cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) (06/13/90)
l86@nikhef.nl (Hugo Burm) writes: >The developers version of the TT (16 MHz) runs >at 4100 Dhrystones >(Turbo C 2.0, 68020 compiler switch on, cache on, >run in dual purpose RAM (time sliced with the video logic)) >A normal ST runs at 1700. 4100 Dhrystones? ACK! That is awful. You can get that kind of performance from a vanilla 386 clone. For comparison sake (no flames please) people on comp.sys.amiga have stated that they have gotten double this figure on the 25mhz A3000. I'm not sure how much of this difference is because of the faster clock or from the 68882 in the A3000. I wonder what kind of Dhrystone figure a Mac IIcx would produce? Chris ------------------------------+--------------------------- Chris Mauritz |Donde hay una cerveza cmm1@cunixa.cc.columbia.edu |hay un plan. (c)All rights reserved. | Send flames to /dev/null |El Guerrero Aereo es el rey! ------------------------------+---------------------------
gl8f@astsun9.astro.Virginia.EDU (Greg Lindahl) (06/13/90)
In article <CMM.0.88.645215952.cmm1@cunixa.cc.columbia.edu> cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) writes: > >4100 Dhrystones? ACK! That is awful. You can get that kind of >performance from a vanilla 386 clone. Indeed, Dhrystone is an awful benchmark. Depending on how you do the string copies, Dhrystone performance can vary 30% or more on a single machine between compilers. Also, given what Alan Pratt said a long time about about the TT's memory system, you can expect 50% better performance from the ram above 2 megs which doesn't have video contention. Now can we shut up about this topic until the TT is in stores? We aren't getting anywhere with all these stupid postings. -- "Perhaps I'm commenting a bit cynically, but I think I'm qualified to." - Dan Bernstein
ckp@grebyn.com (Checkpoint Technologies) (06/13/90)
In article <CMM.0.88.645215952.cmm1@cunixa.cc.columbia.edu> cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) writes: >l86@nikhef.nl (Hugo Burm) writes: > >>The developers version of the TT (16 MHz) runs >>at 4100 Dhrystones >>(Turbo C 2.0, 68020 compiler switch on, cache on, >>run in dual purpose RAM (time sliced with the video logic)) >>A normal ST runs at 1700. What version of Dhrystone? There's a vast difference between Dhrystone 1.x and Dhrystone 2.x. Dhrystone 1.x can be optimized a lot by removing benchmark code; smart compilers will see that the computed results aren't used, and so the computations are discarded. V2.x defeats this by *using* all the answers computed. V2.0 ran ~1200 on a MicroVAX II. >4100 Dhrystones? ACK! That is awful. You can get that kind of >performance from a vanilla 386 clone. For comparison sake (no flames I achieved about 5000 Dhrystones (V2.1) on a 25Mhz 386 running Interactive Unix, with register parameters and aggresive optimization. That's 386 native mode too. >please) people on comp.sys.amiga have stated that they have gotten >double this figure on the 25mhz A3000. I'm not sure how much of >this difference is because of the faster clock or from the 68882 >in the A3000. I wonder what kind of Dhrystone figure a Mac IIcx >would produce? Dhrystone is an integer benchmark only; the floating point chip can have no effect on it. I suspect the Amiga 3000 advantages are from the clock speed, and also probably from the compiler (Lattice C optimizes quite well). -- First comes the logo: C H E C K P O I N T T E C H N O L O G I E S / / \\ / / Then, the disclaimer: All expressed opinions are, indeed, opinions. \ / o Now for the witty part: I'm pink, therefore, I'm spam! \/
daveh@cbmvax.commodore.com (Dave Haynie) (06/14/90)
