Teach the constant folder to look through bitcast constant expressions

much more effectively when trying to constant fold a load of a constant.
Previously, we only handled bitcasts by trying to find a totally generic
byte representation of the constant and use that. Now, we look through
the bitcast to see what constant we might fold the load into, and then
try to form a constant expression cast of the found value that would be
equivalent to loading the value.

You might wonder why on earth this actually matters. Well, turns out
that the Itanium ABI causes us to create a single array for a vtable
where the first elements are virtual base offsets, followed by the
virtual function pointers. Because the array is homogenous the element
type is consistently i8* and we inttoptr the virtual base offsets into
the initial elements.

Then constructors bitcast these pointers to i64 pointers prior to
loading them. Boom, no more constant folding of virtual base offsets.
This is the first fix to LLVM to address the *insane* performance Eric
Niebler discovered with Clang on his range comprehensions[1]. There is
more to come though, this doesn't *really* fix the problem fully.

[1]: http://ericniebler.com/2014/04/27/range-comprehensions/

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@208856 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Analysis/ConstantFolding.cpp

@@ -466,6 +466,52 @@ static Constant *FoldReinterpretLoadFromConstPtr(Constant *C,
   return ConstantInt::get(IntType->getContext(), ResultVal);
 }
 
+static Constant *ConstantFoldLoadThroughBitcast(ConstantExpr *CE,
+                                                const DataLayout *DL) {
+  if (!DL)
+    return nullptr;
+  auto *DestPtrTy = dyn_cast<PointerType>(CE->getType());
+  if (!DestPtrTy)
+    return nullptr;
+  Type *DestTy = DestPtrTy->getElementType();
+
+  Constant *C = ConstantFoldLoadFromConstPtr(CE->getOperand(0), DL);
+  if (!C)
+    return nullptr;
+
+  do {
+    Type *SrcTy = C->getType();
+
+    // If the type sizes are the same and a cast is legal, just directly
+    // cast the constant.
+    if (DL->getTypeSizeInBits(DestTy) == DL->getTypeSizeInBits(SrcTy)) {
+      Instruction::CastOps Cast = Instruction::BitCast;
+      // If we are going from a pointer to int or vice versa, we spell the cast
+      // differently.
+      if (SrcTy->isIntegerTy() && DestTy->isPointerTy())
+        Cast = Instruction::IntToPtr;
+      else if (SrcTy->isPointerTy() && DestTy->isIntegerTy())
+        Cast = Instruction::PtrToInt;
+
+      if (CastInst::castIsValid(Cast, C, DestTy))
+        return ConstantExpr::getCast(Cast, C, DestTy);
+    }
+
+    // If this isn't an aggregate type, there is nothing we can do to drill down
+    // and find a bitcastable constant.
+    if (!SrcTy->isAggregateType())
+      return nullptr;
+
+    // We're simulating a load through a pointer that was bitcast to point to
+    // a different type, so we can try to walk down through the initial
+    // elements of an aggregate to see if some part of th e aggregate is
+    // castable to implement the "load" semantic model.
+    C = C->getAggregateElement(0u);
+  } while (C);
+
+  return nullptr;
+}
+
 /// ConstantFoldLoadFromConstPtr - Return the value that a load from C would
 /// produce if it is constant and determinable.  If this is not determinable,
 /// return null.
@@ -491,6 +537,10 @@ Constant *llvm::ConstantFoldLoadFromConstPtr(Constant *C,
     }
   }
 
+  if (CE->getOpcode() == Instruction::BitCast)
+    if (Constant *LoadedC = ConstantFoldLoadThroughBitcast(CE, TD))
+      return LoadedC;
+
   // Instead of loading constant c string, use corresponding integer value
   // directly if string length is small enough.
   StringRef Str;

test/Transforms/ConstProp/loads.ll

@@ -219,3 +219,37 @@ entry:
 ; BE-LABEL: @test15(
 ; BE: ret i64 2
 }
+
+@gv7 = constant [4 x i8*] [i8* null, i8* inttoptr (i64 -14 to i8*), i8* null, i8* null]
+define i64 @test16.1() {
+  %v = load i64* bitcast ([4 x i8*]* @gv7 to i64*), align 8
+  ret i64 %v
+
+; LE-LABEL: @test16.1(
+; LE: ret i64 0
+
+; BE-LABEL: @test16.1(
+; BE: ret i64 0
+}
+
+define i64 @test16.2() {
+  %v = load i64* bitcast (i8** getelementptr inbounds ([4 x i8*]* @gv7, i64 0, i64 1) to i64*), align 8
+  ret i64 %v
+
+; LE-LABEL: @test16.2(
+; LE: ret i64 -14
+
+; BE-LABEL: @test16.2(
+; BE: ret i64 -14
+}
+
+define i64 @test16.3() {
+  %v = load i64* bitcast (i8** getelementptr inbounds ([4 x i8*]* @gv7, i64 0, i64 2) to i64*), align 8
+  ret i64 %v
+
+; LE-LABEL: @test16.3(
+; LE: ret i64 0
+
+; BE-LABEL: @test16.3(
+; BE: ret i64 0
+}