markus@techfak.uni-bielefeld.de (Markus Illenseer) (06/20/91)
In the german Amiga-Mag 'Amiga' (M&T) released these days (7/91) we can read the following, very interesting article: [translated and shorted copie] === The US-Company RCS offers the 68040 Card 'Fusion-40' since "now". With more than 18 Mips, that means upto 3 times faster than any A3000 and upto 5 times faster than any (plain) A2000, this Amiga can be used for all professional use. [useless information belonging 040 deleted] The Processor is working internally with a Tact-Rate of 50 Mhz, though the external Rate will be 25 MHz. The card supports upto 32 MB RAM . [SIMMs, not mentioned in the text, but shown on the picture, and 8 MB onboard, the rest via Piggy-Back, also guessed, because there were only 8 SIMM- sockets.] The price: 6000 DM including the Chip and 4 MB RAM. === As the price is EXACTLY 6000 DM, I suppose it is not yet fixed. BTW, the US-Dollar is now : 1.80 DM = 1$US The given 18 Mips is a bit slow, but as it is a CARD for the A2000 it may be right. Also it is not mentioned whether the card can be plug into the Processor-Slot or in a Zorro-II(I) Slot, so i can't say if this card will run on a A3000. [to be noticed: I have nothing to do with RCS nor with ADC (The German Distributor), I am just coping this article to the public.] -- CU, Markus Markus Illenseer, Computer Science , University of Bielefeld, Germany I read the news today, oh boys ... about a lucky man who made the grade ... -------------------------------------------------------------------------
menzies@CAM.ORG (Stephen Menzies) (06/22/91)
markus@techfak.uni-bielefeld.de (Markus Illenseer) writes: >In the german Amiga-Mag 'Amiga' (M&T) released these days (7/91) we can read >the following, very interesting article: >[translated and shorted copie] >=== >The US-Company RCS offers the 68040 Card 'Fusion-40' since "now". ^^^^^^^^^^^ No, it's a Canadian Company located in Montreal,Quebec. >With more than 18 Mips, that means upto 3 times faster than any A3000 and >upto 5 times faster than any (plain) A2000, this Amiga can be used for >all professional use. >[useless information belonging 040 deleted] >The Processor is working internally with a Tact-Rate of 50 Mhz, though the >external Rate will be 25 MHz. >The card supports upto 32 MB RAM . >[SIMMs, not mentioned in the text, but shown on the picture, and 8 MB >onboard, the rest via Piggy-Back, also guessed, because there were only 8 SIMM- >sockets.] No, it's ALL onboard. The board itself supports: 1meg x 8 simm modules expandable upto 8megs or, 4meg x 8 simm modules expandable upto 32megs. The minimum is 4megs. I believe there are permutations on the above but I would have to double check. >The price: 6000 DM including the Chip and 4 MB RAM. >=== >As the price is EXACTLY 6000 DM, I suppose it is not yet fixed. >BTW, the US-Dollar is now : 1.80 DM = 1$US >The given 18 Mips is a bit slow, but as it is a CARD for the A2000 it may be >right. Also it is not mentioned whether the card can be plug into the >Processor-Slot or in a Zorro-II(I) Slot, so i can't say if this card will run on >a A3000. The RCS board fits into the A2000 processor slot. The board runs at 1750 Drystones/mip using Amiga Bench Drystone Rating. This translates to 31650 Drystones/sec. Users can expect a much better rating once popular softwares are optimized for the 040. The board has been running under the 2.0 OS and I might add, the present software runs even more reliably than under 1.3. For one, the Copyback caches can remain on ALL the time. The 2.0 OS seems to have been developed with the 040 in mind. >[to be noticed: I have nothing to do with RCS nor with ADC (The German >Distributor), I am just coping this article to the public.] >-- >CU, Markus >Markus Illenseer, Computer Science , University of Bielefeld, Germany >I read the news today, oh boys ... about a lucky man who made the grade ... >------------------------------------------------------------------------- While I am NOT an employee of RCS, I have been independently testing the Fusion_40 for 2 weeks now, in particular , with 3D Animation software. If anyone requires info on how well a particular software (if I have it) performs with the Fusion_40 (modelling and rendering speed comparisons against my own A3000/25) , feel free to ask here (I read these groups on a regular basis) or if not of general interest, by E-Mail. I've preformed numerous tests (some quite large) with Imagine1.1.... have now started with Caligari Broadcast 2.01...and will soon be looking at Lightwave.....others to follow. To some extent I've tested ADPro, DPIII, and several PD's that I use constantly like Snap1.61 and Browser1.7 (ok). RCS Management should be connected to the Net within the next 2 weeks, hopefully sooner. In the meantime, I am willing to relay questions of a technical nature or product availibility etc, to them. --steve -- Stephen Menzies Email: menzies@CAM.ORG
