Constant fold all of the vector binops. This allows us to compile this:

"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

0 files changed, 0 insertions, 0 deletions