forked from OSchip/llvm-project
394 lines
18 KiB
LLVM
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
|
|
}
|
|
|