burkert1@platon.fmi.uni-passau.de (Klaus Burkert) (06/24/91)
In article <1991Jun20.114837.22962@unibi.uni-bielefeld.de> markus@techfak.uni-bielefeld.de (Markus Illenseer) writes: >In the german Amiga-Mag 'Amiga' (M&T) released these days (7/91) we can read >the following, very interesting article: [...] >The Processor is working internally with a Tact-Rate of 50 Mhz, though the >external Rate will be 25 MHz. > >The card supports upto 32 MB RAM . > >[SIMMs, not mentioned in the text, but shown on the picture, and 8 MB >onboard, the rest via Piggy-Back, also guessed, because there were only 8 SIMM- >sockets.] All on Board, you can use 4 or 8 SIMMs of 1MB or 4MB type giving you 4, 8 or 16, 32 MB RAM. > >The price: 6000 DM including the Chip and 4 MB RAM. >As the price is EXACTLY 6000 DM, I suppose it is not yet fixed. I think in ACD's own Ad in a local Magazine ('local' not for Germany but for the area of Bremen where ACD resides), the Price was ficxed to 5990.- DM. >The given 18 Mips is a bit slow, but as it is a CARD for the A2000 it may be >right. Also it is not mentioned whether the card can be plug into the >Processor-Slot or in a Zorro-II(I) Slot, so i can't say if this card will run on >a A3000. I've not tested it too deep by my own, but last time I was at their shop, the board was running 1.3 and thus the Copyback-Mode had to be turned off, since 1.3 doesn't support it. Under 2.x there shall be support and higher ratingins will be possible. The board is buil for the A2000's Coprocessor-Slot, but there also a Version for the A3000 announced and I remember the price around 3600.- DM. > >[to be noticed: I have nothing to do with RCS nor with ADC (The German >Distributor), I am just coping this article to the public.] Nor do I, just bought a few things there, but it's ACD and their address is ACD, Dammweg 15, D-W-2800 Bremen. ------------------------------------------------------------- Klaus Burkert email: burkert1@platon.fmi.uni-passau.de Brandweg 11 voice: +49-851/83993 D-W-8390 Passau / Federal Republic of Germany
mks@cbmvax.commodore.com (Michael Sinz) (06/24/91)
[Much stuff deleted] In article <1991Jun21.183207.27427@CAM.ORG> menzies@CAM.ORG (Stephen Menzies) writes: >markus@techfak.uni-bielefeld.de (Markus Illenseer) writes: >>The Processor is working internally with a Tact-Rate of 50 Mhz, though the >>external Rate will be 25 MHz. Hold on... Just because the CPU wants a 50MHz input clock does not mean that you can call it 50MHz tact-rate. The reason you place a 50MHz clock into the chip is such that it can have a stable. 25MHz clock to play with. In fact, some designs have 100MHz clocks going through a divider to bring the 50MHz clock into the CPU. This is again to provide a stable clock. The 68040 (chip) currently is only available at 25MHz. Anything trying to imply 50MHz is pulling someone's chain. Also, any attempt to go beyond that clock rate is *VERY* dangerous and should be looked at as suspect. (The 68040 is built to a rather tight spec and that includes the clock) >The RCS board fits into the A2000 processor slot. The board runs at 1750 >Drystones/mip using Amiga Bench Drystone Rating. This translates to ?