Transforms/InstCombine/vec_insert_to_shuffle.ll

llvm-svn: 27997

nondeterminism being bad) could cause some trivial missed optimizations (dead
phi nodes being left around for later passes to clean up).

With this, llvm-gcc4 now bootstraps and correctly compares.  I don't know
why I never tried to do it before... :)

llvm-svn: 27984

llvm-svn: 27912

llvm-svn: 27881

can be converted to losslessly, we can continue the conversion to a direct call.

llvm-svn: 27880

if the pointer is known aligned.

llvm-svn: 27781

Make the insert/extract elt -> shuffle code more aggressive.

This fixes CodeGen/PowerPC/vec_shuffle.ll

llvm-svn: 27728

llvm-svn: 27727

maximal shuffles out of them where possible.

llvm-svn: 27717

insert/extractelement operations.  This implements
Transforms/ScalarRepl/vector_promote.ll

llvm-svn: 27710

llvm-svn: 27652

llvm-svn: 27625

aggressive in some cases where LLVMGCC 4 is inserting casts for no reason.

This implements InstCombine/cast.ll:test27/28.

llvm-svn: 27620

llvm-svn: 27573

llvm-svn: 27571

are visible to analysis as intrinsics.  That is, make sure someone doesn't pass
free around by address in some struct (as happens in say 176.gcc).

This doesn't get rid of any indirect calls, just ensure calls to free and malloc
are always direct.

llvm-svn: 27560

llvm-svn: 27513

llvm-svn: 27478

us to compile oh-so-realistic stuff like this:

 vec_vperm(A, B, (vector unsigned char){14});

to:
        vspltb v0, v0, 14

instead of:

        vspltisb v0, 14
        vperm v0, v2, v1, v0

llvm-svn: 27452

        %tmp = cast <4 x uint> %tmp to <4 x int>                ; <<4 x int>> [#uses=1]
        %tmp = cast <4 x int> %tmp to <4 x float>               ; <<4 x float>> [#uses=1]

into:

        %tmp = cast <4 x uint> %tmp to <4 x float>              ; <<4 x float>> [#uses=1]

llvm-svn: 27355

        %tmp = cast <4 x uint>* %testData to <4 x int>*         ; <<4 x int>*> [#uses=1]
        %tmp = load <4 x int>* %tmp             ; <<4 x int>> [#uses=1]

to this:

        %tmp = load <4 x uint>* %testData               ; <<4 x uint>> [#uses=1]
        %tmp = cast <4 x uint> %tmp to <4 x int>                ; <<4 x int>> [#uses=1]

llvm-svn: 27353

elimination of one load from this:

int AreSecondAndThirdElementsBothNegative( vector float *in ) {
#define QNaN 0x7FC00000
const vector unsigned int testData = (vector unsigned int)( QNaN, 0, 0, QNaN );
vector float test = vec_ld( 0, (float*) &testData );
return ! vec_any_ge( test, *in );
}

Now generating:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        addi r6, r1, -16
        lvx v0, r5, r4
        stvx v0, 0, r6
        lvx v1, 0, r3
        vcmpgefp. v0, v0, v1
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        xori r3, r3, 1
        cntlzw r3, r3
        srwi r3, r3, 5
        mtspr 256, r2
        blr

llvm-svn: 27352

llvm-svn: 27344

llvm-svn: 27332

llvm-svn: 27330

Fold (B&A)^A == ~B & A

This implements InstCombine/xor.ll:test2[56]

llvm-svn: 27328

extract_element'd value, do so.

llvm-svn: 27323

llvm-svn: 27300

llvm-svn: 27261

llvm-svn: 27161

llvm-svn: 27125

llvm-svn: 27052

llvm-svn: 27051

llvm-svn: 26993

llvm-svn: 26992

llvm-svn: 26953

Transforms/CorrelatedExprs/switch.ll

Patch contributed by Eric Kidd!

llvm-svn: 26872

- Added more debugging info.
- Allow reuse of IV of negative stride. e.g. -4 stride == 2 * iv of -2 stride.

llvm-svn: 26841

for more IV reuses.

llvm-svn: 26837

of a smaller stride even if they have a common loop invariant expression part.

llvm-svn: 26828