[Bug target/124271] x86/AVX2: missed simplification — low32×low32→u64 vectorized multiply expands to generic u64-mul sequence instead of single vpmuludq

[liuhongt at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=124271

--- Comment #7 from Hongtao Liu <liuhongt at gcc dot gnu.org> ---
(In reply to Hongtao Liu from comment #6)
> > 
> > > +      unsigned int inner_prec = outer_prec / 2;
> > > +      poly_uint64 outer_nelts = TYPE_VECTOR_SUBPARTS (type);
> > > +      tree inner_scalar = build_nonstandard_integer_type (inner_prec, 1);
> > 
> > I think 1 here should be `TYPE_UNSIGNED (TREE_TYPE (type))` otherwise you
> > get a type mismatch I think.

static inline  long mul32( long a,  long b) {
  return (a & 0xffffffff) * (b & 0xffffffff);
}

void many_mul3(long* __restrict a,
               const  long* __restrict b)
{
    for (int i = 0; i < 1024; i++)
        a[i] = mul32(a[i], b[i]);
}

Looks like vec_widen_mult_even_expr allow unsigned input and signed output
  <bb 3> [local count: 1063004408]:
  # ivtmp.20_32 = PHI <ivtmp.20_19(5), 0(2)>
  vect__4.11_22 = MEM <const vector(4) long int> [(const long int *)b_10(D) +
ivtmp.20_32 * 1];
  vect__6.7_26 = MEM <vector(4) long int> [(long int *)a_11(D) + ivtmp.20_32 *
1];
  _17 = VIEW_CONVERT_EXPR<vector(8) unsigned int>(vect__4.11_22);
  _24 = VIEW_CONVERT_EXPR<vector(8) unsigned int>(vect__6.7_26);
  vect__16.13_18 = WIDEN_MULT_EVEN_EXPR <_17, _24>;
  MEM <vector(4) long int> [(long int *)a_11(D) + ivtmp.20_32 * 1] =
vect__16.13_18;
  ivtmp.20_19 = ivtmp.20_32 + 32;
  if (ivtmp.20_19 != 8192)


But using TYPE_UNSIGNED (TREE_TYPE (type)) instead of 1 will generate
vec_widen_smult_even_optab which is incorrect


Others changed as suggested

diff --git a/gcc/match.pd b/gcc/match.pd
index 7f16fd4e081..d99d83bab84 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -436,6 +436,32 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
                                     { zeros; })
                           { ones; } { zeros; })))))))))

+#if GIMPLE
+/*    (x & lowhalf_mask) * (y & lowhalf_mask)
+    -> VEC_WIDEN_MULT_EVEN (VIEW_CONVERT (x), VIEW_CONVERT (y)).  */
+(simplify
+ (mult (bit_and @0 VECTOR_CST@2)
+      (bit_and @1 @2))
+ (if (uniform_vector_p (@2)
+      && TYPE_VECTOR_SUBPARTS (type).is_constant ()
+      && TYPE_VECTOR_SUBPARTS (type).to_constant () > 1)
+   (with
+    {
+      auto elem = wi::to_wide (uniform_vector_p (@2));
+      unsigned int outer_prec = TYPE_PRECISION (TREE_TYPE (type));
+      unsigned int inner_prec = outer_prec / 2;
+      poly_uint64 outer_nelts = TYPE_VECTOR_SUBPARTS (type);
+      tree inner_scalar = build_nonstandard_integer_type (inner_prec, 1);
+      tree inner_type = build_vector_type (inner_scalar, outer_nelts * 2);
+    }
+    (if (GET_MODE_CLASS (TYPE_MODE (inner_type)) == MODE_VECTOR_INT
+        && elem == wi::mask (inner_prec, false, outer_prec)
+        && optab_handler (vec_widen_umult_even_optab,
+                          TYPE_MODE (inner_type)) != CODE_FOR_nothing)
+       (vec_widen_mult_even (view_convert:inner_type @0)
+                           (view_convert:inner_type @1))))))
+#endif
+