[PPC] Use SeparateConstOffsetFromGEP

This mirrors r222331, which enabled SeparateConstOffsetFromGEP on AArch64, in
the PowerPC backend. Yields, on a POWER7 machine, a 30% speedup on
SingleSource/Benchmarks/Shootout/nestedloop (this might just be from LICM,
there is a store moved out of the inner loop) and a potential speedup on
MultiSource/Benchmarks/mediabench/mpeg2/mpeg2dec/mpeg2decode. Regardless, it
makes some code look cleaner, and synchronizing the backends in this regard
seems like a generally good thing.

llvm-svn: 222504

1 files changed, 20 insertions, 0 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp b/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp
index f15189c..e930a9c 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetMachine.cpp
@@ -22,6 +22,7 @@
 #include "llvm/Support/FormattedStream.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Target/TargetOptions.h"
+#include "llvm/Transforms/Scalar.h"
 using namespace llvm;
 
 static cl::
@@ -32,6 +33,11 @@ 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>
+EnableGEPOpt("ppc-gep-opt", cl::Hidden,
+             cl::desc("Enable optimizations on complex GEPs"),
+             cl::init(true));
+
 extern "C" void LLVMInitializePowerPCTarget() {
   // Register the targets
   RegisterTargetMachine<PPC32TargetMachine> A(ThePPC32Target);
@@ -168,6 +174,20 @@ TargetPassConfig *PPCTargetMachine::createPassConfig(PassManagerBase &PM) {
 
 void PPCPassConfig::addIRPasses() {
   addPass(createAtomicExpandPass(&getPPCTargetMachine()));
+
+  if (TM->getOptLevel() == CodeGenOpt::Aggressive && EnableGEPOpt) {
+    // Call SeparateConstOffsetFromGEP pass to extract constants within indices
+    // and lower a GEP with multiple indices to either arithmetic operations or
+    // multiple GEPs with single index.
+    addPass(createSeparateConstOffsetFromGEPPass(TM, true));
+    // Call EarlyCSE pass to find and remove subexpressions in the lowered
+    // result.
+    addPass(createEarlyCSEPass());
+    // Do loop invariant code motion in case part of the lowered result is
+    // invariant.
+    addPass(createLICMPass());
+  }
+
   TargetPassConfig::addIRPasses();
 }