Prev: Request for parallel computing books in comp.parallel
Next: Press Release - Reliable Software Technologies, Ada-Europe 2010
From: Peter Flass on 8 Jun 2010 06:43 Georg Bauhaus wrote: > On 6/8/10 8:27 AM, James J. Weinkam wrote: > >> Nevertheless, it remains true that the assembly language programmer who >> knows what he is about has complete control over the binary code >> generated, although I would venture to say that few, if any, assembly >> language programmers think of what they are doing in those terms most of >> the time. > > Would this control include control over pipelines, parallelism, > and possibly translation of assembly instructions to microcode? > Probably more so than with a(n) HLL. For example, if you're concerned about it, you can organize instructions to maximize parallelism.
From: robin on 8 Jun 2010 07:10 "Shmuel (Seymour J.) Metz" <spamtrap(a)library.lspace.org.invalid> wrote in message news:4c0cbfba$6$fuzhry+tra$mr2ice(a)news.patriot.net... | In <4c0bbadb$0$34203$c30e37c6(a)exi-reader.telstra.net>, on 06/07/2010 | at 01:12 AM, David Frank <robin51(a)dodo.com.au> said: | | >What don't you understand about the publication, | >"Automatic Digital Computation"? | | Its relevance. It has the documented evidence of numerical programs performed BEFORE FORTRAN and ALGOL. | >With that information, most people can find the publication and read | >it. | | So can you. The last time that I went through that exercise, it turned | out that you had lied. I don't lie. If anyone is lying it's you. You haven't povided any documentary evidence to back up your silly claims.
From: robin on 8 Jun 2010 07:16 "Peter Flass" <Peter_Flass(a)Yahoo.com> wrote in message news:hujp34$m4p$1(a)news.eternal-september.org... | That's it. I believe it was an IBM 704, although probably other old | computers used them also. Drums were popular as storage on systems, | even with disks, because, being head per track, they were much faster. | They were often used as a swap medium. Some drums were head-per-track. Those on the Pilot ACE (and ACE too, I think) and DEUCE had moving heads for their drums.
From: glen herrmannsfeldt on 8 Jun 2010 08:03 In comp.lang.fortran James J. Weinkam <jjw(a)cs.sfu.ca> wrote: > Your point is well taken for machines of the 60's and 70's, > at least for the IBM ones with which I am most familiar. > For example in 360 assembler, if you wanted to add two numbers > you had your choice of A, AR, AH, AP, AL, ALR, AE, AER, AD, > ADR, AXR, AU, AUR, AW, AWR and maybe a few more that I have > forgotten. There was a one-to-one correspondence between each > of these mnemonics and their corresponding numerical op codes. > The assembly language programmer had to choose the correct > mnemonic instruction to suit the circumstances. (snip) And note that the hex value for the opcode for many of those add instructions has A for its low digit. Also, the divide instructions have D for their low hex digit. Subtract and multiply come in between, with B and C. Starting with S/370, some instructions have a two byte opcode. There are now even more add instructions with 64 bit operations in z/Architecture, AGR, AGFR, AY, AG, AGF, add logical with carry ALCR, ALCGR, ALC, ALCG, IEEE binary floating point operations AEBR, ADBR, and AXBR, and finally decimal floating point instructions ADTR and AXTR. -- glen
From: Peter Hermann on 8 Jun 2010 08:26
In comp.lang.ada J. Clarke <jclarke.usenet(a)cox.net> wrote: > working with assembler but in my day it was a 1:1 correspondence--you > knew exactly what binary each assembly language instruction would emit, in the zenith of Assembler (-: i.e. after your time :-) we had macros which could produce hundreds of statements with one stroke... |