define <16 x i8> @combine_v16i8(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine_v16i8:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip2.8b v2, v0, v1
-; CHECK-NEXT: zip1.8b v0, v0, v1
-; CHECK-NEXT: mov.d v0[1], v2[0]
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.16b v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <8 x i8> %0, <8 x i8> %1, <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>
ret <16 x i8> %3
define <16 x i8> @combine2_v16i8(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine2_v16i8:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip1.8b v2, v0, v1
-; CHECK-NEXT: zip2.8b v0, v0, v1
-; CHECK-NEXT: mov.d v2[1], v0[0]
-; CHECK-NEXT: mov.16b v0, v2
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.16b v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
%4 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
define <8 x i16> @combine_v8i16(<4 x i16> %0, <4 x i16> %1) {
; CHECK-LABEL: combine_v8i16:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip2.4h v2, v0, v1
-; CHECK-NEXT: zip1.4h v0, v0, v1
-; CHECK-NEXT: mov.d v0[1], v2[0]
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.8h v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x i16> %3
define <8 x i16> @combine2_v8i16(<4 x i16> %0, <4 x i16> %1) {
; CHECK-LABEL: combine2_v8i16:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip1.4h v2, v0, v1
-; CHECK-NEXT: zip2.4h v0, v0, v1
-; CHECK-NEXT: mov.d v2[1], v0[0]
-; CHECK-NEXT: mov.16b v0, v2
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.8h v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <4 x i16> %0, <4 x i16> %1, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
%4 = shufflevector <4 x i16> %0, <4 x i16> %1, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
define <4 x i32> @combine_v4i32(<2 x i32> %0, <2 x i32> %1) {
; CHECK-LABEL: combine_v4i32:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip2.2s v2, v0, v1
-; CHECK-NEXT: zip1.2s v0, v0, v1
-; CHECK-NEXT: mov.d v0[1], v2[0]
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.4s v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <2 x i32> %0, <2 x i32> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x i32> %3
define <4 x i32> @combine2_v4i32(<2 x i32> %0, <2 x i32> %1) {
; CHECK-LABEL: combine2_v4i32:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip1.2s v2, v0, v1
-; CHECK-NEXT: zip2.2s v0, v0, v1
-; CHECK-NEXT: mov.d v2[1], v0[0]
-; CHECK-NEXT: mov.16b v0, v2
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.4s v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <2 x i32> %0, <2 x i32> %1, <2 x i32> <i32 0, i32 2>
%4 = shufflevector <2 x i32> %0, <2 x i32> %1, <2 x i32> <i32 1, i32 3>
define <16 x i8> @combine_v16i8_undef(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine_v16i8_undef:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip2.8b v2, v0, v1
-; CHECK-NEXT: zip1.8b v0, v0, v1
-; CHECK-NEXT: mov.d v0[1], v2[0]
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.16b v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <8 x i8> %0, <8 x i8> %1, <16 x i32> <i32 0, i32 undef, 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>
ret <16 x i8> %3
define <16 x i8> @combine2_v16i8_undef(<8 x i8> %0, <8 x i8> %1) {
