Recognize inline asm 'rev /bin/bash, ' as a bswap intrinsic call.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@123048 91177308-0d34-0410-b5e6-96231b3b80d8

8 files changed, 117 insertions, 55 deletions

diff --git a/include/llvm/CodeGen/IntrinsicLowering.h b/include/llvm/CodeGen/IntrinsicLowering.h
index eefbc45cb2..767b666225 100644
--- a/include/llvm/CodeGen/IntrinsicLowering.h
+++ b/include/llvm/CodeGen/IntrinsicLowering.h
@@ -48,6 +48,11 @@ namespace llvm {
     /// be capable of handling this kind of change.
     ///
     void LowerIntrinsicCall(CallInst *CI);
+
+    /// LowerToByteSwap - Replace a call instruction into a call to bswap
+    /// intrinsic. Return false if it has determined the call is not a
+    /// simple integer bswap.
+    static bool LowerToByteSwap(CallInst *CI);
   };
 }
 
diff --git a/lib/CodeGen/IntrinsicLowering.cpp b/lib/CodeGen/IntrinsicLowering.cpp
index 47625110ff..3861ddadf6 100644
--- a/lib/CodeGen/IntrinsicLowering.cpp
+++ b/lib/CodeGen/IntrinsicLowering.cpp
@@ -538,3 +538,27 @@ void IntrinsicLowering::LowerIntrinsicCall(CallInst *CI) {
          "Lowering should have eliminated any uses of the intrinsic call!");
   CI->eraseFromParent();
 }
+
+bool IntrinsicLowering::LowerToByteSwap(CallInst *CI) {
+  // Verify this is a simple bswap.
+  if (CI->getNumArgOperands() != 1 ||
+      CI->getType() != CI->getArgOperand(0)->getType() ||
+      !CI->getType()->isIntegerTy())
+    return false;
+
+  const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
+  if (!Ty)
+    return false;
+
+  // Okay, we can do this xform, do so now.
+  const Type *Tys[] = { Ty };
+  Module *M = CI->getParent()->getParent()->getParent();
+  Constant *Int = Intrinsic::getDeclaration(M, Intrinsic::bswap, Tys, 1);
+
+  Value *Op = CI->getArgOperand(0);
+  Op = CallInst::Create(Int, Op, CI->getName(), CI);
+
+  CI->replaceAllUsesWith(Op);
+  CI->eraseFromParent();
+  return true;
+}
diff --git a/lib/Target/ARM/ARMBaseInstrInfo.cpp b/lib/Target/ARM/ARMBaseInstrInfo.cpp
index fd13485d1f..046ba8ea40 100644
--- a/lib/Target/ARM/ARMBaseInstrInfo.cpp
+++ b/lib/Target/ARM/ARMBaseInstrInfo.cpp
@@ -2071,7 +2071,6 @@ ARMBaseInstrInfo::getOperandLatency(const InstrItineraryData *ItinData,
   if (!ItinData || ItinData->isEmpty())
     return DefTID.mayLoad() ? 3 : 1;
 
-
   const TargetInstrDesc &UseTID = UseMI->getDesc();
   const MachineOperand &DefMO = DefMI->getOperand(DefIdx);
   if (DefMO.getReg() == ARM::CPSR) {
diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index 9ecc871491..21f7b51cd2 100644
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -33,6 +33,7 @@
 #include "llvm/Intrinsics.h"
 #include "llvm/Type.h"
 #include "llvm/CodeGen/CallingConvLower.h"
+#include "llvm/CodeGen/IntrinsicLowering.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
@@ -43,6 +44,7 @@
 #include "llvm/MC/MCSectionMachO.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/ADT/VectorExtras.h"
+#include "llvm/ADT/StringExtras.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/ErrorHandling.h"
@@ -6092,6 +6094,37 @@ void ARMTargetLowering::computeMaskedBitsForTargetNode(const SDValue Op,
 //                           ARM Inline Assembly Support
 //===----------------------------------------------------------------------===//
 
+bool ARMTargetLowering::ExpandInlineAsm(CallInst *CI) const {
+  // Looking for "rev" which is V6+.
+  if (!Subtarget->hasV6Ops())
+    return false;
+
+  InlineAsm *IA = cast<InlineAsm>(CI->getCalledValue());
+  std::string AsmStr = IA->getAsmString();
+  SmallVector<StringRef, 4> AsmPieces;
+  SplitString(AsmStr, AsmPieces, ";\n");
+
+  switch (AsmPieces.size()) {
+  default: return false;
+  case 1:
+    AsmStr = AsmPieces[0];
+    AsmPieces.clear();
+    SplitString(AsmStr, AsmPieces, " \t,");
+
+    // rev $0, $1
+    if (AsmPieces.size() == 3 &&
+        AsmPieces[0] == "rev" && AsmPieces[1] == "$0" && AsmPieces[2] == "$1" &&
+        IA->getConstraintString().compare(0, 4, "=l,l") == 0) {
+      const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
+      if (Ty && Ty->getBitWidth() == 32)
+        return IntrinsicLowering::LowerToByteSwap(CI);
+    }
+    break;
+  }
+
+  return false;
+}
+
 /// getConstraintType - Given a constraint letter, return the type of
 /// constraint it is for this target.
 ARMTargetLowering::ConstraintType
diff --git a/lib/Target/ARM/ARMISelLowering.h b/lib/Target/ARM/ARMISelLowering.h
index b25cb96d3e..db31e49446 100644
--- a/lib/Target/ARM/ARMISelLowering.h
+++ b/lib/Target/ARM/ARMISelLowering.h
@@ -257,6 +257,8 @@ namespace llvm {
                                                 unsigned Depth) const;
 
