[PPC64LE] Remove implicit-subreg restriction from VSX swap removal

[oota-llvm.git] / lib / Target / PowerPC / PPCVSXSwapRemoval.cpp

diff --git a/lib/Target/PowerPC/PPCVSXSwapRemoval.cpp b/lib/Target/PowerPC/PPCVSXSwapRemoval.cpp
index 939293a5638e26d56706eafa2f6fd76e52688a3f..e7ab71ac2106076e44cbaf6dde7c7518ea552ced 100644 (file)
--- a/lib/Target/PowerPC/PPCVSXSwapRemoval.cpp
+++ b/lib/Target/PowerPC/PPCVSXSwapRemoval.cpp
@@ -79,7 +79,6 @@ struct PPCVSXSwapEntry {
   unsigned int IsStore : 1;
   unsigned int IsSwap : 1;
   unsigned int MentionsPhysVR : 1;
-  unsigned int HasImplicitSubreg : 1;
   unsigned int IsSwappable : 1;
   unsigned int SpecialHandling : 3;
   unsigned int WebRejected : 1;
@@ -224,7 +223,6 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
     for (MachineInstr &MI : MBB) {
 
       bool RelevantInstr = false;
-      bool ImplicitSubreg = false;
 
       for (const MachineOperand &MO : MI.operands()) {
         if (!MO.isReg())
@@ -232,8 +230,6 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
         unsigned Reg = MO.getReg();
         if (isVecReg(Reg)) {
           RelevantInstr = true;
-          if (MO.getSubReg() != 0)
-            ImplicitSubreg = true;
           break;
         }
       }
@@ -249,9 +245,6 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
       PPCVSXSwapEntry SwapEntry{};
       int VecIdx = addSwapEntry(&MI, SwapEntry);
 
-      if (ImplicitSubreg)
-        SwapVector[VecIdx].HasImplicitSubreg = 1;
-
       switch(MI.getOpcode()) {
       default:
         // Unless noted otherwise, an instruction is considered
@@ -260,7 +253,7 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
         // select, compare, etc.).
         SwapVector[VecIdx].IsSwappable = 1;
         break;
-      case PPC::XXPERMDI:
+      case PPC::XXPERMDI: {
         // This is a swap if it is of the form XXPERMDI t, s, s, 2.
         // Unfortunately, MachineCSE ignores COPY and SUBREG_TO_REG, so we
         // can also see XXPERMDI t, SUBREG_TO_REG(s), SUBREG_TO_REG(s), 2,
@@ -268,9 +261,8 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
         // SUBREG_TO_REG to find the real source value for comparison.
         // If the real source value is a physical register, then mark the
         // XXPERMDI as mentioning a physical register.
-        // Any other form of XXPERMDI is lane-sensitive and unsafe
-        // for the optimization.
-        if (MI.getOperand(3).getImm() == 2) {
+        int immed = MI.getOperand(3).getImm();
+        if (immed == 2) {
           unsigned trueReg1 = lookThruCopyLike(MI.getOperand(1).getReg(),
                                                VecIdx);
           unsigned trueReg2 = lookThruCopyLike(MI.getOperand(2).getReg(),
@@ -278,7 +270,26 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
           if (trueReg1 == trueReg2)
             SwapVector[VecIdx].IsSwap = 1;
         }
+        // This is a doubleword splat if it is of the form
+        // XXPERMDI t, s, s, 0 or XXPERMDI t, s, s, 3.  As above we
+        // must look through chains of copy-likes to find the source
+        // register.  We turn off the marking for mention of a physical
+        // register, because splatting it is safe; the optimization
+        // will not swap the value in the physical register.
+        else if (immed == 0 || immed == 3) {
+          unsigned trueReg1 = lookThruCopyLike(MI.getOperand(1).getReg(),
+                                               VecIdx);
+          unsigned trueReg2 = lookThruCopyLike(MI.getOperand(2).getReg(),
+                                               VecIdx);
+          if (trueReg1 == trueReg2) {
+            SwapVector[VecIdx].IsSwappable = 1;
+            SwapVector[VecIdx].MentionsPhysVR = 0;
+          }
+        }
+        // Any other form of XXPERMDI is lane-sensitive and unsafe
+        // for the optimization.
         break;
+      }
       case PPC::LVX:
         // Non-permuting loads are currently unsafe.  We can use special
         // handling for this in the future.  By not marking these as
@@ -307,14 +318,6 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
         SwapVector[VecIdx].IsStore = 1;
         SwapVector[VecIdx].IsSwap = 1;
         break;
-      case PPC::SUBREG_TO_REG:
-        // These are fine provided they are moving between full vector
-        // register classes.  For example, the VRs are a subset of the
-        // VSRs, but each VR and each VSR is a full 128-bit register.
-        if (isVecReg(MI.getOperand(0).getReg()) &&
-            isVecReg(MI.getOperand(2).getReg()))
-          SwapVector[VecIdx].IsSwappable = 1;
-        break;
       case PPC::COPY:
         // These are fine provided they are moving between full vector
         // register classes.
@@ -349,7 +352,6 @@ bool PPCVSXSwapRemoval::gatherVectorInstructions() {
       case PPC::LVSL:
       case PPC::LVSR:
       case PPC::LVXL:
-      case PPC::LXVDSX:
       case PPC::STVEBX:
       case PPC::STVEHX:
       case PPC::STVEWX:
@@ -457,23 +459,19 @@ int PPCVSXSwapRemoval::addSwapEntry(MachineInstr *MI,
 // such operations to the ultimate source register.  If a
 // physical register is encountered, we stop the search and
 // flag the swap entry indicated by VecIdx (the original
-// XXPERMDI) as mentioning a physical register.  Similarly
-// for implicit subregister mentions (which should never
-// happen).
+// XXPERMDI) as mentioning a physical register.
 unsigned PPCVSXSwapRemoval::lookThruCopyLike(unsigned SrcReg,
                                              unsigned VecIdx) {
   MachineInstr *MI = MRI->getVRegDef(SrcReg);
   if (!MI->isCopyLike())
     return SrcReg;
 
