[PPC64LE] Remove unnecessary swaps from lane-insensitive vector computations

[oota-llvm.git] / lib / Target / PowerPC / PPCTargetMachine.cpp

diff --git a/lib/Target/PowerPC/PPCTargetMachine.cpp b/lib/Target/PowerPC/PPCTargetMachine.cpp
index 7267529ef81d19b3fd517768f499c68fea30afaf..fa501e0206ae5ad8c214610698a1193aef6b29be 100644 (file)
--- a/lib/Target/PowerPC/PPCTargetMachine.cpp
+++ b/lib/Target/PowerPC/PPCTargetMachine.cpp
@@ -38,6 +38,10 @@ static cl::opt<bool>
 VSXFMAMutateEarly("schedule-ppc-vsx-fma-mutation-early",
   cl::Hidden, cl::desc("Schedule VSX FMA instruction mutation early"));
 
+static cl::
+opt<bool> DisableVSXSwapRemoval("disable-ppc-vsx-swap-removal", cl::Hidden,
+                                cl::desc("Disable VSX Swap Removal for PPC"));
+
 static cl::opt<bool>
 EnableGEPOpt("ppc-gep-opt", cl::Hidden,
              cl::desc("Enable optimizations on complex GEPs"),
@@ -239,6 +243,7 @@ public:
   bool addPreISel() override;
   bool addILPOpts() override;
   bool addInstSelector() override;
+  void addMachineSSAOptimization() override;
   void addPreRegAlloc() override;
   void addPreSched2() override;
   void addPreEmitPass() override;
@@ -306,6 +311,15 @@ bool PPCPassConfig::addInstSelector() {
   return false;
 }
 
+void PPCPassConfig::addMachineSSAOptimization() {
+  TargetPassConfig::addMachineSSAOptimization();
+  // For little endian, remove where possible the vector swap instructions
+  // introduced at code generation to normalize vector element order.
+  if (Triple(TM->getTargetTriple()).getArch() == Triple::ppc64le &&
+      !DisableVSXSwapRemoval)
+    addPass(createPPCVSXSwapRemovalPass());
+}
+
 void PPCPassConfig::addPreRegAlloc() {
   initializePPCVSXFMAMutatePass(*PassRegistry::getPassRegistry());
   insertPass(VSXFMAMutateEarly ? &RegisterCoalescerID : &MachineSchedulerID,