Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.3 4.3bsd-beta 6/6/85; site amdcad.UUCP
Path: utzoo!watmath!clyde!burl!ulysses!mhuxr!mhuxn!ihnp4!amdcad!jimb
From: jimb@amdcad.UUCP (Jim Budler)
Newsgroups: net.micro.mac
Subject: Re: Processing Speed? [floating point bench marks]
Message-ID: <9049@amdcad.UUCP>
Date: Sat, 1-Feb-86 15:36:27 EST
Article-I.D.: amdcad.9049
Posted: Sat Feb  1 15:36:27 1986
Date-Received: Sun, 2-Feb-86 01:22:18 EST
References: <106@eyelab.UUCP> <891@h-sc1.UUCP> <870@umn-cs.UUCP>
Reply-To: jimb@amdcad.UUCP (Jim Budler)
Organization: AMD, Sunnyvale, California
Lines: 40

In article <870@umn-cs.UUCP> waddingt@umn-cs.UUCP (Jake Waddington ) writes:
>...
>> Also note that Aztec 'C' *might* be using 80 bit
>>FP ('SANE') everywhere (as compared to 32bit floats and 64bit doubles on
>>the PDP). I don't know; that is something you should check before
>>comparing the two. Finally, your compiler for the PDP might be vastly
>>superior to the Aztec compiler. 
>
>
>I am working a some floating point bench marks for Aztec "C", MegaMac "C"
>and TML Pascal.
>I will post full results next week. But sence the question came up I will
>say that:
>...
>	point math. Further Aztec does not use the SANE 80 bit
>	floating point routines. It has it's own and this seems
>	to be why it is slow.
>
>	MegaMax does use the SANE routines and is 4 time faster
>	doing floating point.
>
>	TML Pascal is by far the fastest! It also uses the SANE
>	interface and you can get se the full 80 bits, you cann't
>	in "C". 

[ in the C's you have, see below ]

Some small points:

	SANE is not the fastest implementation, but it is accurate.

	Consulair Mac C uses SANE 80 for all internal FP calculations.

	80 bit FP *is* available in Consulair Mac C.
-- 
 Jim Budler
 Advanced Micro Devices, Inc.
 (408) 749-5806
 Usenet: {ucbvax,decwrl,ihnp4,allegra,intelca}!amdcad!jimb
 Compuserve:	72415,1200