llvm-svn: 27900

llvm-svn: 27895

llvm-svn: 27885

to a vector shuffle.
- VECTOR_SHUFFLE lowering change in preparation for more efficient codegen
of vector shuffle with zero (or any splat) vector.

llvm-svn: 27875

CodeGen/PowerPC/2006-04-19-vmaddfp-crash.ll

llvm-svn: 27868

but i64 is not. If possible, change a i64 op to a f64 (e.g. load, constant)
and then cast it back.

llvm-svn: 27849

llvm-svn: 27847

  instructions.
- Fixed a commute vector_shuff bug.

llvm-svn: 27845

llvm-svn: 27844

llvm-svn: 27843

- Added more movhlps and movlhps patterns.

llvm-svn: 27842

llvm-svn: 27840

llvm-svn: 27836

- Increase cost (complexity) of patterns which match mov{h|l}ps ops. These
  are preferred over shufps in most cases.

llvm-svn: 27835

llvm-svn: 27834

llvm-svn: 27832

llvm-svn: 27828

llvm-svn: 27827

- PINSRWrmi encoding bug.

llvm-svn: 27818

llvm-svn: 27817

llvm-svn: 27816

llvm-svn: 27815

llvm-svn: 27814

llvm-svn: 27813

llvm-svn: 27810

llvm-svn: 27809

void foo2(vector float *A, vector float *B) {
  vector float C = (vector float)vec_cmpeq(*A, *B);
  if (!vec_any_eq(*A, *B))
    *B = (vector float){0,0,0,0};
  *A = C;
}

llvm-svn: 27808

llvm-svn: 27807

llvm-svn: 27806

If an altivec predicate compare is used immediately by a branch, don't
use a (serializing) MFCR instruction to read the CR6 register, which requires
a compare to get it back to CR's.  Instead, just branch on CR6 directly. :)

For example, for:
void foo2(vector float *A, vector float *B) {
  if (!vec_any_eq(*A, *B))
    *B = (vector float){0,0,0,0};
}

We now generate:

_foo2:
        mfspr r2, 256
        oris r5, r2, 12288
        mtspr 256, r5
        lvx v2, 0, r4
        lvx v3, 0, r3
        vcmpeqfp. v2, v3, v2
        bne cr6, LBB1_2 ; UnifiedReturnBlock
LBB1_1: ; cond_true
        vxor v2, v2, v2
        stvx v2, 0, r4
        mtspr 256, r2
        blr
LBB1_2: ; UnifiedReturnBlock
        mtspr 256, r2
        blr

instead of:

_foo2:
        mfspr r2, 256
        oris r5, r2, 12288
        mtspr 256, r5
        lvx v2, 0, r4
        lvx v3, 0, r3
        vcmpeqfp. v2, v3, v2
        mfcr r3, 2
        rlwinm r3, r3, 27, 31, 31
        cmpwi cr0, r3, 0
        beq cr0, LBB1_2 ; UnifiedReturnBlock
LBB1_1: ; cond_true
        vxor v2, v2, v2
        stvx v2, 0, r4
        mtspr 256, r2
        blr
LBB1_2: ; UnifiedReturnBlock
        mtspr 256, r2
        blr

This implements CodeGen/PowerPC/vec_br_cmp.ll.

llvm-svn: 27804

llvm-svn: 27802

to optimize cases where it has to spill a lot

llvm-svn: 27801

even/odd halves.  Thanks to Nate telling me what's what.

llvm-svn: 27793

        vmuloub v5, v3, v2
        vmuleub v2, v3, v2
        vperm v2, v2, v5, v4

This implements CodeGen/PowerPC/vec_mul.ll.  With this, v16i8 multiplies are
6.79x faster than before.

Overall, UnitTests/Vector/multiplies.c is now 2.45x faster with LLVM than with
GCC.

Remove the 'integer multiplies' todo from the README file.

llvm-svn: 27792

llvm-svn: 27790

        li r5, lo16(LCPI1_0)
        lis r6, ha16(LCPI1_0)
        lvx v4, r6, r5
        vmulouh v5, v3, v2
        vmuleuh v2, v3, v2
        vperm v2, v2, v5, v4

where v4 is:
LCPI1_0:                                        ;  <16 x ubyte>
        .byte   2
        .byte   3
        .byte   18
        .byte   19
        .byte   6
        .byte   7
        .byte   22
        .byte   23
        .byte   10
        .byte   11
        .byte   26
        .byte   27
        .byte   14
        .byte   15
        .byte   30
        .byte   31

This is 5.07x faster on the G5 (measured) than lowering to scalar code +
loads/stores.

llvm-svn: 27789

scalarize the sequence into 4 mullw's and a bunch of load/store traffic.

This speeds up v4i32 multiplies 4.1x (measured) on a G5.  This implements
PowerPC/vec_mul.ll

llvm-svn: 27788

llvm-svn: 27786

llvm-svn: 27784

llvm-svn: 27782