test interpret
test run
target aarch64
set enable_simd
target x86_64 has_sse3 has_ssse3 has_sse41

function %wpdps(i16x8, i16x8) -> i32x4 {
block0(v0: i16x8, v1: i16x8):
    v2 = widening_pairwise_dot_product_s v0, v1
    return v2
}
; run: %wpdps([1 2 3 4 5 6 7 8], [8000 7000 6000 5000 4000 3000 2000 1000]) == [22000 38000 38000 22000]
; run: %wpdps([1 -2 3 -4 5 -6 7 -8], [32767 32767 32767 32767 -32768 -32768 -32768 -32768]) == [-32767 -32767 32768 32768]
; run: %wpdps([-32768 -32768 32767 32767 -32768 -32768 32767 32767], [-32768 -32768 32767 32767 32767 32767 -32768 -32768]) == [2147483648 2147352578 -2147418112 -2147418112]