From: Richard Sandiford <richard.sandiford@arm.com>
To: Tamar Christina <Tamar.Christina@arm.com>
Cc: Richard Biener <rguenther@suse.de>, nd <nd@arm.com>,
"gcc-patches\@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH 1/4]middle-end Vect: Add support for dot-product where the sign for the multiplicant changes.
Date: Mon, 12 Jul 2021 11:25:30 +0100 [thread overview]
Message-ID: <mpt5yxfj0bp.fsf@arm.com> (raw)
In-Reply-To: <VI1PR08MB53259C129C42CFADD2FDBA8DFF159@VI1PR08MB5325.eurprd08.prod.outlook.com> (Tamar Christina's message of "Mon, 12 Jul 2021 09:56:54 +0000")
Tamar Christina <Tamar.Christina@arm.com> writes:
>> -----Original Message-----
>> From: Richard Sandiford <richard.sandiford@arm.com>
>> Sent: Monday, July 12, 2021 10:39 AM
>> To: Tamar Christina <Tamar.Christina@arm.com>
>> Cc: Richard Biener <rguenther@suse.de>; nd <nd@arm.com>; gcc-
>> patches@gcc.gnu.org
>> Subject: Re: [PATCH 1/4]middle-end Vect: Add support for dot-product
>> where the sign for the multiplicant changes.
>>
>> Tamar Christina <Tamar.Christina@arm.com> writes:
>> > Hi,
>> >
>> >> Richard Sandiford <richard.sandiford@arm.com> writes:
>> >> >> @@ -992,21 +1029,27 @@ vect_recog_dot_prod_pattern (vec_info
>> >> *vinfo,
>> >> >> /* FORNOW. Can continue analyzing the def-use chain when this
>> >> >> stmt in
>> >> a phi
>> >> >> inside the loop (in case we are analyzing an outer-loop). */
>> >> >> vect_unpromoted_value unprom0[2];
>> >> >> + enum optab_subtype subtype = optab_vector;
>> >> >> if (!vect_widened_op_tree (vinfo, mult_vinfo, MULT_EXPR,
>> >> WIDEN_MULT_EXPR,
>> >> >> - false, 2, unprom0, &half_type))
>> >> >> + false, 2, unprom0, &half_type, &subtype))
>> >> >> + return NULL;
>> >> >> +
>> >> >> + if (subtype == optab_vector_mixed_sign
>> >> >> + && TYPE_UNSIGNED (unprom_mult.type)
>> >> >> + && TYPE_PRECISION (half_type) * 4 > TYPE_PRECISION
>> >> >> + (unprom_mult.type))
>> >> >> return NULL;
>> >> >
>> >> > Isn't the final condition here instead that TYPE1 is narrower than TYPE2?
>> >> > I.e. we need to reject the case in which we multiply a signed and
>> >> > an unsigned value to get a (logically) signed result, but then
>> >> > zero-extend it (rather than sign-extend it) to the precision of the
>> addition.
>> >> >
>> >> > That would make the test:
>> >> >
>> >> > if (subtype == optab_vector_mixed_sign
>> >> > && TYPE_UNSIGNED (unprom_mult.type)
>> >> > && TYPE_PRECISION (unprom_mult.type) < TYPE_PRECISION (type))
>> >> > return NULL;
>> >> >
>> >> > instead.
>> >>
>> >> And folding that into the existing test gives:
>> >>
>> >> /* If there are two widening operations, make sure they agree on the
>> sign
>> >> of the extension. The result of an optab_vector_mixed_sign operation
>> >> is signed; otherwise, the result has the same sign as the operands. */
>> >> if (TYPE_PRECISION (unprom_mult.type) != TYPE_PRECISION (type)
>> >> && (subtype == optab_vector_mixed_sign
>> >> ? TYPE_UNSIGNED (unprom_mult.type)
>> >> : TYPE_SIGN (unprom_mult.type) != TYPE_SIGN (half_type)))
>> >> return NULL;
>> >>
>> >
>> > I went with the first one which doesn't add the extra constraints for
>> > the normal dotproduct as that makes it too restrictive. It's the type
>> > of the multiplication that determines the operation so dotproduct can
>> > be used a bit more than where we currently do.
>> >
>> > This was relaxed in an earlier patch.
>>
>> I didn't mean that we should add extra constraints to the normal case though.
>> The existing test I was referring to above was:
>>
>> /* If there are two widening operations, make sure they agree on
>> the sign of the extension. */
>> if (TYPE_PRECISION (unprom_mult.type) != TYPE_PRECISION (type)
>> && TYPE_SIGN (unprom_mult.type) != TYPE_SIGN (half_type))
>> return NULL;
>
> But as I mentioned, this restriction is unneeded and has been removed hence why it's not in my patchset's diff.
> It's removed by https://gcc.gnu.org/pipermail/gcc-patches/2021-May/569851.html which Richi conditioned on
> the rest of these patches being approved.
>
> This change needlessly blocks test vect-reduc-dot-[2,3,6,7].c from being dotproducts for instance
>
> It's also part of the deficiency between GCC codegen and Clang https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88492#c6
Hmm, OK. Just removing the check regresses:
unsigned long __attribute__ ((noipa))
f (signed short *x, signed short *y)
{
unsigned long res = 0;
for (int i = 0; i < 100; ++i)
res += (unsigned int) x[i] * (unsigned int) y[i];
return res;
}
int
main (void)
{
signed short x[100], y[100];
for (int i = 0; i < 100; ++i)
{
x[i] = -1;
y[i] = 1;
}
if (f (x, y) != 0x6400000000ULL - 100)
__builtin_abort ();
return 0;
}
on SVE. We then use SDOT even though the result of the multiplication
is zero- rather than sign-extended to 64 bits. Does something else
in the series stop that from that happening?
Richard
next prev parent reply other threads:[~2021-07-12 10:25 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
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 [this message]
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=mpt5yxfj0bp.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=Tamar.Christina@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=nd@arm.com \
--cc=rguenther@suse.de \
/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).