From: Richard Biener <rguenther@suse.de>
To: Tamar Christina <Tamar.Christina@arm.com>
Cc: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>, nd <nd@arm.com>
Subject: RE: [PATCH 1/4]middle-end Vect: Add support for dot-product where the sign for the multiplicant changes.
Date: Mon, 10 May 2021 15:29:09 +0200 (CEST) [thread overview]
Message-ID: <nycvar.YFH.7.76.2105101522390.9200@zhemvz.fhfr.qr> (raw)
In-Reply-To: <VI1PR08MB5325748CA53CAFBD3B39AFB1FF549@VI1PR08MB5325.eurprd08.prod.outlook.com>
On Mon, 10 May 2021, Tamar Christina wrote:
>
>
> > -----Original Message-----
> > From: Richard Biener <rguenther@suse.de>
> > Sent: Monday, May 10, 2021 12:40 PM
> > To: Tamar Christina <Tamar.Christina@arm.com>
> > Cc: gcc-patches@gcc.gnu.org; nd <nd@arm.com>
> > Subject: RE: [PATCH 1/4]middle-end Vect: Add support for dot-product
> > where the sign for the multiplicant changes.
> >
> > On Fri, 7 May 2021, Tamar Christina wrote:
> >
> > > Hi Richi,
> > >
> > > > -----Original Message-----
> > > > From: Richard Biener <rguenther@suse.de>
> > > > Sent: Friday, May 7, 2021 12:46 PM
> > > > To: Tamar Christina <Tamar.Christina@arm.com>
> > > > Cc: gcc-patches@gcc.gnu.org; nd <nd@arm.com>
> > > > Subject: Re: [PATCH 1/4]middle-end Vect: Add support for dot-product
> > > > where the sign for the multiplicant changes.
> > > >
> > > > On Wed, 5 May 2021, Tamar Christina wrote:
> > > >
> > > > > Hi All,
> > > > >
> > > > > This patch adds support for a dot product where the sign of the
> > > > > multiplication arguments differ. i.e. one is signed and one is
> > > > > unsigned but the precisions are the same.
> > > > >
> > > > > #define N 480
> > > > > #define SIGNEDNESS_1 unsigned
> > > > > #define SIGNEDNESS_2 signed
> > > > > #define SIGNEDNESS_3 signed
> > > > > #define SIGNEDNESS_4 unsigned
> > > > >
> > > > > SIGNEDNESS_1 int __attribute__ ((noipa)) f (SIGNEDNESS_1 int res,
> > > > > SIGNEDNESS_3 char *restrict a,
> > > > > SIGNEDNESS_4 char *restrict b)
> > > > > {
> > > > > for (__INTPTR_TYPE__ i = 0; i < N; ++i)
> > > > > {
> > > > > int av = a[i];
> > > > > int bv = b[i];
> > > > > SIGNEDNESS_2 short mult = av * bv;
> > > > > res += mult;
> > > > > }
> > > > > return res;
> > > > > }
> > > > >
> > > > > The operations are performed as if the operands were extended to a
> > > > > 32-bit
> > > > value.
> > > > > As such this operation isn't valid if there is an intermediate
> > > > > conversion to an unsigned value. i.e. if SIGNEDNESS_2 is unsigned.
> > > > >
> > > > > more over if the signs of SIGNEDNESS_3 and SIGNEDNESS_4 are
> > > > > flipped the same optab is used but the operands are flipped in the
> > > > > optab
> > > > expansion.
> > > > >
> > > > > To support this the patch extends the dot-product detection to
> > > > > optionally ignore operands with different signs and stores this
> > > > > information in the optab subtype which is now made a bitfield.
> > > > >
> > > > > The subtype can now additionally controls which optab an EXPR can
> > > > > expand
> > > > to.
> > > > >
> > > > > Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
> > > > >
> > > > > Ok for master?
> > > > >
> > > > > Thanks,
> > > > > Tamar
> > > > >
> > > > > gcc/ChangeLog:
> > > > >
> > > > > * optabs.def (usdot_prod_optab): New.
> > > > > * doc/md.texi: Document it.
> > > > > * optabs-tree.c (optab_for_tree_code): Support usdot_prod_optab.
> > > > > * optabs-tree.h (enum optab_subtype): Likewise.
> > > > > * optabs.c (expand_widen_pattern_expr): Likewise.
> > > > > * tree-cfg.c (verify_gimple_assign_ternary): Likewise.
> > > > > * tree-vect-loop.c (vect_determine_dot_kind): New.
> > > > > (vectorizable_reduction): Query dot-product kind.
> > > > > * tree-vect-patterns.c (vect_supportable_direct_optab_p): Take
> > > > optional
> > > > > optab subtype.
> > > > > (vect_joust_widened_type, vect_widened_op_tree): Optionally
> > > > ignore
> > > > > mismatch types.
> > > > > (vect_recog_dot_prod_pattern): Support usdot_prod_optab.
> > > > >
> > > > > --- inline copy of patch --
> > > > > diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index
> > > > >
> > > >
> > d166a0debedf4d8edf55c842bcf4ff4690b3e9ce..baf20416e63745097825fc30fd
> > > > f2
> > > > > e66bc80d7d23 100644
> > > > > --- a/gcc/doc/md.texi
> > > > > +++ b/gcc/doc/md.texi
> > > > > @@ -5440,11 +5440,13 @@ Like @samp{fold_left_plus_@var{m}}, but
> > > > takes
> > > > > an additional mask operand @item @samp{sdot_prod@var{m}}
> > @cindex
> > > > > @code{udot_prod@var{m}} instruction pattern @itemx
> > > > > @samp{udot_prod@var{m}}
> > > > > +@cindex @code{usdot_prod@var{m}} instruction pattern @itemx
> > > > > +@samp{usdot_prod@var{m}}
> > > > > Compute the sum of the products of two signed/unsigned elements.
