From: "H. Peter Anvin" <hpa@zytor.com>
To: Peter Zijlstra <peterz@infradead.org>, Brian Gerst <brgerst@gmail.com>
Cc: Borislav Petkov <bp@suse.de>, x86-ml <x86@kernel.org>,
Denys Vlasenko <dvlasenk@redhat.com>,
LKML <linux-kernel@vger.kernel.org>,
Dmitry Vyukov <dvyukov@google.com>,
Andi Kleen <andi@firstfloor.org>,
zengzhaoxiu@163.com, Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>,
Zhaoxiu Zeng <zhaoxiu.zeng@gmail.com>,
Andy Lutomirski <luto@amacapital.net>
Subject: Re: [PATCH -v2] x86/hweight: Get rid of the special calling convention
Date: Wed, 11 May 2016 21:54:50 -0700 [thread overview]
Message-ID: <B403FEFA-78F7-4D8F-A46C-E5174527D79E@zytor.com> (raw)
In-Reply-To: <20160511112409.GE3190@twins.programming.kicks-ass.net>
On May 11, 2016 4:24:09 AM PDT, Peter Zijlstra <peterz@infradead.org> wrote:
>On Wed, May 11, 2016 at 07:15:19AM -0400, Brian Gerst wrote:
>
>> I think he meant the out of line version would be asm, so you could
>> control what registers were clobbered.
>
>Yeah, it might save a few cycles on the call, but given that most
>machines should have popcnt these days is it worth the hassle/cost of
>duplicating the lib/hweight.c magic in asm (and remember, twice, once
>for 32bit and once for 64bit) ?
I was thinking it isn't really very complex code even in assembly as it is super-regular; you can even crib the gcc-generated code if you wish.
--
Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.
next prev parent reply other threads:[~2016-05-12 4:56 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-05 2:06 [PATCH V2 01/30] bitops: add parity functions Zeng Zhaoxiu
2016-04-05 4:23 ` [PATCH V2 02/30] Include generic parity.h in some architectures' bitops.h Zeng Zhaoxiu
2016-04-06 8:41 ` [PATCH v2 " zengzhaoxiu
2016-04-05 19:04 ` [PATCH V2 01/30] bitops: add parity functions Sam Ravnborg
2016-04-06 5:33 ` Zeng Zhaoxiu
2016-04-06 8:24 ` Sam Ravnborg
2016-04-06 8:22 ` [PATCH v2 " zengzhaoxiu
2016-04-06 8:46 ` [PATCH v2 03/30] Add alpha-specific " zengzhaoxiu
2016-04-06 8:53 ` [PATCH v2 04/30] Add blackfin-specific " zengzhaoxiu
2016-04-06 8:57 ` [PATCH v2 05/30] Add ia64-specific " zengzhaoxiu
2016-04-06 8:59 ` [PATCH v2 06/30] Add mips-specific " zengzhaoxiu
2016-04-06 10:23 ` zengzhaoxiu
2016-04-06 9:03 ` [PATCH v2 07/30] Add powerpc-specific " zengzhaoxiu
2016-04-06 9:07 ` [PATCH v2 08/30] Add sparc-specific " zengzhaoxiu
2016-04-06 18:44 ` Sam Ravnborg
2016-04-07 3:56 ` Zeng Zhaoxiu
2016-04-06 9:08 ` [PATCH v2 09/30] Add tile-specific " zengzhaoxiu
2016-04-06 13:27 ` Chris Metcalf
2016-04-07 3:55 ` Zeng Zhaoxiu
2016-04-06 9:14 ` [PATCH v2 10/30] Add x86-specific " zengzhaoxiu
2016-04-06 10:13 ` Borislav Petkov
2016-04-06 10:37 ` One Thousand Gnomes
2016-04-06 10:53 ` Borislav Petkov
2016-04-07 3:55 ` Zeng Zhaoxiu
2016-04-07 9:39 ` Borislav Petkov
2016-04-11 2:43 ` Zeng Zhaoxiu
2016-04-15 2:11 ` Borislav Petkov
2016-04-07 3:55 ` Zeng Zhaoxiu
2016-04-07 9:41 ` Borislav Petkov
2016-04-06 19:45 ` Andi Kleen
2016-04-07 3:56 ` Zeng Zhaoxiu
2016-04-07 6:31 ` Dmitry Vyukov
2016-04-07 9:43 ` Borislav Petkov
2016-05-04 18:46 ` [RFC PATCH] x86/hweight: Get rid of the special calling convention Borislav Petkov
