From: Jeff Law <jeffreyalaw@gmail.com>
To: Robin Dapp <rdapp.gcc@gmail.com>,
gcc-patches <gcc-patches@gcc.gnu.org>,
palmer <palmer@dabbelt.com>, Kito Cheng <kito.cheng@gmail.com>,
"juzhe.zhong@rivai.ai" <juzhe.zhong@rivai.ai>,
vineetg@rivosinc.com
Subject: Re: [PATCH] RISC-V: Enable pressure-aware scheduling by default.
Date: Fri, 18 Aug 2023 17:08:14 -0600 [thread overview]
Message-ID: <04b8f9ee-31f6-d699-7acc-acfa1b9102e5@gmail.com> (raw)
In-Reply-To: <6c8b8a16-bbf9-b697-0f4c-26a838fb5665@gmail.com>
On 8/18/23 07:57, Robin Dapp wrote:
> Hi,
>
> this patch enables pressure-aware scheduling for riscv. There have been
> various requests for it so I figured I'd just go ahead and send
> the patch.
Thanks. Your timing is good, I was pondering nominating a victim to
pick this up next week ;-)
>
> There is some slight regression in code quality for a number of
> vector tests where we spill more due to different instructions order.
> The ones I looked at were a mix of bad luck and/or brittle tests.
> Comparing the size of the generated assembly or the number of vsetvls
> for SPECint also didn't show any immediate benefit but that's obviously
> not a very fine-grained analysis.
Yea. In fact I wouldn't really expect significant changes other than
those key loops in x264.
>
> As cost and scheduling models mature I expect the situation to improve
> and for now I think it's generally favorable to enable pressure-aware
> scheduling so we can work with it rather than trying to find every
> possible problem in advance. Any other opinions on that?
Agreed. I wouldn't be surprised if largely turns into a set-and-forget.
>
> Regards
> Robin
>
> This patch enables register -fsched-pressure by default and sets
> the algorithm to "model". As with other backends, this helps
> reduce unnecessary spills.
>
> gcc/ChangeLog:
>
> * common/config/riscv/riscv-common.cc: Add -fsched-pressure.
> * config/riscv/riscv.cc (riscv_option_override): Set sched
> pressure algorithm.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/riscv/rvv/base/narrow_constraint-1.c: Add
> -fno-sched-pressure.
> * gcc.target/riscv/rvv/base/narrow_constraint-17.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-18.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-19.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-20.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-21.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-22.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-23.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-24.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-25.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-26.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-27.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-28.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-29.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-30.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-31.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-4.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-5.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-8.c: Ditto.
> * gcc.target/riscv/rvv/base/narrow_constraint-9.c: Ditto.
> * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-10.c: Ditto.
> * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-11.c: Ditto.
> * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-12.c: Ditto.
> * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-3.c: Ditto.
> * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-9.c: Ditto.
OK. Just one nit below.
>
> diff --git a/gcc/common/config/riscv/riscv-common.cc b/gcc/common/config/riscv/riscv-common.cc
> index 4737dcd44a1..59848b21162 100644
> --- a/gcc/common/config/riscv/riscv-common.cc
> +++ b/gcc/common/config/riscv/riscv-common.cc
> @@ -2017,9 +2017,11 @@ static const struct default_options riscv_option_optimization_table[] =
> {
> { OPT_LEVELS_1_PLUS, OPT_fsection_anchors, NULL, 1 },
> { OPT_LEVELS_2_PLUS, OPT_free, NULL, 1 },
> + { OPT_LEVELS_1_PLUS, OPT_fsched_pressure, NULL, 1 },
> #if TARGET_DEFAULT_ASYNC_UNWIND_TABLES == 1
> { OPT_LEVELS_ALL, OPT_fasynchronous_unwind_tables, NULL, 1 },
> { OPT_LEVELS_ALL, OPT_funwind_tables, NULL, 1},
> + /* Enable -fsched-pressure by default when optimizing. */
> #endif
> { OPT_LEVELS_NONE, 0, NULL, 0 }
> };
Shouldn't the comment move up to before the OPT_fsched_pressure line?
> diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
> index 49062bef9fc..96c5362d2fd 100644
> --- a/gcc/config/riscv/riscv.cc
> +++ b/gcc/config/riscv/riscv.cc
> @@ -65,6 +65,7 @@ along with GCC; see the file COPYING3. If not see
> #include "cfgloop.h"
> #include "cfgrtl.h"
> #include "sel-sched.h"
> +#include "sched-int.h"
> #include "fold-const.h"
> #include "gimple-iterator.h"
> #include "gimple-expr.h"
> @@ -7095,6 +7096,10 @@ riscv_option_override (void)
> sorry (
> "Current RISC-V GCC cannot support VLEN greater than 4096bit for 'V' Extension");
>
> + SET_OPTION_IF_UNSET (&global_options, &global_options_set,
> + param_sched_pressure_algorithm,
> + SCHED_PRESSURE_MODEL);
> +
FWIW, I tried both variants of the pressure model. They seemed roughly
on-par with each other across specint.
Jeff
next prev parent reply other threads:[~2023-08-18 23:08 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-18 13:57 Robin Dapp
2023-08-18 23:08 ` Jeff Law [this message]
2023-08-18 23:24 ` Vineet Gupta
2023-08-19 3:23 ` Jeff Law
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=04b8f9ee-31f6-d699-7acc-acfa1b9102e5@gmail.com \
--to=jeffreyalaw@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=juzhe.zhong@rivai.ai \
--cc=kito.cheng@gmail.com \
--cc=palmer@dabbelt.com \
--cc=rdapp.gcc@gmail.com \
--cc=vineetg@rivosinc.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).