llvm-project/llvm/test/CodeGen/AArch64/aarch64-interleaved-accesse...

394 lines
18 KiB
LLVM

; RUN: llc -mtriple=aarch64 -lower-interleaved-accesses=true < %s | FileCheck %s -check-prefix=NEON
; RUN: llc -mtriple=aarch64 -lower-interleaved-accesses=true -mattr=-neon < %s | FileCheck %s -check-prefix=NONEON
; NEON-LABEL: load_factor2:
; NEON: ld2 { v0.8b, v1.8b }, [x0]
; NONEON-LABEL: load_factor2:
; NONEON-NOT: ld2
define <8 x i8> @load_factor2(<16 x i8>* %ptr) {
%wide.vec = load <16 x i8>, <16 x i8>* %ptr, align 4
%strided.v0 = shufflevector <16 x i8> %wide.vec, <16 x i8> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
%strided.v1 = shufflevector <16 x i8> %wide.vec, <16 x i8> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
%add = add nsw <8 x i8> %strided.v0, %strided.v1
ret <8 x i8> %add
}
; NEON-LABEL: load_factor3:
; NEON: ld3 { v0.4s, v1.4s, v2.4s }, [x0]
; NONEON-LABEL: load_factor3:
; NONEON-NOT: ld3
define <4 x i32> @load_factor3(i32* %ptr) {
%base = bitcast i32* %ptr to <12 x i32>*
%wide.vec = load <12 x i32>, <12 x i32>* %base, align 4
%strided.v2 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
%strided.v1 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
%add = add nsw <4 x i32> %strided.v2, %strided.v1
ret <4 x i32> %add
}
; NEON-LABEL: load_factor4:
; NEON: ld4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
; NONEON-LABEL: load_factor4:
; NONEON-NOT: ld4
define <4 x i32> @load_factor4(i32* %ptr) {
%base = bitcast i32* %ptr to <16 x i32>*
%wide.vec = load <16 x i32>, <16 x i32>* %base, align 4
%strided.v0 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
%strided.v2 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
%add = add nsw <4 x i32> %strided.v0, %strided.v2
ret <4 x i32> %add
}
; NEON-LABEL: store_factor2:
; NEON: st2 { v0.8b, v1.8b }, [x0]
; NONEON-LABEL: store_factor2:
; NONEON-NOT: st2
define void @store_factor2(<16 x i8>* %ptr, <8 x i8> %v0, <8 x i8> %v1) {
%interleaved.vec = shufflevector <8 x i8> %v0, <8 x i8> %v1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
store <16 x i8> %interleaved.vec, <16 x i8>* %ptr, align 4
ret void
}
; NEON-LABEL: store_factor3:
; NEON: st3 { v0.4s, v1.4s, v2.4s }, [x0]
; NONEON-LABEL: store_factor3:
; NONEON-NOT: st3
define void @store_factor3(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
%base = bitcast i32* %ptr to <12 x i32>*
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%v2_u = shufflevector <4 x i32> %v2, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_u, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
store <12 x i32> %interleaved.vec, <12 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_factor4:
; NEON: st4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
; NONEON-LABEL: store_factor4:
; NONEON-NOT: st4
define void @store_factor4(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
%base = bitcast i32* %ptr to <16 x i32>*
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%v2_v3 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_v3, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 1, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
store <16 x i32> %interleaved.vec, <16 x i32>* %base, align 4
ret void
}
; The following cases test that interleaved access of pointer vectors can be
; matched to ldN/stN instruction.
