From: "Martin Liška" <mliska@suse.cz>
To: Mayshao-oc <Mayshao-oc@zhaoxin.com>, Uros Bizjak <ubizjak@gmail.com>
Cc: "Silvia Zhao(BJ-RD)" <SilviaZhao@zhaoxin.com>,
TimHu-oc <TimHu-oc@zhaoxin.com>,
"Cobe Chen(BJ-RD)" <CobeChen@zhaoxin.com>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>,
"Hawk Wang(BJ-RD)" <HawkWang@zhaoxin.com>,
"Louis Qi(BJ-RD)" <LouisQi@zhaoxin.com>,
Jan Hubicka <hubicka@ucw.cz>
Subject: Re: [PATCH] [x86_64] Zhaoxin lujiazui enablement
Date: Tue, 25 Oct 2022 06:38:14 +0200 [thread overview]
Message-ID: <9263704e-b2f1-f21d-f888-a884547a0cf5@suse.cz> (raw)
In-Reply-To: <d429723ce0c848e4870b56521c67c66a@zhaoxin.com>
[-- Attachment #1: Type: text/plain, Size: 801 bytes --]
Hello.
I noticed this patch set which is kind of related to https://gcc.gnu.org/bugzilla/show_bug.cgi?id=107364.
And I have a couple of questions:
1) I noticed you drop AVX and F16C features for the newly added "lujiazui". Why do you need it?
I would expect these features would be properly detected by cpuid?
2) If you really need it, can you please test for me the attached patch? It should come up
with a new function.
3) Have question about:
else if (vendor == signature_CENTAUR_ebx && family < 0x07)
cpu_model->__cpu_vendor = VENDOR_CENTAUR;
else if (vendor == signature_SHANGHAI_ebx
|| vendor == signature_CENTAUR_ebx)
Are there any signature_CENTAUR_ebx models with family == 0x7 ?
Similarly, are there any signature_SHANGHAI_ebx modes with family < 0x7 ?
Thanks,
Martin
[-- Attachment #2: 0001-i386-add-reset_cpu_feature.patch --]
[-- Type: text/x-patch, Size: 2440 bytes --]
From fa0bd99da8fd92b15a2cee55737a5962657da212 Mon Sep 17 00:00:00 2001
From: Martin Liska <mliska@suse.cz>
Date: Tue, 25 Oct 2022 06:28:44 +0200
Subject: [PATCH] i386: add reset_cpu_feature
gcc/ChangeLog:
* common/config/i386/cpuinfo.h (has_cpu_feature): Add comment.
(reset_cpu_feature): New.
(get_zhaoxin_cpu): Use reset_cpu_feature.
---
gcc/common/config/i386/cpuinfo.h | 38 +++++++++++++++++++++++++++-----
1 file changed, 33 insertions(+), 5 deletions(-)
diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h
index d45451c5704..19ea7132fd5 100644
--- a/gcc/common/config/i386/cpuinfo.h
+++ b/gcc/common/config/i386/cpuinfo.h
@@ -76,6 +76,8 @@ has_cpu_feature (struct __processor_model *cpu_model,
}
}
+/* Save FEATURE to either CPU_MODEL or CPU_FEATURES2. */
+
static inline void
set_cpu_feature (struct __processor_model *cpu_model,
unsigned int *cpu_features2,
@@ -100,6 +102,32 @@ set_cpu_feature (struct __processor_model *cpu_model,
}
}
+/* Drop FEATURE from either CPU_MODEL or CPU_FEATURES2. */
+
+static inline void
+reset_cpu_feature (struct __processor_model *cpu_model,
+ unsigned int *cpu_features2,
+ enum processor_features feature)
+{
+ unsigned index, offset;
+ unsigned f = feature;
+
+ if (f < 32)
+ {
+ /* The first 32 features. */
+ cpu_model->__cpu_features[0] &= ~(1U << f);
+ }
+ else
+ {
+ /* The rest of features. cpu_features2[i] contains features from
+ (32 + i * 32) to (31 + 32 + i * 32), inclusively. */
+ f -= 32;
+ index = f / 32;
+ offset = f % 32;
+ cpu_features2[index] &= ~(1U << offset);
+ }
+}
+
/* Get the specific type of AMD CPU and return AMD CPU name. Return
NULL for unknown AMD CPU. */
@@ -565,11 +593,11 @@ get_zhaoxin_cpu (struct __processor_model *cpu_model,
cpu_model->__cpu_type = ZHAOXIN_FAM7H;
if (model == 0x3b)
{
- cpu = "lujiazui";
- CHECK___builtin_cpu_is ("lujiazui");
- cpu_model->__cpu_features[0] &= ~(1U <<(FEATURE_AVX & 31));
- cpu_features2[0] &= ~(1U <<((FEATURE_F16C - 32) & 31));
- cpu_model->__cpu_subtype = ZHAOXIN_FAM7H_LUJIAZUI;
+ cpu = "lujiazui";
+ CHECK___builtin_cpu_is ("lujiazui");
+ reset_cpu_feature (cpu_model, cpu_features2, FEATURE_AVX);
+ reset_cpu_feature (cpu_model, cpu_features2, FEATURE_F16C);
+ cpu_model->__cpu_subtype = ZHAOXIN_FAM7H_LUJIAZUI;
}
break;
default:
--
2.38.0
next prev parent reply other threads:[~2022-10-25 4:38 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-25 2:08 MayShao
2022-03-27 9:15 ` Uros Bizjak
2022-03-28 7:25 ` Mayshao-oc
2022-10-25 4:38 ` Martin Liška [this message]
2022-10-26 9:06 ` Mayshao-oc
2022-10-26 10:46 ` Martin Liška
2022-10-27 9:09 ` Mayshao-oc
2022-10-27 9:11 ` Martin Liška
2022-05-17 3:15 [PATCH] [x86_64]: " mayshao
2022-05-17 6:23 ` Richard Biener
2022-05-17 9:33 ` Mayshao-oc
2022-05-22 16:41 ` Uros Bizjak
2022-05-23 10:44 ` Mayshao-oc
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=9263704e-b2f1-f21d-f888-a884547a0cf5@suse.cz \
--to=mliska@suse.cz \
--cc=CobeChen@zhaoxin.com \
--cc=HawkWang@zhaoxin.com \
--cc=LouisQi@zhaoxin.com \
--cc=Mayshao-oc@zhaoxin.com \
--cc=SilviaZhao@zhaoxin.com \
--cc=TimHu-oc@zhaoxin.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hubicka@ucw.cz \
--cc=ubizjak@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).