[x86][FastISel] Teach how to select nontemporal stores.

[oota-llvm.git] / lib / Target / X86 / X86MCInstLower.cpp

diff --git a/lib/Target/X86/X86MCInstLower.cpp b/lib/Target/X86/X86MCInstLower.cpp
index c61dc125ebc89b91eb4ce04baa5d71320d114baa..a59ddb7e995f83f0a350d8cd49473d3e6bb64329 100644 (file)
--- a/lib/Target/X86/X86MCInstLower.cpp
+++ b/lib/Target/X86/X86MCInstLower.cpp
@@ -460,6 +460,7 @@ ReSimplify:
 
   // Commute operands to get a smaller encoding by using VEX.R instead of VEX.B
   // if one of the registers is extended, but other isn't.
+  case X86::VMOVZPQILo2PQIrr:
   case X86::VMOVAPDrr:
   case X86::VMOVAPDYrr:
   case X86::VMOVAPSrr:
@@ -477,18 +478,19 @@ ReSimplify:
       unsigned NewOpc;
       switch (OutMI.getOpcode()) {
       default: llvm_unreachable("Invalid opcode");
-      case X86::VMOVAPDrr:  NewOpc = X86::VMOVAPDrr_REV;  break;
-      case X86::VMOVAPDYrr: NewOpc = X86::VMOVAPDYrr_REV; break;
-      case X86::VMOVAPSrr:  NewOpc = X86::VMOVAPSrr_REV;  break;
-      case X86::VMOVAPSYrr: NewOpc = X86::VMOVAPSYrr_REV; break;
-      case X86::VMOVDQArr:  NewOpc = X86::VMOVDQArr_REV;  break;
-      case X86::VMOVDQAYrr: NewOpc = X86::VMOVDQAYrr_REV; break;
-      case X86::VMOVDQUrr:  NewOpc = X86::VMOVDQUrr_REV;  break;
-      case X86::VMOVDQUYrr: NewOpc = X86::VMOVDQUYrr_REV; break;
-      case X86::VMOVUPDrr:  NewOpc = X86::VMOVUPDrr_REV;  break;
-      case X86::VMOVUPDYrr: NewOpc = X86::VMOVUPDYrr_REV; break;
-      case X86::VMOVUPSrr:  NewOpc = X86::VMOVUPSrr_REV;  break;
-      case X86::VMOVUPSYrr: NewOpc = X86::VMOVUPSYrr_REV; break;
+      case X86::VMOVZPQILo2PQIrr: NewOpc = X86::VMOVPQI2QIrr;   break;
+      case X86::VMOVAPDrr:        NewOpc = X86::VMOVAPDrr_REV;  break;
+      case X86::VMOVAPDYrr:       NewOpc = X86::VMOVAPDYrr_REV; break;
+      case X86::VMOVAPSrr:        NewOpc = X86::VMOVAPSrr_REV;  break;
+      case X86::VMOVAPSYrr:       NewOpc = X86::VMOVAPSYrr_REV; break;
+      case X86::VMOVDQArr:        NewOpc = X86::VMOVDQArr_REV;  break;
+      case X86::VMOVDQAYrr:       NewOpc = X86::VMOVDQAYrr_REV; break;
+      case X86::VMOVDQUrr:        NewOpc = X86::VMOVDQUrr_REV;  break;
+      case X86::VMOVDQUYrr:       NewOpc = X86::VMOVDQUYrr_REV; break;
+      case X86::VMOVUPDrr:        NewOpc = X86::VMOVUPDrr_REV;  break;
+      case X86::VMOVUPDYrr:       NewOpc = X86::VMOVUPDYrr_REV; break;
+      case X86::VMOVUPSrr:        NewOpc = X86::VMOVUPSrr_REV;  break;
+      case X86::VMOVUPSYrr:       NewOpc = X86::VMOVUPSYrr_REV; break;
       }
       OutMI.setOpcode(NewOpc);
     }
@@ -531,6 +533,23 @@ ReSimplify:
     break;
   }
 
+  case X86::CLEANUPRET: {
+    // Replace CATCHRET with the appropriate RET.
+    OutMI = MCInst();
+    OutMI.setOpcode(getRetOpcode(AsmPrinter.getSubtarget()));
+    break;
+  }
+
+  case X86::CATCHRET: {
+    // Replace CATCHRET with the appropriate RET.
+    const X86Subtarget &Subtarget = AsmPrinter.getSubtarget();
+    unsigned ReturnReg = Subtarget.is64Bit() ? X86::RAX : X86::EAX;
+    OutMI = MCInst();
+    OutMI.setOpcode(getRetOpcode(Subtarget));
+    OutMI.addOperand(MCOperand::createReg(ReturnReg));
+    break;
+  }
+
   // TAILJMPd, TAILJMPd64 - Lower to the correct jump instructions.
   case X86::TAILJMPr:
   case X86::TAILJMPd:
@@ -1076,6 +1095,18 @@ void X86AsmPrinter::EmitInstruction(const MachineInstr *MI) {
                             X86ATTInstPrinter::getRegisterName(Reg));
     break;
   }
+  case X86::CLEANUPRET: {
+    // Lower these as normal, but add some comments.
+    OutStreamer->AddComment("CLEANUPRET");
+    break;
+  }
+
+  case X86::CATCHRET: {
+    // Lower these as normal, but add some comments.
+    OutStreamer->AddComment("CATCHRET");
+    break;
+  }
+
   case X86::TAILJMPr:
   case X86::TAILJMPm:
   case X86::TAILJMPd: