From: Alexander Monakov <amonakov@ispras.ru>
To: "Joshi, Tejas Sanjay" <TejasSanjay.Joshi@amd.com>
Cc: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>,
"honza.hubicka@gmail.com" <honza.hubicka@gmail.com>,
"Kumar, Venkataramanan" <Venkataramanan.Kumar@amd.com>
Subject: Re: [PATCH][X86_64] Separate znver4 insn reservations from older znvers
Date: Mon, 14 Nov 2022 21:51:37 +0300 (MSK) [thread overview]
Message-ID: <a0fbeb54-edbd-be90-e99-3c9a6f330e0@ispras.ru> (raw)
In-Reply-To: <DM6PR12MB4795D38A7C29749BBDEABB98E3059@DM6PR12MB4795.namprd12.prod.outlook.com>
On Mon, 14 Nov 2022, Joshi, Tejas Sanjay wrote:
> [Public]
>
> Hi,
Hi. I'm still waiting for feedback on fixes for existing models:
https://inbox.sourceware.org/gcc-patches/5ae6fc21-edc6-133-aee2-a41e16eb5b7@ispras.ru/T/#t
did you have a chance to look at those?
> PFA the patch which adds znver4 instruction reservations separately from older
> znver versions:
> * This also models separate div, fdiv and ssediv units accordingly.
Why are you modeling 'fdiv' and 'ssediv' separately? When preparing the above
patches, I checked that x87 and SSE divisions use the same hardware unit, and
I don't see a strong reason to artificially clone it in the model.
(integer divider is a separate unit from the floating-point divider)
> * Does not blow-up the insn-automata.cc size (it grew from 201502 to 206141 for me.)
> * The patch successfully builds, bootstraps, and passes make check.
> * I have also run spec, showing no regressions for 1-copy 3-iteration runs. However, I observe 1.5% gain for 507.cactuBSSN_r.
I have a question on AVX512 modeling in your patch:
> +;; AVX instructions
> +(define_insn_reservation "znver4_sse_log" 1
> + (and (eq_attr "cpu" "znver4")
> + (and (eq_attr "type" "sselog,sselog1")
> + (and (eq_attr "mode" "V4SF,V8SF,V2DF,V4DF")
> + (eq_attr "memory" "none"))))
> + "znver4-direct,znver4-fpu")
> +
> +(define_insn_reservation "znver4_sse_log_evex" 1
> + (and (eq_attr "cpu" "znver4")
> + (and (eq_attr "type" "sselog,sselog1")
> + (and (eq_attr "mode" "V16SF,V8DF")
> + (eq_attr "memory" "none"))))
> + "znver4-direct,znver4-fpu0+znver4-fpu1|znver4-fpu2+znver4-fpu3")
> +
This is an AVX512 instruction, and you're modeling that it occupies two ports at
once and thus has half throughput, but later in the AVX512 section:
> +;; AVX512 instructions
> +(define_insn_reservation "znver4_sse_mul_evex" 3
> + (and (eq_attr "cpu" "znver4")
> + (and (eq_attr "type" "ssemul")
> + (and (eq_attr "mode" "V16SF,V8DF")
> + (eq_attr "memory" "none"))))
> + "znver4-double,znver4-fpu0|znver4-fpu3")
none of the instructions are modeled this way. If that's on purpose, can you
add a comment? It's surprising, since generally AVX512 has half throughput
compared to AVX256 on Zen 4, but the model doesn't seem to reflect that.
Alexander
next prev parent reply other threads:[~2022-11-14 18:51 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-14 16:18 Joshi, Tejas Sanjay
2022-11-14 18:51 ` Alexander Monakov [this message]
2022-11-15 12:08 ` Joshi, Tejas Sanjay
2022-11-15 12:51 ` Alexander Monakov
2022-11-21 11:40 ` Joshi, Tejas Sanjay
2022-11-21 15:30 ` Alexander Monakov
2022-12-01 11:28 ` Joshi, Tejas Sanjay
2022-12-01 19:01 ` Alexander Monakov
2022-12-12 21:41 ` Jan Hubička
2022-12-22 17:34 ` Joshi, Tejas Sanjay
2023-01-03 14:36 ` Jan Hubicka
2023-01-03 14:52 ` Alexander Monakov
2023-01-03 18:28 ` Jan Hubicka
2023-01-05 5:52 ` Joshi, Tejas Sanjay
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=a0fbeb54-edbd-be90-e99-3c9a6f330e0@ispras.ru \
--to=amonakov@ispras.ru \
--cc=TejasSanjay.Joshi@amd.com \
--cc=Venkataramanan.Kumar@amd.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=honza.hubicka@gmail.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).