; CHECK-LABEL: combine2_v16i8_undef:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip1.8b v2, v0, v1
-; CHECK-NEXT: zip2.8b v0, v0, v1
-; CHECK-NEXT: mov.d v2[1], v0[0]
-; CHECK-NEXT: mov.16b v0, v2
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.16b v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 0, i32 undef, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
%4 = shufflevector <8 x i8> %0, <8 x i8> %1, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
define <8 x i16> @combine_v8i16_undef(<4 x i16> %0, <4 x i16> %1) {
; CHECK-LABEL: combine_v8i16_undef:
; CHECK: // %bb.0:
-; CHECK-NEXT: zip2.4h v2, v0, v1
-; CHECK-NEXT: zip1.4h v0, v0, v1
-; CHECK-NEXT: mov.d v0[1], v2[0]
+; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
+; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
+; CHECK-NEXT: zip1.8h v0, v0, v1
; CHECK-NEXT: ret
%3 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 undef, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x i16> %3
; CHECK-NEXT: fneg v4.2s, v5.2s
; CHECK-NEXT: fmla v3.2s, v0.2s, v2.2s
; CHECK-NEXT: fmla v4.2s, v1.2s, v2.2s
-; CHECK-NEXT: zip2 v1.2s, v4.2s, v3.2s
-; CHECK-NEXT: zip1 v0.2s, v4.2s, v3.2s
-; CHECK-NEXT: mov v0.d[1], v1.d[0]
+; CHECK-NEXT: zip1 v0.4s, v4.4s, v3.4s
; CHECK-NEXT: ret
entry:
%0 = fsub fast <4 x float> %b, %c
; CHECK-NEXT: fneg v3.2s, v3.2s
; CHECK-NEXT: fmla v2.2s, v7.2s, v1.2s
; CHECK-NEXT: fmla v3.2s, v0.2s, v1.2s
-; CHECK-NEXT: zip2 v1.2s, v3.2s, v2.2s
-; CHECK-NEXT: zip1 v0.2s, v3.2s, v2.2s
-; CHECK-NEXT: mov v0.d[1], v1.d[0]
+; CHECK-NEXT: zip1 v0.4s, v3.4s, v2.4s
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: fmla v16.2s, v0.2s, v5.2s
; CHECK-NEXT: fsub v0.2s, v7.2s, v16.2s
; CHECK-NEXT: fadd v1.2s, v6.2s, v3.2s
-; CHECK-NEXT: zip2 v2.2s, v0.2s, v1.2s
-; CHECK-NEXT: zip1 v0.2s, v0.2s, v1.2s
-; CHECK-NEXT: mov v0.d[1], v2.d[0]
+; CHECK-NEXT: zip1 v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
entry:
%ar = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: fmla v5.2s, v4.2s, v1.2s
; CHECK-NEXT: fmla v3.2s, v0.2s, v1.2s
; CHECK-NEXT: mov v1.d[1], v2.d[0]
-; CHECK-NEXT: zip2 v4.2s, v3.2s, v5.2s
-; CHECK-NEXT: zip1 v0.2s, v3.2s, v5.2s
+; CHECK-NEXT: zip1 v0.4s, v3.4s, v5.4s
; CHECK-NEXT: str q1, [x0]
-; CHECK-NEXT: mov v0.d[1], v4.d[0]
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: fmul v4.2s, v0.2s, v5.2s
; CHECK-NEXT: fmla v2.2s, v0.2s, v1.2s
; CHECK-NEXT: fsub v0.2s, v3.2s, v4.2s
-; CHECK-NEXT: zip2 v1.2s, v0.2s, v2.2s
-; CHECK-NEXT: zip1 v0.2s, v0.2s, v2.2s
-; CHECK-NEXT: mov v0.d[1], v1.d[0]
+; CHECK-NEXT: zip1 v0.4s, v0.4s, v2.4s
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: zip2 v1.2s, v1.2s, v3.2s
; CHECK-NEXT: fadd v1.2s, v1.2s, v4.2s
; CHECK-NEXT: fsub v0.2s, v0.2s, v2.2s
-; CHECK-NEXT: zip2 v2.2s, v1.2s, v0.2s
-; CHECK-NEXT: zip1 v0.2s, v1.2s, v0.2s
-; CHECK-NEXT: mov v0.d[1], v2.d[0]
+; CHECK-NEXT: zip1 v0.4s, v1.4s, v0.4s
; CHECK-NEXT: ret
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: zip2 v1.2s, v1.2s, v3.2s
; CHECK-NEXT: fsub v1.2s, v4.2s, v1.2s
; CHECK-NEXT: fadd v0.2s, v0.2s, v2.2s
-; CHECK-NEXT: zip2 v2.2s, v1.2s, v0.2s
-; CHECK-NEXT: zip1 v0.2s, v1.2s, v0.2s
-; CHECK-NEXT: mov v0.d[1], v2.d[0]
+; CHECK-NEXT: zip1 v0.4s, v1.4s, v0.4s
; CHECK-NEXT: ret
entry:
%a.real = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>