^^^^^^^^^^^^^? >31650 Drystones/sec. Users can expect a much better rating once popular >softwares are optimized for the 040. The board has been running under the >2.0 OS and I might add, the present software runs even more reliably than >under 1.3. For one, the Copyback caches can remain on ALL the time. The 2.0 >OS seems to have been developed with the 040 in mind. Ok, so what is that? A MIP is already rather silly measurement and then adding a Drystones/mip? Where did that come from? Current testing shows that a standard Drystones compiled by standard C with no special 68040 optimizations comes out to 23,000 to 25,000 rating if the 68040 caches are full on and CopyBack mode is enabled. A smarter compiler (68040 smart) would be able to make this number higher, but there are very few compilers out there that can do this and even fewer products compiled with them. CopyBack mode, and in general the 68040, is not supported in AmigaDOS 1.3 or earlier. There are many issues concerning caching that had not been resolved back when 1.3 was made. (The 68030 had just about been introduced and the 68040 was just a "name") AmigaDOS 2.0 supports all of the 68040 modes. CopyBack mode is somewhat supported in that if it is turned on, the ROM will correctly deal with it. A simple SetFunction() to CacheControl() would let the system also use the CACRF_CopyBack bit to turn on/off CopyBack. However, some applications may not be ready for 68040 and CopyBack. CopyBack tends to make programs that write code to RAM not work too well since even if the instruction cache is flushed, the new code may not have been copied to physical RAM from the cache. 2.0's CacheClearU() and CacheClearE() functions deal with that issue correctly. /----------------------------------------------------------------------\ | /// Michael Sinz - Amiga Software Engineer | | /// Operating System Development Group | | /// BIX: msinz UUNET: rutgers!cbmvax!mks | |\\\/// | | \XX/ Quantum Physics: The Dreams that Stuff is made of. | \----------------------------------------------------------------------/
bdraschk@immd4.informatik.uni-erlangen.de (Bernd Raschke) (06/24/91)
menzies@CAM.ORG (Stephen Menzies) writes: >While I am NOT an employee of RCS, I have been independently testing the >Fusion_40 for 2 weeks now, in particular , with 3D Animation software. If >anyone requires info on how well a particular software (if I have it) performs >with the Fusion_40 (modelling and rendering speed comparisons against my >own A3000/25) , feel free to ask here (I read these groups on a regular >basis) or if not of general interest, by E-Mail. > I've preformed numerous tests (some quite large) with Imagine1.1.... >have now started with Caligari Broadcast 2.01...and will soon be looking >at Lightwave.....others to follow. To some extent I've tested ADPro, DPIII, >and several PD's that I use constantly like Snap1.61 and Browser1.7 (ok). for (;;) printf("Post it!\n"); >--steve Ciao, bernd --- Bernd 'The Real Arthur!' Raschke |Only // bdraschk@faui09.informatik.uni-erlangen.de | \\ // Amiga hartmannstr. 129 8520 erlangen 09131 38244 | \X/ makes it possible "Wer nicht an Wunder glaubt, der ist kein Realist"
menzies@CAM.ORG (Stephen Menzies) (06/26/91)
mks@cbmvax.commodore.com (Michael Sinz) writes: > [Much stuff deleted] >>In article <1991Jun21.183207.27427@CAM.ORG> menzies@CAM.ORG (Stephen Menzies) writes: >>>markus@techfak.uni-bielefeld.de (Markus Illenseer) writes: >>>The Processor is working internally with a Tact-Rate of 50 Mhz, though the >>>external Rate will be 25 MHz. >Hold on... Just because the CPU wants a 50MHz input clock does not mean >that you can call it 50MHz tact-rate. The reason you place a 50MHz clock >into the chip is such that it can have a stable. 25MHz clock to play with. >In fact, some designs have 100MHz clocks going through a divider to bring >the 50MHz clock into the CPU. This is again to provide a stable clock. >The 68040 (chip) currently is only available at 25MHz. Anything trying to >imply 50MHz is pulling someone's chain. Also, any attempt to go beyond >that clock rate is *VERY* dangerous and should be looked at as suspect. >(The 68040 is built to a rather tight spec and that includes the clock) Due to the Technical nature of this discussion I have directed these questions to the attention of RCS and asked for *their* reply. RCS (verbatum) reply: [quote]From the mc68040 users manual see 8-1 bus characteristics. Take it to mean what you want, but the fusion-forty at present is a 25mhz design for the amiga2000. "the mc68040 uses two clocks to generate timing - a bus clock(bclk) and a processor clock(pclk). the pclk signal is exactly twice the frequency of the bclk signal and is internally phase-locked to bclk and distributed throughout the device to generate timing for all logic blocks. the bclk signal is only used as the reference signal for the phase-lock-loop (pll), which synchronize the pclk. the use of the dual clock inputs allows the bus interface to operate at half the speed of the internal logic of the of the processor, requiring less stringent memory interface requirments. since the rising edge of bclk is used as the reference point for the pll, all timing specs are referenced to this edge."