; NEON-LABEL: load_ptrvec_factor2:
; NEON: ld2 { v0.2d, v1.2d }, [x0]
; NONEON-LABEL: load_ptrvec_factor2:
; NONEON-NOT: ld2
define <2 x i32*> @load_ptrvec_factor2(i32** %ptr) {
%base = bitcast i32** %ptr to <4 x i32*>*
%wide.vec = load <4 x i32*>, <4 x i32*>* %base, align 4
%strided.v0 = shufflevector <4 x i32*> %wide.vec, <4 x i32*> undef, <2 x i32> <i32 0, i32 2>
ret <2 x i32*> %strided.v0
}
; NEON-LABEL: load_ptrvec_factor3:
; NEON: ld3 { v0.2d, v1.2d, v2.2d }, [x0]
; NONEON-LABEL: load_ptrvec_factor3:
; NONEON-NOT: ld3
define void @load_ptrvec_factor3(i32** %ptr, <2 x i32*>* %ptr1, <2 x i32*>* %ptr2) {
%base = bitcast i32** %ptr to <6 x i32*>*
%wide.vec = load <6 x i32*>, <6 x i32*>* %base, align 4
%strided.v2 = shufflevector <6 x i32*> %wide.vec, <6 x i32*> undef, <2 x i32> <i32 2, i32 5>
store <2 x i32*> %strided.v2, <2 x i32*>* %ptr1
%strided.v1 = shufflevector <6 x i32*> %wide.vec, <6 x i32*> undef, <2 x i32> <i32 1, i32 4>
store <2 x i32*> %strided.v1, <2 x i32*>* %ptr2
ret void
}
; NEON-LABEL: load_ptrvec_factor4:
; NEON: ld4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
; NONEON-LABEL: load_ptrvec_factor4:
; NONEON-NOT: ld4
define void @load_ptrvec_factor4(i32** %ptr, <2 x i32*>* %ptr1, <2 x i32*>* %ptr2) {
%base = bitcast i32** %ptr to <8 x i32*>*
%wide.vec = load <8 x i32*>, <8 x i32*>* %base, align 4
%strided.v1 = shufflevector <8 x i32*> %wide.vec, <8 x i32*> undef, <2 x i32> <i32 1, i32 5>
%strided.v3 = shufflevector <8 x i32*> %wide.vec, <8 x i32*> undef, <2 x i32> <i32 3, i32 7>
store <2 x i32*> %strided.v1, <2 x i32*>* %ptr1
store <2 x i32*> %strided.v3, <2 x i32*>* %ptr2
ret void
}
; NEON-LABEL: store_ptrvec_factor2:
; NEON: st2 { v0.2d, v1.2d }, [x0]
; NONEON-LABEL: store_ptrvec_factor2:
; NONEON-NOT: st2
define void @store_ptrvec_factor2(i32** %ptr, <2 x i32*> %v0, <2 x i32*> %v1) {
%base = bitcast i32** %ptr to <4 x i32*>*
%interleaved.vec = shufflevector <2 x i32*> %v0, <2 x i32*> %v1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
store <4 x i32*> %interleaved.vec, <4 x i32*>* %base, align 4
ret void
}
; NEON-LABEL: store_ptrvec_factor3:
; NEON: st3 { v0.2d, v1.2d, v2.2d }, [x0]
; NONEON-LABEL: store_ptrvec_factor3:
; NONEON-NOT: st3
define void @store_ptrvec_factor3(i32** %ptr, <2 x i32*> %v0, <2 x i32*> %v1, <2 x i32*> %v2) {
%base = bitcast i32** %ptr to <6 x i32*>*
%v0_v1 = shufflevector <2 x i32*> %v0, <2 x i32*> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%v2_u = shufflevector <2 x i32*> %v2, <2 x i32*> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
%interleaved.vec = shufflevector <4 x i32*> %v0_v1, <4 x i32*> %v2_u, <6 x i32> <i32 0, i32 2, i32 4, i32 1, i32 3, i32 5>
store <6 x i32*> %interleaved.vec, <6 x i32*>* %base, align 4
ret void
}
; NEON-LABEL: store_ptrvec_factor4:
; NEON: st4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0]
; NONEON-LABEL: store_ptrvec_factor4:
; NONEON-NOT: st4
define void @store_ptrvec_factor4(i32* %ptr, <2 x i32*> %v0, <2 x i32*> %v1, <2 x i32*> %v2, <2 x i32*> %v3) {
%base = bitcast i32* %ptr to <8 x i32*>*
%v0_v1 = shufflevector <2 x i32*> %v0, <2 x i32*> %v1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%v2_v3 = shufflevector <2 x i32*> %v2, <2 x i32*> %v3, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
%interleaved.vec = shufflevector <4 x i32*> %v0_v1, <4 x i32*> %v2_v3, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 1, i32 3, i32 5, i32 7>
store <8 x i32*> %interleaved.vec, <8 x i32*>* %base, align 4
ret void
}
; Following cases check that shuffle maskes with undef indices can be matched
; into ldN/stN instruction.
