[LLVMdev] Seg faulting on vector ops

[Chuck Rose III]

Hola LLVMers,

 

I'm looking to make use of the vectorization primitives in the Intel
chip with the code we generate from LLVM and so I've started
experimenting with it.  What is the state of the machine code generated
for vectors?  In my tinkering, I seem to be getting some wonky machine
instructions, but I'm most likely just doing something wrong and I'm
hoping you can set me in the correct course.

 

My minimal function creates a float4 vector with a specified scalar in
all the elements.  It then extracts the third element and returns it. 

 

We are currently using the JIT and I'm currently synced to about a week
after the 2.0 branch, so I'm admittedly stale by about a month.

 

In LLVM IR:

 

; ModuleID = 'test vectors'

 

define float @vSelect3(float %x) {

body:

        %pv = alloca <4 x float>                ; <<4 x float>*>
[#uses=1]

        %v = load <4 x float>* %pv              ; <<4 x float>>
[#uses=1]

        %v1 = insertelement <4 x float> %v, float %x, i32 0
; <<4 x

float>> [#uses=1]

        %v2 = insertelement <4 x float> %v1, float %x, i32 1
; <<4 x

float>> [#uses=1]

        %v3 = insertelement <4 x float> %v2, float %x, i32 2
; <<4 x

float>> [#uses=1]

        %v4 = insertelement <4 x float> %v3, float %x, i32 3
; <<4 x

float>> [#uses=1]

        %s = extractelement <4 x float> %v4, i32 3              ;
<float> [#uses

=1]

        ret float %s

}

 

In Intel assembly, I get the following:

 

00000000`01b80010 83ec20          sub     esp,20h

00000000`01b80013 f30f10442424    movss   xmm0,dword ptr [esp+24h]   <--
this loads x into the low float of xmm0

00000000`01b80019 0f284c2404      movaps  xmm1,xmmword ptr [esp+4]   <--
this seg faults because esp+4 isn't 16-byte aligned

What is that line trying to achieve?  X is at [esp+24].  There weren't
any other parameters.  

 

00000000`01b8001e f30f10c8        movss   xmm1,xmm0

00000000`01b80022 8b442424        mov     eax,dword ptr [esp+24h]

00000000`01b80026 660fc4c802      pinsrw  xmm1,eax,2

00000000`01b8002b 89c1            mov     ecx,eax

00000000`01b8002d c1e910          shr     ecx,10h

00000000`01b80030 660fc4c903      pinsrw  xmm1,ecx,3

00000000`01b80035 660fc4c804      pinsrw  xmm1,eax,4

00000000`01b8003a 660fc4c905      pinsrw  xmm1,ecx,5

00000000`01b8003f 660fc4c806      pinsrw  xmm1,eax,6

00000000`01b80044 660fc4c907      pinsrw  xmm1,ecx,7

00000000`01b80049 0fc6c903        shufps  xmm1,xmm1,3

00000000`01b8004d f30f110c24      movss   dword ptr [esp],xmm1

00000000`01b80052 d90424          fld     dword ptr [esp]

00000000`01b80055 83c420          add     esp,20h

00000000`01b80058 c3              ret

 

The code used to generate and run the program was:

 

#include "llvm/Module.h"

#include "llvm/DerivedTypes.h"

#include "llvm/Constants.h"

#include "llvm/Instructions.h"

#include "llvm/ModuleProvider.h"

#include "llvm/Analysis/Verifier.h"

#include "llvm/System/DynamicLibrary.h"

#include "llvm/ExecutionEngine/JIT.h"

#include "llvm/ExecutionEngine/Interpreter.h"

#include "llvm/ExecutionEngine/GenericValue.h"

#include "llvm/Support/ManagedStatic.h"

#include <iostream>

using namespace llvm;

 

Value* makeVector(Value* s, unsigned int dim, BasicBlock* basicBlock)

{

    AllocaInst* pV = new
AllocaInst(VectorType::get(Type::FloatTy,dim),"pv",basicBlock);

    Value* v = new LoadInst(pV,"v",basicBlock);

 

    for (unsigned int i = 0 ; i < dim ; ++i)

        v = new InsertElementInst(v,s,i,"v",basicBlock);

 

    return v;

}

 

Function* generateVectorAndSelect(Module* pModule)

{

    std::vector<Type const*> params;

 

    params.push_back(Type::FloatTy);

 

    FunctionType* funcType =
FunctionType::get(Type::FloatTy,params,NULL);

    Function* func =
cast<Function>(pModule->getOrInsertFunction("vSelect3",funcType));

 

    BasicBlock* basicBlock = new BasicBlock("body",func);

 

    Function::arg_iterator args = func->arg_begin();

    Argument* x = args;

    x->setName("x");

    

    Value* v1 = makeVector(x,4,basicBlock);

    

    Value* s = new ExtractElementInst(v1,3,"s",basicBlock);

 

    new ReturnInst(s,basicBlock);

 

    return func;

}

 

// modified from the fibonacci example

int main(int argc, char **argv) 

{

    Module* pVectorModule = new Module("test vectors");

 

    Function* pMain = generateVectorAndSelect(pVectorModule);

 

    pVectorModule->print(std::cout);

 

    GenericValue gv1, gv2, gvR;

 

    gv1.FloatVal = 2.0f;

 

    ExistingModuleProvider *pMP = new
ExistingModuleProvider(pVectorModule);

 
pMP->getModule()->setDataLayout("e-p:32:32:32-i1:8:8:8-i8:8:8:8-i32:32:3
2:32-f32:32:32:32");

    ExecutionEngine *pEE = ExecutionEngine::create(pMP, false);

 

    std::vector<GenericValue> args;

 

    args.push_back(gv1);

 

    GenericValue result = pEE->runFunction(pMain, args);

 

    return 0;

}

 

 

Any help would be appreciated.  

.  

Thanks,

Chuck.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20070720/9fe46c76/attachment.html>