Add X86 code emitter support AVX encoded MRMDestReg instructions.

Previously we weren't skipping the VVVV encoded register. Based on patch by Michael Liao.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177221 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 63 insertions, 32 deletions

diff --git a/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp b/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
index 30c56061b9..5fbefaec5e 100644
--- a/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
+++ b/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp
@@ -674,9 +674,15 @@ void X86MCCodeEmitter::EmitVEXOpcodePrefix(uint64_t TSFlags, unsigned &CurByte,
     // MRMDestReg instructions forms:
     //  dst(ModR/M), src(ModR/M)
     //  dst(ModR/M), src(ModR/M), imm8
-    if (X86II::isX86_64ExtendedReg(MI.getOperand(0).getReg()))
+    //  dst(ModR/M), src1(VEX_4V), src2(ModR/M)
+    if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
       VEX_B = 0x0;
-    if (X86II::isX86_64ExtendedReg(MI.getOperand(1).getReg()))
+    CurOp++;
+
+    if (HasVEX_4V)
+      VEX_4V = getVEXRegisterEncoding(MI, CurOp++);
+
+    if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
       VEX_R = 0x0;
     break;
   case X86II::MRM0r: case X86II::MRM1r:
@@ -1046,9 +1052,14 @@ EncodeInstruction(const MCInst &MI, raw_ostream &OS,
 
   case X86II::MRMDestReg:
     EmitByte(BaseOpcode, CurByte, OS);
+    SrcRegNum = CurOp + 1;
+
+    if (HasVEX_4V) // Skip 1st src (which is encoded in VEX_VVVV)
+      ++SrcRegNum;
+
     EmitRegModRMByte(MI.getOperand(CurOp),
-                     GetX86RegNum(MI.getOperand(CurOp+1)), CurByte, OS);
-    CurOp += 2;
+                     GetX86RegNum(MI.getOperand(SrcRegNum)), CurByte, OS);
+    CurOp = SrcRegNum + 1;
     break;
 
   case X86II::MRMDestMem:
diff --git a/lib/Target/X86/X86CodeEmitter.cpp b/lib/Target/X86/X86CodeEmitter.cpp
index 5d9dfa99e4..2518e02e2a 100644
--- a/lib/Target/X86/X86CodeEmitter.cpp
+++ b/lib/Target/X86/X86CodeEmitter.cpp
@@ -1047,9 +1047,15 @@ void Emitter<CodeEmitter>::emitVEXOpcodePrefix(uint64_t TSFlags,
       // MRMDestReg instructions forms:
       //  dst(ModR/M), src(ModR/M)
       //  dst(ModR/M), src(ModR/M), imm8
-      if (X86II::isX86_64ExtendedReg(MI.getOperand(0).getReg()))
+      //  dst(ModR/M), src1(VEX_4V), src2(ModR/M)
+      if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
         VEX_B = 0x0;
-      if (X86II::isX86_64ExtendedReg(MI.getOperand(1).getReg()))
+      CurOp++;
+
+      if (HasVEX_4V)
+        VEX_4V = getVEXRegisterEncoding(MI, CurOp++);
+
+      if (X86II::isX86_64ExtendedReg(MI.getOperand(CurOp).getReg()))
         VEX_R = 0x0;
       break;
     case X86II::MRM0r: case X86II::MRM1r:
@@ -1284,9 +1290,14 @@ void Emitter<CodeEmitter>::emitInstruction(MachineInstr &MI,
 
   case X86II::MRMDestReg: {
     MCE.emitByte(BaseOpcode);
+
+    unsigned SrcRegNum = CurOp+1;
+    if (HasVEX_4V) // Skip 1st src (which is encoded in VEX_VVVV)
+      SrcRegNum++;
+
     emitRegModRMByte(MI.getOperand(CurOp).getReg(),
-                     getX86RegNum(MI.getOperand(CurOp+1).getReg()));
-    CurOp += 2;
+                     getX86RegNum(MI.getOperand(SrcRegNum).getReg()));
+    CurOp = SrcRegNum + 1;
     break;
   }
   case X86II::MRMDestMem: {
diff --git a/lib/Target/X86/X86MCInstLower.cpp b/lib/Target/X86/X86MCInstLower.cpp
index 1e8347dfe4..a8a9fd8acc 100644
--- a/lib/Target/X86/X86MCInstLower.cpp
+++ b/lib/Target/X86/X86MCInstLower.cpp
@@ -417,35 +417,44 @@ ReSimplify:
   case X86::VMOVDQAYrr:
   case X86::VMOVDQUrr:
   case X86::VMOVDQUYrr:
-  case X86::VMOVSDrr:
-  case X86::VMOVSSrr:
   case X86::VMOVUPDrr:
   case X86::VMOVUPDYrr:
   case X86::VMOVUPSrr:
   case X86::VMOVUPSYrr: {
-    if (X86II::isX86_64ExtendedReg(OutMI.getOperand(0).getReg()) &&
-        !X86II::isX86_64ExtendedReg(OutMI.getOperand(1).getReg()))
-      break;
-
-    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::VMOVSDrr:   NewOpc = X86::VMOVSDrr_REV;   break;
-    case X86::VMOVSSrr:   NewOpc = X86::VMOVSSrr_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;
+    if (!X86II::isX86_64ExtendedReg(OutMI.getOperand(0).getReg()) &&
+        X86II::isX86_64ExtendedReg(OutMI.getOperand(1).getReg())) {
+      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;
+      }
+      OutMI.setOpcode(NewOpc);
+    }
+    break;
+  }
+  case X86::VMOVSDrr:
+  case X86::VMOVSSrr: {
+    if (!X86II::isX86_64ExtendedReg(OutMI.getOperand(0).getReg()) &&
+        X86II::isX86_64ExtendedReg(OutMI.getOperand(2).getReg())) {
+      unsigned NewOpc;
+      switch (OutMI.getOpcode()) {
+      default: llvm_unreachable("Invalid opcode");
+      case X86::VMOVSDrr:   NewOpc = X86::VMOVSDrr_REV;   break;
+      case X86::VMOVSSrr:   NewOpc = X86::VMOVSSrr_REV;   break;
+      }
+      OutMI.setOpcode(NewOpc);
     }
-    OutMI.setOpcode(NewOpc);
     break;
   }