On Thu, Feb 10, 2022 at 7:59 AM liuhongt <hongtao....@intel.com> wrote:
>
> >But in principle @2 or @3 could safely differ in sign, you'd then need to
> >ensure
> >to insert sign conversions to @2/@3 to the signedness of @4/@5.
> Changed.
> >you are not testing for this anywhere?
> It's tested in vect_recog_cond_expr_convert_pattern, I've move it to match.pd
>
> >Btw, matching up the comments with the types is somewhat difficult,
> >maybe using TYPE_AB, TYPE_CD, TYPE_E instead of 1,2,3 will
> >make that easier ;)
> Changed.
> >I think the precision check should be part of the match.pd pattern. You
> >do not check that the comparison operands are integral - I think float
> >comparisons would be OK in principle but the precision check will not
> >work there.
> Restricted to integeral type.
>
> Here's updated patch.
>
> gcc/ChangeLog:
>
> PR target/103771
> * match.pd (cond_expr_convert_p): New match.
> * tree-vect-patterns.cc (gimple_cond_expr_convert_p): Declare.
> (vect_recog_cond_expr_convert_pattern): New.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/i386/pr103771-2.c: New test.
> * gcc.target/i386/pr103771-3.c: New test.
> ---
> gcc/match.pd | 14 ++++
> gcc/testsuite/gcc.target/i386/pr103771-2.c | 8 ++
> gcc/testsuite/gcc.target/i386/pr103771-3.c | 21 +++++
> gcc/tree-vect-patterns.cc | 96 ++++++++++++++++++++++
> 4 files changed, 139 insertions(+)
> create mode 100644 gcc/testsuite/gcc.target/i386/pr103771-2.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr103771-3.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 7bbb80172fc..7386ee518a1 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -7683,3 +7683,17 @@ and,
> to the number of trailing zeroes. */
> (match (ctz_table_index @1 @2 @3)
> (rshift (mult (bit_and:c (negate @1) @1) INTEGER_CST@2) INTEGER_CST@3))
> +
> +(match (cond_expr_convert_p @0 @2 @3 @6)
> + (cond (simple_comparison@6 @0 @1) (convert@4 @2) (convert@5 @3))
> + (if (INTEGRAL_TYPE_P (type)
> + && INTEGRAL_TYPE_P (TREE_TYPE (@2))
> + && INTEGRAL_TYPE_P (TREE_TYPE (@0))
> + && INTEGRAL_TYPE_P (TREE_TYPE (@3))
> + && TYPE_PRECISION (type) != TYPE_PRECISION (TREE_TYPE (@0))
> + && TYPE_PRECISION (TREE_TYPE (@0))
> + == TYPE_PRECISION (TREE_TYPE (@2))
> + && TYPE_PRECISION (TREE_TYPE (@0))
> + == TYPE_PRECISION (TREE_TYPE (@3))
> + && single_use (@4)
> + && single_use (@5))))
> diff --git a/gcc/testsuite/gcc.target/i386/pr103771-2.c
> b/gcc/testsuite/gcc.target/i386/pr103771-2.c
> new file mode 100644
> index 00000000000..962a3a74ecf
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr103771-2.c
> @@ -0,0 +1,8 @@
> +/* { dg-do compile } */
> +/* { dg-options "-march=cascadelake -O3" } */
> +/* { dg-final { scan-assembler-not "kunpck" } } */
> +/* { dg-final { scan-assembler-not "kand" } } */
> +/* { dg-final { scan-assembler-not "kor" } } */
> +/* { dg-final { scan-assembler-not "kshift" } } */
> +
> +#include "pr103771.c"
> diff --git a/gcc/testsuite/gcc.target/i386/pr103771-3.c
> b/gcc/testsuite/gcc.target/i386/pr103771-3.c
> new file mode 100644
> index 00000000000..ef379b23b12
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr103771-3.c
> @@ -0,0 +1,21 @@
> +/* { dg-do compile } */
> +/* { dg-options "-march=cascadelake -O3" } */
> +/* { dg-final { scan-assembler-not "kunpck" } } */
> +/* { dg-final { scan-assembler-not "kand" } } */
> +/* { dg-final { scan-assembler-not "kor" } } */
> +/* { dg-final { scan-assembler-not "kshift" } } */
> +
> +typedef unsigned char uint8_t;
> +
> +static uint8_t x264_clip_uint8 (int x, unsigned int y)
> +{
> + return x & (~255) ? (-x) >> 31 : y;
> +}
> +
> +void
> +mc_weight (uint8_t* __restrict dst, uint8_t* __restrict src,
> + int i_width,int i_scale, unsigned int* __restrict y)
> +{
> + for(int x = 0; x < i_width; x++)
> + dst[x] = x264_clip_uint8 (src[x] * i_scale, y[x]);
> +}
> diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc
> index 2baf974627e..aa54bc8bf8b 100644
> --- a/gcc/tree-vect-patterns.cc
> +++ b/gcc/tree-vect-patterns.cc
> @@ -924,6 +924,101 @@ vect_reassociating_reduction_p (vec_info *vinfo,
> return true;
> }
>
> +/* match.pd function to match
> + (cond (cmp@3 a b) (convert@1 c) (convert@2 d))
> + with conditions:
> + 1) @1, @2, c, d, a, b are all integral type.
