Xref: utzoo comp.sys.amiga.programmer:4212 comp.sys.amiga.hardware:9822 Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!caen!kuhub.cc.ukans.edu!markv From: markv@kuhub.cc.ukans.edu Newsgroups: comp.sys.amiga.programmer,comp.sys.amiga.hardware Subject: Re: 68040 Compatibility Warning Message-ID: <1991Jun4.111333.31246@kuhub.cc.ukans.edu> Date: 4 Jun 91 11:13:33 CDT References: <22049@cbmvax.commodore.com> <1991Jun1.175626.3234@wintermute.north.de> Organization: University of Kansas Academic Computing Services Lines: 43 >>CopyBack. CopyBack means that when a program writes data to >>memory, it goes into the cache but *not* into the physical RAM. >>That means that if something was to read that RAM and it did not >>go through the data cache on the 68040, it will see old data. >>The two main examples of this are DMA devices and the instruction >>reading of the CPU itself. This means that even if the > Another important case where that mode can be deadly is in a multi-processor > machine. Has Motorola or C= taken any precautions in this direction. It'd be > really nice to run ADos2.0 or SVR4 on two or three processors! Yes. The 040 also has the ability to insure cache coherency with the correct circuitry. If the correct bus interface is used, the 040 can inhibit an access to RAM and supply the correct value on the bus as if it were RAM. This is done by the Data MMU. The 040 can also do bus sniffing, where it watches the bus and updates or invalidates cached data appropriately. This ability assumes that the 040 can see all the cycles on the bus that matter, and this would depend on the card and the interface. If the card takes over the machine and continuously is attached to the bus, then these modes should work, eliminating the need for frequent and costly cache flushes. (When your up to 4K (each) of cache, then your taking a huge performance hit if your flushing the whole thing every time you do DMA). Another compatibility question, do the 2.0 math libraries have the code to handle exceptions from the 040 for the 881/2 transcendental functions that are no longer in hardware on the 040? > Kai > > -- > "I'm beat, I'm torn, Shattered and tossed and worn, Too shocking to see" > BITNET: g14b@dhbrrz41 + UUCP: kaba@wintermute.north.de > Snail: Kai Bartels + Hudemuehler Str. 37 + 2800 Bremen 41 + FRG -- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Mark Gooderum Only... \ Good Cheer !!! Academic Computing Services /// \___________________________ University of Kansas /// /| __ _ Bix: mgooderum \\\ /// /__| |\/| | | _ /_\ makes it Bitnet: MARKV@UKANVAX \/\/ / | | | | |__| / \ possible... Internet: markv@kuhub.cc.ukans.edu ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~