-; RUN: llc -mtriple=arm64-apple-ios7.0 -o - %s | FileCheck %s
+; RUN: llc -mtriple=arm64-apple-ios7.0 -disable-post-ra -o - %s | FileCheck %s
@ptr = global i8* null
%tmp3 = getelementptr double, double* %bar, i64 %inc
store double* %tmp3, double** %ptr
ret <2 x double> %tmp2
-}
\ No newline at end of file
+}
+
+; Check for dependencies between the vector and the scalar load.
+define <4 x float> @test_v4f32_post_reg_ld1lane_dep_vec_on_load(float* %bar, float** %ptr, i64 %inc, <4 x float>* %dep_ptr_1, <4 x float>* %dep_ptr_2) {
+; CHECK-LABEL: test_v4f32_post_reg_ld1lane_dep_vec_on_load:
+; CHECK: BB#0:
+; CHECK-NEXT: ldr s[[LD:[0-9]+]], [x0]
+; CHECK-NEXT: movi.2d v0, #0000000000000000
+; CHECK-NEXT: str q0, [x3]
+; CHECK-NEXT: ldr q0, [x4]
+; CHECK-NEXT: ins.s v0[1], v[[LD]][0]
+; CHECK-NEXT: add [[POST:x[0-9]]], x0, x2, lsl #2
+; CHECK-NEXT: str [[POST]], [x1]
+; CHECK-NEXT: ret
+ %tmp1 = load float, float* %bar
+ store <4 x float> zeroinitializer, <4 x float>* %dep_ptr_1, align 16
+ %A = load <4 x float>, <4 x float>* %dep_ptr_2, align 16
+ %tmp2 = insertelement <4 x float> %A, float %tmp1, i32 1
+ %tmp3 = getelementptr float, float* %bar, i64 %inc
+ store float* %tmp3, float** %ptr
+ ret <4 x float> %tmp2
+}
+
+; Make sure that we test the narrow V64 code path.
+; The tests above don't, because there, 64-bit insert_vector_elt nodes will be
+; widened to 128-bit before the LD1LANEpost combine has the chance to run,
+; making it avoid narrow vector types.
+; One way to trick that combine into running early is to force the vector ops
+; legalizer to run. We achieve that using the ctpop.
+; PR23265
+define <4 x i16> @test_v4i16_post_reg_ld1lane_forced_narrow(i16* %bar, i16** %ptr, i64 %inc, <4 x i16> %A, <2 x i32>* %d) {
+; CHECK-LABEL: test_v4i16_post_reg_ld1lane_forced_narrow:
+; CHECK: ld1.h { v0 }[1], [x0], x{{[0-9]+}}
+ %tmp1 = load i16, i16* %bar
+ %tmp2 = insertelement <4 x i16> %A, i16 %tmp1, i32 1
+ %tmp3 = getelementptr i16, i16* %bar, i64 %inc
+ store i16* %tmp3, i16** %ptr
+ %dl = load <2 x i32>, <2 x i32>* %d
+ %dr = call <2 x i32> @llvm.ctpop.v2i32(<2 x i32> %dl)
+ store <2 x i32> %dr, <2 x i32>* %d
+ ret <4 x i16> %tmp2
+}
+
+declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32>)
+
+; CHECK-LABEL: test_ld1lane_build:
+; CHECK-DAG: ld1.s { [[REG0:v[0-9]+]] }[0], [x0]
+; CHECK-DAG: ld1.s { [[REG0:v[0-9]+]] }[1], [x1]
+; CHECK-DAG: ld1.s { [[REG1:v[0-9]+]] }[0], [x2]
+; CHECK-DAG: ld1.s { [[REG1:v[0-9]+]] }[1], [x3]
+; CHECK: sub.2s v[[REGNUM2:[0-9]+]], [[REG0]], [[REG1]]
+; CHECK-NEXT: str d[[REGNUM2]], [x4]
+; CHECK-NEXT: ret
+define void @test_ld1lane_build(i32* %ptr0, i32* %ptr1, i32* %ptr2, i32* %ptr3, <2 x i32>* %out) {
+ %load0 = load i32, i32* %ptr0, align 4
+ %load1 = load i32, i32* %ptr1, align 4
+ %vec0_0 = insertelement <2 x i32> undef, i32 %load0, i32 0
+ %vec0_1 = insertelement <2 x i32> %vec0_0, i32 %load1, i32 1
+
+ %load2 = load i32, i32* %ptr2, align 4
+ %load3 = load i32, i32* %ptr3, align 4
+ %vec1_0 = insertelement <2 x i32> undef, i32 %load2, i32 0
+ %vec1_1 = insertelement <2 x i32> %vec1_0, i32 %load3, i32 1
+
+ %sub = sub nsw <2 x i32> %vec0_1, %vec1_1
+ store <2 x i32> %sub, <2 x i32>* %out, align 16
+ ret void
+}