RegisterCoalescer: Ignore interferences for constant physregs

When copying to/from a constant register interferences can be ignored.

Also update the documentation for isConstantPhysReg() to make it more
obvious that this transformation is valid.

Differential Revision: https://reviews.llvm.org/D26106

llvm-svn: 286503

4 files changed, 59 insertions, 26 deletions

diff --git a/llvm/include/llvm/CodeGen/MachineRegisterInfo.h b/llvm/include/llvm/CodeGen/MachineRegisterInfo.h
index 4b572791739..85336affedc 100644
--- a/llvm/include/llvm/CodeGen/MachineRegisterInfo.h
+++ b/llvm/include/llvm/CodeGen/MachineRegisterInfo.h
@@ -542,9 +542,8 @@ public:
   void dumpUses(unsigned RegNo) const;
 #endif
 
-  /// isConstantPhysReg - Returns true if PhysReg is unallocatable and constant
-  /// throughout the function.  It is safe to move instructions that read such
-  /// a physreg.
+  /// Returns true if PhysReg is unallocatable and constant throughout the
+  /// function. Writing to a constant register has no effect.
   bool isConstantPhysReg(unsigned PhysReg) const;
 
   /// Get an iterator over the pressure sets affected by the given physical or
diff --git a/llvm/lib/CodeGen/RegisterCoalescer.cpp b/llvm/lib/CodeGen/RegisterCoalescer.cpp
index 2c1a626af53..9705efccb6e 100644
--- a/llvm/lib/CodeGen/RegisterCoalescer.cpp
+++ b/llvm/lib/CodeGen/RegisterCoalescer.cpp
@@ -1570,11 +1570,13 @@ bool RegisterCoalescer::joinReservedPhysReg(CoalescerPair &CP) {
 
   // Deny any overlapping intervals.  This depends on all the reserved
   // register live ranges to look like dead defs.
-  for (MCRegUnitIterator UI(DstReg, TRI); UI.isValid(); ++UI)
-    if (RHS.overlaps(LIS->getRegUnit(*UI))) {
-      DEBUG(dbgs() << "\t\tInterference: " << PrintRegUnit(*UI, TRI) << '\n');
-      return false;
-    }
+  if (!MRI->isConstantPhysReg(DstReg)) {
+    for (MCRegUnitIterator UI(DstReg, TRI); UI.isValid(); ++UI)
+      if (RHS.overlaps(LIS->getRegUnit(*UI))) {
+        DEBUG(dbgs() << "\t\tInterference: " << PrintRegUnit(*UI, TRI) << '\n');
+        return false;
+      }
+  }
 
   // Skip any value computations, we are not adding new values to the
   // reserved register.  Also skip merging the live ranges, the reserved
@@ -1596,24 +1598,26 @@ bool RegisterCoalescer::joinReservedPhysReg(CoalescerPair &CP) {
     const SlotIndex CopyRegIdx = LIS->getInstructionIndex(*CopyMI).getRegSlot();
     const SlotIndex DestRegIdx = LIS->getInstructionIndex(*DestMI).getRegSlot();
 
-    // We checked above that there are no interfering defs of the physical
-    // register. However, for this case, where we intent to move up the def of
-    // the physical register, we also need to check for interfering uses.
-    SlotIndexes *Indexes = LIS->getSlotIndexes();
-    for (SlotIndex SI = Indexes->getNextNonNullIndex(DestRegIdx);
-         SI != CopyRegIdx; SI = Indexes->getNextNonNullIndex(SI)) {
-      MachineInstr *MI = LIS->getInstructionFromIndex(SI);
-      if (MI->readsRegister(DstReg, TRI)) {
-        DEBUG(dbgs() << "\t\tInterference (read): " << *MI);
-        return false;
-      }
-
-      // We must also check for clobbers caused by regmasks.
-      for (const auto &MO : MI->operands()) {
-        if (MO.isRegMask() && MO.clobbersPhysReg(DstReg)) {
-          DEBUG(dbgs() << "\t\tInterference (regmask clobber): " << *MI);
+    if (!MRI->isConstantPhysReg(DstReg)) {
+      // We checked above that there are no interfering defs of the physical
+      // register. However, for this case, where we intent to move up the def of
+      // the physical register, we also need to check for interfering uses.
+      SlotIndexes *Indexes = LIS->getSlotIndexes();
+      for (SlotIndex SI = Indexes->getNextNonNullIndex(DestRegIdx);
+           SI != CopyRegIdx; SI = Indexes->getNextNonNullIndex(SI)) {
+        MachineInstr *MI = LIS->getInstructionFromIndex(SI);
+        if (MI->readsRegister(DstReg, TRI)) {
+          DEBUG(dbgs() << "\t\tInterference (read): " << *MI);
           return false;
         }
+
+        // We must also check for clobbers caused by regmasks.
+        for (const auto &MO : MI->operands()) {
+          if (MO.isRegMask() && MO.clobbersPhysReg(DstReg)) {
+            DEBUG(dbgs() << "\t\tInterference (regmask clobber): " << *MI);
+            return false;
+          }
+        }
       }
     }
 