[unquote] >>The RCS board fits into the A2000 processor slot. The board runs at 1750 >>Drystones/mip using Amiga Bench Drystone Rating. This translates to >?^^^^^^^^^^^^^? >>31650 Drystones/sec. Users can expect a much better rating once popular >>softwares are optimized for the 040. The board has been running under the >>2.0 OS and I might add, the present software runs even more reliably than >>under 1.3. For one, the Copyback caches can remain on ALL the time. The 2.0 >>OS seems to have been developed with the 040 in mind. >Ok, so what is that? A MIP is already rather silly measurement and then >adding a Drystones/mip? Where did that come from? Current testing shows >that a standard Drystones compiled by standard C with no special 68040 >optimizations comes out to 23,000 to 25,000 rating if the 68040 caches >are full on and CopyBack mode is enabled. A smarter compiler (68040 smart) >would be able to make this number higher, but there are very few compilers >out there that can do this and even fewer products compiled with them. Again, RCS's reply: [quote]With regards to mips and dhrystones according to ibm and everex advertising 1 mips (vax mips) is considered to be 1750 dhrystone per second,therefore 10 mips is considered to be 17500 dhrystone per second.[unquote] >[stuff deleted] > However, some applications >may not be ready for 68040 and CopyBack. CopyBack tends to make programs >that write code to RAM not work too well since even if the instruction cache >is flushed, the new code may not have been copied to physical RAM from >the cache.[more stuff deleted] And Again, RCS's reply: [Quote]Copyback will work very well with programs that are copied to ram, however instead of flushing the instruction cache, flush the data cache before you addtask(). this must work,period. If you cannot see this working I strongly suggest that you read the 68040 users manual.[unquote] --------end of RCS replies------------- And I repeat, I am NOT an employee of RCS though I have been independently testing the Fusion_40 for a couple of weeks now, in particular, with 3D Animation software. I am willing though to relay questions of a technical nature direcly to them. --stephen >/----------------------------------------------------------------------\ >| /// Michael Sinz - Amiga Software Engineer | >| /// Operating System Development Group | >| /// BIX: msinz UUNET: rutgers!cbmvax!mks | >|\\\/// | >| \XX/ Quantum Physics: The Dreams that Stuff is made of. | >\----------------------------------------------------------------------/ -- Stephen Menzies Email: menzies@CAM.ORG
mks@cbmvax.commodore.com (Michael Sinz) (06/26/91)
In article <1991Jun25.212433.24418@CAM.ORG> menzies@CAM.ORG (Stephen Menzies) writes: >mks@cbmvax.commodore.com (Michael Sinz) writes: > >>[stuff deleted] >> However, some applications >>may not be ready for 68040 and CopyBack. CopyBack tends to make programs >>that write code to RAM not work too well since even if the instruction cache >>is flushed, the new code may not have been copied to physical RAM from >>the cache.[more stuff deleted] > >And Again, RCS's reply: > >[Quote]Copyback will work very well with programs that are copied to ram, >however instead of flushing the instruction cache, flush the data cache >before you addtask(). this must work,period. If you cannot see this working >I strongly suggest that you read the 68040 users manual.[unquote] I have read the manual (a few times) You must push back the DCache *AND* flush the ICache to work correctly. (Too bad you can not just push the DCache; the push also flushes the DCache which is a loss... :-() Note that AddTask() is not so much the problem (even though it does solve the loading problem.) Many programs do other things that have nothing to do with AddTask(). If RCS would like to see my list (which includes things such as AddLibrary(), AddIntServer(), SetIntVector(), and many more such as IND_ADDHANDLER command to input.device!) Anyway, there are many parts of the system that are even worse off (try running a program with overlays) AmigaDOS 2.0 