Merge remote-tracking branch 'upstream/master' into merge-llvm

Conflicts:
	lib/CodeGen/AsmPrinter/AsmPrinter.cpp
	lib/CodeGen/AsmPrinter/AsmPrinterInlineAsm.cpp
	lib/MC/MCAssembler.cpp
	lib/Support/Atomic.cpp
	lib/Support/Memory.cpp
	lib/Target/ARM/ARMJITInfo.cpp

Change-Id: Ib339baf88df5b04870c8df1bedcfe1f877ccab8d

1 files changed, 48 insertions, 20 deletions

diff --git a/lib/Transforms/IPO/PassManagerBuilder.cpp b/lib/Transforms/IPO/PassManagerBuilder.cpp
index 43b4ab5..6dc1773 100644
--- a/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -14,32 +14,36 @@
 
 
 #include "llvm/Transforms/IPO/PassManagerBuilder.h"
-
 #include "llvm-c/Transforms/PassManagerBuilder.h"
-
-#include "llvm/PassManager.h"
-#include "llvm/DefaultPasses.h"
-#include "llvm/PassManager.h"
+#include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/Passes.h"
 #include "llvm/Analysis/Verifier.h"
+#include "llvm/PassManager.h"
 #include "llvm/Support/CommandLine.h"
+#include "llvm/Support/ManagedStatic.h"
 #include "llvm/Target/TargetLibraryInfo.h"
+#include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Transforms/Vectorize.h"
-#include "llvm/Transforms/IPO.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/Support/ManagedStatic.h"
 
 using namespace llvm;
 
 static cl::opt<bool>
-RunVectorization("vectorize", cl::desc("Run vectorization passes"));
+RunLoopVectorization("vectorize-loops",
+                     cl::desc("Run the Loop vectorization passes"));
+
+static cl::opt<bool>
+RunBBVectorization("vectorize", cl::desc("Run the BB vectorization passes"));
 
 static cl::opt<bool>
 UseGVNAfterVectorization("use-gvn-after-vectorization",
   cl::init(false), cl::Hidden,
   cl::desc("Run GVN instead of Early CSE after vectorization passes"));
 
+static cl::opt<bool> UseNewSROA("use-new-sroa",
+  cl::init(true), cl::Hidden,
+  cl::desc("Enable the new, experimental SROA pass"));
+
 PassManagerBuilder::PassManagerBuilder() {
     OptLevel = 2;
     SizeLevel = 0;
@@ -48,7 +52,8 @@ PassManagerBuilder::PassManagerBuilder() {
     DisableSimplifyLibCalls = false;
     DisableUnitAtATime = false;
     DisableUnrollLoops = false;
-    Vectorize = RunVectorization;
+    Vectorize = RunBBVectorization;
+    LoopVectorize = RunLoopVectorization;
 }
 
 PassManagerBuilder::~PassManagerBuilder() {
@@ -100,7 +105,10 @@ void PassManagerBuilder::populateFunctionPassManager(FunctionPassManager &FPM) {
   addInitialAliasAnalysisPasses(FPM);
 
   FPM.add(createCFGSimplificationPass());
-  FPM.add(createScalarReplAggregatesPass());
+  if (UseNewSROA)
+    FPM.add(createSROAPass());
+  else
+    FPM.add(createScalarReplAggregatesPass());
   FPM.add(createEarlyCSEPass());
   FPM.add(createLowerExpectIntrinsicPass());
 }
@@ -112,6 +120,14 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
       MPM.add(Inliner);
       Inliner = 0;
     }
+
+    // FIXME: This is a HACK! The inliner pass above implicitly creates a CGSCC
+    // pass manager, but we don't want to add extensions into that pass manager.
+    // To prevent this we must insert a no-op module pass to reset the pass
+    // manager to get the same behavior as EP_OptimizerLast in non-O0 builds.
+    if (!GlobalExtensions->empty() || !Extensions.empty())
+      MPM.add(createBarrierNoopPass());
+
     addExtensionsToPM(EP_EnabledOnOptLevel0, MPM);
     return;
   }
@@ -147,7 +163,10 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
 
   // Start of function pass.
   // Break up aggregate allocas, using SSAUpdater.
-  MPM.add(createScalarReplAggregatesPass(-1, false));
+  if (UseNewSROA)
+    MPM.add(createSROAPass(/*RequiresDomTree*/ false));
+  else
+    MPM.add(createScalarReplAggregatesPass(-1, false));
   MPM.add(createEarlyCSEPass());              // Catch trivial redundancies
   if (!DisableSimplifyLibCalls)
     MPM.add(createSimplifyLibCallsPass());    // Library Call Optimizations
@@ -166,6 +185,10 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   MPM.add(createIndVarSimplifyPass());        // Canonicalize indvars
   MPM.add(createLoopIdiomPass());             // Recognize idioms like memset.
   MPM.add(createLoopDeletionPass());          // Delete dead loops
+
+  if (LoopVectorize && OptLevel > 2)
+    MPM.add(createLoopVectorizePass());
+
   if (!DisableUnrollLoops)
     MPM.add(createLoopUnrollPass());          // Unroll small loops
   addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
@@ -201,13 +224,12 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
     // FIXME: We shouldn't bother with this anymore.
     MPM.add(createStripDeadPrototypesPass()); // Get rid of dead prototypes
 
-    // GlobalOpt already deletes dead functions and globals, at -O3 try a
+    // GlobalOpt already deletes dead functions and globals, at -O2 try a
     // late pass of GlobalDCE.  It is capable of deleting dead cycles.
-    if (OptLevel > 2)
+    if (OptLevel > 1) {
       MPM.add(createGlobalDCEPass());         // Remove dead fns and globals.
-
-    if (OptLevel > 1)
       MPM.add(createConstantMergePass());     // Merge dup global constants
+    }
   }
   addExtensionsToPM(EP_OptimizerLast, MPM);
 }
@@ -222,8 +244,11 @@ void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   // Now that composite has been compiled, scan through the module, looking
   // for a main function.  If main is defined, mark all other functions
   // internal.
-  if (Internalize)
-    PM.add(createInternalizePass(true));
+  if (Internalize) {
+    std::vector<const char*> E;
+    E.push_back("main");
+    PM.add(createInternalizePass(E));
+  }
 
   // Propagate constants at call sites into the functions they call.  This
   // opens opportunities for globalopt (and inlining) by substituting function
@@ -265,7 +290,10 @@ void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   PM.add(createInstructionCombiningPass());
   PM.add(createJumpThreadingPass());
   // Break up allocas
-  PM.add(createScalarReplAggregatesPass());
+  if (UseNewSROA)
+    PM.add(createSROAPass());
+  else
+    PM.add(createScalarReplAggregatesPass());
 
   // Run a few AA driven optimizations here and now, to cleanup the code.
   PM.add(createFunctionAttrsPass()); // Add nocapture.
@@ -289,7 +317,7 @@ void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   PM.add(createGlobalDCEPass());
 }
 
-LLVMPassManagerBuilderRef LLVMPassManagerBuilderCreate(void) {
+LLVMPassManagerBuilderRef LLVMPassManagerBuilderCreate() {
   PassManagerBuilder *PMB = new PassManagerBuilder();
   return wrap(PMB);
 }