; NEON-LABEL: load_undef_mask_factor2:
; NEON: ld2 { v0.4s, v1.4s }, [x0]
; NONEON-LABEL: load_undef_mask_factor2:
; NONEON-NOT: ld2
define <4 x i32> @load_undef_mask_factor2(i32* %ptr) {
%base = bitcast i32* %ptr to <8 x i32>*
%wide.vec = load <8 x i32>, <8 x i32>* %base, align 4
%strided.v0 = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 undef, i32 2, i32 undef, i32 6>
%strided.v1 = shufflevector <8 x i32> %wide.vec, <8 x i32> undef, <4 x i32> <i32 undef, i32 3, i32 undef, i32 7>
%add = add nsw <4 x i32> %strided.v0, %strided.v1
ret <4 x i32> %add
}
; NEON-LABEL: load_undef_mask_factor3:
; NEON: ld3 { v0.4s, v1.4s, v2.4s }, [x0]
; NONEON-LABEL: load_undef_mask_factor3:
; NONEON-NOT: ld3
define <4 x i32> @load_undef_mask_factor3(i32* %ptr) {
%base = bitcast i32* %ptr to <12 x i32>*
%wide.vec = load <12 x i32>, <12 x i32>* %base, align 4
%strided.v2 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
%strided.v1 = shufflevector <12 x i32> %wide.vec, <12 x i32> undef, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
%add = add nsw <4 x i32> %strided.v2, %strided.v1
ret <4 x i32> %add
}
; NEON-LABEL: load_undef_mask_factor4:
; NEON: ld4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
; NONEON-LABEL: load_undef_mask_factor4:
; NONEON-NOT: ld4
define <4 x i32> @load_undef_mask_factor4(i32* %ptr) {
%base = bitcast i32* %ptr to <16 x i32>*
%wide.vec = load <16 x i32>, <16 x i32>* %base, align 4
%strided.v0 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 0, i32 4, i32 undef, i32 undef>
%strided.v2 = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <4 x i32> <i32 2, i32 6, i32 undef, i32 undef>
%add = add nsw <4 x i32> %strided.v0, %strided.v2
ret <4 x i32> %add
}
; NEON-LABEL: store_undef_mask_factor2:
; NEON: st2 { v0.4s, v1.4s }, [x0]
; NONEON-LABEL: store_undef_mask_factor2:
; NONEON-NOT: st2
define void @store_undef_mask_factor2(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1) {
%base = bitcast i32* %ptr to <8 x i32>*
%interleaved.vec = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 2, i32 6, i32 3, i32 7>
store <8 x i32> %interleaved.vec, <8 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_undef_mask_factor3:
; NEON: st3 { v0.4s, v1.4s, v2.4s }, [x0]
; NONEON-LABEL: store_undef_mask_factor3:
; NONEON-NOT: st3
define void @store_undef_mask_factor3(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2) {
%base = bitcast i32* %ptr to <12 x i32>*
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%v2_u = shufflevector <4 x i32> %v2, <4 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_u, <12 x i32> <i32 0, i32 4, i32 undef, i32 1, i32 undef, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
store <12 x i32> %interleaved.vec, <12 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_undef_mask_factor4:
; NEON: st4 { v0.4s, v1.4s, v2.4s, v3.4s }, [x0]
; NONEON-LABEL: store_undef_mask_factor4:
; NONEON-NOT: st4
define void @store_undef_mask_factor4(i32* %ptr, <4 x i32> %v0, <4 x i32> %v1, <4 x i32> %v2, <4 x i32> %v3) {
%base = bitcast i32* %ptr to <16 x i32>*
%v0_v1 = shufflevector <4 x i32> %v0, <4 x i32> %v1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%v2_v3 = shufflevector <4 x i32> %v2, <4 x i32> %v3, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%interleaved.vec = shufflevector <8 x i32> %v0_v1, <8 x i32> %v2_v3, <16 x i32> <i32 0, i32 4, i32 8, i32 undef, i32 undef, i32 5, i32 9, i32 13, i32 2, i32 6, i32 10, i32 14, i32 3, i32 7, i32 11, i32 15>
store <16 x i32> %interleaved.vec, <16 x i32>* %base, align 4
ret void
}
; Check that we do something sane with illegal types.