-  unsigned CopySrcReg, CopySrcSubreg;
-  if (MI->isCopy()) {
+  unsigned CopySrcReg;
+  if (MI->isCopy())
     CopySrcReg = MI->getOperand(1).getReg();
-    CopySrcSubreg = MI->getOperand(1).getSubReg();
-  } else {
+  else {
     assert(MI->isSubregToReg() && "bad opcode for lookThruCopyLike");
     CopySrcReg = MI->getOperand(2).getReg();
-    CopySrcSubreg = MI->getOperand(2).getSubReg();
   }
 
   if (!TargetRegisterInfo::isVirtualRegister(CopySrcReg)) {
@@ -481,11 +479,6 @@ unsigned PPCVSXSwapRemoval::lookThruCopyLike(unsigned SrcReg,
     return CopySrcReg;
   }
 
-  if (CopySrcSubreg != 0) {
-    SwapVector[VecIdx].HasImplicitSubreg = 1;
-    return CopySrcReg;
-  }
-
   return lookThruCopyLike(CopySrcReg, VecIdx);
 }
 
@@ -552,11 +545,9 @@ void PPCVSXSwapRemoval::recordUnoptimizableWebs() {
   for (unsigned EntryIdx = 0; EntryIdx < SwapVector.size(); ++EntryIdx) {
     int Repr = EC->getLeaderValue(SwapVector[EntryIdx].VSEId);
 
-    // Reject webs containing mentions of physical registers or implicit
-    // subregs, or containing operations that we don't know how to handle
-    // in a lane-permuted region.
+    // Reject webs containing mentions of physical registers, or containing
+    // operations that we don't know how to handle in a lane-permuted region.
     if (SwapVector[EntryIdx].MentionsPhysVR ||
-        SwapVector[EntryIdx].HasImplicitSubreg ||
         !(SwapVector[EntryIdx].IsSwappable || SwapVector[EntryIdx].IsSwap)) {
 
       SwapVector[Repr].WebRejected = 1;
@@ -765,8 +756,6 @@ void PPCVSXSwapRemoval::dumpSwapVector() {
       DEBUG(dbgs() << "swap ");
     if (SwapVector[EntryIdx].MentionsPhysVR)
       DEBUG(dbgs() << "physreg ");
-    if (SwapVector[EntryIdx].HasImplicitSubreg)
-      DEBUG(dbgs() << "implsubreg ");
 
     if (SwapVector[EntryIdx].IsSwappable) {
       DEBUG(dbgs() << "swappable ");
@@ -809,7 +798,7 @@ void PPCVSXSwapRemoval::dumpSwapVector() {
   DEBUG(dbgs() << "\n");
 }
 
-} // namespace
+} // end default namespace
 
 INITIALIZE_PASS_BEGIN(PPCVSXSwapRemoval, DEBUG_TYPE,
                       "PowerPC VSX Swap Removal", false, false)