If we don't implement this pattern, the vectorizer is happy to
unpack the v4si and use the full mulv2di3.  This results in
more element shuffling than is required.

        * config/i386/i386.c (bdesc_args): Update.  Change
        IX86_BUILTIN_VEC_WIDEN_SMUL_ODD_V4SI to OPTION_MASK_ISA_SSE2.
        (IX86_BUILTIN_VEC_WIDEN_SMUL_EVEN_V4SI): New.
        (ix86_builtin_mul_widen_even): Use it.
        (ix86_builtin_mul_widen_odd): Relax SMUL_ODD from sse4 to sse2.
        (ix86_expand_mul_widen_evenodd): Handle signed for sse2.
        * config/i386/sse.md (vec_widen_<s>mult_hi_<V124_AVX2>): Allow
        for all SSE2.
        (vec_widen_<s>mult_lo_<V124_AVX2>): Likewise.
        (vec_widen_<s>mult_odd_<VI4_AVX2>): Likewise.  Relax from V124_AVX2.
        (vec_widen_smult_even_v4si): New.

From-SVN: r189006