to A(G)HI and BRCL, which is 6 bytes longer.
+      Terminator.ExtraRelaxSize = 6;
+      break;
     case SystemZ::CRJ:
       // Relaxes to a CR/BRCL sequence, which is 2 bytes longer.
       Terminator.ExtraRelaxSize = 2;
@@ -330,6 +336,25 @@ void SystemZLongBranch::setWorstCaseAddresses() {
   }
 }
 
+// Split BRANCH ON COUNT MI into the addition given by AddOpcode followed
+// by a BRCL on the result.
+void SystemZLongBranch::splitBranchOnCount(MachineInstr *MI,
+                                           unsigned AddOpcode) {
+  MachineBasicBlock *MBB = MI->getParent();
+  DebugLoc DL = MI->getDebugLoc();
+  BuildMI(*MBB, MI, DL, TII->get(AddOpcode))
+    .addOperand(MI->getOperand(0))
+    .addOperand(MI->getOperand(1))
+    .addImm(-1);
+  MachineInstr *BRCL = BuildMI(*MBB, MI, DL, TII->get(SystemZ::BRCL))
+    .addImm(SystemZ::CCMASK_ICMP)
+    .addImm(SystemZ::CCMASK_CMP_NE)
+    .addOperand(MI->getOperand(2));
+  // The implicit use of CC is a killing use.
+  BRCL->addRegisterKilled(SystemZ::CC, &TII->getRegisterInfo());
+  MI->eraseFromParent();
+}
+
 // Split MI into the comparison given by CompareOpcode followed
 // a BRCL on the result.
 void SystemZLongBranch::splitCompareBranch(MachineInstr *MI,
@@ -358,6 +383,12 @@ void SystemZLongBranch::relaxBranch(TerminatorInfo &Terminator) {
   case SystemZ::BRC:
     Branch->setDesc(TII->get(SystemZ::BRCL));
     break;
+  case SystemZ::BRCT:
+    splitBranchOnCount(Branch, SystemZ::AHI);
+    break;
+  case SystemZ::BRCTG:
+    splitBranchOnCount(Branch, SystemZ::AGHI);
+    break;
   case SystemZ::CRJ:
     splitCompareBranch(Branch, SystemZ::CR);
     break;