public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Richard Biener <richard.guenther@gmail.com>
To: pan2.li@intel.com
Cc: gcc-patches@gcc.gnu.org, juzhe.zhong@rivai.ai,
	kito.cheng@gmail.com,  jeffreyalaw@gmail.com,
	rdapp.gcc@gmail.com
Subject: Re: [PATCH v2] Internal-fn: Support new IFN SAT_TRUNC for unsigned scalar int
Date: Thu, 27 Jun 2024 08:07:30 +0200	[thread overview]
Message-ID: <CAFiYyc1Ywb8JbPn2gCqUaud079m8CKjNvBjuCCCAK1+u8jif+A@mail.gmail.com> (raw)
In-Reply-To: <20240627051216.1817555-1-pan2.li@intel.com>

On Thu, Jun 27, 2024 at 7:12 AM <pan2.li@intel.com> wrote:
>
> From: Pan Li <pan2.li@intel.com>
>
> This patch would like to add the middle-end presentation for the
> saturation truncation.  Aka set the result of truncated value to
> the max value when overflow.  It will take the pattern similar
> as below.
>
> Form 1:
>   #define DEF_SAT_U_TRUC_FMT_1(WT, NT) \
>   NT __attribute__((noinline))         \
>   sat_u_truc_##T##_fmt_1 (WT x)        \
>   {                                    \
>     bool overflow = x > (WT)(NT)(-1);  \
>     return ((NT)x) | (NT)-overflow;    \
>   }
>
> For example, truncated uint16_t to uint8_t, we have
>
> * SAT_TRUNC (254)   => 254
> * SAT_TRUNC (255)   => 255
> * SAT_TRUNC (256)   => 255
> * SAT_TRUNC (65536) => 255
>
> Given below SAT_TRUNC from uint64_t to uint32_t.
>
> DEF_SAT_U_TRUC_FMT_1 (uint64_t, uint32_t)
>
> Before this patch:
> __attribute__((noinline))
> uint32_t sat_u_truc_T_fmt_1 (uint64_t x)
> {
>   _Bool overflow;
>   unsigned int _1;
>   unsigned int _2;
>   unsigned int _3;
>   uint32_t _6;
>
> ;;   basic block 2, loop depth 0
> ;;    pred:       ENTRY
>   overflow_5 = x_4(D) > 4294967295;
>   _1 = (unsigned int) x_4(D);
>   _2 = (unsigned int) overflow_5;
>   _3 = -_2;
>   _6 = _1 | _3;
>   return _6;
> ;;    succ:       EXIT
>
> }
>
> After this patch:
> __attribute__((noinline))
> uint32_t sat_u_truc_T_fmt_1 (uint64_t x)
> {
>   uint32_t _6;
>
> ;;   basic block 2, loop depth 0
> ;;    pred:       ENTRY
>   _6 = .SAT_TRUNC (x_4(D)); [tail call]
>   return _6;
> ;;    succ:       EXIT
>
> }

OK.

Thanks,
Richard.

