Re: Comparison of Mathematica on Various Computers
- To: mathgroup at smc.vnet.net
- Subject: [mg50293] Re: [mg50276] Comparison of Mathematica on Various Computers
- From: "Hobbs, Sylvia (DPH)" <Sylvia.Hobbs at state.ma.us>
- Date: Wed, 25 Aug 2004 03:36:02 -0400 (EDT)
- Sender: owner-wri-mathgroup at wolfram.com
Bobby, agreed useless in so far as gaming, but for geostatistical modeling of a disease outbreak (as with data kriging) and radiologic modeling where you are trying to visualize an animated image while the calculation is occurring rather than waiting for all calculations to be done then just see a static image, I would disagree. If one never manipulates animation or requires a 3-D picture of a moving function then these things would seem useless. But to again agree with you, it simply depends on what you are doing. To ask how dramatically does the AMD or Intel chip differ in handling floating points, integer operations, square roots, the oddity is that in some sense benchmarks are more tricky than ever to generalize because both AMD and Intel are changing their nomenclature with regards to chip speed. The AMD chip called itself "3000+" because it could go faster on many points than a 3 Gig, but the AMD actually had fewer than 3 Gigs because the AMD accomplishes more per hertz. You can see some one Gigs go faster than a 3 Gig because of a different type of Pentium, front side bus speed, how faster it is going to communicate with the RAM and peripheral devices. Now Intel has followed suite and is in the middle of changing its chip nomenclature system (viz. 325, 500, 700). Sylvia -----Original Message----- From: DrBob [mailto:drbob at bigfoot.com] To: mathgroup at smc.vnet.net Subject: [mg50293] [mg50276] Re: [mg50216] Re: [mg50210] Comparison of Mathematica on Various Computers I hate to say this, it's so obvious, but... Gaming and 3D benchmarks are irrelevant to the question of which machine is faster when running Mathematica--or anything useful, for that matter. Bobby On Mon, 23 Aug 2004 11:10:43 -0400, Hobbs, Sylvia (DPH) <Sylvia.Hobbs at state.ma.us> wrote: > Hi Bobby! > > http://www.computeruser.com/articles/2208,12,84,1,0801,03.html > > Syls > > -----Original Message----- > From: DrBob [mailto:drbob at bigfoot.com] To: mathgroup at smc.vnet.net > Sent: Saturday, August 21, 2004 11:18 AM > To: Hobbs, Sylvia (DPH) > Subject: [mg50293] [mg50276] Re: [mg50216] Re: [mg50210] Comparison of Mathematica on Various > Computers > > Like what? > > Bobby > > On Sat, 21 Aug 2004 03:04:17 -0400 (EDT), Hobbs, Sylvia (DPH) > <Sylvia.Hobbs at state.ma.us> wrote: > >> Don't jump on the AMD bandwagon without checking other benchmarks. Some >> notorious problems are alluded to in the company's own white papers. >> >> Sylvia Hobbs >> >> -----Original Message----- >> From: karl unterkofler [mailto:karl.unterkofler at fh-vorarlberg.ac.at] To: mathgroup at smc.vnet.net >> To: mathgroup at smc.vnet.net >> Subject: [mg50293] [mg50276] [mg50216] [mg50210] Comparison of Mathematica on Various > Computers >> >> ''Comparison of Mathematica on Various Computers'' >> is now on <a href="http://smc.vnet.net/mathbench.html";> >> (or <a href="http://www2.staff.fh-vorarlberg.ac.at/~ku/karl/mma.html";>) >> >> >> Mathematica 5.0 benchmark on >> http://www2.staff.fh-vorarlberg.ac.at/~ku/karl/timings50.html >> >> New results for Mathematica 5.0: >> >> Pentium M 1500MHz >> P4, 3.2 GHz, 2GB RAM, 512kb, XP SP1 >> Pentium 4 XT ("Extreme Edition"), 3.2 GHz, 2GB, Win XP Pro >> xAMD Athlon 3200+, 2GB RAM, WinXP Pro >> Toshiba TE2000 laptop, P3 1.2 GHz, 512MB, Win XP Pro >> >> The new test notebook for Mathematica 5.0 is available at >> http://www2.staff.fh-vorarlberg.ac.at/~ku/karl/math/MMA5.0-Test.nb >> >> >> Karl Unterkofler >> >> >> > > > > -- > DrBob at bigfoot.com > www.eclecticdreams.net > > -- DrBob at bigfoot.com www.eclecticdreams.net