flat assembler
Message board for the users of flat assembler.

Index > Heap > Building a mini-CPU (just wanted to let you know of Logisim)

Goto page Previous  1, 2, 3, 4  Next
Author
Thread Post new topic Reply to topic
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
rocketsoft wrote:
cuote "half a milliionth of a meter"... thats 500nm ...
Quote:
... less than half a millionth of a metre long ...
And still no proof, just words? Hmm ...
Post 29 Jan 2010, 08:22
View user's profile Send private message Visit poster's website Reply with quote
rocketsoft



Joined: 26 Jan 2010
Posts: 189
rocketsoft
look in texts\amdcall.txt
Post 29 Jan 2010, 08:33
View user's profile Send private message Visit poster's website Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
rocketsoft wrote:
look in texts\amdcall.txt
Digital repeaters/amplifiers/squarers have been known about and used for a long time, they are nothing new. And putting them into a binary tree arrangement is not a new idea either.
Post 29 Jan 2010, 08:59
View user's profile Send private message Visit poster's website Reply with quote
rocketsoft



Joined: 26 Jan 2010
Posts: 189
rocketsoft
Well... then it must be something else... like the address addition slowing them down
if every instruction has to wait for the worst case scenario in a ripple-carry adder... that is a carry rippling from bit 0 to bit 31 then u have a mayor bottleneck... and carry look-ahead doesnt work fast either
for that my 4th and biggest discovery can help by speeding up the adder by a factor 6... it simply is a detector on the outputs and the carrys of the adder the detects when there are still changes... when no changes occur for a certain amount of time the carry has stopped rippling so... u can give the next core clock pulse... this means a variable core clock

I looked up "digital repeater" on the net and they all seem to be missing the point
btw driving 1000 or more inputs is very common in a modern cpu
It can be mathemattically proven that, with ideal mosfets(no output capacitance) the theoretical ideal amplification of an amplifier is the natural logarithm (e=2,73)


Last edited by rocketsoft on 29 Jan 2010, 11:18; edited 1 time in total
Post 29 Jan 2010, 10:57
View user's profile Send private message Visit poster's website Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
rocketsoft: What proof do you actually have? Your claim is outrageous. Are you suggesting that all the current, and the past, batch of CPU design engineers have IQs below room temperature? That somehow you have discovered four secrets that no one else has ever thought of? And if your first "secret" (the digital amp thing) is any indication of the quality of other three then I am afraid that you will have nothing new to offer to any of the chip makers.

Ideas are cheap. Implementing ideas is hard. Proving that your ideas are worthwhile is where the money is.

Don't you think it is a little bit greedy to ask to $300Billion when all you have to show is to present some idea from 50 years ago as new? It kind of shows that you really haven't done the necessary background research to backup your claims that you have some worthwhile new ideas.

If you really do have such great ideas then patent them first. This gives you legal protection and allows you to approach companies and license the idea(s) from there. You approached it all backwards, you don't go to companies first asking for money and promise that they can patent them later.
Post 29 Jan 2010, 11:15
View user's profile Send private message Visit poster's website Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
rocketsoft: No one uses a ripple-carry adder or a carry look-ahead adder anymore. These went out of style at least fifteen years ago. There are far better solutions available. Let me help you out a little, search for carry select adder and Kogge-Stone adder.
Post 29 Jan 2010, 11:18
View user's profile Send private message Visit poster's website Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
rocketsoft wrote:
... this means a variable core clock
This is also not new:

http://en.wikipedia.org/wiki/Asynchronous_circuit#Asynchronous_CPU

Since at least 1951. No one will pay $300Billion for old ideas.

Without knowing the history you can't know if you have any new idea, or some old idea that was tried and failed.
Post 29 Jan 2010, 12:09
View user's profile Send private message Visit poster's website Reply with quote
rocketsoft



Joined: 26 Jan 2010
Posts: 189
rocketsoft
Well since your totally missing the point i am not going to bother u anymore... i decided not to patent anything... i dont want money anymore
AMD and INTEL have stupid engineers... that i know for fact
Post 29 Jan 2010, 12:41
View user's profile Send private message Visit poster's website Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
rocketsoft wrote:
AMD and INTEL have stupid engineers... that i know for fact
So what about IBM? TI? ARM? Xilinx? Philips? VIA? NVIDIA? Are they all stupid? Seems like all these companies are hiring the wrong people.
Post 29 Jan 2010, 12:47
View user's profile Send private message Visit poster's website Reply with quote
rocketsoft



Joined: 26 Jan 2010
Posts: 189
rocketsoft
yes, they are all stupid
Post 29 Jan 2010, 17:55
View user's profile Send private message Visit poster's website Reply with quote
Borsuc



Joined: 29 Dec 2005
Posts: 2466
Location: Bucharest, Romania
Borsuc
revolution wrote:
rocketsoft wrote:
AMD and INTEL have stupid engineers... that i know for fact
So what about IBM? TI? ARM? Xilinx? Philips? VIA? NVIDIA? Are they all stupid? Seems like all these companies are hiring the wrong people.
No but they are more interested in profit than "one-time" killer performance, even if what rocketsoft says was possible.

I draw my conclusions from the software world, where open-source projects usually add exotic features a lot faster than big commercial and bloated apps (which takes years of "upgrades" to do so). And seriously, I don't think it's because the software devs for the commercial apps are stupid, not at all... but because improving the app itself is not the main goal, it's profit.

