All of lore.kernel.org
 help / color / mirror / Atom feed
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
To: Yury <yury.norov@gmail.com>
Cc: Alexey Klimov <klimov.linux@gmail.com>,
	Cassidy Burden <cburden@codeaurora.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-arm-msm@vger.kernel.org,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	linux-arm-kernel@lists.infradead.org,
	"David S. Miller" <davem@davemloft.net>,
	Daniel Borkmann <dborkman@redhat.com>,
	Hannes Frederic Sowa <hannes@stressinduktion.org>,
	Lai Jiangshan <laijs@cn.fujitsu.com>,
	Mark Salter <msalter@redhat.com>,
	AKASHI Takahiro <takahiro.akashi@linaro.org>,
	Thomas Graf <tgraf@suug.ch>,
	Valentin Rothberg <valentinrothberg@gmail.com>,
	Chris Wilson <chris@chris-wilson.co.uk>,
	linux@horizon.com
Subject: Re: [PATCH] lib: Make _find_next_bit helper function inline
Date: Sun, 30 Aug 2015 23:47:20 +0200	[thread overview]
Message-ID: <87si701maf.fsf@rasmusvillemoes.dk> (raw)
In-Reply-To: <55E1CC83.1010007@gmail.com> (Yury's message of "Sat, 29 Aug 2015 18:15:15 +0300")

I've lost track of what's up and down in this, but now that I look at
this again let me throw in my two observations of stupid gcc behaviour:
For the current code, both debian's gcc (4.7) and 5.1 partially inlines
_find_next_bit, namely the "if (!nbits || start >= nbits)" test. I know it
does it to avoid a function call, but in this case the early return
condition is unlikely, so there's not much to gain. Moreover, it fails
to optimize the test to simply "if (start >= nbits)" - everything being
unsigned, these are obviously equivalent.

Rasmus

WARNING: multiple messages have this Message-ID (diff)
From: linux@rasmusvillemoes.dk (Rasmus Villemoes)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH] lib: Make _find_next_bit helper function inline
Date: Sun, 30 Aug 2015 23:47:20 +0200	[thread overview]
Message-ID: <87si701maf.fsf@rasmusvillemoes.dk> (raw)
In-Reply-To: <55E1CC83.1010007@gmail.com> (Yury's message of "Sat, 29 Aug 2015 18:15:15 +0300")

I've lost track of what's up and down in this, but now that I look at
this again let me throw in my two observations of stupid gcc behaviour:
For the current code, both debian's gcc (4.7) and 5.1 partially inlines
_find_next_bit, namely the "if (!nbits || start >= nbits)" test. I know it
does it to avoid a function call, but in this case the early return
condition is unlikely, so there's not much to gain. Moreover, it fails
to optimize the test to simply "if (start >= nbits)" - everything being
unsigned, these are obviously equivalent.

Rasmus

  reply	other threads:[~2015-08-30 21:47 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-28 19:09 [PATCH] lib: Make _find_next_bit helper function inline Cassidy Burden
2015-07-28 19:09 ` Cassidy Burden
2015-07-28 21:23 ` Yury
2015-07-28 21:23   ` Yury
2015-07-28 21:38   ` Yury
2015-07-28 21:38     ` Yury
2015-07-28 21:45   ` Andrew Morton
2015-07-28 21:45     ` Andrew Morton
2015-07-29 13:30     ` Alexey Klimov
2015-07-29 13:30       ` Alexey Klimov
2015-07-29 20:40       ` Cassidy Burden
2015-07-29 20:40         ` Cassidy Burden
2015-08-23 22:53         ` Alexey Klimov
2015-08-23 22:53           ` Alexey Klimov
2015-08-29 15:15           ` Yury
2015-08-29 15:15             ` Yury
2015-08-30 21:47             ` Rasmus Villemoes [this message]
2015-08-30 21:47               ` Rasmus Villemoes

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=87si701maf.fsf@rasmusvillemoes.dk \
    --to=linux@rasmusvillemoes.dk \
    --cc=akpm@linux-foundation.org \
    --cc=cburden@codeaurora.org \
    --cc=chris@chris-wilson.co.uk \
    --cc=davem@davemloft.net \
    --cc=dborkman@redhat.com \
    --cc=hannes@stressinduktion.org \
    --cc=klimov.linux@gmail.com \
    --cc=laijs@cn.fujitsu.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@horizon.com \
    --cc=msalter@redhat.com \
    --cc=takahiro.akashi@linaro.org \
    --cc=tgraf@suug.ch \
    --cc=valentinrothberg@gmail.com \
    --cc=yury.norov@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.