solves many of the problems but there is still a need for applications to either know what they are doing or for a set of patches that tries to patch the system in enough places. Note that this still can not catch all of the situations. (Any self modifying code that does not call a special system function to run it would be impossible to "patch" without changing the application itself.) >--------end of RCS replies------------- > >And I repeat, I am NOT an employee of RCS though I have been independently >testing the Fusion_40 for a couple of weeks now, in particular, with 3D >Animation software. I am willing though to relay questions of a technical >nature direcly to them. I would be interested in knowing what they did about the caching issues. I am in charge of the 68040 project here and have found out many interesting things about applications and the assumptions some of them make. In addition, it would be good to coordinate the method of installing the FPSP code such that the various 68040 vendors can just supply the one file they need and have the standard system do the rest. /----------------------------------------------------------------------\ | /// Michael Sinz - Amiga Software Engineer | | /// Operating System Development Group | | /// BIX: msinz UUNET: rutgers!cbmvax!mks | |\\\/// | | \XX/ Quantum Physics: The Dreams that Stuff is made of. | \----------------------------------------------------------------------/
daveh@cbmvax.commodore.com (Dave Haynie) (06/27/91)
In article <1991Jun20.114837.22962@unibi.uni-bielefeld.de> markus@techfak.uni-bielefeld.de (Markus Illenseer) writes: >The US-Company RCS offers the 68040 Card 'Fusion-40' since "now".... >The Processor is working internally with a Tact-Rate of 50 Mhz, though the >external Rate will be 25 MHz. In other words, an ordinary, everyday 68040. All 68040s run with an ALU clock that's twice the speed of the bus clock. The bus clock is the part's rating, which is currently 25MHz and may some day be 33MHz and beyond. >The given 18 Mips is a bit slow, Well, there are MIPS and there are MIPS. You can get a 68040 MIPS rating any number of ways: - Write down the number from the Motorola adds. - Calculate how many [not necessarily typical instructions] per second it'll crank through. - Run any random program for the Amiga that gives you a number it calls "MIPS". - Run Dhrystone 2.1, and divide the result by the number in the charts for a VAX 11/780. >Also it is not mentioned whether the card can be plug into the Processor-Slot >or in a Zorro-II(I) Slot, It will go in the Coprocessor slot. There are two kinds of bus masters in Amiga systems, primary and secondary. The primary bus master can be the on-board CPU, or a device in a Coprocessor slot. Secondary bus masters are on the Zorro bus. The difference is that the primary bus master, which is the default bus master, is responsible for servicing all interrupts and some aspects of bus arbitration. Zorro devices cannot perform these operations. While it's certainly possible to design an OS that can run on a CPU which is a secondary master (with some assistance from the primary master), the Amiga OS is only designed to run on the primary master. -- Dave Haynie Commodore-Amiga (Amiga 3000) "The Crew That Never Rests" {uunet|pyramid|rutgers}!cbmvax!daveh PLINK: hazy BIX: hazy "This is my mistake. Let me make it good." -R.E.M.
menzies@CAM.ORG (Stephen Menzies) (06/27/91)
bdraschk@immd4.informatik.uni-erlangen.de (Bernd Raschke) writes: >menzies@CAM.ORG (Stephen Menzies) writes: >>While I am NOT an employee of RCS, I have been independently testing the >>Fusion_40 for 2 weeks now, in particular , with 3D Animation software. If >>[stuff deleted] >> I've preformed numerous tests (some quite large) with Imagine1.1.... >>have now started with Caligari Broadcast 2.01...and will soon be looking >>at Lightwave.....others to follow. To some extent I've tested ADPro, DPIII, >>and several PD's that I use constantly like Snap1.61 and Browser1.7 (ok). >for (;;) > printf("Post it!\n"); >>--steve >Ciao, > bernd >--- >Bernd 'The Real Arthur!' Raschke |Only // >bdraschk@faui09.informatik.uni-erlangen.de | \\ // Amiga >hartmannstr. 