diff --git a/llvm/test/CodeGen/AArch64/machine_cse_impdef_killflags.ll b/llvm/test/CodeGen/AArch64/machine_cse_impdef_killflags.ll
index e77824f5f14..a3ee2b0069c 100644
--- a/llvm/test/CodeGen/AArch64/machine_cse_impdef_killflags.ll
+++ b/llvm/test/CodeGen/AArch64/machine_cse_impdef_killflags.ll
@@ -5,12 +5,11 @@
 ; The verifier would complain otherwise.
 define i64 @csed-impdef-killflag(i64 %a) {
 ; CHECK-LABEL: csed-impdef-killflag
-; CHECK-DAG:  mov    [[REG0:w[0-9]+]], wzr
 ; CHECK-DAG:  orr    [[REG1:w[0-9]+]], wzr, #0x1
 ; CHECK-DAG:  orr    [[REG2:x[0-9]+]], xzr, #0x2
 ; CHECK-DAG:  orr    [[REG3:x[0-9]+]], xzr, #0x3
 ; CHECK:      cmp    x0, #0
-; CHECK-DAG:  csel   w[[SELECT_WREG_1:[0-9]+]], [[REG0]], [[REG1]], ne
+; CHECK-DAG:  csel   w[[SELECT_WREG_1:[0-9]+]], wzr, [[REG1]], ne
 ; CHECK-DAG:  csel   [[SELECT_XREG_2:x[0-9]+]], [[REG2]], [[REG3]], ne
 ; CHECK:      ubfx   [[SELECT_XREG_1:x[0-9]+]], x[[SELECT_WREG_1]], #0, #32
 ; CHECK-NEXT: add    x0, [[SELECT_XREG_2]], [[SELECT_XREG_1]]
diff --git a/llvm/test/CodeGen/AArch64/regcoal-constreg.mir b/llvm/test/CodeGen/AArch64/regcoal-constreg.mir
new file mode 100644
index 00000000000..aa10c5808b8
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/regcoal-constreg.mir
@@ -0,0 +1,31 @@
+# RUN: llc -mtriple=aarch64-- -run-pass=simple-register-coalescing %s -o - | FileCheck %s
+--- |
+  define void @func() { ret void }
+...
+---
+# Check that we eliminate copies to/from constant physregs regardless of
+# "interfering" reads/writes.
+# CHECK: name: func
+# CHECK-NOT: COPY
+# CHECK: STRWui %wzr, %x1
+# CHECK-NOT: COPY
+# CHECK: STRXui %xzr, %x1
+# CHECK: %wzr = SUBSWri %w1, 0, 0
+name: func
+registers:
+  - { id: 0, class: gpr32 }
+  - { id: 1, class: gpr64 }
+  - { id: 2, class: gpr32 }
+body: |
+  bb.0:
+    %0 = COPY %wzr
+    dead %wzr = SUBSWri %w1, 0, 0, implicit-def %nzcv
+    STRWui %0, %x1, 0
+
+    %1 = COPY %xzr
+    dead %wzr = SUBSWri %w1, 0, 0, implicit-def %nzcv
+    STRXui %1, %x1, 0
+
+    %2 = SUBSWri %w1, 0, 0, implicit-def %nzcv
+    %wzr = COPY %2
+...