Path: utzoo!attcan!uunet!dino!hascall
From: hascall@cs.iastate.edu (John Hascall)
Newsgroups: comp.lang.c
Subject: Re: A study in code optimization in C
Keywords: memcopy
Message-ID: <2360@dino.cs.iastate.edu>
Date: 30 Jul 90 14:13:38 GMT
References: <133@smds.UUCP> <1990Jul26.144134.16053@ux1.cso.uiuc.edu> <134@smds.UUCP>
Sender: usenet@dino.cs.iastate.edu
Organization: Project Vincent, Iowa State University Computation Center
Lines: 26

rh@smds.UUCP (Richard Harter) writes:
}mcdonald@aries.scs.uiuc.edu (Doug McDonald) writes:
}> rh@smds.UUCP (Richard Harter) writes:

}> >The macro shown below is an optimized memory to memory copy macro.
}> >It is probably faster than memcopy on your machine -- I have checked
}> >it on several machines and have always found it to be faster.

}> Oh My!.

}	[Superior timings for a 20KB move on a 386 by memmove given]

}Ouch.  I should have phrased that more carefully.  Yes, the gentleman
}is quite right.  As to be expected, a hardware bulk move is always
}going to beat code that uses item by item move instructions.

}In defense I have to point out that the quoted remark is accurate;
}timings were made on 680x0 boxes, vaxes (!), and some risc boxes,
				   ~~~~~
 Hmmm, sorry, but here's a little more rain on your parade:

 VAXstation 3200 (admittedly, not the most modern VAX), 1000 20KB copies:

		memcpy: 3.18       your macro: 15.43

John Hascall  /  john@iastate.edu  /  hascall@atanasoff.cs.iastate.edu