delorie.com/archives/browse.cgi   search  
Mail Archives: djgpp-workers/2000/03/14/10:13:22

Message-ID: <38CE53D6.208D75E2@hotmail.com>
Date: Tue, 14 Mar 2000 15:59:35 +0100
From: Jesus Gil y Gil <javiputa AT hotmail DOT com>
X-Mailer: Mozilla 4.72 [en] (Win98; U)
X-Accept-Language: en
MIME-Version: 1.0
To: djgpp-workers AT delorie DOT com
Subject: Re: Fastest integer type
References: <200003140840 DOT JAA19626 AT mars DOT lu DOT erisoft DOT se>
Reply-To: djgpp-workers AT delorie DOT com

Martin Stromberg wrote:

> The standard says you should provide types that are the fastest on the
> platform (the definition of fastest is up to the platform) for integer
> types that are at least 8, 16, 32 and 64 bits. I know that ints (32
> bits) are faster than shorts (16 bits) in DJGPP, right?
>
> Are ints (32 bits) faster than chars (8 bits)?
>
> Right,
>
>                                                         MartinS

You should run the benchmark that I posted 3 days ago to
djgpp AT delorie DOT com, it will carify your dudes by yourself.
The speed depends of the processor:
- In 486 the fastest are 16 and 32 bits integers, chars are only a few
slower, floats are more slow than integers, and double slowest.
- In Pentium 8 bit integers are the fastest, 16 bits are faster and 32
bits even more faster, floats and doubles the same speed, a bit slower
that 16 bits integers.
- In AMD K6 all types, 8,16,32 bits integer and float are equally faster.
- In Pentium II and III, 8 bits are two times more slow than all the other
types, 16 bits are much more faster, and 32 bits the fastest again, floats
are equally fast than 32 bits integers, and doubles practically the same.

I expect I've helped you.


- Raw text -


  webmaster     delorie software   privacy  
  Copyright © 2019   by DJ Delorie     Updated Jul 2019