[Bug target/98167] [x86] Failure to optimize operation on indentically shuffled operands into a shuffle of the result of the operation

[crazylht at gmail dot com via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98167

--- Comment #16 from Hongtao.liu <crazylht at gmail dot com> ---
typedef int v4si __attribute__ ((vector_size(16)));

v4si f(v4si a, v4si b) {
    v4si a1 = __builtin_shufflevector (a, a, 2, 3 ,1 ,0);
    v4si b1 = __builtin_shufflevector (b, a, 2, 3 ,1 ,0);
    return a1 * b1;
}

gcc generate 

f:
        vpshufd xmm1, xmm1, 30
        vpshufd xmm0, xmm0, 30
        vpmulld xmm0, xmm0, xmm1
        ret

llvm generate

f:                                      # @f
        vpmulld xmm0, xmm1, xmm0
        vpshufd xmm0, xmm0, 30                  # xmm0 = xmm0[2,3,1,0]
        ret