Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems'

From	Jeff Barnett <jbb@notatt.com>
Newsgroups	alt.windows7.general, alt.comp.os.windows-10, comp.sys.intel, comp.sys.ibm.pc.hardware.chips
Subject	Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems'
Date	2020-07-17 22:06 -0600
Organization	A noiseless patient Spider
Message-ID	<retsfc$rpo$1@dont-email.me> (permalink)
References	(10 earlier) <rvx$q$fknbEfFwwy@255soft.uk> <170720201231335465%nospam@nospam.invalid> <hnf0unFo00aU1@mid.individual.net> <v83OOyp+AlEfFwxc@255soft.uk> <170720202230318530%nospam@nospam.invalid>

Cross-posted to 4 groups.

Show all headers | View raw

On 7/17/2020 8:30 PM, nospam wrote:
> In article <v83OOyp+AlEfFwxc@255soft.uk>, J. P. Gilliver (John)
> <G6JPG@255soft.uk> wrote:
> 
>>>>> I remember - I _think_ it was in the last decade, but it might have
>>>>> been
>>>>> more - being startled when I spoke to a young computing graduate, to
>>>>> find he'd never done any assembler. At that time, after my initial
>>>>> double-take, I thought to myself: the field is big enough, that there'll
>>>>> be plenty of room for him, and in practice he'll probably never have any
>>>>> trouble finding interesting and well-paid employment.
>>>>   there is no need for assembler anymore, except in very rare
>>>> circumstances.
>>>>
>>>
>>> On PCs maybe.
>>>
>>> I bet some embedded stuff for ultra cheap mass market stuff is still
>>> done in assember, or something only very slightly higher level.
>>>
>> Yes. Define "need". Compact code is noticeably more efficient - so runs
>> faster. Yes, for a lot of things, the returns don't justify the effort -
>> for a lot of things that are only done once, or where speed doesn't
>> matter, or - these days - to _some_ extent where modern processor power
>> can hide the inefficiency of the code.
> 
> compact code is not necessarily more efficient. a simple example is an
> unrolled loop, which is less compact yet will run faster. another is
> having a large lookup table versus calculating a value each time.

That depends on the length of the loop body and the number of 
iterations: crossing cache boundaries can extract performance hits. In 
fact, unrolling some loops can punish performance by factors of tens or 
even hundreds. If you carry your argument far enough and force paging 
you may cause arbitrary slow downs. As to look up tables the problems 
are the same. If all the values and indices fit in a small amount of 
storage (i.e. they are COMPACT), well and good. Otherwise all hell can 
break loose.

> however, modern processors are far from simple, which is one reason why
> a compiler can do a better job of optimization than humans can.

Almost always true and more so as the years go by.

> and then there's the issue of portability. anything written in a high
> level language can be recompiled for another processor, normally with
> little to no problem, whereas anything in assembler would need to be
> entirely rewritten from scratch.

Unless you are coding in C or one of its derivatives. There are enough 
places where a C compiler can choose the meaning of an expression (and 
not necessarily consistently) that you have to code in a modest subset 
of the language. And find a compatible compiler for portability.

>> I suspect IrfanView, for example, is mostly coded in either assembler,
>> or at least quite low-level code (or just possibly using an excellent
>> optimiser - which are rare with ultra-high-level languages, such as
>> scripting interpreters).

Scripting interpreters are not a good example of an "ultra-high-level" 
anything. Most are, in fact, among the worst documented, least reliable, 
and least consistent from version to version of any software meant to be 
used by non developers of that software. Of course you may argue that 
they are completely consistent since documentation typically gives no 
serious details of what is supposed to be done in boundary cases.

> it's highly unlikely any of it is in assembler.
> 
-- 
Jeff Barnett

Back to comp.sys.intel | Previous | Next — Previous in thread | Next in thread | Find similar