; NEON-LABEL: load_illegal_factor2:
; NEON: BB#0:
; NEON-NEXT: ldr q[[V:[0-9]+]], [x0]
; NEON-NEXT: uzp1 v0.4s, v[[V]].4s, v{{.*}}.4s
; NEON-NEXT: ret
; NONEON-LABEL: load_illegal_factor2:
; NONEON: BB#0:
; NONEON-NEXT: ldr s0, [x0]
; NONEON-NEXT: ldr s1, [x0, #8]
; NONEON-NEXT: ret
define <3 x float> @load_illegal_factor2(<3 x float>* %p) nounwind {
%tmp1 = load <3 x float>, <3 x float>* %p, align 16
%tmp2 = shufflevector <3 x float> %tmp1, <3 x float> undef, <3 x i32> <i32 0, i32 2, i32 undef>
ret <3 x float> %tmp2
}
; NEON-LABEL: store_illegal_factor2:
; NEON: BB#0:
; NEON-NEXT: uzp1 v0.4s, v0.4s, v{{.*}}.4s
; NEON-NEXT: st1 { v0.d }[0], [x0]
; NEON-NEXT: ret
; NONEON-LABEL: store_illegal_factor2:
; NONEON: BB#0:
; NONEON-NEXT: fmov w[[ELT2:[0-9]+]], s2
; NONEON-NEXT: fmov w[[RES:[0-9]+]], s0
; NONEON-NEXT: bfi x[[RES]], x[[ELT2]], #32, #32
; NONEON-NEXT: str x[[RES]], [x0]
; NONEON-NEXT: ret
define void @store_illegal_factor2(<3 x float>* %p, <3 x float> %v) nounwind {
%tmp1 = shufflevector <3 x float> %v, <3 x float> undef, <3 x i32> <i32 0, i32 2, i32 undef>
store <3 x float> %tmp1, <3 x float>* %p, align 16
ret void
}
; NEON-LABEL: load_factor2_with_extract_user:
; NEON: ld2 { v0.4s, v1.4s }, [x0]
; NEON: mov w0, v0.s[1]
; NONEON-LABEL: load_factor2_with_extract_user:
; NONEON-NOT: ld2
define i32 @load_factor2_with_extract_user(<8 x i32>* %a) {
%1 = load <8 x i32>, <8 x i32>* %a, align 8
%2 = shufflevector <8 x i32> %1, <8 x i32> undef, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
%3 = extractelement <8 x i32> %1, i32 2
ret i32 %3
}
; NEON-LABEL: store_general_mask_factor4:
; NEON: st4 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor4:
; NONEON-NOT: st4
define void @store_general_mask_factor4(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <8 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 16, i32 32, i32 8, i32 5, i32 17, i32 33, i32 9>
store <8 x i32> %i.vec, <8 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor4_undefbeg:
; NEON: st4 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor4_undefbeg:
; NONEON-NOT: st4
define void @store_general_mask_factor4_undefbeg(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <8 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 undef, i32 16, i32 32, i32 8, i32 5, i32 17, i32 33, i32 9>
store <8 x i32> %i.vec, <8 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor4_undefend:
; NEON: st4 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor4_undefend:
; NONEON-NOT: st4
define void @store_general_mask_factor4_undefend(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <8 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 16, i32 32, i32 8, i32 5, i32 17, i32 33, i32 undef>
store <8 x i32> %i.vec, <8 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor4_undefmid:
; NEON: st4 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor4_undefmid:
; NONEON-NOT: st4
define void @store_general_mask_factor4_undefmid(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <8 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 undef, i32 32, i32 8, i32 5, i32 17, i32 undef, i32 9>
store <8 x i32> %i.vec, <8 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor4_undefmulti:
; NEON: st4 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor4_undefmulti:
; NONEON-NOT: st4
define void @store_general_mask_factor4_undefmulti(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <8 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <8 x i32> <i32 4, i32 undef, i32 undef, i32 8, i32 undef, i32 undef, i32 undef, i32 9>
store <8 x i32> %i.vec, <8 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor3:
; NEON: st3 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor3:
; NONEON-NOT: st3
define void @store_general_mask_factor3(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <12 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 4, i32 32, i32 16, i32 5, i32 33, i32 17, i32 6, i32 34, i32 18, i32 7, i32 35, i32 19>
store <12 x i32> %i.vec, <12 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor3_undefmultimid:
; NEON: st3 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor3_undefmultimid:
; NONEON-NOT: st3
define void @store_general_mask_factor3_undefmultimid(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <12 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 4, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 7, i32 35, i32 19>
store <12 x i32> %i.vec, <12 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor3_undef_fail:
; NEON-NOT: st3
; NONEON-LABEL: store_general_mask_factor3_undef_fail:
; NONEON-NOT: st3
define void @store_general_mask_factor3_undef_fail(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <12 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 4, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 8, i32 35, i32 19>
store <12 x i32> %i.vec, <12 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor3_undeflane:
; NEON: st3 { v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s, v{{[0-9]+}}.{{[0-9]+}}s }, [x0]
; NONEON-LABEL: store_general_mask_factor3_undeflane:
; NONEON-NOT: st3
define void @store_general_mask_factor3_undeflane(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <12 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 undef, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 undef, i32 35, i32 19>
store <12 x i32> %i.vec, <12 x i32>* %base, align 4
ret void
}
; NEON-LABEL: store_general_mask_factor3_negativestart:
; NEON-NOT: st3
; NONEON-LABEL: store_general_mask_factor3_negativestart:
; NONEON-NOT: st3
define void @store_general_mask_factor3_negativestart(i32* %ptr, <32 x i32> %v0, <32 x i32> %v1) {
%base = bitcast i32* %ptr to <12 x i32>*
%i.vec = shufflevector <32 x i32> %v0, <32 x i32> %v1, <12 x i32> <i32 undef, i32 32, i32 16, i32 undef, i32 33, i32 17, i32 undef, i32 34, i32 18, i32 2, i32 35, i32 19>
store <12 x i32> %i.vec, <12 x i32>* %base, align 4
ret void
}