From: Lulu Cheng <chenglulu@loongson.cn>
To: Xi Ruoyao <xry111@xry111.site>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: Chenghua Xu <xuchenghua@loongson.cn>,
Youling Tang <tangyouling@loongson.cn>,
Huacai Chen <chenhuacai@kernel.org>,
Jinyang He <hejinyang@loongson.cn>, Wang Xuerui <i@xen0n.name>
Subject: Re: 回复:[PATCH v5] LoongArch: add movable attribute
Date: Fri, 5 Aug 2022 10:38:23 +0800 [thread overview]
Message-ID: <fd65af70-ee83-c15a-5be6-ca63cee509b7@loongson.cn> (raw)
In-Reply-To: <60bac545a09ee202d41421a596ac64a4cb83d89c.camel@xry111.site>
在 2022/8/5 上午9:28, Xi Ruoyao 写道:
> On Fri, 2022-08-05 at 09:05 +0800, Lulu Cheng wrote:
>> I'm working on the implementation of specifing attributes of variables for other architectures.
>> If the address is obtained through the GOT table and 4 instructions, there is not much difference in performance.
> In this case I still prefer a GOT table entry because for 4-instruction
> absolute addressing sequence we'll need to implement 4 new relocation
> types in the kernel module loader.
If it is accessed through the GOT table, dynamic relocation is required
when the module is loaded. And accessing the got table may have a cache
miss.
>> Is it more reasonable for us to refer to the implementation of the model attribute under the IA64 architecture?
> Maybe we can use "model(got)", "model(abs)", "model(pcrel)" etc.
We have a set of instruction implementations that can get a relative pc
64-bit offset:
"pcalau12i %1,%%pc_hi20(%3);"
"addi.d %2,$r0,%%pc_lo12(%3);"
"lu32i.d %2,%%pc64_lo20(%3);"
"lu52i.d %2,%2,%%pc64_hi12(%3);"
"add.d %1,%1,%2;",
This set of instructions can be selected according to the size of the
offset:
"pcalau12i %1,%%pc_hi20(%3);"
"addi.d %2,$r0,%%pc_lo12(%3);"
"lu32i.d %2,%%pc64_lo20(%3);"
"add.d %1,%1,%2;",
for offset within signed 52 bits.
or
"pcalau12i %1,%%pc_hi20(%3);"
"addi.d %2,$r0,%%pc_lo12(%3);"
"lu32i.d %2,%%pc64_lo20(%3);"
"lu52i.d %2,%2,%%pc64_hi12(%3);"
"add.d %1,%1,%2;"
for offset within signed 64 bits.
So my idea is "model(normal)","model (large)" etc.
>> I will compare the performance of the two soon. Do you know the approximate release date of GCC 12.2?
>> I also want to fix this before 12.2 is released.
> GCC 12.2 rc1 will be frozen on Aug 12th.
>
next prev parent reply other threads:[~2022-08-05 2:38 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-29 14:22 [PATCH] LoongArch: add addr_global attribute Xi Ruoyao
2022-07-29 15:31 ` [PATCH v2] " Xi Ruoyao
2022-07-29 17:17 ` [PATCH v3] " Xi Ruoyao
2022-07-30 3:13 ` Lulu Cheng
2022-07-30 6:03 ` Huacai Chen
2022-07-31 9:05 ` Chenghua Xu
2022-08-01 10:04 ` [PATCH v4] LoongArch: add movable attribute Xi Ruoyao
2022-08-01 10:07 ` [PATCH v5] " Xi Ruoyao
2022-08-03 1:36 ` Xi Ruoyao
2022-08-03 2:59 ` WANG Xuerui
2022-08-03 3:15 ` Xi Ruoyao
[not found] ` <-2muj1c-68saz6jhkcyw3jo1xp-1mgcvnkbqi2wjp6tue-qsso54-emxgu3-k85590-kpgox7-w67u6h3cai1l-5bi887dsgzsu-g4d7i7-wl316qxrucx4kv4on7-mnna36-iremg8-nwc5ot-9041t2-hu8nsl.1659495047941@email.android.com>
2022-08-03 3:10 ` 回复:[PATCH " Xi Ruoyao
2022-08-04 7:47 ` Xi Ruoyao
2022-08-05 1:05 ` Lulu Cheng
2022-08-05 1:28 ` Xi Ruoyao
2022-08-05 2:38 ` Lulu Cheng [this message]
2022-08-05 2:51 ` Xi Ruoyao
2022-08-05 3:34 ` Xi Ruoyao
2022-08-05 3:45 ` Xi Ruoyao
2022-08-05 4:01 ` Lulu Cheng
2022-08-05 6:03 ` Xi Ruoyao
2022-08-05 7:19 ` Lulu Cheng
2022-08-05 7:41 ` WANG Xuerui
2022-08-05 7:58 ` Lulu Cheng
2022-08-05 9:53 ` Xi Ruoyao
2022-08-08 4:53 ` Lulu Cheng
2022-08-09 11:30 ` Xi Ruoyao
2022-08-09 13:03 ` Lulu Cheng
2022-08-09 14:04 ` 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=fd65af70-ee83-c15a-5be6-ca63cee509b7@loongson.cn \
--to=chenglulu@loongson.cn \
--cc=chenhuacai@kernel.org \
--cc=gcc-patches@gcc.gnu.org \
--cc=hejinyang@loongson.cn \
--cc=i@xen0n.name \
--cc=tangyouling@loongson.cn \
--cc=xry111@xry111.site \
--cc=xuchenghua@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).