From 473c5111c36eefb30ab21b05f2549364a42e6528 Mon Sep 17 00:00:00 2001
From: Evan Cheng <evan.cheng@apple.com>
Date: Thu, 2 Aug 2007 05:48:35 +0000
Subject: [PATCH] Switch some multiplication instructions over to the new
 scheme for testing.

llvm-svn: 40723
---
 llvm/lib/Target/X86/X86ISelDAGToDAG.cpp | 53 ++++++++++++++++++++++---
 llvm/lib/Target/X86/X86InstrInfo.td     | 12 +++---
 2 files changed, 53 insertions(+), 12 deletions(-)

diff --git a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
index f166b9bc003e..059ed98d41cd 100644
--- a/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
+++ b/llvm/lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -1045,6 +1045,50 @@ SDNode *X86DAGToDAGISel::Select(SDOperand N) {
       break;
     }
 
+    case ISD::MUL: {
+      if (NVT == MVT::i8) {
+        SDOperand N0 = Node->getOperand(0);
+        SDOperand N1 = Node->getOperand(1);
+        SDOperand Tmp0, Tmp1, Tmp2, Tmp3;
+        bool foldedLoad = TryFoldLoad(N, N1, Tmp0, Tmp1, Tmp2, Tmp3);
+        if (!foldedLoad) {
+          foldedLoad = TryFoldLoad(N, N0, Tmp0, Tmp1, Tmp2, Tmp3);
+          if (foldedLoad)
+            std::swap(N0, N1);
+        }
+
+        SDNode *ResNode;
+        if (foldedLoad) {
+          SDOperand Chain = N1.getOperand(0);
+          AddToISelQueue(N0);
+          AddToISelQueue(Chain);
+          AddToISelQueue(Tmp0);
+          AddToISelQueue(Tmp1);
+          AddToISelQueue(Tmp2);
+          AddToISelQueue(Tmp3);
+          SDOperand InFlag(0, 0);
+          Chain = CurDAG->getCopyToReg(Chain, X86::AL, N0, InFlag);
+          InFlag = Chain.getValue(1);
+          SDOperand Ops[] = { Tmp0, Tmp1, Tmp2, Tmp3, Chain, InFlag };
+          ResNode = CurDAG->getTargetNode(X86::MUL8m, MVT::i8, MVT::i8,
+                                          MVT::Other, Ops, 6);
+          ReplaceUses(N1.getValue(1), SDOperand(ResNode, 2));
+        } else {
+          SDOperand Chain = CurDAG->getEntryNode();
+          AddToISelQueue(N0);
+          AddToISelQueue(N1);
+          SDOperand InFlag(0, 0);
+          InFlag = CurDAG->getCopyToReg(Chain, X86::AL, N0, InFlag).getValue(1);
+          ResNode = CurDAG->getTargetNode(X86::MUL8r, MVT::i8, MVT::i8,
+                                          N1, InFlag);
+        }
+
+        ReplaceUses(N.getValue(0), SDOperand(ResNode, 0));
+        return NULL;
+      }
+      break;
+    }
+
     case ISD::MULHU:
     case ISD::MULHS: {
       if (Opcode == ISD::MULHU)
@@ -1076,16 +1120,13 @@ SDNode *X86DAGToDAGISel::Select(SDOperand N) {
       SDOperand N0 = Node->getOperand(0);
       SDOperand N1 = Node->getOperand(1);
 
-      bool foldedLoad = false;
       SDOperand Tmp0, Tmp1, Tmp2, Tmp3;
-      foldedLoad = TryFoldLoad(N, N1, Tmp0, Tmp1, Tmp2, Tmp3);
+      bool foldedLoad = TryFoldLoad(N, N1, Tmp0, Tmp1, Tmp2, Tmp3);
       // MULHU and MULHS are commmutative
       if (!foldedLoad) {
         foldedLoad = TryFoldLoad(N, N0, Tmp0, Tmp1, Tmp2, Tmp3);
-        if (foldedLoad) {
-          N0 = Node->getOperand(1);
-          N1 = Node->getOperand(0);
-        }
+        if (foldedLoad)
+          std::swap(N0, N1);
       }
 
       SDOperand Chain;
diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td
index 190d5b1bcc0a..2597afc4cd64 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.td
+++ b/llvm/lib/Target/X86/X86InstrInfo.td
@@ -548,7 +548,7 @@ def MUL8r  : I<0xF6, MRM4r, (outs),  (ins GR8:$src), "mul{b}\t$src",
                // FIXME: Used for 8-bit mul, ignore result upper 8 bits.
                // This probably ought to be moved to a def : Pat<> if the
                // syntax can be accepted.
-               [(set AL, (mul AL, GR8:$src))]>,
+               []>,
              Imp<[AL],[AL,AH]>;               // AL,AH = AL*GR8
 def MUL16r : I<0xF7, MRM4r, (outs),  (ins GR16:$src), "mul{w}\t$src", []>,
              Imp<[AX],[AX,DX]>, OpSize;    // AX,DX = AX*GR16
@@ -559,22 +559,22 @@ def MUL8m  : I<0xF6, MRM4m, (outs), (ins i8mem :$src),
                // FIXME: Used for 8-bit mul, ignore result upper 8 bits.
                // This probably ought to be moved to a def : Pat<> if the
                // syntax can be accepted.
-               [(set AL, (mul AL, (loadi8 addr:$src)))]>,
-             Imp<[AL],[AX]>;          // AL,AH = AL*[mem8]
+               []>,
+             Imp<[AL],[AL,AH]>;          // AL,AH = AL*[mem8]
 def MUL16m : I<0xF7, MRM4m, (outs), (ins i16mem:$src),
                "mul{w}\t$src", []>, Imp<[AX],[AX,DX]>,
                OpSize; // AX,DX = AX*[mem16]
 def MUL32m : I<0xF7, MRM4m, (outs), (ins i32mem:$src),
-               "mul{l}\t$src", []>, Imp<[EAX],[EAX,EDX]>;// EAX,EDX = EAX*[mem32]
+              "mul{l}\t$src", []>, Imp<[EAX],[EAX,EDX]>;// EAX,EDX = EAX*[mem32]
 
 def IMUL8r  : I<0xF6, MRM5r, (outs),  (ins GR8:$src), "imul{b}\t$src", []>,
-              Imp<[AL],[AX]>;               // AL,AH = AL*GR8
+              Imp<[AL],[AL,AH]>;               // AL,AH = AL*GR8
 def IMUL16r : I<0xF7, MRM5r, (outs),  (ins GR16:$src), "imul{w}\t$src", []>,
               Imp<[AX],[AX,DX]>, OpSize;    // AX,DX = AX*GR16
 def IMUL32r : I<0xF7, MRM5r, (outs),  (ins GR32:$src), "imul{l}\t$src", []>,
               Imp<[EAX],[EAX,EDX]>;         // EAX,EDX = EAX*GR32
 def IMUL8m  : I<0xF6, MRM5m, (outs), (ins i8mem :$src),
-                "imul{b}\t$src", []>, Imp<[AL],[AX]>;        // AL,AH = AL*[mem8]
+                "imul{b}\t$src", []>, Imp<[AL],[AL,AH]>;    // AL,AH = AL*[mem8]
 def IMUL16m : I<0xF7, MRM5m, (outs), (ins i16mem:$src),
                 "imul{w}\t$src", []>, Imp<[AX],[AX,DX]>,
                 OpSize; // AX,DX = AX*[mem16]