Index: include/llvm/IR/Constants.h =================================================================== --- include/llvm/IR/Constants.h +++ include/llvm/IR/Constants.h @@ -943,12 +943,19 @@ Type *Ty ///< The type to trunc or bitcast C to ); - /// @brief Create a BitCast or a PtrToInt cast constant expression + /// @brief Create a BitCast, AddrSpaceCast, or a PtrToInt cast constant + /// expression. static Constant *getPointerCast( Constant *C, ///< The pointer value to be casted (operand 0) Type *Ty ///< The type to which cast should be made ); + /// @brief Create a BitCast or AddrSpaceCast depending on the address space. + static Constant *getBitCastOrAddrSpaceCast( + Constant *C, ///< The constant to addrspacecast or bitcast + Type *Ty ///< The type to bitcast or addrspacecast C to + ); + /// @brief Create a ZExt, Bitcast or Trunc for integer -> integer casts static Constant *getIntegerCast( Constant *C, ///< The integer constant to be casted Index: lib/IR/Constants.cpp =================================================================== --- lib/IR/Constants.cpp +++ lib/IR/Constants.cpp @@ -1499,7 +1499,17 @@ return getBitCast(S, Ty); } -Constant *ConstantExpr::getIntegerCast(Constant *C, Type *Ty, +Constant *ConstantExpr::getBitCastOrAddrSpaceCast(Constant *S, Type *Ty) { + assert(S->getType()->isPtrOrPtrVectorTy() && "Invalid cast"); + assert(Ty->isPtrOrPtrVectorTy() && "Invalid cast"); + + if (S->getType()->getPointerAddressSpace() != Ty->getPointerAddressSpace()) + return getAddrSpaceCast(S, Ty); + + return getBitCast(S, Ty); +} + +Constant *ConstantExpr::getIntegerCast(Constant *C, Type *Ty, bool isSigned) { assert(C->getType()->isIntOrIntVectorTy() && Ty->isIntOrIntVectorTy() && "Invalid cast"); Index: lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp =================================================================== --- lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp +++ lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp @@ -263,9 +263,9 @@ for (unsigned i = 0, e = ToDelete.size(); i != e; ++i) EraseInstFromFunction(*ToDelete[i]); Constant *TheSrc = cast(Copy->getSource()); - Instruction *NewI - = ReplaceInstUsesWith(AI, ConstantExpr::getBitCast(TheSrc, - AI.getType())); + Constant *Cast + = ConstantExpr::getBitCastOrAddrSpaceCast(TheSrc, AI.getType()); + Instruction *NewI = ReplaceInstUsesWith(AI, Cast); EraseInstFromFunction(*Copy); ++NumGlobalCopies; return NewI; Index: test/Transforms/InstCombine/addrspacecast.ll =================================================================== --- test/Transforms/InstCombine/addrspacecast.ll +++ test/Transforms/InstCombine/addrspacecast.ll @@ -2,6 +2,12 @@ target datalayout = "e-p:64:64:64-p1:32:32:32-p2:16:16:16-n8:16:32:64" + +declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i32(i8*, i8 addrspace(1)*, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p2i8.i32(i8*, i8 addrspace(2)*, i32, i32, i1) nounwind + + define i32* @combine_redundant_addrspacecast(i32 addrspace(1)* %x) nounwind { ; CHECK-LABEL: @combine_redundant_addrspacecast( ; CHECK: addrspacecast i32 addrspace(1)* %x to i32* @@ -29,3 +35,35 @@ ret float* %z } +@const_array = addrspace(2) constant [60 x i8] [i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, + i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, + i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, + i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, + i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22, i8 2, i8 9, i8 4, i8 22 ] + +declare void @foo(i8*) nounwind + +; A copy from a constant addrspacecast'ed global +; CHECK-LABEL: @memcpy_addrspacecast( +; CHECK-NOT: call void @llvm.memcpy +define i32 @memcpy_addrspacecast() nounwind { +entry: + %alloca = alloca i8, i32 48 + call void @llvm.memcpy.p0i8.p1i8.i32(i8* %alloca, i8 addrspace(1)* addrspacecast (i8 addrspace(2)* getelementptr inbounds ([60 x i8] addrspace(2)* @const_array, i16 0, i16 4) to i8 addrspace(1)*), i32 48, i32 4, i1 false) nounwind + br label %loop.body + +loop.body: + %i = phi i32 [ 0, %entry ], [ %i.inc, %loop.body ] + %sum = phi i32 [ 0, %entry ], [ %sum.inc, %loop.body] + %ptr = getelementptr i8* %alloca, i32 %i + %load = load i8* %ptr + %ext = zext i8 %load to i32 + %sum.inc = add i32 %sum, %ext + %i.inc = add i32 %i, 1 + %cmp = icmp ne i32 %i, 48 + br i1 %cmp, label %loop.body, label %end + +end: + ret i32 %sum.inc +} +