[GlobalMerge] Take into account minsize on Global users' parents.

Now that we can look at users, we can trivially do this: when we would
have otherwise disabled GlobalMerge (currently -O<3), we can just run
it for minsize functions, as it's usually a codesize win.

Differential Revision: http://reviews.llvm.org/D10054

llvm-svn: 239087

3 files changed, 31 insertions, 10 deletions

diff --git a/llvm/lib/CodeGen/GlobalMerge.cpp b/llvm/lib/CodeGen/GlobalMerge.cpp
index 79de17567f7..df54a9c6916 100644
--- a/llvm/lib/CodeGen/GlobalMerge.cpp
+++ b/llvm/lib/CodeGen/GlobalMerge.cpp
@@ -124,6 +124,12 @@ namespace {
     // for more information.
     unsigned MaxOffset;
 
+    /// Whether we should try to optimize for size only.
+    /// Currently, this applies a dead simple heuristic: only consider globals
+    /// used in minsize functions for merging.
+    /// FIXME: This could learn about optsize, and be used in the cost model.
+    bool OnlyOptimizeForSize;
+
     bool doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
                  Module &M, bool isConst, unsigned AddrSpace) const;
     /// \brief Merge everything in \p Globals for which the corresponding bit
@@ -152,9 +158,10 @@ namespace {
   public:
     static char ID;             // Pass identification, replacement for typeid.
     explicit GlobalMerge(const TargetMachine *TM = nullptr,
-                         unsigned MaximalOffset = 0)
+                         unsigned MaximalOffset = 0,
+                         bool OnlyOptimizeForSize = false)
         : FunctionPass(ID), TM(TM), DL(TM->getDataLayout()),
-          MaxOffset(MaximalOffset) {
+          MaxOffset(MaximalOffset), OnlyOptimizeForSize(OnlyOptimizeForSize) {
       initializeGlobalMergePass(*PassRegistry::getPassRegistry());
     }
 
@@ -290,6 +297,12 @@ bool GlobalMerge::doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
           continue;
 
         Function *ParentFn = I->getParent()->getParent();
+
+        // If we're only optimizing for size, ignore non-minsize functions.
+        if (OnlyOptimizeForSize &&
+            !ParentFn->hasFnAttribute(Attribute::MinSize))
+          continue;
+
         size_t UGSIdx = GlobalUsesByFunction[ParentFn];
 
         // If this is the first global the basic block uses, map it to the set
@@ -585,6 +598,7 @@ bool GlobalMerge::doFinalization(Module &M) {
   return false;
 }
 
-Pass *llvm::createGlobalMergePass(const TargetMachine *TM, unsigned Offset) {
-  return new GlobalMerge(TM, Offset);
+Pass *llvm::createGlobalMergePass(const TargetMachine *TM, unsigned Offset,
+                                  bool OnlyOptimizeForSize) {
+  return new GlobalMerge(TM, Offset, OnlyOptimizeForSize);
 }
diff --git a/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp b/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
index a9059ab37f5..f23dd33d014 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetMachine.cpp
@@ -250,10 +250,14 @@ bool AArch64PassConfig::addPreISel() {
   // FIXME: On AArch64, this depends on the type.
   // Basically, the addressable offsets are up to 4095 * Ty.getSizeInBytes().
   // and the offset has to be a multiple of the related size in bytes.
-  if ((TM->getOptLevel() == CodeGenOpt::Aggressive &&
+  if ((TM->getOptLevel() != CodeGenOpt::None &&
        EnableGlobalMerge == cl::BOU_UNSET) ||
-      EnableGlobalMerge == cl::BOU_TRUE)
-    addPass(createGlobalMergePass(TM, 4095));
+      EnableGlobalMerge == cl::BOU_TRUE) {
+    bool OnlyOptimizeForSize = (TM->getOptLevel() < CodeGenOpt::Aggressive) &&
+                               (EnableGlobalMerge == cl::BOU_UNSET);
+    addPass(createGlobalMergePass(TM, 4095, OnlyOptimizeForSize));
+  }
+
   if (TM->getOptLevel() != CodeGenOpt::None)
     addPass(createAArch64AddressTypePromotionPass());
 
diff --git a/llvm/lib/Target/ARM/ARMTargetMachine.cpp b/llvm/lib/Target/ARM/ARMTargetMachine.cpp
index e794fb71af6..0f98d52084f 100644
--- a/llvm/lib/Target/ARM/ARMTargetMachine.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetMachine.cpp
@@ -339,15 +339,18 @@ void ARMPassConfig::addIRPasses() {
 }
 
 bool ARMPassConfig::addPreISel() {
-  if ((TM->getOptLevel() == CodeGenOpt::Aggressive &&
+  if ((TM->getOptLevel() != CodeGenOpt::None &&
        EnableGlobalMerge == cl::BOU_UNSET) ||
-      EnableGlobalMerge == cl::BOU_TRUE)
+      EnableGlobalMerge == cl::BOU_TRUE) {
     // FIXME: This is using the thumb1 only constant value for
     // maximal global offset for merging globals. We may want
     // to look into using the old value for non-thumb1 code of
     // 4095 based on the TargetMachine, but this starts to become
     // tricky when doing code gen per function.
-    addPass(createGlobalMergePass(TM, 127));
+    bool OnlyOptimizeForSize = (TM->getOptLevel() < CodeGenOpt::Aggressive) &&
+                               (EnableGlobalMerge == cl::BOU_UNSET);
+    addPass(createGlobalMergePass(TM, 127, OnlyOptimizeForSize));
+  }
 
   return false;
 }