llvm-svn: 27491

2. A shuffle mask element can also be an undef.

llvm-svn: 27472

CodeGen/X86/2006-04-04-CrossBlockCrash.ll

llvm-svn: 27436

or custom lowering fails.

llvm-svn: 27432

legal.

llvm-svn: 27402

  promoted/expanded (e.g. SCALAR_TO_VECTOR from i8/i16 on PPC).
* Add support for targets to request that VECTOR_SHUFFLE nodes be promoted
  to a canonical type, for example, we only want v16i8 shuffles on PPC.
* Move isShuffleLegal out of TLI into Legalize.
* Teach isShuffleLegal to allow shuffles that need to be promoted.

llvm-svn: 27399

llvm-svn: 27391

llvm-svn: 27380

llvm-svn: 27379

llvm-svn: 27375

llvm-svn: 27374

llvm-svn: 27367

llvm-svn: 27364

int %AreSecondAndThirdElementsBothNegative(<4 x float>* %in) {
entry:
        %tmp1 = load <4 x float>* %in           ; <<4 x float>> [#uses=1]
        %tmp = tail call int %llvm.ppc.altivec.vcmpgefp.p( int 1, <4 x float> < float 0x7FF8000000000000, float 0.000000e+00, float 0.000000e+00, float 0x7FF8000000000000 >, <4 x float> %tmp1 )           ; <int> [#uses=1]
        %tmp = seteq int %tmp, 0                ; <bool> [#uses=1]
        %tmp3 = cast bool %tmp to int           ; <int> [#uses=1]
        ret int %tmp3
}

into this:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        lvx v0, 0, r3
        lvx v1, r5, r4
        vcmpgefp. v0, v1, v0
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        mtspr 256, r2
        blr

instead of this:

_AreSecondAndThirdElementsBothNegative:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI1_0)
        lis r5, ha16(LCPI1_0)
        lvx v0, 0, r3
        lvx v1, r5, r4
        vcmpgefp. v0, v1, v0
        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: 27356

llvm-svn: 27349

into elements and operate on each piece.  This allows generic vector integer
multiplies to work on PPC, though the generated code is horrible.

llvm-svn: 27347

have to serialize against each other.  This allows us to schedule lvx's
across each other, for example.

llvm-svn: 27346

"vector unsigned char mergeLowHigh = (vector unsigned char)
( 8, 9, 10, 11, 16, 17, 18, 19, 12, 13, 14, 15, 20, 21, 22, 23 );
vector unsigned char mergeHighLow = vec_xor( mergeLowHigh, vec_splat_u8(8));"

aka:

void %test2(<16 x sbyte>* %P) {
  store <16 x sbyte> cast (<4 x int> xor (<4 x int> cast (<16 x ubyte> < ubyte 8, ubyte 9, ubyte 10, ubyte 11, ubyte 16, ubyte 17, ubyte 18, ubyte 19, ubyte 12, ubyte 13, ubyte 14, ubyte 15, ubyte 20, ubyte 21, ubyte 22, ubyte 23 > to <4 x int>), <4 x int> cast (<16 x sbyte> < sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8, sbyte 8 > to <4 x int>)) to <16 x sbyte>), <16 x sbyte> * %P
  ret void
}

into this:

_test2:
        mfspr r2, 256
        oris r4, r2, 32768
        mtspr 256, r4
        li r4, lo16(LCPI2_0)
        lis r5, ha16(LCPI2_0)
        lvx v0, r5, r4
        stvx v0, 0, r3
        mtspr 256, r2
        blr

instead of this:

_test2:
        mfspr r2, 256
        oris r4, r2, 49152
        mtspr 256, r4
        li r4, lo16(LCPI2_0)
        lis r5, ha16(LCPI2_0)
        vspltisb v0, 8
        lvx v1, r5, r4
        vxor v0, v1, v0
        stvx v0, 0, r3
        mtspr 256, r2
        blr

... which occurs here:
http://developer.apple.com/hardware/ve/calcspeed.html

llvm-svn: 27343

llvm-svn: 27342

llvm-svn: 27341

llvm-svn: 27340

llvm-svn: 27339

multiple register classes.  This fixes PowerPC/2006-04-01-FloatDoubleExtend.ll

llvm-svn: 27334

llvm-svn: 27317

Now all UnitTests/Vector/* tests pass on PPC.

llvm-svn: 27299

This fixes UnitTests/Vector/simple.c with altivec.