Thread

Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Yousuf Khan <bbbl67@spammenot.yahoo.com> - 2020-07-14 08:39 -0400
  Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-15 13:42 -0500
    Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Brian Gregory <void-invalid-dead-dontuse@email.invalid> - 2020-07-15 19:48 +0100
    Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Yousuf Khan <bbbl67@spammenot.yahoo.com> - 2020-07-16 09:37 -0400
      Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 14:19 -0500
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Yousuf Khan <bbbl67@spammenot.yahoo.com> - 2020-07-18 12:18 -0400
          Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-18 20:46 -0500
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Paul <nospam@needed.invalid> - 2020-07-18 23:40 -0400
    Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-16 11:35 -0700
      Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-16 13:28 -0700
      Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 16:01 -0500
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "Jonathan N. Little" <lws4art@gmail.com> - 2020-07-16 17:37 -0400
          Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 18:12 -0500
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "Jonathan N. Little" <lws4art@gmail.com> - 2020-07-16 19:31 -0400
              Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-17 01:29 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-17 09:55 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-17 17:52 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "Jonathan N. Little" <lws4art@gmail.com> - 2020-07-17 10:28 -0400
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-16 14:42 -0700
          Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 18:33 -0500
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-16 18:35 -0700
              Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 23:47 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-16 22:35 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-17 02:54 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-17 15:47 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-17 12:31 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Brian Gregory <void-invalid-dead-dontuse@email.invalid> - 2020-07-18 02:18 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-18 02:28 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-17 22:30 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Jeff Barnett <jbb@notatt.com> - 2020-07-17 22:06 -0600
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-17 22:33 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-18 02:09 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-17 22:30 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-17 22:26 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-18 02:09 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Brian Gregory <void-invalid-dead-dontuse@email.invalid> - 2020-07-18 13:04 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-18 11:57 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Brian Gregory <void-invalid-dead-dontuse@email.invalid> - 2020-07-19 16:11 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-18 13:54 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-18 09:51 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-18 11:58 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-18 17:30 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-18 12:48 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-18 18:29 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-17 19:10 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-17 22:29 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-17 14:06 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-17 19:32 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-18 02:21 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-17 22:23 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-18 01:37 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Rene Lamontagne <rlamont@shaw.ca> - 2020-07-18 09:16 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-18 13:57 -0700
                General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-17 15:31 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-17 15:55 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') T <T@invalid.invalid> - 2020-07-17 12:49 -0700
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-18 00:13 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') Brian Gregory <void-invalid-dead-dontuse@email.invalid> - 2020-07-18 02:23 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-18 02:34 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') Char Jackson <none@none.invalid> - 2020-07-17 14:56 -0500
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-18 00:15 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') Andy Burns <usenet@andyburns.uk> - 2020-07-18 10:39 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') T <T@invalid.invalid> - 2020-07-18 14:00 -0700
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') T <T@invalid.invalid> - 2020-07-18 14:07 -0700
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') T <T@invalid.invalid> - 2020-07-19 01:28 -0700
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-19 15:09 +0100
                Re: General ramblings (with some Linux flavouring). (Was: Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems') T <T@invalid.invalid> - 2020-07-20 05:35 -0700
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' nospam <nospam@nospam.invalid> - 2020-07-17 12:31 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-17 01:15 -0500
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Paul <nospam@needed.invalid> - 2020-07-17 02:59 -0400
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-17 10:27 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-17 10:50 +0100
                Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-17 17:20 +0100
      Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Rene Lamontagne <rlamont@shaw.ca> - 2020-07-16 16:04 -0500
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Paul <nospam@needed.invalid> - 2020-07-16 19:08 -0400
          Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Rene Lamontagne <rlamont@shaw.ca> - 2020-07-16 19:06 -0500
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Char Jackson <none@none.invalid> - 2020-07-16 20:33 -0500
              Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 23:49 -0500
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-16 22:36 -0700
          Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Rene Lamontagne <rlamont@shaw.ca> - 2020-07-17 08:45 -0500
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' T <T@invalid.invalid> - 2020-07-17 12:50 -0700
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Paul <nospam@needed.invalid> - 2020-07-17 15:59 -0400
    Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-16 20:17 +0100
      Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-16 15:22 -0500
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' "J. P. Gilliver (John)" <G6JPG@255soft.uk> - 2020-07-16 22:26 +0100
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Char Jackson <none@none.invalid> - 2020-07-16 18:15 -0500
          OT: Disable line wrap for long lines (was Re: Linux founder tells Intel to stop ...) VanguardLH <V@nguard.LH> - 2020-07-17 03:10 -0500
            Re: OT: Disable line wrap for long lines (was Re: Linux founder tells Intel to stop ...) Char Jackson <none@none.invalid> - 2020-07-17 14:46 -0500
        Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-17 09:35 +0100
          Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' VanguardLH <V@nguard.LH> - 2020-07-19 08:19 -0500
            Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' Andy Burns <usenet@andyburns.uk> - 2020-07-19 16:39 +0100
  Re: Linux founder tells Intel to stop inventing 'magic instructions' and 'start fixing real problems' John Doe <always.look@message.header> - 2020-07-15 19:55 +0000

csiph-web