 
+    virtual bool ExpandInlineAsm(CallInst *CI) const;
+
     ConstraintType getConstraintType(const std::string &Constraint) const;
 
     /// Examine constraint string and operand type and determine a weight value.
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index f871b5a770..99ada9826c 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -28,6 +28,7 @@
 #include "llvm/Instructions.h"
 #include "llvm/Intrinsics.h"
 #include "llvm/LLVMContext.h"
+#include "llvm/CodeGen/IntrinsicLowering.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
@@ -11729,38 +11730,8 @@ bool X86TargetLowering::IsDesirableToPromoteOp(SDValue Op, EVT &PVT) const {
 //                           X86 Inline Assembly Support
 //===----------------------------------------------------------------------===//
 
-static bool LowerToBSwap(CallInst *CI) {
-  // FIXME: this should verify that we are targetting a 486 or better.  If not,
-  // we will turn this bswap into something that will be lowered to logical ops
-  // instead of emitting the bswap asm.  For now, we don't support 486 or lower
-  // so don't worry about this.
-
-  // Verify this is a simple bswap.
-  if (CI->getNumArgOperands() != 1 ||
-      CI->getType() != CI->getArgOperand(0)->getType() ||
-      !CI->getType()->isIntegerTy())
-    return false;
-
-  const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
-  if (!Ty || Ty->getBitWidth() % 16 != 0)
-    return false;
-
-  // Okay, we can do this xform, do so now.
-  const Type *Tys[] = { Ty };
-  Module *M = CI->getParent()->getParent()->getParent();
-  Constant *Int = Intrinsic::getDeclaration(M, Intrinsic::bswap, Tys, 1);
-
-  Value *Op = CI->getArgOperand(0);
-  Op = CallInst::Create(Int, Op, CI->getName(), CI);
-
-  CI->replaceAllUsesWith(Op);
-  CI->eraseFromParent();
-  return true;
-}
-
 bool X86TargetLowering::ExpandInlineAsm(CallInst *CI) const {
   InlineAsm *IA = cast<InlineAsm>(CI->getCalledValue());
-  InlineAsm::ConstraintInfoVector Constraints = IA->ParseConstraints();
 
   std::string AsmStr = IA->getAsmString();
 
@@ -11775,6 +11746,10 @@ bool X86TargetLowering::ExpandInlineAsm(CallInst *CI) const {
     AsmPieces.clear();
     SplitString(AsmStr, AsmPieces, " \t");  // Split with whitespace.
 
