SledgeHammer - 100 Million transistors.

[IIB]

I listened to AMDs 1st q' earnings reprot meeting, where AMDs chairmen JS the 3rd said AMD had sampeled its Sledgehammer processor a device which contains 100 Million transistors.
so I guess AMD will be overtaking Intel on moore's law as the Sledgehammer will have the highest transitstor count of all x86 processors when it ships...

he also said AMD had working single and dual Hammer systems. and that the chance AMD will ship hammer q4' are "High".

Duron will not make the shift to 130 nano meter production and will die out as the year go on...


This post is best viewed with common sense enabled<P ID="edit"><FONT SIZE=-1><EM>Edited by iib on 04/18/02 04:00 PM.</EM></FONT></P>

 

[AMD_Man]

At the rate we're accelerating, we'll have a 1 trillion transistor processor in 20-25 years!

AMD technology + Intel technology = Intel/AMD Pentathlon IV; the <b>ULTIMATE</b> PC processor

 

[IIB]

if things go according to moore's law then we should have a trillion transistors processor within 4.5-6 years.
the law states that transistor count will multiply evry 18 months.

This post is best viewed with common sense enabled

 

[Matisaro]

if things go according to moore's law then we should have a trillion transistors processor within 4.5-6 years.
the law states that transistor count will multiply evry 18 months.

double, not multiply.

A trillion is 1,000,000,000,000. It is a thousand billion. A trillion
is a thousand times a thousand times a thousand times a thousand.

1billion now
2billion 18 months
4billion 36 months
8billion 54 months
16billion 72 months
32billion 90 months
64billion 108 months
128billion 126 months
256billion 144months
512billion 162 months
1024billion (just over a trillion) 180 months



180 months from now, we will have a trillion transistors on a die, according to moores.

that translates into 15 years, so you both are wrong.


This concludes the math lesson.

The Cash Left In My Pocket,The BEST Benchmark

 

[AMD_Man]

that translates into 15 years, so you both are wrong.

My bad, I didn't actually calculate it. :tongue:

EDIT: Wait a second, I am right! We're not at 1 billion transistors right now! We're at approx 100 million!

AMD technology + Intel technology = Intel/AMD Pentathlon IV; the <b>ULTIMATE</b> PC processor

 

[Matisaro]

Who said a billion and screwed me up, bah!

Ok, let me check again.



The Cash Left In My Pocket,The BEST Benchmark

 

[tnadrev]

a billion (us) is 1000 million, or 1,000,000,000 (9 zeroes) we have 100,000,000...

a trillion? 1,000,000,000,000 (12 zeroes)
T(t)=1E8*1.0393^t
... t = 239 months...

(dont forget that million and billion are bigger in the british system, 1 with 12 zeroes, and 1 with 18 zeroes respectively)

(bb || !bb) - Shakespeare

 

[tnadrev]

which is 19 years, 11 months

(bb || !bb) - Shakespeare

 

[Matisaro]

New figures


100million now
200million 18
400million 36
800million 54
1.6billion 72
3.2billion 90
6.4billion 108
12.8billion 126
25.4billion 144
50.8billion 162
101.6billion 180
203.2billion 198
406.4billion 216
812.8billion 234

and add 6 months for the ~200billion to go(1/4)

240 months which is 20 years, which makes amd_man correct DING DING DING DING!

The Cash Left In My Pocket,The BEST Benchmark

 

[tnadrev]

but also... hammer is not out yet... add 6-8 months,
20 years and 5-7 months

(bb || !bb) - Shakespeare

 

[AMD_Man]

How many transistors does the GF4 have?

AMD technology + Intel technology = Intel/AMD Pentathlon IV; the <b>ULTIMATE</b> PC processor

 

[tnadrev]

i am 99% sure it is ~63 million

(bb || !bb) - Shakespeare

 

[xxsk8er101xx]

bool Joke = true;

if(JOKE == true){

hmmmm...

eh well the department of defense doesn't know where 1.2 trillion dollars went.