In article <CMM.0.88.645215952.cmm1@cunixa.cc.columbia.edu> cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) writes: >l86@nikhef.nl (Hugo Burm) writes: >>The developers version of the TT (16 MHz) runs >>at 4100 Dhrystones >4100 Dhrystones? ACK! That is awful. You can get that kind of >performance from a vanilla 386 clone. Benchmarking is kind of a black art, and Dhrystone is one of the blackest forms of this art. First, saying "Dhrystone" is kind of meaningless in this era of optimizing compilers -- some compilers can produce far faster numbers with Dhrystone 1.1 vs. Dhrystone 2.x, on the same hardware. So first thing, you want to compare like with like. Then of course there's the compiler used. You can get a nearly 2:1 increase going from early C compilers to the latest Lattice with all the "go faster" flags set, on the same [Amiga] hardware. Then you get to the issue of "memory model". For 68030s, you should be running with 32 bit integers, just like RISC machines or VAXen or other 32 bit CPUs that show up in the comparisons. But you can get higher numbers in many cases choosing 16 bit integers. Benchmarks for Clones will just about always use 16 bit integers. Then consider the operating system. Most machines have an OS eating part of the CPU time during any benchmark. On an MS-DOS machine, you can throw out MS-DOS and use a '386 program loader to further boost the numbers. And on a '386 with cache, the entire Dhrystone program will fit in a 16K cache. All of which means that current '386 machines under MS-DOS tend to give pretty high Dhrystone numbers. It doesn't say too much about what such machines will do with actual programs, or even moreso, actual programs in a real operating system. So don't pay too much attention to Dhrystone; it's best at comparing Amigas to Amigas, Ataris to Ataris, etc. where the software is invarient. As move toward more and more dissimilar architectures, you often find unusual differences, especially with Dhrystone 1.1. >I'm not sure how much of this difference is because of the faster clock or >from the 68882 in the A3000. I wonder what kind of Dhrystone figure a Mac >IIcx would produce? Dhrystone has no floating point component. The '882 won't affect the results. Other than clock speed, the compiler will have a noticable difference. The caches, burst memory, etc. do too. >Chris Mauritz |Donde hay una cerveza -- Dave Haynie Commodore-Amiga (Amiga 3000) "The Crew That Never Rests" {uunet|pyramid|rutgers}!cbmvax!daveh PLINK: hazy BIX: hazy "I have been given the freedom to do as I see fit" -REM
towns@atari.UUCP (John Townsend) (06/14/90)
in article <CMM.0.88.645215952.cmm1@cunixa.cc.columbia.edu>, cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) says: > > l86@nikhef.nl (Hugo Burm) writes: > >>The developers version of the TT (16 MHz) runs >>at 4100 Dhrystones >>(Turbo C 2.0, 68020 compiler switch on, cache on, >>run in dual purpose RAM (time sliced with the video logic)) >>A normal ST runs at 1700. > > 4100 Dhrystones? ACK! That is awful. You can get that kind of > performance from a vanilla 386 clone. For comparison sake (no flames > please) people on comp.sys.amiga have stated that they have gotten > double this figure on the 25mhz A3000. I'm not sure how much of > this difference is because of the faster clock or from the 68882 > in the A3000. I wonder what kind of Dhrystone figure a Mac IIcx > would produce? > > Chris > > [... Longish Signature Deleted ...] Why don't you try comparing the figure to something that is in the same "computing class"??? Why not see what the Dhrystones are for a Macintosh SE/30 are? Or perhaps a Mac IIcx? Comparing the figures of a TT to an Amiga 3000 running at 25MHz is not even close to a fair comparison. I would be willing to bet that the TT would compete favorably with an equally equipped A3000. -- John Townsend Atari Corp.