> + 2) There's single_use for both @1 and @2.
> + 3) a, c and d have same precision.
> + 4) c and @1 have different precision.
> +
> + record a and c and d and @3. */
> +
> +extern bool gimple_cond_expr_convert_p (tree, tree*, tree (*)(tree));
> +
> +/* Function vect_recog_cond_expr_convert
> +
> + Try to find the following pattern:
> +
> + TYPE_AB A,B;
> + TYPE_CD C,D;
> + TYPE_E E;
> + TYPE_E op_true = (TYPE_E) A;
> + TYPE_E op_false = (TYPE_E) B;
> +
> + E = C cmp D ? op_true : op_false;
> +
> + where
> + TYPE_PRECISION (TYPE_E) != TYPE_PRECISION (TYPE_CD);
> + TYPE_PRECISION (TYPE_AB) == TYPE_PRECISION (TYPE_CD);
> + single_use of op_true and op_false.
> + TYPE_AB could differ in sign.
> +
> + Input:
> +
> + * STMT_VINFO: The stmt from which the pattern search begins.
> + here it starts with E = c cmp D ? op_true : op_false;
> +
> + Output:
> +
> + TYPE1 E' = C cmp D ? A : B;
> + TYPE3 E = (TYPE3) E';
> +
> + There may extra nop_convert for A or B to handle different signness.
> +
> + * TYPE_OUT: The vector type of the output of this pattern.
> +
> + * Return value: A new stmt that will be used to replace the sequence of
> + stmts that constitute the pattern. In this case it will be:
> + E = (TYPE3)E';
> + E' = C cmp D ? A : B; is recorded in pattern definition statements; */
> +
> +static gimple *
> +vect_recog_cond_expr_convert_pattern (vec_info *vinfo,
> + stmt_vec_info stmt_vinfo, tree
> *type_out)
> +{
> + gassign *last_stmt = dyn_cast <gassign *> (stmt_vinfo->stmt);
> + tree lhs, match[4], temp, type, new_lhs, op2;
> + gimple *cond_stmt;
> + gimple *pattern_stmt;
> +
> + if (!last_stmt)
> + return NULL;
> +
> + lhs = gimple_assign_lhs (last_stmt);
> +
> + /* Find E = C cmp D ? (TYPE3) A ? (TYPE3) B;
> + TYPE_PRECISION (A) == TYPE_PRECISION (C). */
> + if (!gimple_cond_expr_convert_p (lhs, &match[0], NULL))
> + return NULL;
> +
> + vect_pattern_detected ("vect_recog_cond_expr_convert_pattern", last_stmt);
> +
> + op2 = match[2];
> + type = TREE_TYPE (match[1]);
> + if (TYPE_SIGN (type) != TYPE_SIGN (TREE_TYPE (match[2])))
> + {
> + op2 = vect_recog_temp_ssa_var (type, NULL);
> + gimple* nop_stmt = gimple_build_assign (op2, CONVERT_EXPR, match[2]);
Please use NOP_EXPR here ...
> + append_pattern_def_seq (vinfo, stmt_vinfo, nop_stmt,
> + get_vectype_for_scalar_type (vinfo, type));
> + }
> +
> + temp = vect_recog_temp_ssa_var (type, NULL);
> + cond_stmt = gimple_build_assign (temp, build3 (COND_EXPR, type, match[3],
> + match[1], op2));
> + append_pattern_def_seq (vinfo, stmt_vinfo, cond_stmt,
> + get_vectype_for_scalar_type (vinfo, type));
> + new_lhs = vect_recog_temp_ssa_var (TREE_TYPE (lhs), NULL);
> + pattern_stmt = gimple_build_assign (new_lhs, CONVERT_EXPR, temp);
... and here. OK with that change.
Thanks,
Richard.
> + *type_out = STMT_VINFO_VECTYPE (stmt_vinfo);
> +
> + if (dump_enabled_p ())
> + dump_printf_loc (MSG_NOTE, vect_location,
> + "created pattern stmt: %G", pattern_stmt);
> + return pattern_stmt;
> +}
> +
> /* Function vect_recog_dot_prod_pattern
>
> Try to find the following pattern:
> @@ -5492,6 +5587,7 @@ static vect_recog_func vect_vect_recog_func_ptrs[] = {
> /* Must come after over_widening, which narrows the shift as much as
> possible beforehand. */
> { vect_recog_average_pattern, "average" },
> + { vect_recog_cond_expr_convert_pattern, "cond_expr_convert" },
> { vect_recog_mulhs_pattern, "mult_high" },
> { vect_recog_cast_forwprop_pattern, "cast_forwprop" },
> { vect_recog_widen_mult_pattern, "widen_mult" },
> --
> 2.18.1
>
