Rocksolid Light - comp.lang.asm.x86 - Re: Optimize speed 8086 instruction "rep movsb" and "rep stosb"

Optimize speed 8086 instruction "rep movsb" and "rep stosb"

<d60a7938-4b3c-4b10-91b2-1dc33fe6abf8n@googlegroups.com>

https://news.novabbs.org/devel/article-flat.php?id=797&group=comp.lang.asm.x86#797

copy link Newsgroups: comp.lang.asm.x86

Path: i2pn2.org!i2pn.org!eternal-september.org!reader01.eternal-september.org!.POSTED!not-for-mail
From: phutranhoang@nospicedham.gmail.com (Phu Tran Hoang)
Newsgroups: comp.lang.asm.x86
Subject: Optimize speed 8086 instruction "rep movsb" and "rep stosb"
Date: Thu, 21 Jul 2022 22:19:55 -0700 (PDT)
Organization: A noiseless patient Spider
Lines: 25
Approved: fbkotler@myfairpoint.net - comp.lang.asm.x86 moderation team.
Message-ID: <d60a7938-4b3c-4b10-91b2-1dc33fe6abf8n@googlegroups.com>
MIME-Version: 1.0
Content-Type: text/plain; charset="UTF-8"
Injection-Date: Fri, 22 Jul 2022 05:19:55 +0000
Injection-Info: reader01.eternal-september.org; posting-host="72eccefa569787c9acac825e7950fa24";
logging-data="3108788"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1/489Y5ocb14QF3aJ02ATVXUz8acnuF33w="
User-Agent: G2/1.0
Cancel-Lock: sha1:W4p12OtreHcVOoZxmtcBuIJ1urU=

by: Phu Tran Hoang - Fri, 22 Jul 2022 05:19 UTC

;Replace "rep movsb" by the following code
test di,1 ; alaign by word
jz $+4
movsb
dec cx

shr cx,1
rep movsw
jnc $+3
movsb

;Replace "rep stosb" by the following code
mov ah, al
test di,1 ; alaign by word
jz $+4
stosb
dec cx

shr cx,1
rep stosw
jnc $+3
stosb

Re: Optimize speed 8086 instruction "rep movsb" and "rep stosb"

<tbe96u$uv3$1@gioia.aioe.org>

copy mid

https://news.novabbs.org/devel/article-flat.php?id=799&group=comp.lang.asm.x86#799

copy link Newsgroups: comp.lang.asm.x86

Path: i2pn2.org!i2pn.org!eternal-september.org!reader01.eternal-september.org!.POSTED!not-for-mail
From: nowhere@nospicedham.nevernet.at (wolfgang kern)
Newsgroups: comp.lang.asm.x86
Subject: Re: Optimize speed 8086 instruction "rep movsb" and "rep stosb"
Date: Fri, 22 Jul 2022 15:37:33 +0200
Organization: Aioe.org NNTP Server
Lines: 51
Approved: fbkotler@myfairpoint.net - comp.lang.asm.x86 moderation team.
Message-ID: <tbe96u$uv3$1@gioia.aioe.org>
References: <d60a7938-4b3c-4b10-91b2-1dc33fe6abf8n@googlegroups.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Info: reader01.eternal-september.org; posting-host="72eccefa569787c9acac825e7950fa24";
logging-data="3322882"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1+NF61RDmFjLdpy7aBcxSRnWYsSqO6y50Y="
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101
Thunderbird/91.11.0
Cancel-Lock: sha1:OERh0yyILySMAAxCgTBFlJg0Hhg=

by: wolfgang kern - Fri, 22 Jul 2022 13:37 UTC

On 22/07/2022 07:19, Phu Tran Hoang wrote:
> ;Replace "rep movsb" by the following code
> test di,1 ; alaign by word
> jz $+4
> movsb
> dec cx
>
> shr cx,1
> rep movsw
> jnc $+3
> movsb
>
>
>
> ;Replace "rep stosb" by the following code
> mov ah, al
> test di,1 ; alaign by word
> jz $+4
> stosb
> dec cx
>
> shr cx,1
> rep stosw
> jnc $+3
> stosb

[jnc+1 ? stosb/stosw are only one byte code "AA/AB"]

Yes, pre- and post-aligning string operations are
the main speed-gain in my OS. It works with 32-bit
reduction/extension for any odd start and size.

But I also align source or destination to quad bounds.

TEST esi,3
JZ isAligned
.... ;adjust for an aligned loop start here
isAligned:
SHR ecx,1 ;no action at all if ecx=0
JNC +1
LODSB
SHR ecx,1
JNC +2 ; +2 for use32
LODSW ; because prefix required here
REP LODSD ;falls through if ECX=Zero

and with similar dummy reads up front and at end it
can part-read disk sectors at any offset and size.
__
wolfgang

Frankly, Scarlett, I don't have a fix. -- Rhett Buggler

devel / comp.lang.asm.x86 / Re: Optimize speed 8086 instruction "rep movsb" and "rep stosb"

Subject	Author
Optimize speed 8086 instruction "rep movsb" and "rep stosb"	Phu Tran Hoang
Optimize speed 8086 instruction "rep movsb" and "rep stosb"	wolfgang kern