Jihad needs scientists
in [Design]
|
From: Phil Carmody on 11 Feb 2007 17:23 kensmith(a)green.rahul.net (Ken Smith) writes: > >Actually, when I was doing such things, I used AAD and AAM quite a > >bit. There were neat tricks in there, but it's been 20 years since > >I've done any significant x86 assembler. > > I did quite a lot of 8086 asm. I used the AAM exactly once that I can > think of. I had to add 32 bit values many times. For every one of you there were a dozen cobol programmers. .... > > If you want to complain here it's not about > >the lack of othogonality, rather the dearth of registers. > >Remember, x86 is thirty years old. > > AX, BX, CX, DX, IS, IP, DS, ES Thats 8 16 bit registers. That > isn't a serious shortage. The fact that you can't use the DS and ES as > would make sense and that the memory operations were so slow made it so > that you always felt short on registers. You're rusty. 7 GPRs plus a stack register. 4 segment registers which are not GPRs at all. Before modern pipelined versions, it was much quicker to use memory operands than loading into a register, working on it there, and writing it back out again. Of course, if you were going to do more than one thing then the overhead of the load and store was amortized, and registers would be preferable. Apart from the big iron, things from a similar era tended to have fewer. Phil -- "Home taping is killing big business profits. We left this side blank so you can help." -- Dead Kennedys, written upon the B-side of tapes of /In God We Trust, Inc./.
From: Ken Smith on 11 Feb 2007 17:54 In article <87ejow2v23.fsf(a)nonospaz.fatphil.org>, Phil Carmody <thefatphil_demunged(a)yahoo.co.uk> wrote: >kensmith(a)green.rahul.net (Ken Smith) writes: [...] >> > If you want to complain here it's not about >> >the lack of othogonality, rather the dearth of registers. >> >Remember, x86 is thirty years old. >> >> AX, BX, CX, DX, IS, IP, DS, ES Thats 8 16 bit registers. That >> isn't a serious shortage. The fact that you can't use the DS and ES as >> would make sense and that the memory operations were so slow made it so >> that you always felt short on registers. > >You're rusty. 7 GPRs plus a stack register. 4 segment registers which >are not GPRs at all. No, I'm pointing out that the segment registers are 16 bit registers that can't be used for normal stuff. They are special purpose but only serving to implement a stupid idea. They could have been just more 16 bit registers. >Before modern pipelined versions, it was much quicker to use memory >operands No, it was "a lot less slow" not "much quicker". The memory operations forced a trip through the ALU. This dragged the speed way down. > than loading into a register, working on it there, and writing >it back out again. Of course, if you were going to do more than one >thing then the overhead of the load and store was amortized, and >registers would be preferable. You had to load the CX register to do a LOOP. -- -- kensmith(a)rahul.net forging knowledge
From: MassiveProng on 11 Feb 2007 19:06 On 11 Feb 2007 23:49:53 +0200, Phil Carmody <thefatphil_demunged(a)yahoo.co.uk> Gave us: >krw <krw(a)att.bizzzz> writes: >> In article <87vei835di.fsf(a)nonospaz.fatphil.org>, >> thefatphil_demunged(a)yahoo.co.uk says... >> > krw <krw(a)att.bizzzz> writes: >> > > In article <87zm7k3a0l.fsf(a)nonospaz.fatphil.org>, >> > > thefatphil_demunged(a)yahoo.co.uk says... >> > > > Care to highlight the major architectural differences between the >> > > > current FSL offerings in the 6800 family to the original processor? >> > > > And on-die serial controllers et al. do not count as part of the >> > > > processor architecture. >> > > >> > > A Core-2-duo will still execute 8088 binaries. >> > >> > My god, do you take not-answering-the-question lessons from BAH? >> >> Why don't you go play with your brother, the dumb donkey? You >> obviously can't make conversation with the adults. > >The capabilities of the X register, you say? No that's the same since >the original design. You were so close. If you'd have mentioned the >Y register then you'd have picked up on something that's only been >the same since 1979, rather than 1975. > >Or were you instead simply devoid of technical content? > >We can all see the answer to that latter question. > The acronym for today is: API
From: MassiveProng on 11 Feb 2007 19:08 On 12 Feb 2007 00:23:00 +0200, Phil Carmody <thefatphil_demunged(a)yahoo.co.uk> Gave us: >kensmith(a)green.rahul.net (Ken Smith) writes: >> >Actually, when I was doing such things, I used AAD and AAM quite a >> >bit. There were neat tricks in there, but it's been 20 years since >> >I've done any significant x86 assembler. >> >> I did quite a lot of 8086 asm. I used the AAM exactly once that I can >> think of. I had to add 32 bit values many times. > >For every one of you there were a dozen cobol programmers. > >... >> > If you want to complain here it's not about >> >the lack of othogonality, rather the dearth of registers. >> >Remember, x86 is thirty years old. >> >> AX, BX, CX, DX, IS, IP, DS, ES Thats 8 16 bit registers. That >> isn't a serious shortage. The fact that you can't use the DS and ES as >> would make sense and that the memory operations were so slow made it so >> that you always felt short on registers. > >You're rusty. 7 GPRs plus a stack register. 4 segment registers which >are not GPRs at all. > >Before modern pipelined versions, it was much quicker to use memory >operands than loading into a register, working on it there, and writing >it back out again. Of course, if you were going to do more than one >thing then the overhead of the load and store was amortized, and >registers would be preferable. Apart from the big iron, things from a >similar era tended to have fewer. > Mortgage your memory! It'll pay off in the end. ;-]
From: unsettled on 11 Feb 2007 21:16
Ken Smith wrote: > In article <OtidnQWNJOAtcVTYnZ2dnUVZ8qrinZ2d(a)pipex.net>, > T Wake <usenet.es7at(a)gishpuppy.com> wrote: > [.....] > >>yes, but I am confused on terminology. With a Windows XP machine, what you >>do call the OS? > > > The Linux on the other partition. A properly installed Linux uses all the available partitions. |