+    // FIXME: this should verify that we are targetting a 486 or better.  If not,
+    // we will turn this bswap into something that will be lowered to logical ops
+    // instead of emitting the bswap asm.  For now, we don't support 486 or lower
+    // so don't worry about this.
     // bswap $0
     if (AsmPieces.size() == 2 &&
         (AsmPieces[0] == "bswap" ||
@@ -11784,7 +11759,10 @@ bool X86TargetLowering::ExpandInlineAsm(CallInst *CI) const {
          AsmPieces[1] == "${0:q}")) {
       // No need to check constraints, nothing other than the equivalent of
       // "=r,0" would be valid here.
-      return LowerToBSwap(CI);
+      const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
+      if (!Ty || Ty->getBitWidth() % 16 != 0)
+        return false;
+      return IntrinsicLowering::LowerToByteSwap(CI);
     }
     // rorw $$8, ${0:w}  -->  llvm.bswap.i16
     if (CI->getType()->isIntegerTy(16) &&
@@ -11794,15 +11772,18 @@ bool X86TargetLowering::ExpandInlineAsm(CallInst *CI) const {
         AsmPieces[2] == "${0:w}" &&
         IA->getConstraintString().compare(0, 5, "=r,0,") == 0) {
       AsmPieces.clear();
-      const std::string &Constraints = IA->getConstraintString();
-      SplitString(StringRef(Constraints).substr(5), AsmPieces, ",");
+      const std::string &ConstraintsStr = IA->getConstraintString();
+      SplitString(StringRef(ConstraintsStr).substr(5), AsmPieces, ",");
       std::sort(AsmPieces.begin(), AsmPieces.end());
       if (AsmPieces.size() == 4 &&
           AsmPieces[0] == "~{cc}" &&
           AsmPieces[1] == "~{dirflag}" &&
           AsmPieces[2] == "~{flags}" &&
           AsmPieces[3] == "~{fpsr}") {
-        return LowerToBSwap(CI);
+        const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
+        if (!Ty || Ty->getBitWidth() % 16 != 0)
+          return false;
+        return IntrinsicLowering::LowerToByteSwap(CI);
       }
     }
     break;
@@ -11822,36 +11803,45 @@ bool X86TargetLowering::ExpandInlineAsm(CallInst *CI) const {
           if (Words.size() == 3 && Words[0] == "rorw" && Words[1] == "$$8" &&
               Words[2] == "${0:w}") {
             AsmPieces.clear();
-            const std::string &Constraints = IA->getConstraintString();
-            SplitString(StringRef(Constraints).substr(5), AsmPieces, ",");
+            const std::string &ConstraintsStr = IA->getConstraintString();
+            SplitString(StringRef(ConstraintsStr).substr(5), AsmPieces, ",");
             std::sort(AsmPieces.begin(), AsmPieces.end());
             if (AsmPieces.size() == 4 &&
                 AsmPieces[0] == "~{cc}" &&
                 AsmPieces[1] == "~{dirflag}" &&
                 AsmPieces[2] == "~{flags}" &&
                 AsmPieces[3] == "~{fpsr}") {
-              return LowerToBSwap(CI);
+              const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
+              if (!Ty || Ty->getBitWidth() % 16 != 0)
+                return false;
+              return IntrinsicLowering::LowerToByteSwap(CI);
             }
           }
         }
       }
     }
-    if (CI->getType()->isIntegerTy(64) &&
-        Constraints.size() >= 2 &&
-        Constraints[0].Codes.size() == 1 && Constraints[0].Codes[0] == "A" &&
-        Constraints[1].Codes.size() == 1 && Constraints[1].Codes[0] == "0") {
-      // bswap %eax / bswap %edx / xchgl %eax, %edx  -> llvm.bswap.i64
-      SmallVector<StringRef, 4> Words;
-      SplitString(AsmPieces[0], Words, " \t");
-      if (Words.size() == 2 && Words[0] == "bswap" && Words[1] == "%eax") {
-        Words.clear();
-        SplitString(AsmPieces[1], Words, " \t");
-        if (Words.size() == 2 && Words[0] == "bswap" && Words[1] == "%edx") {
+
+    if (CI->getType()->isIntegerTy(64)) {
+      InlineAsm::ConstraintInfoVector Constraints = IA->ParseConstraints();
+      if (Constraints.size() >= 2 &&
+          Constraints[0].Codes.size() == 1 && Constraints[0].Codes[0] == "A" &&
+          Constraints[1].Codes.size() == 1 && Constraints[1].Codes[0] == "0") {
+        // bswap %eax / bswap %edx / xchgl %eax, %edx  -> llvm.bswap.i64
+        SmallVector<StringRef, 4> Words;
+        SplitString(AsmPieces[0], Words, " \t");
+        if (Words.size() == 2 && Words[0] == "bswap" && Words[1] == "%eax") {
           Words.clear();
-          SplitString(AsmPieces[2], Words, " \t,");
-          if (Words.size() == 3 && Words[0] == "xchgl" && Words[1] == "%eax" &&
-              Words[2] == "%edx") {
-            return LowerToBSwap(CI);
+          SplitString(AsmPieces[1], Words, " \t");
+          if (Words.size() == 2 && Words[0] == "bswap" && Words[1] == "%edx") {
+            Words.clear();
+            SplitString(AsmPieces[2], Words, " \t,");
+            if (Words.size() == 3 && Words[0] == "xchgl" && Words[1] == "%eax" &&
+                Words[2] == "%edx") {
+              const IntegerType *Ty = dyn_cast<IntegerType>(CI->getType());
+              if (!Ty || Ty->getBitWidth() % 16 != 0)
+                return false;
+              return IntrinsicLowering::LowerToByteSwap(CI);
+            }
           }
         }
       }
diff --git a/test/CodeGen/ARM/bswap-inline-asm.ll b/test/CodeGen/ARM/bswap-inline-asm.ll
new file mode 100644
index 0000000000..472213d5f8
--- /dev/null
+++ b/test/CodeGen/ARM/bswap-inline-asm.ll
@@ -0,0 +1,9 @@
+; RUN: llc < %s -mtriple=arm-apple-darwin -mattr=+v6 | FileCheck %s
+
+define i32 @t1(i32 %x) nounwind {
+; CHECK: t1:
+; CHECK-NOT: InlineAsm
+; CHECK: rev
+  %asmtmp = tail call i32 asm "rev $0, $1\0A", "=l,l"(i32 %x) nounwind
+  ret i32 %asmtmp
+}
diff --git a/test/CodeGen/X86/bswap-inline-asm.ll b/test/CodeGen/X86/bswap-inline-asm.ll
index ecb4cecf10..3bb9124633 100644
--- a/test/CodeGen/X86/bswap-inline-asm.ll
+++ b/test/CodeGen/X86/bswap-inline-asm.ll
@@ -1,5 +1,5 @@
-; RUN: llc < %s -march=x86-64 > %t
-; RUN: not grep APP %t
+; RUN: llc < %s -mtriple=x86_64-apple-darwin > %t
+; RUN: not grep InlineAsm %t
 ; RUN: FileCheck %s < %t
 
 ; CHECK: foo: