Is Moore's Law Still Relevant?

[Guest]

Intel's new tri-gate transistor, or 3D transistor, is already praised as the most significant innovation for microprocessor architectures in years.

Is Moore's Law Still Relevant? : Read more

 

[Zeh]

I believe this trigate technology is getting a bit overestimated, altough I truly wish I'm wrong.

 

[cbrownx88]

As long as it can pay Crysis and fit in my pocket?

 

[jprahman]

I doubt it's overestimated. If the claims that Intel makes are true then it will be pretty significant improvement, although the biggest gains will likely be in terms of reduced power consumption. I doubt performance will rise massively because architectural improvements are what bring about the greatest improvements in performance, not improved transistor designs, although, the higher clock speeds that tri-gate transistors enable will still have some impact on performance.

 

[silversurfernhs]

i think the new smart phones, netbooks, SSDs and tablets threw a wrench into it...

 

[bugo30]

Now Intel is dealing with ARM and an army of chip designers

an ARMy of chip designers?

 

[tommysch]

[citation][nom]cbrownx88[/nom]As long as it can pay Crysis and fit in my pocket?[/citation]

The real benchmark is: Can it play Crysis at 5760*1080 in 3D?

 

[cyprod]

My question is, has Moore's law ever been relevent? Granted, I do software, but I play at all levels from firmware on up and at no point in my day does the question as to how many transistors something has ever come up. The hardware people never mention it either. The things that matter, die size, power consuption and functionality provided. Transistor count seems more of a pissing match than anything. I mean, being a software guy, I could code algorithm X in 10 clever lines of code, or I could do it in 50 lines without much issue. I could probably stretch it to 100 lines if I was clever. Transistor count is similar. Who cares about how many transistors. It's just an interesting statistic, nothing more, nothing less.

 

[NightLight]

I think this is a significant step forwards! It's like adding another story to your house. This invention will be around for years to come. Well done intel.

 

[fazers_on_stun]

First of all, I disagree with the statement that Netburst was a 'dead end' - the architecture incorporated many novel ideas which are now being recycled in Sandy Bridge and in Bulldozer. While it was not as good performance-wise as AMD's K8 (due to too much leakage so that the clocks never got up to '10GHz', plus the branch prediction was not up to snuff for the 32-stage pipeline), it was ahead of its time. I suggest reading Kanter's analysis of both Sandy Bridge architecture http://www.realworldtech.com/page.cfm?ArticleID=RWT091810191937&p=1 and Bulldozer architecture http://www.realworldtech.com/page.cfm?ArticleID=RWT082610181333&p=1 for more information.

Second, transistor count does correlate to capability. Sure you could have some lousy design where a particular circuit uses 10,000 transistors while a good design uses only 2,000, same as in software coding. But assuming a similar degree of optimization, a CPU with 1 billion transistors will usually outperform (or be more capable) than one with a mere 500 million of the same transistors (i.e., same process node and characteristics). For example, in heavily-threaded loads a quad-core will usually outperform a dual core.

However I do think that Moore's law (process shrink) is in the realm of diminishing returns, as is core-count and architectural changes. What we need is some breakthrough, out-of-the-box design - graphene transistors, quantum computing, neural networks, even true trinary logic instead of binary. Trouble is, binary silicon designs are where all the expertise and money is, until it butts up against a dead end..

 

[Guest]

Intel have been making pathetick AMD style CPUs for few yeara. I had 3.4GHz Pentium 4 6 years ago. Now I have just bought i7 2600K wchih is stupid Athlon style name for i7 3.8GHz... just 400MHz faster than i have 6 years ago. I had also pathetic 3.33GHz Core2 Duo E8600. It was slower than my P4, but just a litle bit and I bought it because of new motherboard features. Where are times when CPU were known by its speed 386DX 40MHz, 486DX2 66MHz, Pentium 100MHz, Pentium 200MMx, Pentium II 300MHz, Pentium III 450MHz, Petium III 700MHz, Pentium 4 1.6GHz, Pentium 4 2.8GHz and finally Pentium 4 3.4GHz... then stupid consumers started complaining about power consumption. I wish nVidia started making x86 CPUs. they would made 20GHz 1kW TDP CPU just like they do theier GeForce GPUs.

 

[doron]

[citation][nom]cyprod[/nom]My question is, has Moore's law ever been relevent? Granted, I do software, but I play at all levels from firmware on up and at no point in my day does the question as to how many transistors something has ever come up. The hardware people never mention it either. The things that matter, die size, power consuption and functionality provided. Transistor count seems more of a pissing match than anything. I mean, being a software guy, I could code algorithm X in 10 clever lines of code, or I could do it in 50 lines without much issue. I could probably stretch it to 100 lines if I was clever. Transistor count is similar. Who cares about how many transistors. It's just an interesting statistic, nothing more, nothing less.[/citation]

In conclusion: Intel, AMD, Nvidia are stupid and you're smart
Dude, you're a software guy right? then for your sake, do avoid ranting about stuff you don't understand.

 

[doron]

[citation][nom]tirinti[/nom]Intel have been making pathetick AMD style CPUs for few yeara. I had 3.4GHz Pentium 4 6 years ago. Now I have just bought i7 2600K wchih is stupid Athlon style name for i7 3.8GHz... just 400MHz faster than i have 6 years ago. I had also pathetic 3.33GHz Core2 Duo E8600. It was slower than my P4, but just a litle bit and I bought it because of new motherboard features. Where are times when CPU were known by its speed 386DX 40MHz, 486DX2 66MHz, Pentium 100MHz, Pentium 200MMx, Pentium II 300MHz, Pentium III 450MHz, Petium III 700MHz, Pentium 4 1.6GHz, Pentium 4 2.8GHz and finally Pentium 4 3.4GHz... then stupid consumers started complaining about power consumption. I wish nVidia started making x86 CPUs. they would made 20GHz 1kW TDP CPU just like they do theier GeForce GPUs.[/citation]

Nothing of what you wrote made sense.

