11 files changed, 18 insertions, 12 deletions
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index a1519de25ee..e1744d1f296 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -186,8 +186,8 @@ unsigned TargetTransformInfo::getRegisterBitWidth(bool Vector) const {
   return TTIImpl->getRegisterBitWidth(Vector);
 }
 
-unsigned TargetTransformInfo::getMaxInterleaveFactor() const {
-  return TTIImpl->getMaxInterleaveFactor();
+unsigned TargetTransformInfo::getMaxInterleaveFactor(unsigned VF) const {
+  return TTIImpl->getMaxInterleaveFactor(VF);
 }
 
 unsigned TargetTransformInfo::getArithmeticInstrCost(
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 0533355b01d..ed27cf84bbb 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -419,7 +419,7 @@ unsigned AArch64TTIImpl::getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys) {
   return Cost;
 }
 
-unsigned AArch64TTIImpl::getMaxInterleaveFactor() {
+unsigned AArch64TTIImpl::getMaxInterleaveFactor(unsigned VF) {
   if (ST->isCortexA57())
     return 4;
   return 2;
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index dd3fd1f5ab7..25c22bcd58e 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -110,7 +110,7 @@ public:
     return 64;
   }
 
-  unsigned getMaxInterleaveFactor();
+  unsigned getMaxInterleaveFactor(unsigned VF);
 
   unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src);
 
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
index 97590f60893..9479d7693eb 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -96,7 +96,7 @@ public:
     return 32;
   }
 
-  unsigned getMaxInterleaveFactor() {
+  unsigned getMaxInterleaveFactor(unsigned VF) {
     // These are out of order CPUs:
     if (ST->isCortexA15() || ST->isSwift())
       return 2;
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index b46acd47f31..08328d9acac 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -215,7 +215,7 @@ unsigned PPCTTIImpl::getRegisterBitWidth(bool Vector) {
 
 }
 
-unsigned PPCTTIImpl::getMaxInterleaveFactor() {
+unsigned PPCTTIImpl::getMaxInterleaveFactor(unsigned VF) {
   unsigned Directive = ST->getDarwinDirective();
   // The 440 has no SIMD support, but floating-point instructions
   // have a 5-cycle latency, so unroll by 5x for latency hiding.
diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
index 21acea1a36d..35e7a1497c8 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.h
@@ -81,7 +81,7 @@ public:
   bool enableAggressiveInterleaving(bool LoopHasReductions);
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector);
-  unsigned getMaxInterleaveFactor();
+  unsigned getMaxInterleaveFactor(unsigned VF);
   unsigned getArithmeticInstrCost(
       unsigned Opcode, Type *Ty,
       TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
diff --git a/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.cpp
index 96edc417822..6dacc742b12 100644
--- a/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.cpp
@@ -76,7 +76,7 @@ unsigned AMDGPUTTIImpl::getNumberOfRegisters(bool Vec) {
 
 unsigned AMDGPUTTIImpl::getRegisterBitWidth(bool) { return 32; }
 
-unsigned AMDGPUTTIImpl::getMaxInterleaveFactor() {
+unsigned AMDGPUTTIImpl::getMaxInterleaveFactor(unsigned VF) {
   // Semi-arbitrary large amount.
   return 64;
 }
diff --git a/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.h
index 4abbdf20e76..791c84e6f28 100644
--- a/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.h
+++ b/llvm/lib/Target/R600/AMDGPUTargetTransformInfo.h
@@ -70,7 +70,7 @@ public:
 
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector);
-  unsigned getMaxInterleaveFactor();
+  unsigned getMaxInterleaveFactor(unsigned VF);
 };
 
 } // end namespace llvm
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 5136619235b..17c86a7b9f0 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -66,7 +66,13 @@ unsigned X86TTIImpl::getRegisterBitWidth(bool Vector) {
 
 }
 
-unsigned X86TTIImpl::getMaxInterleaveFactor() {
+unsigned X86TTIImpl::getMaxInterleaveFactor(unsigned VF) {
+  // If the loop will not be vectorized, don't interleave the loop.
+  // Let regular unroll to unroll the loop, which saves the overflow
+  // check and memory check cost.
+  if (VF == 1)
+    return 1;
+
   if (ST->isAtom())
     return 1;
 
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.h b/llvm/lib/Target/X86/X86TargetTransformInfo.h
index 9f0adcfef62..e570bb55710 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.h
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.h
@@ -72,7 +72,7 @@ public:
 
   unsigned getNumberOfRegisters(bool Vector);
   unsigned getRegisterBitWidth(bool Vector);
-  unsigned getMaxInterleaveFactor();
+  unsigned getMaxInterleaveFactor(unsigned VF);
   unsigned getArithmeticInstrCost(
       unsigned Opcode, Type *Ty,
       TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index cdd3c680e8d..011fd0f6fa8 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4160,7 +4160,7 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
                        std::max(1U, (R.MaxLocalUsers - 1)));
 
   // Clamp the unroll factor ranges to reasonable factors.
-  unsigned MaxInterleaveSize = TTI.getMaxInterleaveFactor();
+  unsigned MaxInterleaveSize = TTI.getMaxInterleaveFactor(VF);
 
   // Check if the user has overridden the unroll max.
   if (VF == 1) {