2016-05-04 19:31 ` Brian Gerst
2016-05-04 19:33 ` H. Peter Anvin
2016-05-04 19:41 ` Borislav Petkov
2016-05-04 19:49 ` H. Peter Anvin
2016-05-04 20:22 ` Borislav Petkov
2016-05-04 20:51 ` H. Peter Anvin
2016-05-04 21:09 ` Andi Kleen
2016-05-05 13:02 ` Denys Vlasenko
2016-05-05 14:04 ` Borislav Petkov
2016-05-10 16:53 ` [PATCH -v2] " Borislav Petkov
2016-05-10 17:23 ` Peter Zijlstra
2016-05-10 19:02 ` Borislav Petkov
2016-05-10 19:03 ` H. Peter Anvin
2016-05-10 19:10 ` Borislav Petkov
2016-05-10 22:30 ` H. Peter Anvin
2016-05-11 4:11 ` Borislav Petkov
2016-05-11 11:15 ` Brian Gerst
2016-05-11 11:24 ` Peter Zijlstra
2016-05-11 12:47 ` Borislav Petkov
2016-05-12 4:54 ` H. Peter Anvin [this message]
2016-05-12 11:57 ` Borislav Petkov
2016-05-12 12:14 ` Peter Zijlstra
2016-05-12 13:09 ` Borislav Petkov
2016-05-18 10:38 ` Borislav Petkov
2016-04-07 14:10 ` [PATCH v2 10/30] Add x86-specific parity functions One Thousand Gnomes
2016-04-06 9:27 ` [PATCH v2 11/30] sunrpc: use parity8 zengzhaoxiu
2016-04-06 9:30 ` [PATCH v2 12/30] mips: use parity functions in cerr-sb1.c zengzhaoxiu
2016-04-06 9:36 ` [PATCH v2 13/30] bch: use parity32 zengzhaoxiu
2016-04-06 9:39 ` [PATCH v2 14/30] media: use parity8 in vivid-vbi-gen.c zengzhaoxiu
2016-04-06 9:41 ` [PATCH v2 15/30] media: use parity functions in saa7115 zengzhaoxiu
2016-04-06 9:43 ` [PATCH v2 16/30] input: use parity32 in grip_mp zengzhaoxiu
2016-04-06 9:44 ` [PATCH v2 17/30] input: use parity64 in sidewinder zengzhaoxiu
2016-04-06 9:45 ` [PATCH v2 18/30] input: use parity16 in ams_delta_serio zengzhaoxiu
2016-04-06 9:47 ` [PATCH v2 19/30] scsi: use parity32 in isci's phy zengzhaoxiu
2016-04-06 9:52 ` [PATCH v2 20/30] mtd: use parity16 in ssfdc zengzhaoxiu
2016-04-06 9:53 ` [PATCH v2 21/30] mtd: use parity functions in inftlcore zengzhaoxiu
2016-04-06 9:58 ` [PATCH v2 22/30] crypto: use parity functions in qat_hal zengzhaoxiu
2016-04-06 10:05 ` [PATCH v2 23/30] mtd: use parity16 in sm_ftl zengzhaoxiu
2016-04-06 10:11 ` [PATCH v2 24/30] ethernet: use parity8 in sun/niu.c zengzhaoxiu
2016-04-06 10:14 ` [PATCH v2 25/30] input: use parity8 in pcips2 zengzhaoxiu
2016-04-06 10:15 ` [PATCH v2 26/30] input: use parity8 in sa1111ps2 zengzhaoxiu
2016-04-06 10:16 ` [PATCH v2 27/30] iio: use parity32 in adxrs450 zengzhaoxiu
2016-04-10 14:37 ` Jonathan Cameron
2016-04-10 14:41 ` Lars-Peter Clausen
2016-04-10 15:13 ` Jonathan Cameron
2016-04-10 15:14 ` Jonathan Cameron
2016-04-06 10:18 ` [PATCH v2 28/30] serial: use parity32 in max3100 zengzhaoxiu
2016-04-06 10:25 ` Greg KH
2016-04-06 10:20 ` [PATCH v2 29/30] input: use parity8 in elantech zengzhaoxiu
2016-04-06 10:21 ` [PATCH v2 30/30] ethernet: use parity8 in broadcom/tg3.c zengzhaoxiu
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=B403FEFA-78F7-4D8F-A46C-E5174527D79E@zytor.com \
--to=hpa@zytor.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=bp@suse.de \
--cc=brgerst@gmail.com \
--cc=dvlasenk@redhat.com \
--cc=dvyukov@google.com \
--cc=keescook@chromium.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=zengzhaoxiu@163.com \
--cc=zhaoxiu.zeng@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 NNTP newsgroup(s).