Re: Vectors (cpu type idea)


"Wolfgang Kern" <nowhere@xxxxxxxx> wrote in message
news:g6c3cp$ver$1@xxxxxxxxxxxxxxxxxxxxxxxx

"cr88192" wrote:
...
Lowest level coding doesn't neccessarily mean 'simple',
but it can avoid delays like useless paranoid protection
and weird code detours given by HLL-abstractions.

I had meant here:
big winding complicated code.

for example, consider the big complicated mess that is BSP generation,
portal generation, and visibility culling, vs the much simpler "just draw
everything" route.

all of the BSP-related code is complicated and ugly, but does tend to run
faster...

What I saw so far, in the AMD/ATI register set description, looks
'complicated enough' and it will need detailed study to figure
out best fitting structure organistaion.
But I think it will perform much faster with low level coding.


I have not looked into the low-level details yet.


[GL vs. DX]
Yeah, and I think at least hardware drivers should be written at lowest
level, even windoze may have problems with direct hw-access.

this is a tradeoff.
for example, often lower-level access is harder to optimize...
with a higher level of abstraction, often a lot more room is given to the
implementation to figure out how to best optimize things, wheras with a
lower level of abstraction, it is up to the asumption that the input code
is already fairly well optimized.

There might be optimising tools around, but I'm confident sure that I
could do it shorter/faster/smarter in machine code if I had all info.

By 'input code' you mean the GPU-commands (instruction/parameters) ?


I meant, in general.

input code I indirectly meant, the code being written by the developers.
for example, if we write in assembler, then the efficiency is often limited
by said assembler code (if the coder isn't very skilled, or the system
architecture changes, the code is no longer so efficient...).


if we write in C, then optimizability and portability somewhat increase (in
many cases, the compiler can adjust to features or shortcommings of the
target, and the demands on the developer are lower).

if we target system libraries, rather than hard-coding everything, then
improvements made to the libraries silently benefit the apps that use them,
....

....


[AGP .vs VESA..] ok
[single chip...] ok

[future CPU...]
these early stages are mostly represented by the gradual transition to
multithreading and concurrent programming.

Yes,
MP with isolated busses (in addition to the shared bus) wouldn't
much suffer on concurrency or lock/block issues.


yep.


for example, my physics engine is now being altered to follow a
multithreaded design, and is adding some features for concurrent message
passing. one minor issue is how to do this without some possible
performance > impact due to competition and locking issues.

Performance penalties depend on the multithreading model and OS features,
ie: my OS allow all actual instances to direct communicate which each
other, share data and read global system flags at any time.
So there can't be any concurrency, because the OS decides the 'when'
and only switches if a certain part of a thread is finished and never
somewhere inbetween.


well, I am dealing with windows and Linux, which have preemptive
multithreading, and make use of mutexes.

I am doing inter-thread communication via message queues (represented as
streams of values stored in arrays...).


[the walking stove...] ok
[power..]

For future power issues I'd pray:
'may Lord Light be on our way and protect us!'

I don't think the current petroleum issues will be a killer,
more just a bit of a setback humans have gotten themselves into.

my thought is that in not too long, people will have largely transitioned
to biofuels and nuclear reactors, but these have tradeoffs. fuels (oils,
alcohols, ...) have a generally high energy density, and are easy to
transport, but are difficult to produce.

I think the fusion generator above our heads got enough power for
all our needs and may last for 'some' time.


the problem is getting it in usably large amounts...

biofuels typically rely on solar anyways, but the volumes are more limited
(more fuel means bigger facility, ...).


nuclear can be very productive and very cheap, but for whatever reason many
people are afraid of it (especially breeder reactors and likewise).

China, India, and Japan use large amounts of nuclear power (uncluding
breeder reactors) with no real problems. even the soviets only had a few
problems, and they were pioneering many of these technologies, while making
use of minimal safety and poor workmanship.

I still personally believe that nuclear is likely to be both the safest,
cleanest, and most economical option, and we have enough nuclear fuel (if we
include U-238, Plutonium, Thorium, ...) that there is no danger of running
out (only that many people in the US and Europe are afraid of anything that
isn't the ultra-rare U-235, which then they only burn a small amount of it
and try to discard the rest, in a show of pure inefficiency...).

for example, of all companies, Hitachi is making liquid-Sodium cooled
breeder reactors, why should the US be so damn afraid?...