cmm1@cunixa.cc.columbia.edu (Christopher M Mauritz) (06/15/90)
In article <2217@atari.UUCP> towns@atari.UUCP (John Townsend) writes: >in article <CMM.0.88.645215952.cmm1@cunixa.cc.columbia.edu>, cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) says: >> >> 4100 Dhrystones? ACK! That is awful. You can get that kind of >> performance from a vanilla 386 clone. For comparison sake (no flames >> please) people on comp.sys.amiga have stated that they have gotten >> double this figure on the 25mhz A3000. I'm not sure how much of >> this difference is because of the faster clock or from the 68882 >> in the A3000. I wonder what kind of Dhrystone figure a Mac IIcx >> would produce? >> >> Chris >> >> [... Longish Signature Deleted ...] > >Why don't you try comparing the figure to something that is in the >same "computing class"??? Why not see what the Dhrystones are for a >Macintosh SE/30 are? Or perhaps a Mac IIcx? > >Comparing the figures of a TT to an Amiga 3000 running at 25MHz is >not even close to a fair comparison. I would be willing to bet that >the TT would compete favorably with an equally equipped A3000. Hehe, well maybe if you guys got the silly machine out the door so we could get a look at it and see for ourselves, we COULD make some valid comparisons. This is rather comical. Yes, sorry about comparing a 25mhz machine with a 16mhz machine (slaps wrist...smack!). We shall see what the real numbers are like soon (or do we have to wait until 4th quarter 199X?) Sorry to be such a cynic, but you guys make it so easy. :-) > >-- John Townsend > Atari Corp. <longish signature inserted> ------------------------------+--------------------------- Chris Mauritz |Donde hay una cerveza cmm1@cunixa.cc.columbia.edu |hay un plan. (c)All rights reserved. | Send flames to /dev/null |El Guerrero Aereo es el rey! ------------------------------+---------------------------
jfbruno@rodan.acs.syr.edu (John Bruno) (06/15/90)
In article <1990Jun15.133149.22197@cunixf.cc.columbia.edu> cmm1@cunixa.cc.columbia.edu (Christopher M Mauritz) writes: >In article <2217@atari.UUCP> towns@atari.UUCP (John Townsend) writes: >>in article <CMM.0.88.645215952.cmm1@cunixa.cc.columbia.edu>, cmm1@CUNIXA.CC.COLUMBIA.EDU (Christopher M Mauritz) says: >>> >>> 4100 Dhrystones? ACK! That is awful. >>> [My Amiga can beat up Your Atari drivel deleted] >>> >>> Chris >>> >>> [... Longish Signature Deleted ...] >> >>Why don't you try comparing the figure to something that is in the >>same "computing class"??? Why not see what the Dhrystones are for a >>Macintosh SE/30 are? Or perhaps a Mac IIcx? >> >>Comparing the figures of a TT to an Amiga 3000 running at 25MHz is >>not even close to a fair comparison. I would be willing to bet that >>the TT would compete favorably with an equally equipped A3000. > >Hehe, well maybe if you guys got the silly machine out the door >so we could get a look at it and see for ourselves, we COULD >make some valid comparisons. This is rather comical. > >Yes, sorry about comparing a 25mhz machine with a 16mhz machine >(slaps wrist...smack!). We shall see what the real numbers are >like soon (or do we have to wait until 4th quarter 199X?) > >Sorry to be such a cynic, but you guys make it so easy. :-) > >> >>-- John Townsend >> Atari Corp. > >------------------------------+--------------------------- >Chris Mauritz |Donde hay una cerveza >cmm1@cunixa.cc.columbia.edu |hay un plan. >(c)All rights reserved. | >Send flames to /dev/null |El Guerrero Aereo es el rey! ^^^^^^^^^^^^^^^^^^^^^^^^ Hehe, Chris, we'd all appreciate it if you would take your own advice and keep keep your childish posts to yourself. Dhrystones blahblah dhrystones this that drivel drivel... Gimme a break! Those Byte magazine geek benchmarks don't mean squat! No matter how fast your machine is, it'll still take you 15 minutes to type a letter and X minutes to type in a spreadsheet. I'm sure everybody is real impressed that your Amiga can do more GigaHoozits than our Ataris, so what? Well, enough of that, we now return you to our regular programming. Let's see, where were we.... Ah yes, I think we were discussing a non-existent machine, or was it the differences between Dhrystone 1.X and 2.Y... Real interesting stuff, doncha think? ---jb
Bob_BobR_Retelle@cup.portal.com (06/16/90)
John Townsend writes: >Why don't you try comparing the figure to something that is in the >same "computing class"??? ... >Comparing the figures of a TT to an Amiga 3000 running at 25MHz is >not even close to a fair comparison. I would be willing to bet that >the TT would compete favorably with an equally equipped A3000. Does this mean we should slow an Amiga 3000 down to 16Mhz...? ...or try to find a 25Mhz TT...?? (Just to make it fair...) BobR