Fix gcc.c-torture/execute/pr110817-[13].c on the SPARC

As discussed in the audit trail, the TARGET_VECTORIZE_GET_MASK_MODE hook of
the SPARC back-end always returns Pmode (SImode would probably have been OK)
and this causes build_truth_vector_type_for_mode to generate questionable
types like:

<vector_type 0x7ffff6f6da80
    type <boolean_type 0x7ffff6f6d9d8 public QI
        size <integer_cst 0x7ffff6e04f18 constant 8>
        unit-size <integer_cst 0x7ffff6e04f30 constant 1>
        align:8 warn_if_not_align:0 symtab:0 alias-set -1 canonical-type
0x7ffff6f6d9d8 precision:1 min <integer_cst 0x7ffff6f69678 -1> max
<integer_cst 0x7ffff6f7deb8 0>>
    DI
    size <integer_cst 0x7ffff6e04e28 type <integer_type 0x7ffff6e150a8
bitsizetype> constant 64>
    unit-size <integer_cst 0x7ffff6e04e40 type <integer_type 0x7ffff6e15000
sizetype> constant 8>
    align:64 warn_if_not_align:0 symtab:0 alias-set -1 canonical-type
0x7ffff6f6da80 nunits:1>

which then go through this trick in store_constructor:

        /* Use sign-extension for uniform boolean vectors with
           integer modes and single-bit mask entries.
           Effectively "vec_duplicate" for bitmasks.  */
        if (elt_size == 1
            && !TREE_SIDE_EFFECTS (exp)
            && VECTOR_BOOLEAN_TYPE_P (type)
            && SCALAR_INT_MODE_P (TYPE_MODE (type))
            && (elt = uniform_vector_p (exp))
            && !VECTOR_TYPE_P (TREE_TYPE (elt)))
          {
            rtx op0 = force_reg (TYPE_MODE (TREE_TYPE (elt)),
                                 expand_normal (elt));
            rtx tmp = gen_reg_rtx (mode);
            convert_move (tmp, op0, 0);

            /* Ensure no excess bits are set.
               GCN needs this for nunits < 64.
               x86 needs this for nunits < 8.  */
            auto nunits = TYPE_VECTOR_SUBPARTS (type).to_constant ();
            if (maybe_ne (GET_MODE_PRECISION (mode), nunits))
              tmp = expand_binop (mode, and_optab, tmp,
                          GEN_INT ((HOST_WIDE_INT_1U << nunits) - 1),
                          target, true, OPTAB_WIDEN);
            if (tmp != target)
              emit_move_insn (target, tmp);
            break;
          }

to yield code that cannot possibly work on a big-endian platform.

Coaxing build_truth_vector_type_for_mode to generate more sensible types
fixes the problem but runs afoul of the TARGET_VECTORIZE_GET_MASK_MODE
hook for some AVX512 modes, so is probably not worth the risk.  Moreover,
I didn't manage to come up with a big-endian implementation of the above
trick that would make some sense for the questionable vector types, so the
fix simply disables it.

gcc/
	PR target/121192
	* expr.cc (store_constructor) <VECTOR_TYPE>: Disable the special
	trick for uniform boolean vectors with integer modes and single-bit
	mask entries on big-endian platforms.

diff --git a/gcc/expr.cc b/gcc/expr.cc
index 8a1d72ad23b4aa1d72fb40c828d1475f56c63f93..70b4eda6df37573eac1d21d5d1b22772458729c1 100644 (file)
--- a/gcc/expr.cc
+++ b/gcc/expr.cc
@@ -8012,7 +8012,8 @@ store_constructor (tree exp, rtx target, int cleared, poly_int64 size,
            && VECTOR_BOOLEAN_TYPE_P (type)
            && SCALAR_INT_MODE_P (TYPE_MODE (type))
            && (elt = uniform_vector_p (exp))
-           && !VECTOR_TYPE_P (TREE_TYPE (elt)))
+           && !VECTOR_TYPE_P (TREE_TYPE (elt))
+           && !BYTES_BIG_ENDIAN)
          {
            rtx op0 = force_reg (TYPE_MODE (TREE_TYPE (elt)),
                                 expand_normal (elt));
@@ -8022,7 +8023,7 @@ store_constructor (tree exp, rtx target, int cleared, poly_int64 size,
            /* Ensure no excess bits are set.
               GCN needs this for nunits < 64.
               x86 needs this for nunits < 8.  */
-           auto nunits = TYPE_VECTOR_SUBPARTS (type).to_constant ();
+           unsigned int nunits = TYPE_VECTOR_SUBPARTS (type).to_constant ();
            if (maybe_ne (GET_MODE_PRECISION (mode), nunits))
              tmp = expand_binop (mode, and_optab, tmp,
                                  GEN_INT ((HOST_WIDE_INT_1U << nunits) - 1),