3 files changed, 19 insertions, 0 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index abdeac019a1..1c81d34014f 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -91,6 +91,8 @@ void AArch64Subtarget::initializeProperties() {
   case Falkor:
     MaxInterleaveFactor = 4;
     VectorInsertExtractBaseCost = 2;
+    // FIXME: remove this to enable 64-bit SLP if performance looks good.
+    MinVectorRegisterBitWidth = 128;
     break;
   case Kryo:
     MaxInterleaveFactor = 4;
@@ -99,6 +101,8 @@ void AArch64Subtarget::initializeProperties() {
     PrefetchDistance = 740;
     MinPrefetchStride = 1024;
     MaxPrefetchIterationsAhead = 11;
+    // FIXME: remove this to enable 64-bit SLP if performance looks good.
+    MinVectorRegisterBitWidth = 128;
     break;
   case ThunderX2T99:
     CacheLineSize = 64;
@@ -108,6 +112,8 @@ void AArch64Subtarget::initializeProperties() {
     PrefetchDistance = 128;
     MinPrefetchStride = 1024;
     MaxPrefetchIterationsAhead = 4;
+    // FIXME: remove this to enable 64-bit SLP if performance looks good.
+    MinVectorRegisterBitWidth = 128;
     break;
   case ThunderX:
   case ThunderXT88:
@@ -116,6 +122,8 @@ void AArch64Subtarget::initializeProperties() {
     CacheLineSize = 128;
     PrefFunctionAlignment = 3;
     PrefLoopAlignment = 2;
+    // FIXME: remove this to enable 64-bit SLP if performance looks good.
+    MinVectorRegisterBitWidth = 128;
     break;
   case CortexA35: break;
   case CortexA53: break;
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index 2c66221886c..df54bf3f48e 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -83,6 +83,9 @@ protected:
   // NegativeImmediates - transform instructions with negative immediates
   bool NegativeImmediates = true;
 
+  // Enable 64-bit vectorization in SLP.
+  unsigned MinVectorRegisterBitWidth = 64;
+
   bool UseAA = false;
   bool PredictableSelectIsExpensive = false;
   bool BalanceFPOps = false;
@@ -191,6 +194,10 @@ public:
 
   bool isXRaySupported() const override { return true; }
 
+  unsigned getMinVectorRegisterBitWidth() const {
+    return MinVectorRegisterBitWidth;
+  }
+
   bool isX18Reserved() const { return ReserveX18; }
   bool hasFPARMv8() const { return HasFPARMv8; }
   bool hasNEON() const { return HasNEON; }
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index 39258115dcb..280d97f3c50 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -87,6 +87,10 @@ public:
     return 64;
   }
 
+  unsigned getMinVectorRegisterBitWidth() {
+    return ST->getMinVectorRegisterBitWidth();
+  }
+
   unsigned getMaxInterleaveFactor(unsigned VF);
 
   int getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,