s390x: manual `vec_packs` does not optimize well

[folkertdev]

https://godbolt.org/z/PqG76bKcq

I believe that

define <8 x i16> @narrow_manual(<4 x i32> %a, <4 x i32> %b) unnamed_addr {
bb2:
  %0 = shufflevector <4 x i32> %a, <4 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %1 = tail call <8 x i32> @llvm.smax.v8i32(<8 x i32> %0, <8 x i32> splat (i32 -32768))
  %2 = tail call <8 x i32> @llvm.smin.v8i32(<8 x i32> %1, <8 x i32> splat (i32 32767))
  %3 = trunc nsw <8 x i32> %2 to <8 x i16>
  ret <8 x i16> %3
}

declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>) #2

declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>) #2

should optimize into a vec_packs. In the linked godbolt, we see that x86_64 and aarch64 are able to make this optimization. (wasm32 is not, that'll be its own issue).

Instead we get

narrow_manual:
        vrepif  %v0, -32768
        vmxf    %v1, %v24, %v0
        vmxf    %v0, %v26, %v0
        vrepif  %v2, 32767
        vmnf    %v0, %v2, %v0
        vmnf    %v1, %v2, %v1
        vpkf    %v24, %v1, %v0
        br      %r14

narrow_builtin:
        vpksf   %v24, %v24, %v26
        br      %r14

cc @uweigand