From: Andrew Stubbs <ams@codesourcery.com>
To: Tobias Burnus <burnus@net-b.de>, gcc-patches <gcc-patches@gcc.gnu.org>
Subject: Re: [Patch] GCN: Add pre-initial support for gfx1100
Date: Mon, 8 Jan 2024 10:06:40 +0000 [thread overview]
Message-ID: <84ca1c2a-719c-481a-9190-1ef591eeaa33@codesourcery.com> (raw)
In-Reply-To: <b53b0b78-c963-4d4f-83c5-2aa6071f5163@net-b.de>
On 07/01/2024 19:20, Tobias Burnus wrote:
> ROCm meanwhile supports also some consumer cards; besides the semi-new
> gfx1030, support for gfx1100 was added more recently (in ROCm 5.7.1 for
> "Ubuntu 22.04 only" and without parenthesis since ROCm 6.0.0).
>
> GCC has already very limited support for gfx1030 - whose multlib support
> is - on purpose - not yet enabled by default and is WIP.
>
> The attached patch now adds gfx1100 on top of it, assuming that it
> mostly behaves the same as gfx1030. This is really WIP as there are
> known build (assembly) issues (see below) and not only "just" runtime
> issues.
>
> gfx1100 differs at least in the following aspects from the previously
> supported cards:
>
> * gfx1100 has an 'architected flat scratch' which is different from
> 'absolute flat scratch' which all others (but fiji: 'offset flat
> scratch') have. Hence, '.amdhsa_reserve_flat_scratch 0'
> has to be excluded to avoid assembly errors.
>
> * gfx1100 also does not support 'v_mov_b32_sdwa', failing to assembly
> libc/argz/libc_a-argz_stringify.o with:
> "sdwa variant of this instruction is not supported"
> → This has not been address in the patch, hence, specifying gfx1100 in
> --with-multilib-list= will fail to build when an in-tree newlib is build.
>
> * * *
>
> The attached patch fixes in addition one issue in libgomp (string-length
> len constant is too short for gfx1030 (and gfx1100) = 7 characters) and
> it includes the fix that __gfx1030__ is not defined, which I have
> submitted separately (yesterday).
>
> With the caveat that gfx1100 is even less usable than gfx1030 and it
> won't build newlib, is it nonetheless
>
> OK for mainline ?
>
> (As gfx1100 is not enabled by default in multilib, a regular build will
> will not fail and I think the *.md issue can be addressed separately.)
This looks fine to me. I know there will be things that need fixing for
both experimental architectures.
Andrew
P.S. Apologies, but I think my commits today conflict a little; you
should be able to drop the hunks that patch deleted code.
next prev parent reply other threads:[~2024-01-08 10:06 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-07 19:20 Tobias Burnus
2024-01-08 10:06 ` Andrew Stubbs [this message]
2024-01-08 14:30 ` Tobias Burnus
2024-01-08 19:48 ` Thomas Schwinge
2024-02-19 17:05 ` GCN: Restore lost '__gfx90a__' target CPU definition (was: [Patch] GCN: Add pre-initial support for gfx1100) Thomas Schwinge
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=84ca1c2a-719c-481a-9190-1ef591eeaa33@codesourcery.com \
--to=ams@codesourcery.com \
--cc=burnus@net-b.de \
--cc=gcc-patches@gcc.gnu.org \
/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).