> > > > > -Operand 1 and operand 2 are of the same mode. Their product,
> > > > > which is of a -wider mode, is computed and added to operand 3.
> > > > > Operand 3 is of a mode equal or -wider than the mode of the
> > > > > product. The result is placed in operand 0, which -is of the same mode
> > as operand 3.
> > > > > +Operand 1 and operand 2 are of the same mode but may differ in
> > signs.
> > > > > +Their product, which is of a wider mode, is computed and added to
> > > > operand 3.
> > > > > +Operand 3 is of a mode equal or wider than the mode of the product.
> > > > > +The result is placed in operand 0, which is of the same mode as
> > operand 3.
> > > >
> > > > This doesn't really say what the 's', 'u' and 'us' specify. Since
> > > > we're doing a widen multiplication and then a non-widening addition
> > > > we only need to know the effective sign of the multiplication so I think
> > the existing 's' and 'u'
> > > > are enough to cover all cases?
> > >
> > > The existing 's' and 'u' enforce that both operands of the
> > > multiplication are of the same sign. So for e.g. 'u' both operand must be
> > unsigned.
> > >
> > > In the `us` case one can be signed and one unsigned. Operationally
> > > this does a sign extension to the wider type for the signed value, and
> > > the unsigned value gets zero extended first, and then converts it to
> > > unsigned to perform the unsigned multiplication, conforming to the C
> > promotion rules.
> > >
> > > TL;DR; Without a new optab I can't tell during expansion which
> > > semantic the operation had at the gimple/C level as modes don't carry signs.
> > >
> > > Long version:
> > >
> > > The problem with using the existing patterns, because of their
> > > enforcement of `av` and `bv` being the same sign is that we can't
> > > remove the explicit sign extensions, but the multiplication must be done on
> > the sign/zero extended char input in the same sign.
> > >
> > > Which means (unless I am mistaken) to get the correct result, you
> > > can't use neither `udot` nor `sdot` as semantically these would zero
> > > or sign extend both operands from char to int to perform the
> > > multiplication in the same sigh. Whereas in this case, one parameter is zero
> > and one parameter is sign extended and the result is always an unsigned
> > number.
> > >
> > > So basically
> > >
> > > udot<unsigned c, unsigned a, unsigned b> ==
> > > c = zero-ext (a) * zero-ext (b)
> > > sdot<signed c, signed a, signed b> ==
> > > c = sign-ext (a) * sign-ext (b)
> > > usdot<unsigned c, unsigned a, signed b> ==
> > > c = ((unsigned-conv) sign-ext (a)) * zero-ext (b)
> > >
> > > So semantically the existing optabs won't fit here. udot would
> > > internally promote to unsigned types before the multiplication so the
> > > result of the multiplication would be wrong. sdot would promote both to
> > signed and do signed multiplication, so the result is also wrong.
> > >
> > > Now if I relax the constraint on the signs of udot and sdot there are two
> > problems:
> > > RTL Modes don't contain signs. So a target can't tell me how the operands
> > will be promoted.
> > > So:
> > >
> > > 1) I can't really check which semantics the target will adhere to on
> > expansion.
> > > 2) at expand time I have no way to differentiate between the two
> > instructions variants, given just modes
> > > I can't tell whether I expand to the normal dot-product or the new
> > instruction.
> >
> > Ah, OK. Indeed with such a weird instruction the new variant makes sense.
> > Still can you please amend the optab documentation to say which operand is
> > unsigned and which is signed? Just 'may differ in signs'
> > is bad.
>
> Sure, will expand on it.
>
> >
> > Since the multiplication is commutative I wonder why you need to handle
> > both signed_to_unsigned and unsigned_to_signed - we should just enforce
> > a canonical order (like the optab does).
>
> Sure, I thought it would have been better to change the order at expand time,
> but can do so at detection time.
>
> > I also think it's a particular bad fit for
> > the bad optab_for_tree_code API - would any of that improve when using a
> > direct internal function here?
>
> Somewhat, but this has considerable knock on effects, e.g. currently DOT_PROD is
> treated as a widening operation and so is handled by supportable_widening_operation
> which does not support calls. There's a significant number of places which work on the
> tree EXPR (including constant folding) which all need to be changed.
>
> > In particular all the changes around
> > optab_subtype look like they make a bad API worse ... at least a single
> > optab_vector_mixed_sign should suffice here, no need to make it a flags
> > kind.
>
> The reason I did so is because depending on where the query is done it does use
> different subtypes currently. During detection it uses optab_default, and during
> vectorization optab_vector. For this instruction this difference doesn't seem to be
> used, but did not want to lose this information in case something depended on it.
>
> But can make it just one.
>
> >
> > + /* If we have a sign changing dot product we need to check that the
> > + promoted type if unsigned has at least the same precision as the
> > final
> > + type of the dot-product. */
> > + if (subtype != optab_default)
> > + {
> > + tree mult_type = TREE_TYPE (unprom_mult.op);
> > + if (TYPE_SIGN (mult_type) == UNSIGNED
> > + && TYPE_PRECISION (mult_type) < TYPE_PRECISION (type))
> > + return NULL;
> > + }
> >
> > I don't understand this - how do we ever arrive at a result with less precision?
