https://llvm.org/bugs/show_bug.cgi?id=28530
Bug ID: 28530
Summary: [AArch64] recognize the shufflevector equivalent of a
vector select
Product: libraries
Version: trunk
Hardware: PC
OS: All
Status: NEW
Severity: normal
Priority: P
Component: Backend: AArch64
Assignee: unassignedb...@nondot.org
Reporter: spatel+l...@rotateright.com
CC: llvm-bugs@lists.llvm.org
Classification: Unclassified
$ cat shufsel.ll
define <4 x i32> @foo(<4 x i32> %a, <4 x i32> %b) {
%sel = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x i32> %a,
<4 x i32> %b
ret <4 x i32> %sel
}
define <4 x i32> @goo(<4 x i32> %a, <4 x i32> %b) {
%shuf = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 5,
i32 6, i32 3>
ret <4 x i32> %shuf
}
I'm guessing that one of these is generally better than the other (and there
may be a better way than either of these?):
$ ./llc shufsel.ll -o - -mtriple=aarch64
.LCPI0_0:
.word 4294967295 // 0xffffffff
.word 0 // 0x0
.word 0 // 0x0
.word 4294967295 // 0xffffffff
foo:
adrp x8, .LCPI0_0
ldr q2, [x8, :lo12:.LCPI0_0]
bsl v2.16b, v0.16b, v1.16b
mov v0.16b, v2.16b
ret
goo: // @goo
ext v1.16b, v0.16b, v1.16b, #12
ext v0.16b, v1.16b, v0.16b, #4
ext v1.16b, v1.16b, v1.16b, #8
ext v0.16b, v0.16b, v1.16b, #12
ret
Note that in http://reviews.llvm.org/D22114 , there's a proposal to
canonicalize to the shufflevector form of the IR.
--
You are receiving this mail because:
You are on the CC list for the bug.
_______________________________________________
llvm-bugs mailing list
llvm-bugs@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
