From: Jinyang He <hejinyang@loongson.cn>
To: Xi Ruoyao <xry111@xry111.site>,
Chenghua Xu <xuchenghua@loongson.cn>,
Lulu Cheng <chenglulu@loongson.cn>
Cc: Weining Lu <luweining@loongson.cn>, Xing Li <lixing@loongson.cn>,
yala <zhaojunchao@loongson.cn>, Peng Fan <fanpeng@loongson.cn>,
gcc-patches@gcc.gnu.org, Huang Pei <huangpei@loongson.cn>
Subject: Re: [PATCH] LoongArch: Fix atomic_exchange make comparison and may jump out
Date: Thu, 17 Nov 2022 09:39:36 +0800 [thread overview]
Message-ID: <f2e58619-359e-7c57-7ba7-4aec2a1a2c1c@loongson.cn> (raw)
In-Reply-To: <0390618e9d9e74eb2ea22ae8a934cbc37cd483a7.camel@xry111.site>
On 2022/11/16 下午7:46, Xi Ruoyao wrote:
> On Wed, 2022-11-16 at 10:11 +0800, Jinyang He wrote:
>
>>>> + return "%G6\\n\\t"
>>>> + "1:\\n\\t"
>>>> + "ll.<amo>\\t%0,%1\\n\\t"
>>>> + "and\\t%7,%0,%z3\\n\\t"
>>>> + "or%i5\\t%7,%7,%5\\n\\t"
>>>> + "sc.<amo>\\t%7,%1\\n\\t"
>>>> + "beqz\\t%7,1b\\n\\t";
>>> Do we need a "dbar 0x700" after beqz?
>>>
>>> /* snip */
>> That's worth discussing. Actually I don't see any dbar hint definition
>> like 0x700 in the manual right now.
>> Besides, I think what should be provided here is a relaxed version. And
>> whether the barrier exsit or not is depend on the specific memory_order.
> It's not related to memory order, but for a hardware issue workaround.
> Jiaxun told me (via LKML):
>
> I had checked with Loongson guys and they confirmed that the
> workaround still needs to be applied to latest 3A4000 processors,
> including 3A4000 for MIPS and 3A5000 for LoongArch.
>
> Though, the reason behind the workaround varies with the evaluation
> of their uArch, for GS464V based core, barrier is required as the
> uArch design allows regular load to be reordered after an atomic
> linked load, and that would break assumption of compiler atomic
> constraints.
That certainly seems to be needed, but before or after. It's beyond my
recognition and cc huangpei@loongson.cn for help.
>
> Without these dbar instructions I'd got random test failures in GCC
> libgomp test suite.
>
> We use a non-zero hint here because it is treated exactly same as zero
> in 3A5000, and the future LoongArch processors can fix the issue and
> ignore the dbar 0x700 instruction.
Thanks, it's a nice workaround.
next prev parent reply other threads:[~2022-11-17 1:39 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-15 13:03 Jinyang He
2022-11-15 14:21 ` Xi Ruoyao
2022-11-16 2:11 ` Jinyang He
2022-11-16 11:46 ` Xi Ruoyao
2022-11-17 1:39 ` Jinyang He [this message]
2022-11-17 2:55 ` Jinyang He
2022-11-17 3:38 ` Xi Ruoyao
2022-11-17 3:46 ` Jinyang He
2022-11-17 5:56 ` Xi Ruoyao
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=f2e58619-359e-7c57-7ba7-4aec2a1a2c1c@loongson.cn \
--to=hejinyang@loongson.cn \
--cc=chenglulu@loongson.cn \
--cc=fanpeng@loongson.cn \
--cc=gcc-patches@gcc.gnu.org \
--cc=huangpei@loongson.cn \
--cc=lixing@loongson.cn \
--cc=luweining@loongson.cn \
--cc=xry111@xry111.site \
--cc=xuchenghua@loongson.cn \
--cc=zhaojunchao@loongson.cn \
/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).