similar to: [LLVMdev] Trying to optimize out store/load pair

Hello all, My app is using LLVM JIT as a runtime engine for image analysis (similar to opencl). I'm placing values into a struct to pass byref to a series of functions. After running the createStandardModulePasses(...) set of optimizations, the function calls are all inlined but the struct store/load pairs haven't been optimized away. I've attached the code below. What I'd like to

Hello. I'm having problems at instruction selection with my back end with the following basic-block due to a vector add with immediate constant vector (obtained by vectorizing a simple C program doing vector sum map): vector.ph: ; preds = %vector.memcheck50 %.splatinsert = insertelement <8 x i64> undef, i64 %i.07.unr, i32 0

On Sep 29, 2010, at 8:35 AMPDT, Ralf Karrenberg wrote: > Hello everybody, > > I have stumbled upon a test case (the attached module is a slightly > reduced version) that shows extremely reduced performance on linux > compared to windows when executed using LLVM's JIT. > > We narrowed the problem down to the actual code being generated, the > source IR on both systems

How can I get the name of the virtual Registers present on an instruction. eg. %add18 = add nsw i32 %mul17, %37 in this case I want to extract the name of the virutal registers as "add18", "mul17","37". This can easily be done in the case of store Instruction eg. store i32 %add20, i32* %t, align 4 in this case functions like

Hello everyone, please I need your help. To reproduce my problem I created simple pass for backends (TestPass.cpp in attached files). That pass I call from Mips backend in this way (MipsTargetMachine.cpp): bool MipsPassConfig::addPreRegAlloc() { addPass(createTestPass()); return false; } The problem becomes, when I am trying compile file ldtoa.ll (in attached files). Compiling

I have cloned an instruction from one basic block to another newly created block in newly created function. And since am cloning an instruction the operands of that instruction still points to the instructions of old block. Due to which am getting an error as "Instruction does not dominate all uses!". example:- original function and block:- %a = alloca i32, align 4 %x = alloca

Hello everybody, I have stumbled upon a test case (the attached module is a slightly reduced version) that shows extremely reduced performance on linux compared to windows when executed using LLVM's JIT. We narrowed the problem down to the actual code being generated, the source IR on both systems is the same. Try compiling the attached module: llc -O3 -filetype=asm -o BAD.s BAD.ll Under