Intel P4 vs AMD

The 955 has a total of 1066 mhz of memory speed to split between the cores making it 533mhz each. Each HT bus runs 2000 mhz. Sophocles Optetron has 3 HT links in addtion to the direct memory controller.
Intel isn't even close.

 

The real world CCE encoding performance is were the AMD really leaves P4 in the dust. In most benchmarks AMD is just faster in degrees comparable to mhz. CCE is the reason I didn't go Intel dual core. Again not even close.

 

Anyone in the electronics industry knows that heat is our greatest enemy. excessive heat ruins transistors resistors diodes, etc etc. Therefore AMD has to be the better choice, because in comparison they run much cooler.

 

What 6402 said. LOL

I thought that I had made the differences in frontside bus clear. And yes brobear if Intel gets the lead and I ready to do a build I'll buy it instead but I fear that may be some time coming. Intel went down the wrong path for too long and wasn't paying attention to what the little Texas company was up to. I have a feeling that AMD has already developed its future CPU's but don't have a reason to release them because they're already ahead and gaining in market share while Intel plays catch
up.

 

The trick for Intel to jump ahead would be to jump on the Hypertransport bandwagon. They are allowed but it would embarrass them so they'll stall and loose time while they figure another route.
They shouldn't have any trouble making a fast processor but again they need to face the end of netburst and produce a top notch native 64 bit x86 compatible processor.
They don't have to go through all the trouble AMD did. Their rescources are bigger to start with.

Or Intel could just continue to advertize mhz and do volume discounts on inferior products. It has worked in the past. But it sucks for competition.

 

New material structure produces world's fastest transistor.


A new type of transistor structure, invented by scientists at the University of Illinois at Urbana-Champaign, has broken the 600 gigahertz speed barrier. The goal of a terahertz transistor for high-speed computing and communications applications could now be within reach.

The new device -- built from indium phosphide and indium gallium arsenide -- is designed with a compositionally graded collector, base and emitter to reduce transit time and improve current density. With their pseudomorphic heterojunction bipolar transistor, the researchers have demonstrated a speed of 604 gigahertz -- the fastest transistor operation to date.

"Pseudomorphic grading of the material structure allows us to lower the bandgap in selected areas," said Milton Feng, the Holonyak Professor of Electrical and Computer Engineering and a researcher at the Coordinated Science Laboratory at Illinois. "This permits faster electron flow in the collector. The compositional grading of the transistor components also improves current density and signal charging time."

Feng and graduate student Walid Hafez fabricated the new device in the university's Micro and Nanotechnology Laboratory. They describe the pseudomorphic HBT concept, and discuss the transistor's high-speed operation, in the April 11 issue of the journal Applied Physics Letters.

The goal of a terahertz transistor was not possible using the previous device structure, Feng said. "To achieve such speed in a typical HBT, the current density would become so large it would melt the components. In our pseudomorphic HBT, we can operate at higher frequencies with less current density. With this new material structure, a terahertz transistor is achievable."

Faster transistors could facilitate faster computers, more flexible and secure wireless communications systems, and more effective electronic combat systems.

Can't wait!!
A 600gig processor? 400gig ram? 200gig GPU?
Sounds like science fiction.But then so did landing on the moon 50 years ago.

http://www.physorg.com/news3662.html

 

yeah but is it really nesserary ,probably not you get to a certian point and its overkill ,like car audio you have systems that can produce 170 db but you cant listen to it that loud so theres no point to do it

 

Just to let all know that i was running a P4 3.4 with 2 Gb ram and have changed to the below listed specs and thier is no comparison , AMD RULES

 

@abbccdd,
No its probably not neccessary,however, mans never ending quest for speed and power will see it become reality one day.I can't honestly see
electronics engineers saying: OK we have achieved 4GHZ,thats fast enough,lets stop there.There will always be someone that wants to go faster

 

yes theres alway the challange ,thats what drives it

 

Sophocles what do you make of this claim. I am not as astute as some of you, but this seems like a extreme claim?

sorry here it is

 

Well yes or we would still me using the 100mgz processors.
Some of you guysmay not know this, but my first computer wes a texas instument(TI) TI99/4a. That's when apple was king of the hill. My next was the Commodore 64. Got online when all it said was LOGIN:

As far as car audio, now here is where my feet is wet. You cannot produce 170 db in ANY car that can be purchased off the lot and then some. Even the tricked out show cars and vans such as Cerwin Vega Pioneer etc. can barely achieave 140 or more. I do agree with 1 thing though you cannot listen to that high (120 or more for very long)! For one thing you eyeballs vibrate so much you cannot see the road.
happy computering!

 

What are they claiming. Conspicuously missing is the name of the CPU that is being discussed. Plus, a lot of the reviews on Newegg can be taken with a grain of salt.

 

baltekmi ,your wrong on that i think the world record is around 175db ,i will try to find some info on that [bold]READ THIS!!![/bold]

Scott Owens, owner of Edge Audio in Phoenix, AZ, wowed everyone at the 2005 MECA Finals in Nashville, TN by hitting the highest score ever recorded in MECA at 179.6 db in his final run Sunday, October 30th. Scott had hit a 179.2 db the day before, setting a record at that point which he eclipsed.

heres the link

http://www.mecacaraudio.com/

 

brobear sorry read it again

 

Sophocles

Seems we agree once again as well as on the fact that AMDs are currently doing better than Intel. I just don't see the overall picture for Intel as being as bad as portrayed. They're still selling processors, even to the custom market, to people who know what they're doing.

MrBass
Thanks for the input on heat. We've noted that on several occasions, but we can't stress the fact enough it seems. That's why companies are making the big bucks for the custom coolers to cool down those performance systems, both AMD and Intel. I think most of us have conceded that AMD is friendlier to custom settings than Intel. At least I've not heard anyone stating Intel's superiority lately.

Sophocles,
Are you going to break down and get the VapoChill to see if you can squeeze a few more MHz out of your system? Liquid nitrogen just keeps diasppearing for some reason.

 

aabbccdd

I am not disputing 170spls, i am sure it can be done or has been done.
But it cannot happen in real world. You cannot produce that must power in a car you use everyday. But we do use our computers everyday and it is a real world.

 

sure you can ,read that link i put up(theres a pic of the van the guy has) you just cant listen to it that loud ,it can be done though ,thats my point

 

no link

 

baltekmi ,your wrong on that i think the world record is around 175db ,i will try to find some info on that READ THIS!!!

Scott Owens, owner of Edge Audio in Phoenix, AZ, wowed everyone at the 2005 MECA Finals in Nashville, TN by hitting the highest score ever recorded in MECA at 179.6 db in his final run Sunday, October 30th. Scott had hit a 179.2 db the day before, setting a record at that point which he eclipsed.

heres the link

http://www.mecacaraudio.com/