>
> The user could have manually truncated the results, i.e. in the detection code notice `mult`
>
> int av = a[i];
> int bv = b[i];
> SIGNEDNESS_2 short mult = av * bv;
> res += mult;
>
> which is a short, so it's manually truncating the multiplication which
> is done as int by the instruction. If `mult` is unsigned then it will
> truncate the result if the signed input to usdot was negative, unless
> the Intermediate calculation is of the same precision as the
> instruction. i.e. if mult is unsigned int then there's no truncation
> going on, it's casting from int to unsigned int so it's safe to use then
> as the instruction does the same thing internally.
It looks to me that we simply should only ever allow sing-changes
from multiplication result to the sum. At least your example
above is not special to mixed sign multiplications, no?
> > And why's this not an issue for signed multiplication?
>
> It is, but in that case it's handled by the type jousting, which doesn't
> allow the type mismatch. i.e.
>
> #define SIGNEDNESS_1 unsigned
> #define SIGNEDNESS_2 unsigned
> #define SIGNEDNESS_3 signed
> #define SIGNEDNESS_4 signed
>
> SIGNEDNESS_1 int __attribute__ ((noipa))
> f (SIGNEDNESS_1 int res, SIGNEDNESS_3 char *restrict a,
> SIGNEDNESS_4 char *restrict b)
> {
> for (__INTPTR_TYPE__ i = 0; i < N; ++i)
> {
> int av = a[i];
> int bv = b[i];
> SIGNEDNESS_2 short mult = av * bv;
> res += mult;
> }
> return res;
> }
>
> Is also not detected as a dot product. By adding the carve out to the
> widen multiplication detection it now allows this case through so I
> handle it in the detection code. Thinking about it now, it seems more
> logical to add this case handling inside the type jousting code as I
> don't think it's ever something you'd want.
Yeah, I think we only need to look through sign changes on the
multiplication result.
> > Also...
> >
> > + /* If we have a sign changing dot-product the dot-product itself does
> > any
> > + sign conversions, so consume the type and use the unpromoted types.
> > */
> > + tree mult_arg1, mult_arg2;
> > + if (subtype == optab_default)
> > + {
> > + mult_arg1 = mult_oprnd[0];
> > + mult_arg2 = mult_oprnd[1];
> > + }
> > + else
> > + {
> > + mult_arg1 = unprom0[0].op;
> > + mult_arg2 = unprom0[1].op;
> > + }
> > pattern_stmt = gimple_build_assign (var, DOT_PROD_EXPR,
> > - mult_oprnd[0], mult_oprnd[1],
> > oprnd1);
> > + mult_arg1, mult_arg2, oprnd1);
> >
> > I thought DOT_PROD always performs the promotion. Maybe mult_oprnd
> > and unprom0 are just misnamed here?
>
> Somewhat, in a normal dot-product the sign of the multiplication are the
> same here as the "unpromoted" types. So after vect_convert_input these
> two types are the same.
>
> However because here the sign changes and to maintain the semantics of
> the C code there's an extra conversion here to get the arguments in the
> same sign. That needs to be stripped before given to the instruction
> which does the conversion internally.
Yes, but then why's that not done by the detection code? That is,
does it (mis-)handle the (int)short_a * (int)(unsigned short)short_b
where we'd want the mixed-sign handling and not strip the
unsigned short conversion from short_b?
Richard.
>
> Regards,
> Tamar
>
> >
> > Richard.
> >
> > > Regards,
> > > Tamar
> > >
> > > >
> > > > The tree.def docs say the sum is also possibly widening but I don't
> > > > see this covered by the optab so we should eventually remove this
> > > > feature from the tree side. In fact the tree-cfg.c verifier
> > > > requires the addition to be not widening - thus only tree.def needs
> > adjustment.
> > > >
> > > > > @cindex @code{ssad@var{m}} instruction pattern @item
> > > > > @samp{ssad@var{m}} diff --git a/gcc/optabs-tree.h
> > > > > b/gcc/optabs-tree.h index
> > > > >
> > > >
> > c3aaa1a416991e856d3e24da45968a92ebada82c..ebc23ac86fe99057f375781c2f
> > > > 19
> > > > > 90e0548ba08d 100644
> > > > > --- a/gcc/optabs-tree.h
> > > > > +++ b/gcc/optabs-tree.h
> > > > > @@ -27,11 +27,29 @@ along with GCC; see the file COPYING3. If not
> > see
> > > > > shift amount vs. machines that take a vector for the shift amount.