Hydrogen could be the key, create it with solar-panels or similar
natural 'tools' (plants/bacteria may know better than silicon).
Then first burn it, feed motors or O-H cells with it, and after that
reuse (we may even drink) the resulting waste.


burning oxygen and hydrogen tends to produce some small amount of peroxide
in the waste as well, so drinking it directly may not be entirely safe
(distilation or passing it through an organic filter would probably
react-out the peroxide though), but then again, there are much less safe
things around...


[Batteries]
When I look at a toy of my son (battery powered helicopter)
this tiny accus can store immense power and reload really fast.
Recently I had to replace the accu in my mobile phone and wondered about
a four times larger capacity for only half the price as for the previous.

Electrical cars are available and aren't too bad on milage/load.
We just haven't enough reload/replace stations yet.
Another idea is to have power-rails on highways...


yes, however, if we consider how much power usage an android is likely to
have, and existing battery capacities, the batteries would likely be fairly
decent size (say, a decent chunk of the torso), and may only allow the thing
to run for a time measurable in hours (one would have to be sure to recharge
their android often).

I would think, ideally, the think 'should' be be able to run a few days or
weeks or more if needed without reflueling or recharging...

none the less, lithium ion and NiMH batteries are still a lot better than
lead acid (which would likely be pitiful, largish lead-acid batteries unable
to even keep my damn desktop running for any reasonable amount of time...).


in general, liquid fuels could be the most practical means of energy
storage > (and, an android being human-like, could possibly justify using
much of its
body volume as fuel storage). as noted though, the body would need to be
designed in such a way as to prevent the thing from burning violently if
ignited.

Don't say this too loud, future terrorists may read us...
liquid gas ie: hydrogen holds a vast amount of burnable power.


hydrogen though, would need to be stored in pressurized tanks.

but, yes, a hydrogen-based fuel storage would offer a good deal of energy
capacity (vs current litium-ion batteries), but as can be noted, would still
need either a small engine or fuel cells (likely to remain expensive), to
convert it back to electricity.

also, as a detractor, electrolysis is not a very efficient way of producing
hydrogen (so, a better option may be needed). for example, I had read before
of someone pulling off higher-efficiency water cracking with microwaves, so
efficient production could be possible.


[the self repairing android solder...]
plagiat! :) mother Nature's invention ...

[interesting ideas ...]
We will see many failed attempts to create human like machines before
a 'temporary final' solution brings us back to where we once started.
The design of current humans took nature several aeons, perhaps computers
can help to shorten the evaluation time now.


possibly...


fuel cells would be better, if they can be made to work effectively with
liquid fuels (and be made cheap enough...).

I'm sure they can be made effective and cheap as well, but the obstacles
for more research are the big oil companies and their brothers in greed.

yes, that is possible...


__
wolfgang





.

Relevant Pages

  • Re: Vectors (cpu type idea)
    ... (more fuel means bigger facility, ... reuse the resulting waste. ... lead acid (which would likely be pitiful, largish lead-acid batteries ... I look one more time on how Nature decided to power us. ...
    (alt.lang.asm)
  • Re: Mike K. still doesnt get it
    ... portable generator made a different noise when you used less power, ... thing as a massively distributed power network. ... is used to reduce the amount of power into the grid - but the turbines ... they are still burning fuel. ...
    (rec.martial-arts)
  • Re: Mike K. still doesnt get it
    ... portable generator made a different noise when you used less power, ... thing as a massively distributed power network. ... is used to reduce the amount of power into the grid - but the turbines ... they are still burning fuel. ...
    (rec.martial-arts)
  • Re: Vectors (cpu type idea)
    ... here, I use some lead/acid batteries, and really the capacity/volume/weight ... if, say, the torso could store approx 6L of fuel, we would have around 45MW, ... We got a nuclear power plant in Austria since many years, ... many people are terrified of breeder reactors (in a worst-case scenario, ...
    (alt.lang.asm)
  • Re: Could this be done? (engine mod, remove two pistons)
    ... It takes a certain amount of fuel burned to create sufficient power to ... Four cylinders will use a certain amount of fuel per cylinder to move ...
    (rec.autos.tech)