diff options
Diffstat (limited to 'gcc/match.pd')
| -rw-r--r-- | gcc/match.pd | 61 |
1 files changed, 61 insertions, 0 deletions
diff --git a/gcc/match.pd b/gcc/match.pd index dde9576..b7f28ab 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -303,6 +303,67 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (view_convert (bit_and:itype (view_convert @0) (ne @1 { build_zero_cst (type); }))))))) +/* In SWAR (SIMD within a register) code a signed comparison of packed data + can be constructed with a particular combination of shift, bitwise and, + and multiplication by constants. If that code is vectorized we can + convert this pattern into a more efficient vector comparison. */ +(simplify + (mult (bit_and (rshift @0 uniform_integer_cst_p@1) + uniform_integer_cst_p@2) + uniform_integer_cst_p@3) + (with { + tree rshift_cst = uniform_integer_cst_p (@1); + tree bit_and_cst = uniform_integer_cst_p (@2); + tree mult_cst = uniform_integer_cst_p (@3); + } + /* Make sure we're working with vectors and uniform vector constants. */ + (if (VECTOR_TYPE_P (type) + && tree_fits_uhwi_p (rshift_cst) + && tree_fits_uhwi_p (mult_cst) + && tree_fits_uhwi_p (bit_and_cst)) + /* Compute what constants would be needed for this to represent a packed + comparison based on the shift amount denoted by RSHIFT_CST. */ + (with { + HOST_WIDE_INT vec_elem_bits = vector_element_bits (type); + poly_int64 vec_nelts = TYPE_VECTOR_SUBPARTS (type); + poly_int64 vec_bits = vec_elem_bits * vec_nelts; + unsigned HOST_WIDE_INT cmp_bits_i, bit_and_i, mult_i; + unsigned HOST_WIDE_INT target_mult_i, target_bit_and_i; + cmp_bits_i = tree_to_uhwi (rshift_cst) + 1; + mult_i = tree_to_uhwi (mult_cst); + target_mult_i = (HOST_WIDE_INT_1U << cmp_bits_i) - 1; + bit_and_i = tree_to_uhwi (bit_and_cst); + target_bit_and_i = 0; + + /* The bit pattern in BIT_AND_I should be a mask for the least + significant bit of each packed element that is CMP_BITS wide. */ + for (unsigned i = 0; i < vec_elem_bits / cmp_bits_i; i++) + target_bit_and_i = (target_bit_and_i << cmp_bits_i) | 1U; + } + (if ((exact_log2 (cmp_bits_i)) >= 0 + && cmp_bits_i < HOST_BITS_PER_WIDE_INT + && multiple_p (vec_bits, cmp_bits_i) + && vec_elem_bits <= HOST_BITS_PER_WIDE_INT + && target_mult_i == mult_i + && target_bit_and_i == bit_and_i) + /* Compute the vector shape for the comparison and check if the target is + able to expand the comparison with that type. */ + (with { + /* We're doing a signed comparison. */ + tree cmp_type = build_nonstandard_integer_type (cmp_bits_i, 0); + poly_int64 vector_type_nelts = exact_div (vec_bits, cmp_bits_i); + tree vec_cmp_type = build_vector_type (cmp_type, vector_type_nelts); + tree vec_truth_type = truth_type_for (vec_cmp_type); + tree zeros = build_zero_cst (vec_cmp_type); + tree ones = build_all_ones_cst (vec_cmp_type); + } + (if (expand_vec_cmp_expr_p (vec_cmp_type, vec_truth_type, LT_EXPR) + && expand_vec_cond_expr_p (vec_cmp_type, vec_truth_type, LT_EXPR)) + (view_convert:type (vec_cond (lt:vec_truth_type + (view_convert:vec_cmp_type @0) + { zeros; }) + { ones; } { zeros; }))))))))) + (for cmp (gt ge lt le) outp (convert convert negate negate) outn (negate negate convert convert) |