> The below tests are passed for this patch:
> *. The rv64gcv fully regression tests.
> *. The rv64gcv build with glibc.
> *. The x86 bootstrap tests.
> *. The x86 fully regression tests.
>
> gcc/ChangeLog:
>
>         * internal-fn.def (SAT_TRUNC): Add new signed IFN sat_trunc as
>         unary_convert.
>         * match.pd: Add new matching pattern for unsigned int sat_trunc.
>         * optabs.def (OPTAB_CL): Add unsigned and signed optab.
>         * tree-ssa-math-opts.cc (gimple_unsigend_integer_sat_trunc): Add
>         new decl for the matching pattern generated func.
>         (match_unsigned_saturation_trunc): Add new func impl to match
>         the .SAT_TRUNC.
>         (math_opts_dom_walker::after_dom_children): Add .SAT_TRUNC match
>         function under BIT_IOR_EXPR case.
>
> Signed-off-by: Pan Li <pan2.li@intel.com>
> ---
>  gcc/internal-fn.def       |  2 ++
>  gcc/match.pd              | 16 ++++++++++++++++
>  gcc/optabs.def            |  3 +++
>  gcc/tree-ssa-math-opts.cc | 32 ++++++++++++++++++++++++++++++++
>  4 files changed, 53 insertions(+)
>
> diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def
> index a8c83437ada..915d329c05a 100644
> --- a/gcc/internal-fn.def
> +++ b/gcc/internal-fn.def
> @@ -278,6 +278,8 @@ DEF_INTERNAL_SIGNED_OPTAB_FN (MULHRS, ECF_CONST | ECF_NOTHROW, first,
>  DEF_INTERNAL_SIGNED_OPTAB_FN (SAT_ADD, ECF_CONST, first, ssadd, usadd, binary)
>  DEF_INTERNAL_SIGNED_OPTAB_FN (SAT_SUB, ECF_CONST, first, sssub, ussub, binary)
>
> +DEF_INTERNAL_SIGNED_OPTAB_FN (SAT_TRUNC, ECF_CONST, first, sstrunc, ustrunc, unary_convert)
> +
>  DEF_INTERNAL_COND_FN (ADD, ECF_CONST, add, binary)
>  DEF_INTERNAL_COND_FN (SUB, ECF_CONST, sub, binary)
>  DEF_INTERNAL_COND_FN (MUL, ECF_CONST, smul, binary)
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 3d0689c9312..06120a1c62c 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -3210,6 +3210,22 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
>   (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
>        && types_match (type, @0, @1))))
>
> +/* Unsigned saturation truncate, case 1 (), sizeof (WT) > sizeof (NT).
> +   SAT_U_TRUNC = (NT)x | (NT)(-(X > (WT)(NT)(-1))).  */
> +(match (unsigned_integer_sat_trunc @0)
> + (bit_ior:c (negate (convert (gt @0 INTEGER_CST@1)))
> +   (convert @0))
> + (with {
> +   unsigned itype_precision = TYPE_PRECISION (TREE_TYPE (@0));
> +   unsigned otype_precision = TYPE_PRECISION (type);
> +   wide_int trunc_max = wi::mask (itype_precision / 2, false, itype_precision);
> +   wide_int int_cst = wi::to_wide (@1, itype_precision);
> +  }
> +  (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
> +       && TYPE_UNSIGNED (TREE_TYPE (@0))
> +       && otype_precision < itype_precision
> +       && wi::eq_p (trunc_max, int_cst)))))
> +
>  /* x >  y  &&  x != XXX_MIN  -->  x > y
>     x >  y  &&  x == XXX_MIN  -->  false . */
>  (for eqne (eq ne)
> diff --git a/gcc/optabs.def b/gcc/optabs.def
> index bc2611abdc2..c16580ce956 100644
> --- a/gcc/optabs.def
> +++ b/gcc/optabs.def
> @@ -63,6 +63,9 @@ OPTAB_CX(fractuns_optab, "fractuns$Q$b$I$a2")
>  OPTAB_CL(satfract_optab, "satfract$b$Q$a2", SAT_FRACT, "satfract", gen_satfract_conv_libfunc)
>  OPTAB_CL(satfractuns_optab, "satfractuns$I$b$Q$a2", UNSIGNED_SAT_FRACT, "satfractuns", gen_satfractuns_conv_libfunc)
>
> +OPTAB_CL(ustrunc_optab, "ustrunc$b$a2", US_TRUNCATE, "ustrunc", NULL)
> +OPTAB_CL(sstrunc_optab, "sstrunc$b$a2", SS_TRUNCATE, "sstrunc", NULL)
> +
>  OPTAB_CD(sfixtrunc_optab, "fix_trunc$F$b$I$a2")
>  OPTAB_CD(ufixtrunc_optab, "fixuns_trunc$F$b$I$a2")
>
> diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
> index 57085488722..3783a874699 100644
> --- a/gcc/tree-ssa-math-opts.cc
> +++ b/gcc/tree-ssa-math-opts.cc
> @@ -4088,6 +4088,7 @@ arith_overflow_check_p (gimple *stmt, gimple *cast_stmt, gimple *&use_stmt,
>
>  extern bool gimple_unsigned_integer_sat_add (tree, tree*, tree (*)(tree));
>  extern bool gimple_unsigned_integer_sat_sub (tree, tree*, tree (*)(tree));
> +extern bool gimple_unsigned_integer_sat_trunc (tree, tree*, tree (*)(tree));
>
>  static void
>  build_saturation_binary_arith_call (gimple_stmt_iterator *gsi, internal_fn fn,
> @@ -4216,6 +4217,36 @@ match_unsigned_saturation_sub (gimple_stmt_iterator *gsi, gphi *phi)
>                                         ops[0], ops[1]);
>  }
>
> +/*
> + * Try to match saturation unsigned sub.
> + * uint16_t x_4(D);
> + * uint8_t _6;
> + * overflow_5 = x_4(D) > 255;
> + * _1 = (unsigned char) x_4(D);
> + * _2 = (unsigned char) overflow_5;
> + * _3 = -_2;
> + * _6 = _1 | _3;
> + * =>
> + * _6 = .SAT_TRUNC (x_4(D));
> + * */
> +static void
> +match_unsigned_saturation_trunc (gimple_stmt_iterator *gsi, gassign *stmt)
> +{
> +  tree ops[1];
> +  tree lhs = gimple_assign_lhs (stmt);
> +  tree type = TREE_TYPE (lhs);
> +
> +  if (gimple_unsigned_integer_sat_trunc (lhs, ops, NULL)
> +    && direct_internal_fn_supported_p (IFN_SAT_TRUNC,
> +                                      tree_pair (type, TREE_TYPE (ops[0])),
> +                                      OPTIMIZE_FOR_BOTH))
> +    {
> +      gcall *call = gimple_build_call_internal (IFN_SAT_TRUNC, 1, ops[0]);
> +      gimple_call_set_lhs (call, lhs);
> +      gsi_replace (gsi, call, /* update_eh_info */ true);
> +    }
> +}
> +
>  /* Recognize for unsigned x
>     x = y - z;
>     if (x > y)
> @@ -6188,6 +6219,7 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
>
>             case BIT_IOR_EXPR:
>               match_unsigned_saturation_add (&gsi, as_a<gassign *> (stmt));
> +             match_unsigned_saturation_trunc (&gsi, as_a<gassign *> (stmt));
>               /* fall-through  */
>             case BIT_XOR_EXPR:
>               match_uaddc_usubc (&gsi, stmt, code);
> --
> 2.34.1
>

  reply	other threads:[~2024-06-27  6:07 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-26  1:45 [PATCH v1] " pan2.li
2024-06-26 13:51 ` Richard Biener
2024-06-26 14:18   ` Li, Pan2
2024-06-27  5:12 ` [PATCH v2] " pan2.li
2024-06-27  6:07   ` Richard Biener [this message]
2024-06-27  6:14     ` Li, Pan2

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAFiYyc1Ywb8JbPn2gCqUaud079m8CKjNvBjuCCCAK1+u8jif+A@mail.gmail.com \
    --to=richard.guenther@gmail.com \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=jeffreyalaw@gmail.com \
    --cc=juzhe.zhong@rivai.ai \
    --cc=kito.cheng@gmail.com \
    --cc=pan2.li@intel.com \
    --cc=rdapp.gcc@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).