https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103571
--- Comment #22 from Hongtao.liu <crazylht at gmail dot com> ---
reply to Uroš Bizjak from comment #21)
> (In reply to Hongtao.liu from comment #19)
> > (In reply to Hongtao.liu from comment #17)
> > > (In reply to Hongtao.liu from comment #16)
> > > > There're already testcases for vec_extract/vec_set/vec_duplicate, but
> > > > those
> > > > testcases are written under TARGET_AVX512FP16, i'll make a copy of them
> > > > and
> > > > test them w/o avx512fp16.
> > >
> > > Also we can relax condition of extendv*hfv*sf and truncv*sfv*hf to
> > > avx512vl/f16c so that vect-float16-1.c could be vectorized.
> > >
> > > vect-float16-1.c
> > >
> > > void
> > > foo (_Float16 *__restrict__ a, _Float16 *__restrict__ b,
> > > _Float16 *__restrict__ c)
> > > {
> > > for (int i = 0; i < 256; i++)
> > > a[i] = b[i] + c[i];
> > > }
> >
> > Even w/ support of extend_optab/trunc_optab, veclower still lower v8hf
> > addition to scalar version. And the mismatch is vectorizer assume '+/-' is
> > supported by default(w/o check optab, just cehck if v8hf is supported in
> > vector_mode_supported_p), and then vectorize the loop, but veclower lower
> > vector operation back to scalar which create much worse code than not
> > vectorized version.
>
> I was under impression that autovectorizer won't vectorize if
> TARGET_VECTORIZE_PRFERRED_SIMD_MODE returns word_mode. Also, the
word_mode is also returned for 64-bit/32-bit vector, but they're vectorized.(In
> documentation for TARGET_VECTOR_MODE_SUPPORTED_P claims that only moves are
> needed.
>
> So, it looks that middle end is somehow inconsistent here. Adding CC.
>
> > Could veclower try widen mode for addition, even veclower can, vNhfmode
> > better be supported under avx512vl or f16c, orelse vectorized code is really
> > bad, then why should we supported vector mode under generic target.
>
> We should use it for parameter passing, moves, inserts, extracts and
> shuffles. In case of VxHF, we can reuse HImode insns for all these
> operations.
Yes, besides TARGET_VECTOR_MODE_SUPPORTED_P, other part in the attached patch
looks fine, the condition should be binded to real instructions but not mode.
