All of lore.kernel.org
 help / color / mirror / Atom feed
From: sboyd@codeaurora.org (Stephen Boyd)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH] ARM: Use udiv/sdiv for __aeabi_{u}idiv library functions
Date: Fri, 08 Nov 2013 11:04:19 -0800	[thread overview]
Message-ID: <527D35B3.9020702@codeaurora.org> (raw)
In-Reply-To: <yw1xr4aqx1vi.fsf@unicorn.mansr.com>

On 11/08/13 09:02, M?ns Rullg?rd wrote:
> Stephen Boyd <sboyd@codeaurora.org> writes:
>
>> +int __aeabi_idiv(int numerator, int denominator)
>> +{
>> +	if (static_key_false(&cpu_has_idiv)) {
>> +		int ret;
>> +
>> +		asm volatile (
>> +		".arch_extension idiv\n"
>> +		"sdiv %0, %1, %2"
>> +		: "=&r" (ret)
> There is no need for the & in the output constraint.  Dropping it allows
> using one of the source registers as destination which may sometimes be
> beneficial.

Ok. Thanks. That does seem to improve things.

before:

00000000 <__aeabi_idiv>:
   0:   e320f000        nop     {0}
   4:   eafffffe        b       0 <___aeabi_idiv>
   8:   e713f110        sdiv    r3, r0, r1
   c:   e1a00003        mov     r0, r3
  10:   e12fff1e        bx      lr

00000014 <__aeabi_uidiv>:
  14:   e320f000        nop     {0}
  18:   eafffffe        b       0 <___aeabi_uidiv>
  1c:   e733f110        udiv    r3, r0, r1
  20:   e1a00003        mov     r0, r3
  24:   e12fff1e        bx      lr

after:

00000000 <__aeabi_idiv>:
   0:   e320f000        nop     {0}
   4:   eafffffe        b       0 <___aeabi_idiv>
   8:   e710f110        sdiv    r0, r0, r1
   c:   e12fff1e        bx      lr

00000010 <__aeabi_uidiv>:
  10:   e320f000        nop     {0}
  14:   eafffffe        b       0 <___aeabi_uidiv>
  18:   e730f110        udiv    r0, r0, r1
  1c:   e12fff1e        bx      lr


-- 
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
hosted by The Linux Foundation

WARNING: multiple messages have this Message-ID (diff)
From: Stephen Boyd <sboyd@codeaurora.org>
To: "Måns Rullgård" <mans@mansr.com>
Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] ARM: Use udiv/sdiv for __aeabi_{u}idiv library functions
Date: Fri, 08 Nov 2013 11:04:19 -0800	[thread overview]
Message-ID: <527D35B3.9020702@codeaurora.org> (raw)
In-Reply-To: <yw1xr4aqx1vi.fsf@unicorn.mansr.com>

On 11/08/13 09:02, Måns Rullgård wrote:
> Stephen Boyd <sboyd@codeaurora.org> writes:
>
>> +int __aeabi_idiv(int numerator, int denominator)
>> +{
>> +	if (static_key_false(&cpu_has_idiv)) {
>> +		int ret;
>> +
>> +		asm volatile (
>> +		".arch_extension idiv\n"
>> +		"sdiv %0, %1, %2"
>> +		: "=&r" (ret)
> There is no need for the & in the output constraint.  Dropping it allows
> using one of the source registers as destination which may sometimes be
> beneficial.

Ok. Thanks. That does seem to improve things.

before:

00000000 <__aeabi_idiv>:
   0:   e320f000        nop     {0}
   4:   eafffffe        b       0 <___aeabi_idiv>
   8:   e713f110        sdiv    r3, r0, r1
   c:   e1a00003        mov     r0, r3
  10:   e12fff1e        bx      lr

00000014 <__aeabi_uidiv>:
  14:   e320f000        nop     {0}
  18:   eafffffe        b       0 <___aeabi_uidiv>
  1c:   e733f110        udiv    r3, r0, r1
  20:   e1a00003        mov     r0, r3
  24:   e12fff1e        bx      lr

after:

00000000 <__aeabi_idiv>:
   0:   e320f000        nop     {0}
   4:   eafffffe        b       0 <___aeabi_idiv>
   8:   e710f110        sdiv    r0, r0, r1
   c:   e12fff1e        bx      lr

00000010 <__aeabi_uidiv>:
  10:   e320f000        nop     {0}
  14:   eafffffe        b       0 <___aeabi_uidiv>
  18:   e730f110        udiv    r0, r0, r1
  1c:   e12fff1e        bx      lr


-- 
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
hosted by The Linux Foundation


  reply	other threads:[~2013-11-08 19:04 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-07 19:20 [PATCH] ARM: Use udiv/sdiv for __aeabi_{u}idiv library functions Stephen Boyd
2013-11-07 19:20 ` Stephen Boyd
2013-11-08  1:34 ` Rob Herring
2013-11-08  1:34   ` Rob Herring
2013-11-08 11:50   ` Jean-Christophe PLAGNIOL-VILLARD
2013-11-08 11:50     ` Jean-Christophe PLAGNIOL-VILLARD
2013-11-08 16:54     ` Russell King - ARM Linux
2013-11-08 16:54       ` Russell King - ARM Linux
2013-11-08 18:51       ` Stephen Boyd
2013-11-08 18:51         ` Stephen Boyd
2013-11-08  9:58 ` Jean-Christophe PLAGNIOL-VILLARD
2013-11-08  9:58   ` Jean-Christophe PLAGNIOL-VILLARD
2013-11-08 16:52   ` Russell King - ARM Linux
2013-11-08 16:52     ` Russell King - ARM Linux
2013-11-08 18:53     ` Stephen Boyd
2013-11-08 18:53       ` Stephen Boyd
2013-11-08 16:48 ` Christopher Covington
2013-11-08 16:48   ` Christopher Covington
2013-11-08 18:51   ` Stephen Boyd
2013-11-08 18:51     ` Stephen Boyd
2013-11-08 17:02 ` Måns Rullgård
2013-11-08 17:02   ` Måns Rullgård
2013-11-08 19:04   ` Stephen Boyd [this message]
2013-11-08 19:04     ` Stephen Boyd

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=527D35B3.9020702@codeaurora.org \
    --to=sboyd@codeaurora.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    /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.