> > > > > */ enum optab_subtype {
> > > > > - optab_default,
> > > > > - optab_scalar,
> > > > > - optab_vector
> > > > > + optab_default = 1 << 0,
> > > > > + optab_scalar = 1 << 1,
> > > > > + optab_vector = 1 << 2,
> > > > > + optab_signed_to_unsigned = 1 << 3, optab_unsigned_to_signed =
> > > > > + 1 << 4
> > > > > };
> > > > >
> > > > > +/* Override the OrEqual-operator so we can use optab_subtype as a
> > > > > +bit flag. */ inline enum optab_subtype& operator |= (enum
> > > > optab_subtype&
> > > > > +a, enum optab_subtype b) {
> > > > > + return a = static_cast<optab_subtype>(static_cast<int>(a)
> > > > > + | static_cast<int>(b));
> > > > > +}
> > > > > +
> > > > > +/* Override the Or-operator so we can use optab_subtype as a bit
> > > > > +flag. */ inline enum optab_subtype operator | (enum
> > > > > +optab_subtype a, enum optab_subtype b) {
> > > > > + return static_cast<optab_subtype>(static_cast<int>(a)
> > > > > + | static_cast<int>(b)); }
> > > > > +
> > > > > /* Return the optab used for computing the given operation on the
> > > > > type
> > > > given by
> > > > > the second argument. The third argument distinguishes between
> > > > > the
> > > > types of
> > > > > vector shifts and rotates. */ diff --git a/gcc/optabs-tree.c
> > > > > b/gcc/optabs-tree.c index
> > > > >
> > > >
> > 95ffe397c23e80c105afea52e9d47216bf52f55a..2f60004545defc53182e004eea
> > > > 1e
> > > > > 5c22b7453072 100644
> > > > > --- a/gcc/optabs-tree.c
> > > > > +++ b/gcc/optabs-tree.c
> > > > > @@ -127,7 +127,17 @@ optab_for_tree_code (enum tree_code code,
> > > > const_tree type,
> > > > > return TYPE_UNSIGNED (type) ? usum_widen_optab :
> > > > > ssum_widen_optab;
> > > > >
> > > > > case DOT_PROD_EXPR:
> > > > > - return TYPE_UNSIGNED (type) ? udot_prod_optab :
> > sdot_prod_optab;
> > > > > + {
> > > > > + gcc_assert (subtype & optab_default
> > > > > + || subtype & optab_vector
> > > > > + || subtype & optab_signed_to_unsigned
> > > > > + || subtype & optab_unsigned_to_signed);
> > > > > +
> > > > > + if (subtype & (optab_unsigned_to_signed |
> > > > optab_signed_to_unsigned))
> > > > > + return usdot_prod_optab;
> > > > > +
> > > > > + return (TYPE_UNSIGNED (type) ? udot_prod_optab :
> > > > sdot_prod_optab);
> > > > > + }
> > > > >
> > > > > case SAD_EXPR:
> > > > > return TYPE_UNSIGNED (type) ? usad_optab : ssad_optab; diff
> > > > > --git a/gcc/optabs.c b/gcc/optabs.c index
> > > > >
> > > >
> > f4614a394587787293dc8b680a38901f7906f61c..2e18b76de1412eab71971753ac
> > > > 67
> > > > > 8597c0d00098 100644
> > > > > --- a/gcc/optabs.c
> > > > > +++ b/gcc/optabs.c
> > > > > @@ -262,6 +262,11 @@ expand_widen_pattern_expr (sepops ops, rtx
> > > > > op0,
> > > > rtx op1, rtx wide_op,
> > > > > bool sbool = false;
> > > > >
> > > > > oprnd0 = ops->op0;
> > > > > + if (nops >= 2)
> > > > > + oprnd1 = ops->op1;
> > > > > + if (nops >= 3)
> > > > > + oprnd2 = ops->op2;
> > > > > +
> > > > > tmode0 = TYPE_MODE (TREE_TYPE (oprnd0));
> > > > > if (ops->code == VEC_UNPACK_FIX_TRUNC_HI_EXPR
> > > > > || ops->code == VEC_UNPACK_FIX_TRUNC_LO_EXPR) @@ -285,6
> > > > +290,27
> > > > > @@ expand_widen_pattern_expr (sepops ops, rtx op0, rtx op1, rtx
> > > > wide_op,
> > > > > ? vec_unpacks_sbool_hi_optab : vec_unpacks_sbool_lo_optab);
> > > > > sbool = true;
> > > > > }
> > > > > + else if (ops->code == DOT_PROD_EXPR)
> > > > > + {
> > > > > + enum optab_subtype subtype = optab_default;
> > > > > + signop sign1 = TYPE_SIGN (TREE_TYPE (oprnd0));
> > > > > + signop sign2 = TYPE_SIGN (TREE_TYPE (oprnd1));
> > > > > + if (sign1 == sign2)
> > > > > + ;
> > > > > + else if (sign1 == SIGNED && sign2 == UNSIGNED)
> > > > > + {
> > > > > + subtype |= optab_signed_to_unsigned;
> > > > > + /* Same as optab_unsigned_to_signed but flip the operands. */
> > > > > + std::swap (op0, op1);
> > > > > + }
> > > > > + else if (sign1 == UNSIGNED && sign2 == SIGNED)
> > > > > + subtype |= optab_unsigned_to_signed;
> > > > > + else
> > > > > + gcc_unreachable ();
> > > > > +
> > > > > + widen_pattern_optab
> > > > > + = optab_for_tree_code (ops->code, TREE_TYPE (oprnd0), subtype);
> > > > > + }
> > > > > else
> > > > > widen_pattern_optab
> > > > > = optab_for_tree_code (ops->code, TREE_TYPE (oprnd0),
> > > > > optab_default); @@ -298,10 +324,7 @@ expand_widen_pattern_expr
