From: Richard Sandiford <richard.sandiford@arm.com>
To: Jan Hubicka <hubicka@ucw.cz>
Cc: Tamar Christina <tamar.christina@arm.com>,
gcc-patches@gcc.gnu.org, nd@arm.com, Richard.Earnshaw@arm.com,
Marcus.Shawcroft@arm.com, Kyrylo.Tkachov@arm.com,
rguenther@suse.de, kubanek0ondrej@gmail.com
Subject: Re: [PATCH]AArch64 fix regexp for live_1.c sve test
Date: Fri, 21 Jul 2023 18:19:47 +0100 [thread overview]
Message-ID: <mpt8rb9i3m4.fsf@arm.com> (raw)
In-Reply-To: <ZLq78QPxk4xSpPTR@kam.mff.cuni.cz> (Jan Hubicka's message of "Fri, 21 Jul 2023 19:10:09 +0200")
Jan Hubicka <hubicka@ucw.cz> writes:
> Avoid scaling flat loop profiles of vectorized loops
>
> As discussed, when vectorizing loop with static profile, it is not always good idea
> to divide the header frequency by vectorization factor because the profile may
> not realistically represent the expected number of iterations. Since in such cases
> we default to relatively low iteration counts (based on average for spec2k17), this
> will make vectorized loop body look cold.
>
> This patch makes vectorizer to look for flat profiles and only possibly reduce the
> profile by known upper bound on iteration counts.
>
> Bootstrapp/regtested of x86_64-linux in progress. I intend to commit this after
> testers pick other profile related changes from today.
> Tamar, Richard, it would be nice to know if it fixes the testcase you was looking at
> and possibly turn it into a testcase?
Yeah, it does! Thanks for the quick fix.
The test was gcc.target/aarch64/sve/live_1.c. Although it wasn't
originally a profile test, I think it should still be a relatively good
way of testing that the latch is treated as more likely than the exit,
without needing to check for that explicitly.
Richard
>
> gcc/ChangeLog:
>
> * tree-vect-loop.cc (scale_profile_for_vect_loop): Avoid scaling flat
> profiles by vectorization factor.
> (vect_transform_loop): Check for flat profiles.
>
> diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
> index b44fb9c7712..d036a7d4480 100644
> --- a/gcc/tree-vect-loop.cc
> +++ b/gcc/tree-vect-loop.cc
> @@ -10837,11 +10837,25 @@ vect_get_loop_len (loop_vec_info loop_vinfo, gimple_stmt_iterator *gsi,
> }
>
> /* Scale profiling counters by estimation for LOOP which is vectorized
> - by factor VF. */
> + by factor VF.
> + If FLAT is true, the loop we started with had unrealistically flat
> + profile. */
>
> static void
> -scale_profile_for_vect_loop (class loop *loop, unsigned vf)
> +scale_profile_for_vect_loop (class loop *loop, unsigned vf, bool flat)
> {
> + /* For flat profiles do not scale down proportionally by VF and only
> + cap by known iteration count bounds. */
> + if (flat)
> + {
> + if (dump_file && (dump_flags & TDF_DETAILS))
> + fprintf (dump_file,
> + "Vectorized loop profile seems flat; not scaling iteration "
> + "count down by the vectorization factor %i\n", vf);
> + scale_loop_profile (loop, profile_probability::always (),
> + get_likely_max_loop_iterations_int (loop));
> + return;
> + }
> /* Loop body executes VF fewer times and exit increases VF times. */
> edge exit_e = single_exit (loop);
> profile_count entry_count = loop_preheader_edge (loop)->count ();
> @@ -10852,7 +10866,13 @@ scale_profile_for_vect_loop (class loop *loop, unsigned vf)
> while (vf > 1
> && loop->header->count > entry_count
> && loop->header->count < entry_count * vf)
> - vf /= 2;
> + {
> + if (dump_file && (dump_flags & TDF_DETAILS))
> + fprintf (dump_file,
> + "Vectorization factor %i seems too large for profile "
> + "prevoiusly believed to be consistent; reducing.\n", vf);
> + vf /= 2;
> + }
>
> if (entry_count.nonzero_p ())
> set_edge_probability_and_rescale_others
> @@ -11184,6 +11204,7 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call)
> gimple *stmt;
> bool check_profitability = false;
> unsigned int th;
> + bool flat = maybe_flat_loop_profile (loop);
>
> DUMP_VECT_SCOPE ("vec_transform_loop");
>
> @@ -11252,7 +11273,6 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call)
> &step_vector, &niters_vector_mult_vf, th,
> check_profitability, niters_no_overflow,
> &advance);
> -
> if (LOOP_VINFO_SCALAR_LOOP (loop_vinfo)
> && LOOP_VINFO_SCALAR_LOOP_SCALING (loop_vinfo).initialized_p ())
> scale_loop_frequencies (LOOP_VINFO_SCALAR_LOOP (loop_vinfo),
> @@ -11545,7 +11565,7 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call)
> assumed_vf) - 1
> : wi::udiv_floor (loop->nb_iterations_estimate + bias_for_assumed,
> assumed_vf) - 1);
> - scale_profile_for_vect_loop (loop, assumed_vf);
> + scale_profile_for_vect_loop (loop, assumed_vf, flat);
>
> if (dump_enabled_p ())
> {
prev parent reply other threads:[~2023-07-21 17:19 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-18 14:43 Tamar Christina
2023-07-20 5:44 ` Richard Sandiford
2023-07-20 7:20 ` Richard Biener
2023-07-20 9:14 ` Richard Sandiford
2023-07-20 8:26 ` Jan Hubicka
2023-07-20 9:16 ` Richard Sandiford
2023-07-21 17:10 ` Jan Hubicka
2023-07-21 17:19 ` Richard Sandiford [this message]
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=mpt8rb9i3m4.fsf@arm.com \
--to=richard.sandiford@arm.com \
--cc=Kyrylo.Tkachov@arm.com \
--cc=Marcus.Shawcroft@arm.com \
--cc=Richard.Earnshaw@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hubicka@ucw.cz \
--cc=kubanek0ondrej@gmail.com \
--cc=nd@arm.com \
--cc=rguenther@suse.de \
--cc=tamar.christina@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).