_________________
Previously known as The_Grey_Beast
Post 29 Jan 2010, 19:14
View user's profile Send private message Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
Borsuc wrote:
revolution wrote:
So what about IBM? TI? ARM? Xilinx? Philips? VIA? NVIDIA? Are they all stupid? Seems like all these companies are hiring the wrong people.
No but they are more interested in profit than "one-time" killer performance,
Nonsense. Performance is the one defining feature that CPU makers aim for and advertise.
Post 29 Jan 2010, 23:46
View user's profile Send private message Visit poster's website Reply with quote
Borsuc



Joined: 29 Dec 2005
Posts: 2466
Location: Bucharest, Romania
Borsuc
revolution wrote:
Nonsense. Performance is the one defining feature that CPU makers aim for and advertise.
Intel: "We discovered a method of boosting the frequencies to 100Ghz!!!! This would leave AMD in the dust, hah!"

If they don't price it extremely high... which would mean most people would consider it a high-end product... they will get a sale once maybe (from everyone) and then what? They want constant profits, so they would rather increase the Ghz in steps...

they don't have to beat AMD by a whole lot, for instance... just be a BIT above, that's what leads to profit. Confused

Imagine you can make a processor up to 1 Thz, you and only you... which one leads to more constant profit, gradually increasing (starting with say, 40Ghz) while keeping the competition below you during perhaps a full decade, or just one year, one time, 1Thz processor which everyone buys, but only once?

Marketing...

_________________
Previously known as The_Grey_Beast
Post 30 Jan 2010, 17:33
View user's profile Send private message Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
Borsuc: Can you spell "conspiracy theory"? Hehe, if anyone could make a 100GHz CPU they would be so far ahead of any competition they would become the one any only maker of CPUs and the others would go bankrupt. That would generate far more profits than any possible collusion to depress CPU speeds.

Businesses are formed to make money. The more competition you have the less money you can make. The more unique your product the less competition you have and the sky's the limit on profits.
Post 31 Jan 2010, 01:48
View user's profile Send private message Visit poster's website Reply with quote
Tyler



Joined: 19 Nov 2009
Posts: 1216
Location: NC, USA
Tyler
Quote:

Businesses are formed to make money. The more competition you have the less money you can make. The more unique your product the less competition you have and the sky's the limit on profits.

Can you spell "monopoly"? Razz
Post 31 Jan 2010, 05:58
View user's profile Send private message Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
I prefer this one: "monopoly" Razz

However if no other company can come up to the same level of performance then the term doesn't apply. Otherwise governments would be accused of stifling the market (and, no, governments would have no reason to stifle innovation. Innovation puts their country at an advantage). Anyhow, it is all moot anyway since no one can make such a fast CPU.
Post 31 Jan 2010, 07:20
View user's profile Send private message Visit poster's website Reply with quote
rocketsoft



Joined: 26 Jan 2010
Posts: 189
rocketsoft
My adder is faster than the carry select adder by about a factor 2 (adding 2 32bit random numers)
and even more for when few carry flips are present (like in the address addition)
The DELTA-ADDER RULES
Post 31 Jan 2010, 12:42
View user's profile Send private message Visit poster's website Reply with quote
Borsuc



Joined: 29 Dec 2005
Posts: 2466
Location: Bucharest, Romania
Borsuc
I don't think that's how it works though... why do you think all the processors have so many different price ranges -- I can assure you that the research & development is by far not the reason for the difference in price of processors in the same generation. Usually they share 90% of the development.

Let me put this differently. If you could make a 10% better processor than the competition at the same price, why the hell BOTHER to make it ANY better than THAT? You'll already get massive sales, after all it's better bang-for-the-buck.

You don't have to be hugely ahead your competition, just slightly.

Or think about software, where pricing is dependent solely almost exclusively on development. Why are there multiple "versions" of the same software (usually a "light" version and a "full" version)... why not just price the full at low price so that you're better than the competition who has the "lite" version at that price? Because you would be wasting profits. Just be 10% above, it's enough. No need to be more than that.

Or "upgrades" to newer versions when they could have very well integrated it in previous versions -- but then you wouldn't have been paying again! Most of the time when you upgrade, more than half of the features are crap and you don't even need them.

It's far more profitable to start with Windows NT and end up with Windows XP after a bunch of versions in-between than starting with XP and pricing it a bit more (more initial development, since it's obviously more complex than NT).

_________________
Previously known as The_Grey_Beast
Post 31 Jan 2010, 19:12
View user's profile Send private message Reply with quote
rocketsoft



Joined: 26 Jan 2010
Posts: 189
rocketsoft
i benchmarked my 2.4Ghz Q6600 at 750MIPS
The processor i am working on should achieve 4000MIPS @5Ghz
This is using modern 3ps inverter delay
The benchmark is just my compiler compiling itself... i measured how many instructions were executed and the time it took
Post 31 Jan 2010, 19:54
View user's profile Send private message Visit poster's website Reply with quote
revolution
When all else fails, read the source


Joined: 24 Aug 2004
Posts: 17270
Location: In your JS exploiting you and your system
revolution
Borsuc: Current CPUs are not being held back, I assure you if there were ways to make them run faster the company would jump at the chance to leap ahead of the competition. Do you really think that Apple–IBM–Motorola are deliberately holding back making the PowerPC faster? Do you really think AMD is deliberately holding back making the X4 faster? Do you really think ARM is deliberately holding back making the Cortex faster? If you answered yes to any of those then that does not make sense!

rocketsoft: Proof please. I seriously doubt you MIPS figure for the Q6600. It goes against all the previously published benchmarks by third-party testers. Perhaps Intel deliberately depressed the working of your CPU before selling it to you? Razz
Post 01 Feb 2010, 00:21
View user's profile Send private message Visit poster's website Reply with quote
Display posts from previous:
Post new topic Reply to topic

Jump to:  
Goto page Previous  1, 2, 3, 4  Next

< Last Thread | Next Thread >
Forum Rules:
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
You can attach files in this forum
You can download files in this forum


Copyright © 1999-2020, Tomasz Grysztar.

Powered by rwasa.