> > > > (sepops ops, rtx op0, rtx op1, rtx wide_op,
> > > > > gcc_assert (icode != CODE_FOR_nothing);
> > > > >
> > > > > if (nops >= 2)
> > > > > - {
> > > > > - oprnd1 = ops->op1;
> > > > > - tmode1 = TYPE_MODE (TREE_TYPE (oprnd1));
> > > > > - }
> > > > > + tmode1 = TYPE_MODE (TREE_TYPE (oprnd1));
> > > > > else if (sbool)
> > > > > {
> > > > > nops = 2;
> > > > > @@ -316,7 +339,6 @@ expand_widen_pattern_expr (sepops ops, rtx
> > > > > op0,
> > > > rtx op1, rtx wide_op,
> > > > > {
> > > > > gcc_assert (tmode1 == tmode0);
> > > > > gcc_assert (op1);
> > > > > - oprnd2 = ops->op2;
> > > > > wmode = TYPE_MODE (TREE_TYPE (oprnd2));
> > > > > }
> > > > >
> > > > > diff --git a/gcc/optabs.def b/gcc/optabs.def index
> > > > >
> > > >
> > b192a9d070b8aa72e5676b2eaa020b5bdd7ffcc8..f470c2168378cec840edf7fbd
> > > > b7c
> > > > > 18615baae928 100644
> > > > > --- a/gcc/optabs.def
> > > > > +++ b/gcc/optabs.def
> > > > > @@ -352,6 +352,7 @@ OPTAB_D (uavg_ceil_optab, "uavg$a3_ceil")
> > > > OPTAB_D
> > > > > (sdot_prod_optab, "sdot_prod$I$a") OPTAB_D (ssum_widen_optab,
> > > > > "widen_ssum$I$a3") OPTAB_D (udot_prod_optab, "udot_prod$I$a")
> > > > > +OPTAB_D (usdot_prod_optab, "usdot_prod$I$a")
> > > > > OPTAB_D (usum_widen_optab, "widen_usum$I$a3") OPTAB_D
> > > > (usad_optab,
> > > > > "usad$I$a") OPTAB_D (ssad_optab, "ssad$I$a") diff --git
> > > > > a/gcc/tree-cfg.c b/gcc/tree-cfg.c index
> > > > >
> > > >
> > 7e3aae5f9c28a49feedc7cc66e8ac0d476b9f28a..58b55bb648ad97d514f1fa18bb
> > > > 00
> > > > > 808fd2678b42 100644
> > > > > --- a/gcc/tree-cfg.c
> > > > > +++ b/gcc/tree-cfg.c
> > > > > @@ -4421,7 +4421,8 @@ verify_gimple_assign_ternary (gassign *stmt)
> > > > > && !SCALAR_FLOAT_TYPE_P (rhs1_type))
> > > > > || (!INTEGRAL_TYPE_P (lhs_type)
> > > > > && !SCALAR_FLOAT_TYPE_P (lhs_type))))
> > > > > - || !types_compatible_p (rhs1_type, rhs2_type)
> > > > > + || (!types_compatible_p (rhs1_type, rhs2_type)
> > > > > + && TYPE_SIGN (rhs1_type) == TYPE_SIGN (rhs2_type))
> > > >
> > > > That's not restrictive enough. I suggest you use
> > > >
> > > > && element_precision (rhs1_type) != element_precision
> > > > (rhs2_type)
> > > >
> > > > instead.
> > > >
> > > > As said, I'm not sure all the changes in this patch are required.
> > > >
> > > > Please elaborate.
> > > >
> > > > Thanks,
> > > > Richard.
> > > >
> > > > > || !useless_type_conversion_p (lhs_type, rhs3_type)
> > > > > || maybe_lt (GET_MODE_SIZE (element_mode (rhs3_type)),
> > > > > 2 * GET_MODE_SIZE (element_mode (rhs1_type))))
> > > > diff --git
> > > > > a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index
> > > > >
> > > >
> > 93fa2928e001c154bd4a9a73ac1dbbbf73c456df..cb8f5fbb6abca181c4171194d1
> > > > 9f
> > > > > ec29ec6e4176 100644
> > > > > --- a/gcc/tree-vect-loop.c
> > > > > +++ b/gcc/tree-vect-loop.c
> > > > > @@ -6401,6 +6401,33 @@ build_vect_cond_expr (enum tree_code
> > code,
> > > > tree vop[3], tree mask,
> > > > > }
> > > > > }
> > > > >
> > > > > +/* Determine the optab_subtype to use for the given CODE and STMT.
> > > > For
> > > > > + most CODE this will be optab_vector, however for certain
> > > > > + operations
> > > > such as
> > > > > + DOT_PROD_EXPR where the operation can different signs for the
> > > > operands we
> > > > > + need to be able to pick the right optabs. */
> > > > > +
> > > > > +static enum optab_subtype
> > > > > +vect_determine_dot_kind (tree_code code, stmt_vec_info
> > > > > +stmt_vinfo) {
> > > > > + enum optab_subtype subtype = optab_vector;
> > > > > + switch (code)
> > > > > + {
> > > > > + case DOT_PROD_EXPR:
> > > > > + {
> > > > > + gassign *stmt = as_a <gassign *> (STMT_VINFO_STMT (stmt_vinfo));
> > > > > + signop rhs1_sign = TYPE_SIGN (TREE_TYPE (gimple_assign_rhs1
> > > > (stmt)));
> > > > > + signop rhs2_sign = TYPE_SIGN (TREE_TYPE (gimple_assign_rhs2
> > > > (stmt)));
> > > > > + if (rhs1_sign != rhs2_sign)
> > > > > + subtype |= optab_unsigned_to_signed;
> > > > > + break;
> > > > > + }
> > > > > + default:
> > > > > + break;
> > > > > + }
> > > > > +
> > > > > + return subtype;
> > > > > +}
> > > > > +
> > > > > /* Function vectorizable_reduction.
> > > > >
> > > > > Check if STMT_INFO performs a reduction operation that can be
> > > > vectorized.
