of various 4-element vectors.

llvm-svn: 27739

llvm-svn: 27734

llvm-svn: 27733

address has to be 16-byte aligned but the values aren't spilled to 128-bit
locations.

llvm-svn: 27732

one type (v4i32) so that we don't have to write patterns for each type, and
so that more CSE opportunities are exposed.

llvm-svn: 27731

Remove some done items from the todo list.

llvm-svn: 27729

llvm-svn: 27726

go away when I start using evan's binop type canonicalizer

llvm-svn: 27725

bitconverted from some other type.

llvm-svn: 27724

llvm-svn: 27722

llvm-svn: 27721

llvm-svn: 27720

llvm-svn: 27719

llvm-svn: 27718

llvm-svn: 27716

llvm-svn: 27715

llvm-svn: 27714

llvm-svn: 27711

llvm-svn: 27699

vla are present in the function. This causes a crash when a leaf function
allocates space on the stack used to store / load with 128-bit SSE
instructions.

llvm-svn: 27698

llvm-svn: 27697

separate functions, for simplicity and code clarity.

llvm-svn: 27693

functions, which makes the code much cleaner :)

llvm-svn: 27692

llvm-svn: 27685

llvm-svn: 27684

llvm-svn: 27683

llvm-svn: 27682

llvm-svn: 27668

tested by CodeGen/Generic/vector.ll

llvm-svn: 27657

llvm-svn: 27654

llvm-svn: 27651

llvm-svn: 27647

llvm-svn: 27645

llvm-svn: 27644

llvm-svn: 27643

llvm-svn: 27639

llvm-svn: 27638

llvm-svn: 27637

Clean up and fix various logical ops issues.

llvm-svn: 27633

different types.

Codegen spltw(0x7FFFFFFF) and spltw(0x80000000) without a constant pool load,
implementing PowerPC/vec_constants.ll:test1.  This compiles:

typedef float vf __attribute__ ((vector_size (16)));
typedef int vi __attribute__ ((vector_size (16)));
void test(vi *P1, vi *P2, vf *P3) {
  *P1 &= (vi){0x80000000,0x80000000,0x80000000,0x80000000};
  *P2 &= (vi){0x7FFFFFFF,0x7FFFFFFF,0x7FFFFFFF,0x7FFFFFFF};
  *P3 = vec_abs((vector float)*P3);
}

to:

_test:
        mfspr r2, 256
        oris r6, r2, 49152
        mtspr 256, r6
        vspltisw v0, -1
        vslw v0, v0, v0
        lvx v1, 0, r3
        vand v1, v1, v0
        stvx v1, 0, r3
        lvx v1, 0, r4
        vandc v1, v1, v0
        stvx v1, 0, r4
        lvx v1, 0, r5
        vandc v0, v1, v0
        stvx v0, 0, r5
        mtspr 256, r2
        blr

instead of (with two constant pool entries):

_test:
        mfspr r2, 256
        oris r6, r2, 49152
        mtspr 256, r6
        li r6, lo16(LCPI1_0)
        lis r7, ha16(LCPI1_0)
        li r8, lo16(LCPI1_1)
        lis r9, ha16(LCPI1_1)
        lvx v0, r7, r6
        lvx v1, 0, r3
        vand v0, v1, v0
        stvx v0, 0, r3
        lvx v0, r9, r8
        lvx v1, 0, r4
        vand v1, v1, v0
        stvx v1, 0, r4
        lvx v1, 0, r5
        vand v0, v1, v0
        stvx v0, 0, r5
        mtspr 256, r2
        blr

GCC produces (with 2 cp entries):

_test:
        mfspr r0,256
        stw r0,-4(r1)
        oris r0,r0,0xc00c
        mtspr 256,r0
        lis r2,ha16(LC0)
        lis r9,ha16(LC1)
        la r2,lo16(LC0)(r2)
        lvx v0,0,r3
        lvx v1,0,r5
        la r9,lo16(LC1)(r9)
        lwz r12,-4(r1)
        lvx v12,0,r2
        lvx v13,0,r9
        vand v0,v0,v12
        stvx v0,0,r3
        vspltisw v0,-1
        vslw v12,v0,v0
        vandc v1,v1,v12
        stvx v1,0,r5
        lvx v0,0,r4
        vand v0,v0,v13
        stvx v0,0,r4
        mtspr 256,r12
        blr

llvm-svn: 27624