home *** CD-ROM | disk | FTP | other *** search
- Path: nntp.earthlink.net!usenet
- From: psheffield@earthlink.net (Patrick Sheffield)
- Newsgroups: comp.sys.amiga.programmer,comp.sys.amiga.games,alt.sys.amiga.demos,comp.sys.amiga.misc
- Subject: Re: AB3D II beats Quake....
- Date: 29 Mar 1996 23:04:38 GMT
- Organization: Earthlink Network, Inc.
- Message-ID: <1673.6662T802T2273@earthlink.net>
- References: <4jbcno$7m9@soleil.uvsq.fr>
- NNTP-Posting-Host: psheffield.earthlink.net
- X-Newsreader: THOR 2.22 (Amiga;TCP/IP) *UNREGISTERED*
-
- >One of the big problem of the Pentium and 680x0 is that the opcode are not
- >of the same size. 680x0 can have opcode of 2,4,8,10 bytes and x86 can even
- >have opcode of one byte (those compatible with 286).
- >On the other hand, RISC CPU have all their opcode with the same length
- >(usually 32 bits) ; in fact, while RISC was meant to have a Reduce
- >Instruction Set, this is today not that true. RISC is now mostly caracterized
- >by the fact that opcode all have the same size, which allow massive
- >predecoding of the instruction flow. RISC CPU can predecode up to 8
- >instructions in parallel, because they know that every 32 bits there's a new
- >intruction.
-
- >On CISC, it's not possible, because opcode are not 32 bit aligned. This
- >means that before decoding intstruction i, you must decode instructions 0 to
- >i-1.
-
- >This way RISC can also implement powerful branch prediction, which tend to
- >add no overhead whether the branch is taken or not.
- >Such prediction technology are not usable in CISC ; using them would mean
- >adding thousand of transistors that could be used to speed up other
- >instructions.
-
- Very interesting! This would mean that one could get a bit more life out of a
- CISC based instruction set by properly aligning all opcodes (effectively
- padding them all to 32 bits). It would be a bit more memory expensive, but
- then you could take that RISC advantage and design your processor accordingly.
- You'd have to have a loader that set everything up properly, but then you
- could run older programs at much higher speeds without re-compiling.
-
- Why you'd want to go to all that trouble, I'm not sure, but it is an interest-
- ing mental exercise...
-
- Patrick Sheffield
-
-