> > > > > @@ -7189,7 +7216,8 @@ vectorizable_reduction (loop_vec_info
> > > > loop_vinfo,
> > > > > bool ok = true;
> > > > >
> > > > > /* 4.1. check support for the operation in the loop */
> > > > > - optab optab = optab_for_tree_code (code, vectype_in,
> > optab_vector);
> > > > > + enum optab_subtype subtype = vect_determine_dot_kind (code,
> > > > stmt_info);
> > > > > + optab optab = optab_for_tree_code (code, vectype_in,
> > > > > + subtype);
> > > > > if (!optab)
> > > > > {
> > > > > if (dump_enabled_p ())
> > > > > diff --git a/gcc/tree-vect-patterns.c b/gcc/tree-vect-patterns.c
> > > > > index
> > > > >
> > > >
> > 441d6cd28c4eaded7abd756164890dbcffd2f3b8..943c001fb13777b4d1513841f
> > > > a84
> > > > > 942316846d5e 100644
> > > > > --- a/gcc/tree-vect-patterns.c
> > > > > +++ b/gcc/tree-vect-patterns.c
> > > > > @@ -201,7 +201,8 @@ vect_get_external_def_edge (vec_info *vinfo,
> > > > > tree
> > > > > var) static bool vect_supportable_direct_optab_p (vec_info
> > > > > *vinfo, tree otype, tree_code code,
> > > > > tree itype, tree *vecotype_out,
> > > > > - tree *vecitype_out = NULL)
> > > > > + tree *vecitype_out = NULL,
> > > > > + enum optab_subtype subtype =
> > > > optab_default)
> > > > > {
> > > > > tree vecitype = get_vectype_for_scalar_type (vinfo, itype);
> > > > > if (!vecitype)
> > > > > @@ -211,7 +212,7 @@ vect_supportable_direct_optab_p (vec_info
> > > > > *vinfo,
> > > > tree otype, tree_code code,
> > > > > if (!vecotype)
> > > > > return false;
> > > > >
> > > > > - optab optab = optab_for_tree_code (code, vecitype,
> > > > > optab_default);
> > > > > + optab optab = optab_for_tree_code (code, vecitype, subtype);
> > > > > if (!optab)
> > > > > return false;
> > > > >
> > > > > @@ -487,14 +488,31 @@ vect_joust_widened_integer (tree type, bool
> > > > > shift_p, tree op, }
> > > > >
> > > > > /* Return true if the common supertype of NEW_TYPE and
> > > > *COMMON_TYPE
> > > > > - is narrower than type, storing the supertype in *COMMON_TYPE if
> > so.
> > > > */
> > > > > + is narrower than type, storing the supertype in *COMMON_TYPE if
> > so.
> > > > > + If ALLOW_SHORT_SIGN_MISMATCH then accept that
> > *COMMON_TYPE
> > > > and NEW_TYPE
> > > > > + may be of different signs but equal precision. */
> > > > >
> > > > > static bool
> > > > > -vect_joust_widened_type (tree type, tree new_type, tree
> > > > *common_type)
> > > > > +vect_joust_widened_type (tree type, tree new_type, tree
> > > > *common_type,
> > > > > + bool allow_short_sign_mismatch = false)
> > > > > {
> > > > > if (types_compatible_p (*common_type, new_type))
> > > > > return true;
> > > > >
> > > > > + /* Check if the mismatch is only in the sign and if we have
> > > > > + allow_short_sign_mismatch then allow it. */
> > > > > + if (allow_short_sign_mismatch
> > > > > + && TYPE_SIGN (*common_type) != TYPE_SIGN (new_type))
> > > > > + {
> > > > > + bool sign = TYPE_SIGN (*common_type) == UNSIGNED;
> > > > > + tree eq_type
> > > > > + = build_nonstandard_integer_type (TYPE_PRECISION (new_type),
> > > > > + sign);
> > > > > +
> > > > > + if (types_compatible_p (*common_type, eq_type))
> > > > > + return true;
> > > > > + }
> > > > > +
> > > > > /* See if *COMMON_TYPE can hold all values of NEW_TYPE. */
> > > > > if ((TYPE_PRECISION (new_type) < TYPE_PRECISION (*common_type))
> > > > > && (TYPE_UNSIGNED (new_type) || !TYPE_UNSIGNED
> > > > (*common_type)))
> > > > > @@ -532,6 +550,9 @@ vect_joust_widened_type (tree type, tree
> > > > new_type, tree *common_type)
> > > > > to a type that (a) is narrower than the result of STMT_INFO and
> > > > > (b) can hold all leaf operand values.
> > > > >
> > > > > + If ALLOW_SHORT_SIGN_MISMATCH then allow that the signs of the
> > > > operands
> > > > > + may differ in signs but not in precision.
