Re: MASM Expert needed immediately

"f0dder" <f0dder_nospam@xxxxxxxxxxxxxxxx> écrivait
news:4478bf81$0$67261$157c6196@xxxxxxxxxxxxxxxxxxxxx:

Betov wrote:
f0dder wrote:

Then, write an Assembler that beats RosAsm speed with SSE.

Umm, I must admit I fail to see how SSE would speed up an assembler...
the use of floating-point calculations there is pretty limited.

What i am pointing to, with this (even if this hurts
"Mad_Guy"...), is that in matter of speed i am not
completely naive...


Instead of saying stupidities, ask yourself the reasons why,
after so many years of development, Intel prefered to implement
the SSE joke, rather than making the Strings Intructions faster
(and why AMD did it).

I wouldn't mind seing decently implemented string instructions, LOOP,
et cetera.

What i mind, is that making the Strings instructions fast
does not interrest Intel, AT ALL. What is all of this
about? Speed? Well, let them do faster processor. This is
what they do. So what?

By introducing tons of new instructions Intel and AMD did
nothing but commercial war. At some time they both understood
that they had no way but compromising to keep something
consistant alive, but all of this was commercial war and
nothing else.

Now, using these intructions is something that we sould never
do. Doing so, is pushing the consummers to BUY new PCs if they
want to use such and such program. In other words, playing
the nasty game aside of the majors, and giving a hand to the
Crime&Co.

If they had really wanted to speed up the computers above the
natural speed up, they would have implemented, first, fast
Memory blocks moves, and evidently not fancyful barrils of
instructions designed for saving, in the best case, half of
the time (ridiculous), on Multi-Media.


Betov.

< http://rosasm.org >




.

Relevant Pages

  • Re: Intel SSE sucks dogshit for 3D graphics
    ... > Because they're high latency. ... > latencies of SSE when there isn't all that much to do for any one test. ... don't know why Intel did not include it originally, ... lower instruction latencies on a Pentium-4. ...
    (comp.lang.asm.x86)
  • Re: Did Intel ever develop its own x86-64 a long time ago?
    ... license allowed it to take AMD64, while AMD's cross licence allowed it ... to take SSE. ... For example when Intel added MMX, AMD responded ...
    (comp.sys.ibm.pc.hardware.chips)
  • Re: Did Intel ever develop its own x86-64 a long time ago?
    ... Intel's cross license allowed it to take AMD64, while AMD's cross licence allowed it to take SSE. ... For example when Intel added MMX, AMD responded ...
    (comp.sys.ibm.pc.hardware.chips)
  • Intel SSE sucks dogshit for 3D graphics
    ... I say, it's a lousy, braindead set of instructions for 3D graphics. ... Because they're high latency. ... SSE and SSE2 lack a "sum of scalar fields" instruction. ... Impressive, because the truth is told in each gripe, then Intel labels each ...
    (comp.lang.asm.x86)
  • Re: AMD vs Intel timing on this code...
    ... > It does tend to be processor specific and in particular with Intel ... > hardware, the old string instructions have usually been well off the ... Alex McDonald ...
    (comp.lang.asm.x86)