--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -force-streaming-compatible-sve < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+declare void @def(ptr)
+
+define void @alloc_v4i8(ptr %st_ptr) #0 {
+; CHECK-LABEL: alloc_v4i8:
+; CHECK: // %bb.0:
+; CHECK-NEXT: sub sp, sp, #32
+; CHECK-NEXT: stp x30, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT: mov x19, x0
+; CHECK-NEXT: add x0, sp, #12
+; CHECK-NEXT: bl def
+; CHECK-NEXT: ldr s0, [sp, #12]
+; CHECK-NEXT: ptrue p0.h, vl4
+; CHECK-NEXT: uunpklo z0.h, z0.b
+; CHECK-NEXT: fmov w8, s0
+; CHECK-NEXT: mov z1.h, z0.h[3]
+; CHECK-NEXT: mov z2.h, z0.h[1]
+; CHECK-NEXT: mov z0.h, z0.h[2]
+; CHECK-NEXT: fmov w9, s1
+; CHECK-NEXT: fmov w10, s2
+; CHECK-NEXT: strh w8, [sp]
+; CHECK-NEXT: fmov w8, s0
+; CHECK-NEXT: strh w9, [sp, #6]
+; CHECK-NEXT: strh w10, [sp, #4]
+; CHECK-NEXT: strh w8, [sp, #2]
+; CHECK-NEXT: ldr d0, [sp]
+; CHECK-NEXT: st1b { z0.h }, p0, [x19]
+; CHECK-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT: add sp, sp, #32
+; CHECK-NEXT: ret
+ %alloc = alloca [4 x i8]
+ call void @def(ptr %alloc)
+ %load = load <4 x i8>, ptr %alloc
+ %strided.vec = shufflevector <4 x i8> %load, <4 x i8> poison, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
+ store <4 x i8> %strided.vec, ptr %st_ptr
+ ret void
+}
+
+define void @alloc_v6i8(ptr %st_ptr) #0 {
+; CHECK-LABEL: alloc_v6i8:
+; CHECK: // %bb.0:
+; CHECK-NEXT: sub sp, sp, #32
+; CHECK-NEXT: stp x30, x19, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT: mov x19, x0
+; CHECK-NEXT: add x0, sp, #8
+; CHECK-NEXT: bl def
+; CHECK-NEXT: ldr d0, [sp, #8]
+; CHECK-NEXT: mov z1.b, z0.b[4]
+; CHECK-NEXT: mov z2.b, z0.b[5]
+; CHECK-NEXT: fmov w8, s0
+; CHECK-NEXT: fmov w9, s1
+; CHECK-NEXT: fmov w10, s2
+; CHECK-NEXT: mov z3.b, z0.b[3]
+; CHECK-NEXT: mov z4.b, z0.b[1]
+; CHECK-NEXT: mov z0.b, z0.b[2]
+; CHECK-NEXT: strb w8, [sp]
+; CHECK-NEXT: fmov w8, s3
+; CHECK-NEXT: strb w9, [sp, #5]
+; CHECK-NEXT: fmov w9, s4
+; CHECK-NEXT: strb w10, [sp, #4]
+; CHECK-NEXT: fmov w10, s0
+; CHECK-NEXT: strb w8, [sp, #3]
+; CHECK-NEXT: strb w9, [sp, #2]
+; CHECK-NEXT: strb w10, [sp, #1]
+; CHECK-NEXT: ldr d0, [sp]
+; CHECK-NEXT: mov z1.h, z0.h[2]
+; CHECK-NEXT: fmov w8, s0
+; CHECK-NEXT: fmov w9, s1
+; CHECK-NEXT: str w8, [x19]
+; CHECK-NEXT: strh w9, [x19, #4]
+; CHECK-NEXT: ldp x30, x19, [sp, #16] // 16-byte Folded Reload
+; CHECK-NEXT: add sp, sp, #32
+; CHECK-NEXT: ret
+ %alloc = alloca [6 x i8]
+ call void @def(ptr %alloc)
+ %load = load <6 x i8>, ptr %alloc
+ %strided.vec = shufflevector <6 x i8> %load, <6 x i8> poison, <6 x i32> <i32 0, i32 2, i32 1, i32 3, i32 5, i32 4>
+ store <6 x i8> %strided.vec, ptr %st_ptr
+ ret void
+}
+
+define void @alloc_v8f64(ptr %st_ptr) #0 {
+; CHECK-LABEL: alloc_v8f64:
+; CHECK: // %bb.0:
+; CHECK-NEXT: sub sp, sp, #96
+; CHECK-NEXT: stp x20, x19, [sp, #80] // 16-byte Folded Spill
+; CHECK-NEXT: mov x19, x0
+; CHECK-NEXT: mov x0, sp
+; CHECK-NEXT: str x30, [sp, #64] // 8-byte Folded Spill
+; CHECK-NEXT: mov x20, sp
+; CHECK-NEXT: bl def
+; CHECK-NEXT: ld2 { v0.2d, v1.2d }, [x20], #32
+; CHECK-NEXT: ldr x30, [sp, #64] // 8-byte Folded Reload
+; CHECK-NEXT: ld2 { v2.2d, v3.2d }, [x20]
+; CHECK-NEXT: stp q0, q2, [x19]
+; CHECK-NEXT: ldp x20, x19, [sp, #80] // 16-byte Folded Reload
+; CHECK-NEXT: add sp, sp, #96
+; CHECK-NEXT: ret
+ %alloc = alloca [8 x double]
+ call void @def(ptr %alloc)
+ %load = load <8 x double>, ptr %alloc
+ %strided.vec = shufflevector <8 x double> %load, <8 x double> poison, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
+ store <4 x double> %strided.vec, ptr %st_ptr
+ ret void
+}
+
+attributes #0 = { "target-features"="+sve" nounwind}