home *** CD-ROM | disk | FTP | other *** search
- Path: nyx.cs.du.edu!not-for-mail
- From: kathomas@nyx.cs.du.edu (Karl Thomas)
- Newsgroups: comp.sys.amiga.datacomm,comp.sys.amiga.advocacy,comp.sys.amiga.misc,comp.sys.amiga.networking
- Subject: Re: New Press Release!
- Date: 19 Mar 1996 20:23:51 -0700
- Organization: University of Denver, Math/CS Dept.
- Message-ID: <4into7$136@nyx.cs.du.edu>
- References: <2937.6638T1404T1877@mozart.inet.co.th> <4hivul$nn8@server05.icaen.uiowa.edu> <4i440e$1b9@infa.central.susx.ac.uk> <4i5hlq$rn3@nyx.cs.du.edu> <314B536E.5B1D@infohwy.com> <4im6oj$h9u@soleil.uvsq.fr>
- NNTP-Posting-Host: nyx.nyx.net
- X-Newsreader: NN version 6.5.0 #3 (NOV)
-
- Nicolas POMAREDE <pomarede> writes:
-
- >Lars Nelson <lars@infohwy.com> wrote:
- >>Karl Thomas wrote:
-
- >> One benchmark was faster than another. So what. Don't you know
- >>that software applications run on a 68060 Amiga can run faster than on a
- >>Pentium Mhz for Mhz. Have you tried running Lightwave on a Pentium versus
- >>a 68060? Amiga wins. What's hilarious is that the Pentium is a 64-bit
- >>processor running on new hardware, and the 68060 is still 32-bit and
- >>running on old hardware.
-
- What benefit would Motorola derive from underestimating their own benchmarks?
-
- >An italian paper on raytracing/rendering has made a test last month to
- >compare the cyberstorm against a P133. They used one of the test picture
- >of Lightwave (the one with 16 cubes with different mapping effects).
- >The pentium 133 took approx. 12 min. and the 68060/60 took a little more
- >than 13 min.
- >In other word, this would mean that the 68060 was twice faster than
- >the P133 (considering that it ran at half clock speed).
-
- Do you actually think that the '060-66 is twice as fast as the Pentium?
- LightWave just wasn't well optimized for the Pentium if this is the case.
- Most programs aren't as well optimized for the secondary market they're
- ported to, I can give you many examples of Mac programs that aren't as
- optimized for Windows when they are ported and Windows programs that
- aren't as well optimized for the Mac.
-
-
- >Of course, there might be other tests (perhaps Lightwave has been particularly
- >optimised for the 68060), but applications certainly have great benefit
- >from the large number of register of the 680x0 family (compared to the
- >very poor x86 registers set)
-
- True, floating point is about 20% faster per Mhz on an '060 compare to a
- Pentium but not twice as well optimized. Then again Windows (3.1, '95,
- and NT) doesn't have the best graphics api in the world.
-