Amazing how we can't comprehend trillion. Not mocking. It is a huge number. cos a trillion transisters will melt a hole in the fabric of space and time. ;p
}

The observation made in 1965 by Gordon Moore, co-founder of Intel, that the number of transistors per square inch on integrated circuits had doubled every year since the integrated circuit was invented. Moore predicted that this trend would continue for the foreseeable future. In subsequent years, the pace slowed down a bit, but data density has doubled approximately every 18 months, and this is the current definition of Moore's Law, which Moore himself has blessed. Most experts, including Moore himself, expect Moore's Law to hold for at least another two decades.

<b>Just so you know doubling means the same as <i>multipling</i> by TWO (A * 2) ='s Doubling. So he was right just he didn't use the word you could understand. He could have made it clear he meant multipling by two however.

So that concludes the math lesson.

<A HREF="http://www.anandtech.com/mysystemrig.html?id=9933" target="_new"> My Rig </A>

 

[tnadrev]

he WAS doubling?
(speaking of millions and trillions, i beleive this is my 200th post... humbling...)



(bb || !bb) - Shakespeare

 

[Matisaro]

Just so you know doubling means the same as multipling by TWO (A * 2) ='s Doubling. So he was right just he didn't use the word you could understand. He could have made it clear he meant multipling by two however.

Yes, but while doubling can ONLY mean x2, using the term multiplying, while also making a guess of 6 years, means that the person was incorrect(not doubling but using a higher factor).

End of discussion/logic lesson.

The Cash Left In My Pocket,The BEST Benchmark

 

[tnadrev]

also, is it cheating, having the on die memory controller?

(bb || !bb) - Shakespeare

 

[Matisaro]

The controler and large cache makes up most of those transistors, but its still the cpu die, not cheating.

The Cash Left In My Pocket,The BEST Benchmark

 

[xxsk8er101xx]

Congrats on your 200th post!

<A HREF="http://www.anandtech.com/mysystemrig.html?id=9933" target="_new"> My Rig </A>

 

[xxsk8er101xx]

no it just means he is really bad at math

<A HREF="http://www.anandtech.com/mysystemrig.html?id=9933" target="_new"> My Rig </A>

 

[peteb]

The other point from this is he did say

that the number of transistors <b>per square inch</b> on integrated circuits had doubled every year since the integrated circuit was invented

Now this, to the thread in general, does not mean the cpu transistor count has to double, merely that it has to double per sq inch. i.e. if die sizes shrink, then the overall number of transistors does not have to double....

data <b>density</b> has doubled approximately every 18 months

<edit>

Ironically then this means that the Tbred is still technically a continuation of Moore's law, since it represents a higher density of transistors. The die shrink to 80sqmm even with the same number of transistors is a qualify.

So, processors could, by that definition, continue to shrink through .13, .09 and wherever possible, without changing architecture and still obey Moore's law....?

<EDIT2>

Okay, the original paraphrased quote from Intel, who should know quite frankly...

Gordon Moore made his famous observation in 1965, just four years after the first planar integrated circuit was discovered. The press called it "Moore's Law" and the name has stuck. In his original paper, Moore predicted that the number of transistors per integrated circuit would double every 18 months. He forecast that this trend would continue through 1975. Through Intel's technology, Moore's Law has been maintained for far longer, and still holds true as we enter the new century. The mission of Intel's technology development team is to continue to break down barriers to Moore's Law.

If anyone can be bothered to read his original paper, it is <A HREF="http://www.intel.com/research/silicon/moorespaper.pdf" target="_new">here</A> !

So all my above pontification about density is nonsense, and Moore's original 'law' and paper referred to components per IC, not density, so xxsk8er101xx, your quote may have been a little inaccurate.