 

[Moores Law]

Bu.. but I AM THE LAW! D:

 

[memadmax]

I fought the law, and the, law won...

 

[Guest]

"However, Moore's Law has also been somewhat abused as a marketing tool to justify new processors and force innovation into a tight pair of shoes, that was not always the best choice, such as Intel's Netburst products that turned out to be a dead end and almost brought the company down to its knees"


That's very inaccurate, yes Intel lost some marketshare and mindshare at the time, but it was in NO WAY in any financial trouble. It was INTEL it could have been selling cow's turd as processors and the vast majority of people would still choose intel procs over AMD's counterparts.

 

[illo]

[citation][nom]tirinti[/nom]Intel have been making pathetick AMD style CPUs for few yeara. I had 3.4GHz Pentium 4 6 years ago. Now I have just bought i7 2600K wchih is stupid Athlon style name for i7 3.8GHz... just 400MHz faster than i have 6 years ago. I had also pathetic 3.33GHz Core2 Duo E8600. It was slower than my P4, but just a litle bit and I bought it because of new motherboard features. Where are times when CPU were known by its speed 386DX 40MHz, 486DX2 66MHz, Pentium 100MHz, Pentium 200MMx, Pentium II 300MHz, Pentium III 450MHz, Petium III 700MHz, Pentium 4 1.6GHz, Pentium 4 2.8GHz and finally Pentium 4 3.4GHz... then stupid consumers started complaining about power consumption. I wish nVidia started making x86 CPUs. they would made 20GHz 1kW TDP CPU just like they do theier GeForce GPUs.[/citation]


lolwut?

 

[Kamab]

More transistors per unit area means you can add more to a design or make it smaller. Physical components (MUX's, registers, logic gates) all require transistors. Of course the amount of transistors you can fit per unit area is important.

This is huge for semi-conductor fabrication, which is probably on a software level that not many people "play on", but tends to affect us all in the industry in that the embedded processors I work on continue to get faster and contain more features from year to year.

 

[Jprobes]

[citation][nom]tirinti[/nom]Intel have been making pathetick AMD style CPUs for few yeara. I had 3.4GHz Pentium 4 6 years ago. Now I have just bought i7 2600K wchih is stupid Athlon style name for i7 3.8GHz... just 400MHz faster than i have 6 years ago. I had also pathetic 3.33GHz Core2 Duo E8600. It was slower than my P4, but just a litle bit and I bought it because of new motherboard features. Where are times when CPU were known by its speed 386DX 40MHz, 486DX2 66MHz, Pentium 100MHz, Pentium 200MMx, Pentium II 300MHz, Pentium III 450MHz, Petium III 700MHz, Pentium 4 1.6GHz, Pentium 4 2.8GHz and finally Pentium 4 3.4GHz... then stupid consumers started complaining about power consumption. I wish nVidia started making x86 CPUs. they would made 20GHz 1kW TDP CPU just like they do theier GeForce GPUs.[/citation]

Sounds like someone needs to divide their drug stash by 0 and take a vacay....

 

[jprahman]

I have a feeling triniti knows absolutely nothing about CPU architecture or how CPUs in general work... plus that whole drug thing too...

 

[cyprod]

[citation][nom]doron[/nom]In conclusion: Intel, AMD, Nvidia are stupid and you're smartDude, you're a software guy right? then for your sake, do avoid ranting about stuff you don't understand.[/citation]
Excuse me? Hostile much? Where did I say anything about my being smarter or anybody else being dumber? I mearly stated that transistor count is a meaningless statistic in the big picture of the world. I'd be willing to bet if you ask anybody who works in tech their honest opinion, they'll agree. I'm willing to put money on it that Gordon Moore would agree.

 

[Guest]

tirinti, the same tirinti from polish forums? What a find 😀 He's been saying the same shit about how fast Netburst is and how pathetic high IPC designs are for as long as I can remember.Hey, BD is supposed to be a high speed design with low FO4 number so maybe you will get what you want after all...

 

[Kamab]

[citation][nom]cyprod[/nom]Excuse me? Hostile much? Where did I say anything about my being smarter or anybody else being dumber? I mearly stated that transistor count is a meaningless statistic in the big picture of the world. I'd be willing to bet if you ask anybody who works in tech their honest opinion, they'll agree. I'm willing to put money on it that Gordon Moore would agree.[/citation]

Transistor count per Unit area is an incredibly important underlying statistic that drives the embedded circuits / microprocessor industry. Most people might think its meaningless, because it's an incredibly low level concept.

Transistor count / Area leads to better processor/circuit capabilities -> hardware performance -> software performance. Its not a single driving force though. Architecture improvements don't have much to do with transistor count and have a huge effect on processor performance.

 

[IndignantSkeptic]

can someone please explain to me why a processor, that is not really parallel, needs so many transistors?

 

[jprahman]

Mainly cache. Each bit of cache requires six transistors, IIRC, so a byte requires 6*8 = 48 transistors minimum. Modern quad-core CPUs have upwards of 9MB total cache, so 9 Million bytes * 48 transistors per byte = 432,000,000,000 transistors, although that figure may be slightly inflated. There's also the matter of the out-of-order execution engine that modern CPUs use, which I hear is pretty large, and the instruction decoders and instruction fetch logic is quite complex as well.