llvm-svn: 27298

to:

test_extract_elt:
        alloc r3 = ar.pfs,0,1,0,0
        adds r8 = 12, r32
        ;;
        ldfs f8 = [r8]
        mov ar.pfs = r3
        br.ret.sptk.many rp

instead of:

test_extract_elt:
        alloc r3 = ar.pfs,0,1,0,0
        adds r8 = 28, r32
        adds r9 = 24, r32
        adds r10 = 20, r32
        adds r11 = 16, r32
        ;;
        ldfs f6 = [r8]
        ;;
        ldfs f6 = [r9]
        adds r8 = 12, r32
        adds r9 = 8, r32
        adds r14 = 4, r32
        ;;
        ldfs f6 = [r10]
        ;;
        ldfs f6 = [r11]
        ldfs f8 = [r8]
        ;;
        ldfs f6 = [r9]
        ;;
        ldfs f6 = [r14]
        ;;
        ldfs f6 = [r32]
        mov ar.pfs = r3
        br.ret.sptk.many rp

llvm-svn: 27297

vector.ll:test_extract_elt2 into:

_test_extract_elt2:
        lfd f1, 32(r3)
        blr

instead of:

_test_extract_elt2:
        lfd f0, 56(r3)
        lfd f0, 48(r3)
        lfd f0, 40(r3)
        lfd f1, 32(r3)
        lfd f0, 24(r3)
        lfd f0, 16(r3)
        lfd f0, 8(r3)
        lfd f0, 0(r3)
        blr

llvm-svn: 27296

Generic/vector.ll:test_extract_elt on non-sse X86 systems.

llvm-svn: 27294

needs to be promoted or expanded.  Relegalize the scalar store once created.
This fixes CodeGen/Generic/vector.ll:test1 on non-SSE x86 targets.

llvm-svn: 27293

decimated vectors.  This fixes UnitTests/Vector/sumarray-dbl.c

llvm-svn: 27280

handling cases where the vector elements need promotion, expansion, and when
the vector type itself needs to be decimated.

llvm-svn: 27278

llvm-svn: 27274

Handle constantpacked vectors with constantexpr elements.

This fixes CodeGen/Generic/vector-constantexpr.ll

llvm-svn: 27241

sure to build it as SHUFFLE(X, undef, mask), not SHUFFLE(X, X, mask).

The later is not canonical form, and prevents the PPC splat pattern from
matching.  For a particular splat, we go from generating this:

	li r10, lo16(LCPI1_0)
	lis r11, ha16(LCPI1_0)
	lvx v3, r11, r10
	vperm v3, v2, v2, v3

to generating:

	vspltw v3, v2, 3

llvm-svn: 27236

llvm-svn: 27235

vector_shuffle node.  For this:

void test(__m128 *res, __m128 *A, __m128 *B) {
  *res = _mm_unpacklo_ps(*A, *B);
}

we now produce this code:

_test:
        movl 8(%esp), %eax
        movaps (%eax), %xmm0
        movl 12(%esp), %eax
        unpcklps (%eax), %xmm0
        movl 4(%esp), %eax
        movaps %xmm0, (%eax)
        ret

instead of this:

_test:
        subl $76, %esp
        movl 88(%esp), %eax
        movaps (%eax), %xmm0
        movaps %xmm0, (%esp)
        movaps %xmm0, 32(%esp)
        movss 4(%esp), %xmm0
        movss 32(%esp), %xmm1
        unpcklps %xmm0, %xmm1
        movl 84(%esp), %eax
        movaps (%eax), %xmm0
        movaps %xmm0, 16(%esp)
        movaps %xmm0, 48(%esp)
        movss 20(%esp), %xmm0
        movss 48(%esp), %xmm2
        unpcklps %xmm0, %xmm2
        unpcklps %xmm1, %xmm2
        movl 80(%esp), %eax
        movaps %xmm2, (%eax)
        addl $76, %esp
        ret

GCC produces this (with -fomit-frame-pointer):

_test:
        subl    $12, %esp
        movl    20(%esp), %eax
        movaps  (%eax), %xmm0
        movl    24(%esp), %eax
        unpcklps        (%eax), %xmm0
        movl    16(%esp), %eax
        movaps  %xmm0, (%eax)
        addl    $12, %esp
        ret

llvm-svn: 27233

llvm-svn: 27232

llvm-svn: 27231

llvm-svn: 27229