[AArch64] generate vuzp instead of mov

when a BUILD_VECTOR is created out of a sequence of EXTRACT_VECTOR_ELT with a
specific pattern sequence, either <0, 2, 4, ...> or <1, 3, 5, ...>, replace the
BUILD_VECTOR with either vuzp1 or vuzp2.

With this patch LLVM generates the following code for the first function fun1 in the testcase:
adrp x8, .LCPI0_0
ldr  q0, [x8, :lo12:.LCPI0_0]
tbl  v0.16b, { v0.16b }, v0.16b
ext  v1.16b, v0.16b, v0.16b, #8
uzp1 v0.8b, v0.8b, v1.8b
str  d0, [x8]
ret

Without this patch LLVM currently generates this code:
adrp    x8, .LCPI0_0
ldr     q0, [x8, :lo12:.LCPI0_0]
tbl     v0.16b, { v0.16b }, v0.16b
mov     v1.16b, v0.16b
mov     v1.b[1], v0.b[2]
mov     v1.b[2], v0.b[4]
mov     v1.b[3], v0.b[6]
mov     v1.b[4], v0.b[8]
mov     v1.b[5], v0.b[10]
mov     v1.b[6], v0.b[12]
mov     v1.b[7], v0.b[14]
str     d1, [x8]
ret

llvm-svn: 326443

0 files changed, 0 insertions, 0 deletions