On Mon, May 31, 2021 at 2:09 PM H.J. Lu <hjl.to...@gmail.com> wrote:
>
> On Wed, May 26, 2021 at 10:28:16AM +0200, Richard Biener wrote:
> > > > >
> > > > > -- Target Hook: rtx TARGET_GEN_MEMSET_VALUE (rtx DATA,
> > > > > scalar_int_mode
> > > > > MODE)
> > > > > This function returns the RTL of a register containing
> > > > > 'GET_MODE_SIZE (MODE)' consecutive copies of the unsigned char
> > > > > value given in the RTL register DATA. For example, if MODE is 4
> > > > > bytes wide, return the RTL for 0x01010101*DATA.
> > > >
> > > > For this one I wonder if it should be an optab instead. Couldn't you
> > > > use the existing vec_duplicate for this by using (paradoxical) subregs
> > > > like (subreg:TI (vec_duplicate:VnQI (subreg:VnQI (reg:QI ...)))?
> > >
> > > I tried. It doesn't even work on x86. See:
> > >
> > > https://gcc.gnu.org/pipermail/gcc-patches/2021-May/570661.html
> >
> > Not sure what I should read from there...
> >
> > > There are special cases to subreg HI, SI and DI modes of TI mode in
> > > ix86_gen_memset_value_from_prev. simplify_gen_subreg doesn't
> > > work here. Each backend may need its own special handling.
> >
> > OK, I guess I'm not (RTL) qualified enough to further review these parts,
> > sorry. Since we're doing code generation the canonical way to communicate
> > with backends should be optabs, not some set of disconnected target hooks.
> > But as said, I probably don't know enough of RTL to see why it's the only
> > way.
> >
> > Richard.
>
> Here is the patch to add optabs instead. Does it look OK?
>
> Thanks.
>
> H.J.
> ---
> Add 2 optabs:
>
> 1. integer_extract: Extract lower bit value from the integer value in
> TImode, OImode or XImode.
That sounds very specific, esp. the restriction to {TI,OI,XI}mode.
It also sounds like it matches (subreg:{TI,OI,XI} (...) 0). There are
existing target hooks verifying subreg validity - why's that not a good
fit here? ISTR you say gen_lowpart () doesn't work (or was it
simplify_gen_subreg?), why's that so?
> 2. vec_const_duplicate: Broadcast a QImode constant to a vector. It is
> similar to vec_duplicate. Since the resulting vector is computable at
> compile-time, vec_duplicate may not be faster and backend can opt out
> broadcasting from a constant while opting in broadcasting from a
> variable.
Is it for the latter that you choose to use a new optab since
vec_duplicate is not allowed to FAIL? You should probably document
that the constant value duplicated should be of the component mode of
m.
> and rewrite builtin_memset_read_str/builtin_memset_gen_str to support
> target instructions to duplicate QImode value to TImode, OImode or XImode
> value for memmset.
>
> Add TARGET_GEN_MEMSET_SCRATCH_RTX to allow the backend to use a hard
> scratch register to avoid stack realignment when expanding memset.
>
> PR middle-end/90773
> * builtins.c (gen_memset_value_from_prev): New function.
> (gen_memset_broadcast): Likewise.
> (builtin_memset_read_str): Use gen_memset_value_from_prev
> and gen_memset_broadcast.
> (builtin_memset_gen_str): Likewise.
> * optabs.def: Add integer_extract and vec_const_duplicate.
> * target.def (gen_memset_scratch_rtx): New hook.
> * doc/md.texi: Document vec_const_duplicate and integer_extract.
> * doc/tm.texi.in: Add TARGET_GEN_MEMSET_SCRATCH_RTX.
> * doc/tm.texi: Regenerated.