129 8520 erlangen 09131 38244 | \X/ makes it possible > "Wer nicht an Wunder glaubt, der ist kein Realist" Ok, sure. Scene dis: solid color sphere on solid colored ground. Software: Imagine 1.1 Render: Ray-trace with shadows. A3000/25.......................00:20:02 A2000/50MHz GVP 030/882........00:10:59 A3000/Progressive 040..........00:09:15 (Copyback ON) A2000/RCS Fusion-Forty.........00:06:30 (CopyBack ON) Note: this was the *only* test I was able to perform where I was able to make a comparison with the Progressive board. These were the results but I would hardly call one rendering conclusive. --------------------------------------------------- Scene dis: a garden scene (Exploded_Garden). Polygons: 73,104 Software: Imagine1.1 Render: 24 bit Raytrace with shadows. Resolution: 768 x 482 hi-res x=6 y=7 Anti-Aliasing: Full (0) Depth:10 A3000/25.......................32:27:55 A2000/RCS Fusion-Forty.........09:30:00 ..and it may interest some raytracers who like to preview their work in _scanline_ before a final raytrace: A2000/RCS Fusion-Forty (same file,scanlined)...00:13:34 (!) ..for me, this figure is very important. Preliminary scanline rendering can take upto 2x the availiable memory required to raytrace. To scanline this file, I required 22megs (the Fusion40 had 32megs onboard) whereas to raytrace, I only needed 12megs Ram. --------------------------------------------- Better rendering speeds will be possible once software packages have been optimized for the 040. ---------------------------------------------- Presently, I'm working with the Broadcast version of Caligari on the 040. If anyone requires information on Caligari's performance, I should have a good idea within a week or so. Preliminary tests have shown me that Caligari's _Q(uick)Render_ is atleast 2x as fast (compared to A3000/25) and the realtime response of a full (wireframe) representation of the object is much smoother for complex objects. --stephen -- Stephen Menzies Email: menzies@CAM.ORG
bdraschk@immd4.informatik.uni-erlangen.de (Bernd Raschke) (06/27/91)
menzies@CAM.ORG (Stephen Menzies) writes: >Scene dis: solid color sphere on solid colored ground. >Software: Imagine 1.1 >Render: Ray-trace with shadows. >A3000/25.......................00:20:02 >A2000/50MHz GVP 030/882........00:10:59 >A3000/Progressive 040..........00:09:15 (Copyback ON) >A2000/RCS Fusion-Forty.........00:06:30 (CopyBack ON) Seems strange to me. Shouldn't an A3000 040-board be faster than an A2000 version? The CPU slot of an A2000 is 16bit, so the card has to have it's memory on board, while the A3000 card has no own ram and uses the ram on the mainboard. Is that fact responsible for the difference in speed? Ciao, bernd >--stephen --- Bernd 'The Real Arthur!' Raschke |Only // bdraschk@faui09.informatik.uni-erlangen.de | \\ // Amiga hartmannstr. 129 8520 erlangen 09131 38244 | \X/ makes it possible "Liebling, aeh, Sweatheart! What watch?" "10 watch!" "Oh.. such much!"
menzies@CAM.ORG (Stephen Menzies) (06/29/91)
bdraschk@immd4.informatik.uni-erlangen.de (Bernd Raschke) writes: >menzies@CAM.ORG (Stephen Menzies) writes: >>Scene dis: solid color sphere on solid colored ground. >>Software: Imagine 1.1 >>Render: Ray-trace with shadows. >>A3000/25.......................00:20:02 >>A2000/50MHz GVP 030/882........00:10:59 >>A3000/Progressive 040..........00:09:15 (Copyback ON) >>A2000/RCS Fusion-Forty.........00:06:30 (CopyBack ON) >Seems strange to me. Shouldn't an A3000 040-board be faster than an A2000 >version? The CPU slot of an A2000 is 16bit, so the card has to have it's >memory on board, while the A3000 card has no own ram and uses the ram on >the mainboard. Is that fact responsible for the difference in speed? >Ciao, > bernd >>--stephen >--- >Bernd 'The Real Arthur!' Raschke |Only // >bdraschk@faui09.informatik.uni-erlangen.de | \\ // Amiga >hartmannstr. 129 8520 erlangen 09131 38244 | \X/ makes it possible > "Liebling, aeh, Sweatheart! What watch?" "10 watch!" "Oh.. such much!" -----start of RCS reply (verbatum): 1> Maybe; 2> Possible incorrect Cache Controls; 3> The efficient coding of the floating point support package, hand coded by RCS for the Fusion-Forty; 4> Design differences/philosophy. -----end of forwarded RCS reply----- Again, I am NOT an employee of RCS, however I am independantly testing their 040 board with 3D Animation software (in particular). If you have any questions of a technical nature, I am willing to forward your questions to them for a reply. --stephen -- Stephen Menzies Email: menzies@CAM.ORG