llvm-svn: 32472

llvm-svn: 32471

llvm-svn: 32470

llvm-svn: 32469

llvm-svn: 32468

and legalizer separated like they currently are, I don't see a way to handle
this xform.

llvm-svn: 32466

This is not sufficient to fix X86/store-fp-constant.ll

llvm-svn: 32465

LBB1_1: #bb
        movdqa (%esi), %xmm2
        movaps %xmm2, %xmm3
        punpcklbw %xmm0, %xmm3
        movaps %xmm3, %xmm4
        punpcklwd %xmm0, %xmm4
        cvtdq2ps %xmm4, %xmm4
        mulps %xmm1, %xmm4
        movaps %xmm4, (%edi)
        leal 1(,%eax,4), %ebx
        shll $4, %ebx
        punpckhwd %xmm0, %xmm3
        cvtdq2ps %xmm3, %xmm3
        mulps %xmm1, %xmm3
        movaps %xmm3, (%edx,%ebx)
        leal 2(,%eax,4), %ebx
        shll $4, %ebx
        punpckhbw %xmm0, %xmm2
        movaps %xmm2, %xmm3
        punpcklwd %xmm0, %xmm3
        cvtdq2ps %xmm3, %xmm3
        mulps %xmm1, %xmm3
        movaps %xmm3, (%edx,%ebx)
        leal 3(,%eax,4), %ebx
        shll $4, %ebx
        punpckhwd %xmm0, %xmm2
        cvtdq2ps %xmm2, %xmm2
        mulps %xmm1, %xmm2
        movaps %xmm2, (%edx,%ebx)
        addl $64, %edi
        incl %eax
        addl $16, %esi
        cmpl %ecx, %eax
        jne LBB1_1      #bb

instead of:

LBB1_1: #bb
        movdqa (%esi), %xmm2
        movaps %xmm2, %xmm3
        punpcklbw %xmm0, %xmm3
        movaps %xmm3, %xmm4
        punpcklwd %xmm0, %xmm4
        cvtdq2ps %xmm4, %xmm4
        mulps %xmm1, %xmm4
        movaps %xmm4, (%edi)
        leal 1(,%eax,4), %ebx
        shll $4, %ebx
        punpckhwd %xmm0, %xmm3
        cvtdq2ps %xmm3, %xmm3
        mulps %xmm1, %xmm3
        movaps %xmm3, (%edx,%ebx)
        leal 2(,%eax,4), %ebx
        shll $4, %ebx
        punpckhbw %xmm0, %xmm2
        movaps %xmm2, %xmm3
        punpcklwd %xmm0, %xmm3
        cvtdq2ps %xmm3, %xmm3
        mulps %xmm1, %xmm3
        movaps %xmm3, (%edx,%ebx)
        leal 3(,%eax,4), %ebx
        shll $4, %ebx
        punpckhwd %xmm0, %xmm2
        cvtdq2ps %xmm2, %xmm2
        mulps %xmm1, %xmm2
        movaps %xmm2, (%edx,%ebx)
        addl $64, %edi
        incl %eax
        addl $16, %esi
        cmpl %ecx, %eax
        jne LBB1_1      #bb

for a testcase.

llvm-svn: 32463

llvm-svn: 32462

llvm-svn: 32460

llvm-svn: 32459

to the createIntegerCast and createFPCast for CastInst instructions.

llvm-svn: 32457

integer and floating point cast creation. createIntegerCast generates
ZExt/SExt, BitCast or Trunc. createFPCast generates FPExt, Bitcast, or
FPTrunc.

llvm-svn: 32456

llvm-svn: 32454

llvm-svn: 32453

llvm-svn: 32452

emitted for external globals in PPC64-JIT-PIC mode (which is good because
we didn't handle them before!).

This also fixes a bug handling the picbase delta, which we would get wrong
in some cases.

llvm-svn: 32451

to infer the cast from its operand and type. This fixes:
test/Regression/Bytecode/2006-12-11-Cast-ConstExpr.ll

llvm-svn: 32450

llvm-svn: 32448

llvm-svn: 32447

union to perform the bitcast.

llvm-svn: 32444

llvm-svn: 32442

For now, just grab the stream and perform the output on it directly.

llvm-svn: 32441

llvm-svn: 32440

llvm-svn: 32439

Transforms/ConstProp/bitcast.ll and fixes
SingleSource/Regression/C/2003-10-12-GlobalVarInitializers

llvm-svn: 32438

llvm-svn: 32436

llvm-svn: 32434

llvm-svn: 32433

llvm-svn: 32432

dag combiner.

llvm-svn: 32431

Supports constant pools
Supports relocations to jump tables
Supports relocations within the data segment (global = address of global)
Allocates memory in a non-hacky for all non-code objects.

llvm-svn: 32430

llvm-svn: 32428

_pairtest:
        movl 8(%esp), %eax
        movl 4(%esp), %ecx
        movd %eax, %xmm0
        movd %ecx, %xmm1
        addss %xmm0, %xmm1
        movl 12(%esp), %eax
        movss %xmm1, (%eax)
        ret

instead of:

_pairtest:
        subl $12, %esp
        movl 20(%esp), %eax
        movl %eax, 4(%esp)
        movl 16(%esp), %eax
        movl %eax, (%esp)
        movss (%esp), %xmm0
        addss 4(%esp), %xmm0
        movl 24(%esp), %eax
        movss %xmm0, (%eax)
        addl $12, %esp
        ret

llvm-svn: 32427

llvm-svn: 32426

llvm-svn: 32424

The rot example works if the type is cast to ubyte.

Move sroa examples together and upgrade them to HEAD syntax.

llvm-svn: 32423

This implements Transforms/ScalarRepl/union-packed.ll

llvm-svn: 32422

Regression/Transforms/IndVarsSimplify/2006-12-10-BitCast.ll

llvm-svn: 32420

 * Add support for promoting unions with fp values in them.  This produces
   our new int<->fp bitcast instructions, implementing
   Transforms/ScalarRepl/union-fp-int.ll

As an example, this allows us to compile this:

union intfloat { int i; float f; };
float invsqrt(const float arg_x) {
    union intfloat x = { .f = arg_x };
    const float xhalf = arg_x * 0.5f;
    x.i = 0x5f3759df - (x.i >> 1);
    return x.f * (1.5f - xhalf * x.f * x.f);
}

into:

_invsqrt:
        movss 4(%esp), %xmm0
        movd %xmm0, %eax
        sarl %eax
        movl $1597463007, %ecx
        subl %eax, %ecx
        movd %ecx, %xmm1
        mulss LCPI1_0, %xmm0
        mulss %xmm1, %xmm0
        movss LCPI1_1, %xmm2
        mulss %xmm1, %xmm0
        subss %xmm0, %xmm2
        movl 8(%esp), %eax
        mulss %xmm2, %xmm1
        movss %xmm1, (%eax)
        ret

instead of:

_invsqrt:
        subl $4, %esp
        movss 8(%esp), %xmm0
        movss %xmm0, (%esp)
        movl (%esp), %eax
        movl $1597463007, %ecx
        sarl %eax
        subl %eax, %ecx
        movl %ecx, (%esp)
        mulss LCPI1_0, %xmm0
        movss (%esp), %xmm1
        mulss %xmm1, %xmm0
        mulss %xmm1, %xmm0
        movss LCPI1_1, %xmm2
        subss %xmm0, %xmm2
        mulss %xmm2, %xmm1
        movl 12(%esp), %eax
        movss %xmm1, (%eax)
        addl $4, %esp
        ret

llvm-svn: 32418