> > > > > +
> > > > > Return 0 if STMT_INFO isn't such a tree, or if no such COMMON_TYPE
> > > > > exists. */
> > > > >
> > > > > @@ -539,7 +560,8 @@ static unsigned int vect_widened_op_tree
> > > > > (vec_info *vinfo, stmt_vec_info stmt_info, tree_code code,
> > > > > tree_code widened_code, bool shift_p,
> > > > > unsigned int max_nops,
> > > > > - vect_unpromoted_value *unprom, tree *common_type)
> > > > > + vect_unpromoted_value *unprom, tree *common_type,
> > > > > + bool allow_short_sign_mismatch = false)
> > > > > {
> > > > > /* Check for an integer operation with the right code. */
> > > > > gassign *assign = dyn_cast <gassign *> (stmt_info->stmt); @@
> > > > > -600,7
> > > > > +622,8 @@ vect_widened_op_tree (vec_info *vinfo, stmt_vec_info
> > > > stmt_info, tree_code code,
> > > > > = vinfo->lookup_def (this_unprom->op);
> > > > > nops = vect_widened_op_tree (vinfo, def_stmt_info, code,
> > > > > widened_code, shift_p, max_nops,
> > > > > - this_unprom, common_type);
> > > > > + this_unprom, common_type,
> > > > > + allow_short_sign_mismatch);
> > > > > if (nops == 0)
> > > > > return 0;
> > > > >
> > > > > @@ -617,7 +640,8 @@ vect_widened_op_tree (vec_info *vinfo,
> > > > stmt_vec_info stmt_info, tree_code code,
> > > > > if (i == 0)
> > > > > *common_type = this_unprom->type;
> > > > > else if (!vect_joust_widened_type (type, this_unprom->type,
> > > > > - common_type))
> > > > > + common_type,
> > > > > + allow_short_sign_mismatch))
> > > > > return 0;
> > > > > }
> > > > > }
> > > > > @@ -888,21 +912,24 @@ vect_reassociating_reduction_p (vec_info
> > > > > *vinfo,
> > > > >
> > > > > Try to find the following pattern:
> > > > >
> > > > > - type x_t, y_t;
> > > > > + type1a x_t
> > > > > + type1b y_t;
> > > > > TYPE1 prod;
> > > > > TYPE2 sum = init;
> > > > > loop:
> > > > > sum_0 = phi <init, sum_1>
> > > > > S1 x_t = ...
> > > > > S2 y_t = ...
> > > > > - S3 x_T = (TYPE1) x_t;
> > > > > - S4 y_T = (TYPE1) y_t;
> > > > > + S3 x_T = (TYPE3) x_t;
> > > > > + S4 y_T = (TYPE4) y_t;
> > > > > S5 prod = x_T * y_T;
> > > > > [S6 prod = (TYPE2) prod; #optional]
> > > > > S7 sum_1 = prod + sum_0;
> > > > >
> > > > > - where 'TYPE1' is exactly double the size of type 'type', and 'TYPE2' is
> > the
> > > > > - same size of 'TYPE1' or bigger. This is a special case of a reduction
> > > > > + where 'TYPE1' is exactly double the size of type 'type1a' and 'type1b',
> > > > > + the sign of 'TYPE1' must be one of 'type1a' or 'type1b' but the sign of
> > > > > + 'type1a' and 'type1b' can differ. 'TYPE2' is the same size of 'TYPE1' or
> > > > > + bigger and must be the same sign. This is a special case of a
> > > > > + reduction
> > > > > computation.
> > > > >
> > > > > Input:
> > > > > @@ -939,15 +966,16 @@ vect_recog_dot_prod_pattern (vec_info
> > > > > *vinfo,
> > > > >
> > > > > /* Look for the following pattern
> > > > > DX = (TYPE1) X;
> > > > > - DY = (TYPE1) Y;
> > > > > + DY = (TYPE2) Y;
> > > > > DPROD = DX * DY;
> > > > > - DDPROD = (TYPE2) DPROD;
> > > > > + DDPROD = (TYPE3) DPROD;
> > > > > sum_1 = DDPROD + sum_0;
> > > > > In which
> > > > > - DX is double the size of X
> > > > > - DY is double the size of Y
> > > > > - DX, DY, DPROD all have the same type but the sign
> > > > > - between DX, DY and DPROD can differ.
> > > > > + between DX, DY and DPROD can differ. The sign of DPROD
> > > > > + is one of the signs of DX or DY.
> > > > > - sum is the same size of DPROD or bigger
> > > > > - sum has been recognized as a reduction variable.
> > > > >
> > > > > @@ -986,14 +1014,41 @@ vect_recog_dot_prod_pattern (vec_info
> > *vinfo,
> > > > > inside the loop (in case we are analyzing an outer-loop). */
> > > > > vect_unpromoted_value unprom0[2];
> > > > > if (!vect_widened_op_tree (vinfo, mult_vinfo, MULT_EXPR,
> > > > WIDEN_MULT_EXPR,
> > > > > - false, 2, unprom0, &half_type))
> > > > > + false, 2, unprom0, &half_type, true))
> > > > > return NULL;
> > > > >
> > > > > + /* Check to see if there is a sign change happening in the
> > > > > + operands of
> > > > the
> > > > > + multiplication and pick the appropriate optab subtype. */
> > > > > + enum optab_subtype subtype;
> > > > > + tree rhs_type1 = unprom0[0].type;
> > > > > + tree rhs_type2 = unprom0[1].type;
> > > > > + if (TYPE_SIGN (rhs_type1) == TYPE_SIGN (rhs_type2))
> > > > > + subtype = optab_default;
> > > > > + else if (TYPE_SIGN (rhs_type1) == SIGNED
> > > > > + && TYPE_SIGN (rhs_type2) == UNSIGNED)
> > > > > + subtype = optab_signed_to_unsigned;
> > > > > + else if (TYPE_SIGN (rhs_type1) == UNSIGNED
> > > > > + && TYPE_SIGN (rhs_type2) == SIGNED)
> > > > > + subtype = optab_unsigned_to_signed;