> ---
> gcc/builtins.c | 117 +++++++++++++++++++++++++++++++++++++--------
> gcc/doc/md.texi | 16 +++++++
> gcc/doc/tm.texi | 5 ++
> gcc/doc/tm.texi.in | 2 +
> gcc/optabs.def | 4 ++
> gcc/target.def | 7 +++
> 6 files changed, 131 insertions(+), 20 deletions(-)
>
> diff --git a/gcc/builtins.c b/gcc/builtins.c
> index af1fe49bb48..7683169eb96 100644
> --- a/gcc/builtins.c
> +++ b/gcc/builtins.c
> @@ -6598,26 +6598,106 @@ expand_builtin_strncpy (tree exp, rtx target)
> return NULL_RTX;
> }
>
> +/* Return the RTL of a register in MODE generated from PREV in the
> + previous iteration. */
> +
> +static rtx
> +gen_memset_value_from_prev (void *prevp, scalar_int_mode mode)
> +{
> + rtx target = nullptr;
> + by_pieces_prev *prev = (by_pieces_prev *) prevp;
> + if (prev != nullptr && prev->data != nullptr)
> + {
> + /* Use the previous data in the same mode. */
> + if (prev->mode == mode)
> + return prev->data;
> +
> + /* Extract the RTL in MODE from PREV. */
> + enum insn_code icode
> + = convert_optab_handler (integer_extract_optab, mode,
> + prev->mode);
> + if (icode != CODE_FOR_nothing)
> + {
> + target = gen_reg_rtx (mode);
> + class expand_operand ops[2];
> + create_output_operand (&ops[0], target, mode);
> + create_input_operand (&ops[1], prev->data, prev->mode);
> + expand_insn (icode, 2, ops);
> + if (!rtx_equal_p (target, ops[0].value))
> + emit_move_insn (target, ops[0].value);
> + }
> + else
> + target = simplify_gen_subreg (mode, prev->data, prev->mode, 0);
> + }
> + return target;
> +}
> +
> +/* Return the RTL of a register in MODE broadcasted from DATA. */
> +
> +static rtx
> +gen_memset_broadcast (enum optab_tag broadcast_optab, rtx data,
> + scalar_int_mode mode)
> +{
> + /* Skip if regno_reg_rtx isn't initialized. */
> + if (!regno_reg_rtx)
> + return nullptr;
> +
> + rtx target = nullptr;
> +
> + unsigned int nunits = GET_MODE_SIZE (mode) / GET_MODE_SIZE (QImode);
> + machine_mode vector_mode;
> + if (!mode_for_vector (QImode, nunits).exists (&vector_mode))
> + gcc_unreachable ();
> +
> + enum insn_code icode = optab_handler (broadcast_optab, vector_mode);
> + if (icode != CODE_FOR_nothing)
> + {
> + target = targetm.gen_memset_scratch_rtx (vector_mode);
> + class expand_operand ops[2];
> + create_output_operand (&ops[0], target, vector_mode);
> + create_input_operand (&ops[1], (rtx) data, QImode);
> + expand_insn (icode, 2, ops);
> + if (!rtx_equal_p (target, ops[0].value))
> + emit_move_insn (target, ops[0].value);
> + if (REGNO (target) < FIRST_PSEUDO_REGISTER)
> + target = gen_rtx_REG (mode, REGNO (target));
> + else
> + target = convert_to_mode (mode, target, 1);
> + }
> +
> + return target;
> +}
> +
> /* Callback routine for store_by_pieces. Read GET_MODE_BITSIZE (MODE)
> bytes from constant string DATA + OFFSET and return it as target
> constant. If PREV isn't nullptr, it has the RTL info from the
> previous iteration. */
>
> rtx
> -builtin_memset_read_str (void *data, void *prevp,
> +builtin_memset_read_str (void *data, void *prev,
> HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
> scalar_int_mode mode)
> {
> - by_pieces_prev *prev = (by_pieces_prev *) prevp;
> - if (prev != nullptr && prev->data != nullptr)
> + rtx target;
> +
> + /* Don't use the previous value if size is 1. */
> + if (GET_MODE_SIZE (mode) != 1)
> {
> - /* Use the previous data in the same mode. */
> - if (prev->mode == mode)
> - return prev->data;
> + target = gen_memset_value_from_prev (prev, mode);
> + if (target != nullptr)
> + return target;
> }
>
> const char *c = (const char *) data;
> - char *p = XALLOCAVEC (char, GET_MODE_SIZE (mode));
> + char *p = XALLOCAVEC (char, GET_MODE_SIZE (QImode));
> + memset (p, *c, GET_MODE_SIZE (QImode));
> + rtx src = c_readstr (p, QImode);
> + target = gen_memset_broadcast (vec_const_duplicate_optab, src,
> + mode);
> + if (target != nullptr)
> + return target;
> +
> + p = XALLOCAVEC (char, GET_MODE_SIZE (mode));
>
> memset (p, *c, GET_MODE_SIZE (mode));
>
> @@ -6631,7 +6711,7 @@ builtin_memset_read_str (void *data, void *prevp,
> nullptr, it has the RTL info from the previous iteration. */
>
> static rtx
> -builtin_memset_gen_str (void *data, void *prevp,
> +builtin_memset_gen_str (void *data, void *prev,
> HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
> scalar_int_mode mode)
> {
> @@ -6639,22 +6719,19 @@ builtin_memset_gen_str (void *data, void *prevp,
> size_t size;
> char *p;
>
> - by_pieces_prev *prev = (by_pieces_prev *) prevp;
> - if (prev != nullptr && prev->data != nullptr)
> - {
> - /* Use the previous data in the same mode. */
> - if (prev->mode == mode)
> - return prev->data;
> -
> - target = simplify_gen_subreg (mode, prev->data, prev->mode, 0);
> - if (target != nullptr)
> - return target;
> - }
> -
> size = GET_MODE_SIZE (mode);
> if (size == 1)
> return (rtx) data;
>
> + target = gen_memset_value_from_prev (prev, mode);
> + if (target != nullptr)
> + return target;
> +
> + target = gen_memset_broadcast (vec_duplicate_optab, (rtx) data,
> + mode);
> + if (target != nullptr)
> + return target;
> +
> p = XALLOCAVEC (char, size);
> memset (p, 1, size);
> coeff = c_readstr (p, mode);
> diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
> index 00caf3844cc..a798fb1a97e 100644
> --- a/gcc/doc/md.texi
> +++ b/gcc/doc/md.texi
> @@ -5079,6 +5079,16 @@ vectors go through the @code{mov@var{m}} pattern
> instead.