-* <font color=red> !! S O L D !! </font color=red> *-
To the gentleman in the pink Tutu<P ID="edit"><FONT SIZE=-1><EM>Edited by peteb on 04/19/02 00:42 AM.</EM></FONT></P>

 

[xxsk8er101xx]

possibly inaccurate but not necassarly wrong.

btw that smartass remark was just to fun for me and i couldn't hold myself back. Don't take it personal. Us new yorkers have a hard time holding smartass remarks back. It's like second nature.

<A HREF="http://www.anandtech.com/mysystemrig.html?id=9933" target="_new"> My Rig </A>

 

[peteb]

I'll look forward to it because I'm flying into JFK on Saturday.

I certainly have no intention of turning this thread into a dictionary contest either, so I'll leave the whole inaccurate/wrong thing alone.

-* <font color=red> !! S O L D !! </font color=red> *-
To the gentleman in the pink Tutu

 

[ksoth]

One thing I read is that current CPU design (silicon transistors) will hit a brick wall at a certain size/transistor count. You can only get the transistors so close together. Let's check some math here...

At .25 micron the Athlon classic had 22 million transistors and a 184 square millimeter (sm) die size, or 119,000 transistors per sm. The shrink to .18 micron dropped that die size to 105 sm, or 209,000 transistors per sm. At .18 micron the Palomino had 38 million transistors and a die size of 128 sm, or 296,000 transistors per sm. At 0.13 micron the Thoroughbred will have 38 million transistors and a die size of 80 sm, or 475,000 transistors per sm. The rule seems to be that for every 28% process shrink (.25 to .18, .18 to .13), you get about 1.6-1.75 times as many transistors per square millimeter. For the Pentium 4, it comes out to be 2 times as many transistors per square millimeter for that die shrink. Let's be generous and make that 2.5 times as many transistors per sm for every 28% die shrink, allowing for future technologies.

So, for every 28% micron shrink, you'd get thrice the transistors per area. So starting at 475,000 transistors per sm at .13, another 28% drop to .09 micron would yield 1,062,500 transistors per sm. A 28% drop to .065 micron would yield 2,656,250 transistors per sm. If we continually drop the size to size to .01 micron (7 "steps" of 28% from .13 micron), you'd get about 290,000,000 transistors per square millimeter.

With that number, a 1 trillion transistor count chip at 0.01 micron would then be 3,500 square millimeters in size!!!!!!! That's nearly an 2.3 inch by 2.3 inch die size, which really big and pretty impossible. Now, let's srink the process down to 0.005 micron you'd then have still have a 555 square millimeter die size, or 1 inch by 1 inch, which is still pretty huge.

This is interesting, and doesn't bode well for a 1 trillion transistor chip in 20 years. Of course these number's aren't perfect, but I think they're pretty good, and probably pretty accurate, if not a little too generous. In 20 years time, we probably will have abandoned silicon transistors and replaced them with chemical, DNA, or quantum computers.

But, just to show you how greatly these numbers can vary, if 2.5 time was changed to 2 times, the die size at .01 micron would be 5 inches by 5 inches (16,450 sm) and at .005 2.5 inches by 2.5 inches (4,100 sm). However, if it were 3 times instead of 2.5 times the die size at .01 micron would be 1.25 inches by 1.25 inches (1,000 sm) and at .005 micron it would be 111 square milimeters, which would work just fine.

Any thoughts, corrections, additions?

"Trying is the first step towards failure."

 

[juin]

listened to AMDs 1st q' earnings reprot meeting, where AMDs chairmen JS the 3rd said AMD had sampeled its Sledgehammer processor a device which contains 100 Million transistors.
so I guess AMD will be overtaking Intel on moore's law as the Sledgehammer will have the highest transitstor count of all x86 processors when it ships


1 that a claim and not a fact
2 Also intel try to go at the 100 millions mark and 3 GHz before 2003.
3 That sledgehammer and not clawhammer so for 03 Q2.

cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie

 

[AMD_Man]

What a party pooper! Who cares who gets to 100 million first? Please don't make this another AMD vs. Intel thread.

AMD technology + Intel technology = Intel/AMD Pentathlon IV; the <b>ULTIMATE</b> PC processor