> > > > > + else
> > > > > + gcc_unreachable ();
> > > > > +
> > > > > + /* If we have a sign changing dot product we need to check that the
> > > > > + promoted type if unsigned has at least the same precision as the
> > final
> > > > > + type of the dot-product. */
> > > > > + if (subtype != optab_default)
> > > > > + {
> > > > > + tree mult_type = TREE_TYPE (unprom_mult.op);
> > > > > + if (TYPE_SIGN (mult_type) == UNSIGNED
> > > > > + && TYPE_PRECISION (mult_type) < TYPE_PRECISION (type))
> > > > > + return NULL;
> > > > > + }
> > > > > +
> > > > > vect_pattern_detected ("vect_recog_dot_prod_pattern",
> > > > > last_stmt);
> > > > >
> > > > > tree half_vectype;
> > > > > if (!vect_supportable_direct_optab_p (vinfo, type,
> > > > > DOT_PROD_EXPR,
> > > > half_type,
> > > > > - type_out, &half_vectype))
> > > > > + type_out, &half_vectype, subtype))
> > > > > return NULL;
> > > > >
> > > > > /* Get the inputs in the appropriate types. */ @@ -1002,8
> > > > > +1057,22 @@ vect_recog_dot_prod_pattern (vec_info *vinfo,
> > > > > unprom0, half_vectype);
> > > > >
> > > > > var = vect_recog_temp_ssa_var (type, NULL);
> > > > > +
> > > > > + /* If we have a sign changing dot-product the dot-product itself does
> > any
> > > > > + sign conversions, so consume the type and use the unpromoted
> > > > > + types. */ tree mult_arg1, mult_arg2; if (subtype ==
> > > > > + optab_default)
> > > > > + {
> > > > > + mult_arg1 = mult_oprnd[0];
> > > > > + mult_arg2 = mult_oprnd[1];
> > > > > + }
> > > > > + else
> > > > > + {
> > > > > + mult_arg1 = unprom0[0].op;
> > > > > + mult_arg2 = unprom0[1].op;
> > > > > + }
> > > > > pattern_stmt = gimple_build_assign (var, DOT_PROD_EXPR,
> > > > > - mult_oprnd[0], mult_oprnd[1], oprnd1);
> > > > > + mult_arg1, mult_arg2, oprnd1);
> > > > >
> > > > > return pattern_stmt;
> > > > > }
> > > > >
> > > > >
> > > > >
> > > >
> > > > --
> > > > Richard Biener <rguenther@suse.de>
> > > > SUSE Software Solutions Germany GmbH, Maxfeldstrasse 5, 90409
> > > > Nuernberg, Germany; GF: Felix Imendörffer; HRB 36809 (AG Nuernberg)
> > >
> >
> > --
> > Richard Biener <rguenther@suse.de>
> > SUSE Software Solutions Germany GmbH, Maxfeldstrasse 5, 90409
> > Nuernberg, Germany; GF: Felix Imendörffer; HRB 36809 (AG Nuernberg)
>
--
Richard Biener <rguenther@suse.de>
SUSE Software Solutions Germany GmbH, Maxfeldstrasse 5, 90409 Nuernberg,
Germany; GF: Felix Imendörffer; HRB 36809 (AG Nuernberg)
next prev parent reply other threads:[~2021-05-10 13:29 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-05 17:38 Tamar Christina
2021-05-05 17:38 ` [PATCH 2/4]AArch64: Add support for sign differing dot-product usdot for NEON and SVE Tamar Christina
2021-05-10 16:49 ` Richard Sandiford
2021-05-25 14:57 ` Tamar Christina
2021-05-26 8:50 ` Richard Sandiford
2021-05-05 17:39 ` [PATCH 3/4][AArch32]: Add support for sign differing dot-product usdot for NEON Tamar Christina
2021-05-05 17:42 ` FW: " Tamar Christina
[not found] ` <VI1PR08MB5325B832EE3BB6139886C0E9FF259@VI1PR08MB5325.eurprd08.prod.outlook.com>
2021-05-25 15:02 ` Tamar Christina
2021-05-26 10:45 ` Kyrylo Tkachov
2021-05-06 9:23 ` Christophe Lyon
2021-05-06 9:27 ` Tamar Christina
2021-05-05 17:39 ` [PATCH 4/4]middle-end: Add tests middle end generic tests for sign differing dotproduct Tamar Christina
[not found] ` <VI1PR08MB532511701573C18A33AC6291FF259@VI1PR08MB5325.eurprd08.prod.outlook.com>
2021-05-25 15:01 ` FW: " Tamar Christina
[not found] ` <11s2181-8856-30rq-26or-84q8o7qrr2o@fhfr.qr>
2021-05-26 8:48 ` Tamar Christina
2021-06-14 12:08 ` Tamar Christina
2021-05-07 11:45 ` [PATCH 1/4]middle-end Vect: Add support for dot-product where the sign for the multiplicant changes Richard Biener
2021-05-07 12:42 ` Tamar Christina
2021-05-10 11:39 ` Richard Biener
2021-05-10 12:58 ` Tamar Christina
2021-05-10 13:29 ` Richard Biener [this message]
2021-05-25 14:57 ` Tamar Christina
2021-05-26 8:56 ` Richard Biener
2021-06-02 9:28 ` Tamar Christina
2021-06-04 10:12 ` Tamar Christina
2021-06-07 10:10 ` Richard Sandiford
2021-06-14 12:06 ` Tamar Christina
2021-06-21 8:11 ` Tamar Christina
2021-06-22 10:56 ` Richard Sandiford
2021-06-22 11:16 ` Richard Sandiford
2021-07-12 9:18 ` Tamar Christina
2021-07-12 9:39 ` Richard Sandiford
2021-07-12 9:56 ` Tamar Christina
2021-07-12 10:25 ` Richard Sandiford
2021-07-12 12:29 ` Tamar Christina
2021-07-12 14:55 ` Richard Sandiford
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=nycvar.YFH.7.76.2105101522390.9200@zhemvz.fhfr.qr \
--to=rguenther@suse.de \
--cc=Tamar.Christina@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=nd@arm.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).