Re: duplicate ops (Re: updated assembler)


"wolfgang kern" <nowhere@xxxxxxxxxxx> wrote in message
news:f1fdut$4gh$1@xxxxxxxxxxxxxxxxxxxxxxxx

"cr88192" wrote:

[HW-drivers]
64-bit drivers: that is the problem we have now,
the OEMs are simply not bothering at this point...

Unfortunately right.
And I add: "if we could have just the needed information"
then we could write the drivers ourself regardless for which OS ever.


yes.


Are these new addon-cards designed by robots and nobody knows how they
really work internal ?? (is the former utopic future already present?)


who knows...


[emulation and speed...]

It will depend on the ratio between CPU/BUS-speed and HW-requirements.

My fast line cameras need IRQ-response within a few nanoSec to keep the
frames stable and in synch with real time. So if I like to use it without
any expensive extra hardware (driver chip and huge,fast buffers) it needs
at least a 2 GHz CPU and a 200 MHZ BUS running unprotected (all ring0).

So a factor *5 wont do it here, but granted this is a special task anyway.


yes.

in any case, slow hardware would still be better than no hardware...


I figured more recently, that since we are only simulating a small piece
of (presumably relocatable) code, we only really need to allow such a
table for "executable" memory, and not a full 4GB address space.
this leads to a much smaller array.

Yes, for not top speed hardware your approach may be fast enough.

But think of IRQ9 driven direct screen (ie: 100Hz/100KHz 1024*768*8/32)
display, a delay of ~13 nanoSec will produce a one dot blurring.
Looks like this IRQ9 method isn't used anymore because windoze's
hardware treating takes too much time even on >2GHz machines.


yes, that is a problem...

most of the crap that usually needs emulation anyways though is things like
network cards (video cards tend to have better support, and even the crappy
old fallback support of VESA...).


one thing that would also be nice (but is unrealistic):

at least some bus-side standardization of HW interfaces, so that most
generic features of a paricular piece of hardware can be supported without
knowing the specifics (like PCI, but much more involved).

basically, not only the bus is standardized, but many common pieces of
hardware, which are used as design templates (with specific vendors going
over this, but keeping baseline compatibility if at all possible).


in cases where this has existed: ATA, ATAPI, ... the results have been very
good.

RTL8139 has become de-facto for 10/100 ethernet cards, but not for Gb.

....



[side talk..]
I think I need a newer motherboard.
...
dunno, any one else have issues with the NForce3 150 or 250?...

Sorry, due to lack on information I'm bound to S3 and ATI graphics.


no, this is my motherboard chipset.
seems boards using the NForce3 250 are still being sold, but I don't know if
they have since fixed this problem, whatever it may be...


Perhaps another problem with BUS-timing or wrong PCI-config on
HW where neiter BIOS nor the OS knows about how to ... ?


dunno.


...
newer boards seem to demand PCI-E cards afaik.

My newest (AMD64, bought this year) still got an 200 MHz AGP-slot,
but I never buy brand-new brands, I always let others test it first :)


looking around recently, some boards still use AGP, this is good, maybe.

feeling tempted by this:
Athlon X2, AM2, or such...;
some or another MOBO;
2-4GB/ram (ram is fairly cheap vs other things it seems, but it is a
speed/cost/capacity tradeoff, me more biased twards capacity than speed);
new video card (the ones I am using are rather dated now);
....


when?
dunno...

total cost?
dunno, depends.
maybe somewhere around 600-800 for the parts I want (or, at least, this is a
"reasonable" budget).

(of course, personally, I could use more money in the bank as well, if I
payed for it myself this would be a not exactly minor dent...).


__
wolfgang





.

Relevant Pages

  • Re: What ever happened with hardware decoding?
    ... Are there any video cards that support full h/w assist decoding? ... >> I am curious if anyone knows why there is no hardware decoding with MCE. ...
    (microsoft.public.windows.mediacenter)
  • Re: duplicate ops (Re: updated assembler)
    ... like network cards (video cards tend to have better support, ... and even the crappy old fallback support of VESA...). ... hardware, which are used as design templates (with specific vendors going ... :) Oh yeah, unfortunately money wont grow on trees ... ...
    (alt.lang.asm)
  • Re: duplicate ops (Re: updated assembler)
    ... like network cards (video cards tend to have better support, ... and even the crappy old fallback support of VESA...). ... generic features of a paricular piece of hardware can be supported without ... DirectX was once annonced to become the missig link, ...
    (alt.lang.asm)
  • Re: halo help
    ... 99.99% of Chipsets do not have Hardware T&L support. ... That game requires a video card with Hardware Transform ... SiS Video Cards ...
    (microsoft.public.games)
  • Re: rt20 scheduling latency testcase and failure data
    ... The system was under heavy network load for some of the time, ... # Firmware Drivers ... # ACPI Support ... # ISDN4Linux hardware drivers ...
    (Linux-Kernel)