>
> This pattern is not allowed to @code{FAIL}.
>
> +@cindex @code{vec_const_duplicate@var{m}} instruction pattern
> +@item @samp{vec_const_duplicate@var{m}}
> +Initialize vector output operand 0 in mode @var{m} so that each element
> +has the value given by constant input operand 1.
> +
> +This pattern only handles duplicates of constant inputs. Non-constant
> +vectors go through the @code{vec_duplicate@var{m}} pattern instead.
> +
> +This pattern is not allowed to @code{FAIL}.
> +
> @cindex @code{vec_series@var{m}} instruction pattern
> @item @samp{vec_series@var{m}}
> Initialize vector output operand 0 so that element @var{i} is equal to
> @@ -7904,6 +7914,12 @@ inclusive and operand 1 exclusive.
> If this pattern is not defined, a call to the library function
> @code{__clear_cache} is used.
>
> +@cindex @code{integer_extract@var{m}@var{n}} instruction pattern
> +@item @samp{integer_extract@var{m}@var{n}}
> +Extract lower bit value from the integer value in @code{TImode},
> +@code{OImode} or @code{XImode}. Operand 1 is the integer in mode
> +@var{n} and operand 0 stores value to be extracted in mode @var{m}.
> +
> @end table
>
> @end ifset
> diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
> index e3a080e4a7c..8ccc262b1fc 100644
> --- a/gcc/doc/tm.texi
> +++ b/gcc/doc/tm.texi
> @@ -11894,6 +11894,11 @@ This function prepares to emit a conditional
> comparison within a sequence
> @var{bit_code} is @code{AND} or @code{IOR}, which is the op on the compares.
> @end deftypefn
>
> +@deftypefn {Target Hook} rtx TARGET_GEN_MEMSET_SCRATCH_RTX (machine_mode
> @var{mode})
> +This hook should return an rtx for scratch register in @var{mode} to
> +be used by memset broadcast. The default is @code{gen_reg_rtx}.
> +@end deftypefn
> +
> @deftypefn {Target Hook} unsigned TARGET_LOOP_UNROLL_ADJUST (unsigned
> @var{nunroll}, class loop *@var{loop})
> This target hook returns a new value for the number of times @var{loop}
> should be unrolled. The parameter @var{nunroll} is the number of times
> diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in
> index d9fbbe20e6f..99bf01fe25d 100644
> --- a/gcc/doc/tm.texi.in
> +++ b/gcc/doc/tm.texi.in
> @@ -7960,6 +7960,8 @@ lists.
>
> @hook TARGET_GEN_CCMP_NEXT
>
> +@hook TARGET_GEN_MEMSET_SCRATCH_RTX
> +
> @hook TARGET_LOOP_UNROLL_ADJUST
>
> @defmac POWI_MAX_MULTS
> diff --git a/gcc/optabs.def b/gcc/optabs.def
> index b192a9d070b..fd8ab8b4a26 100644
> --- a/gcc/optabs.def
> +++ b/gcc/optabs.def
> @@ -100,6 +100,8 @@ OPTAB_CD(vec_init_optab, "vec_init$a$b")
>
> OPTAB_CD (while_ult_optab, "while_ult$a$b")
>
> +OPTAB_CD (integer_extract_optab, "integer_extract$a$b")
> +
> OPTAB_NL(add_optab, "add$P$a3", PLUS, "add", '3', gen_int_fp_fixed_libfunc)
> OPTAB_NX(add_optab, "add$F$a3")
> OPTAB_NX(add_optab, "add$Q$a3")
> @@ -453,3 +455,5 @@ OPTAB_DC (vec_series_optab, "vec_series$a", VEC_SERIES)
> OPTAB_D (vec_shl_insert_optab, "vec_shl_insert_$a")
> OPTAB_D (len_load_optab, "len_load_$a")
> OPTAB_D (len_store_optab, "len_store_$a")
> +
> +OPTAB_DC (vec_const_duplicate_optab, "vec_const_duplicate$a", VEC_DUPLICATE)
> diff --git a/gcc/target.def b/gcc/target.def
> index 1dffedc81e4..b89e7c24471 100644
> --- a/gcc/target.def
> +++ b/gcc/target.def
> @@ -2724,6 +2724,13 @@ DEFHOOK
> rtx, (rtx_insn **prep_seq, rtx_insn **gen_seq, rtx prev, int cmp_code, tree
> op0, tree op1, int bit_code),
> NULL)
>
> +DEFHOOK
> +(gen_memset_scratch_rtx,
> + "This hook should return an rtx for scratch register in @var{mode} to\n\
> +be used by memset broadcast. The default is @code{gen_reg_rtx}.",
> + rtx, (machine_mode mode),
> + gen_reg_rtx)
> +
> /* Return a new value for loop unroll size. */
> DEFHOOK
> (loop_unroll_adjust,
> --
> 2.31.1
>
