I think you mistake Moore law with the inability to make a CPU that is thermally stable without massive HSF or Watercooling. Current trends are to keep the HSF size as is for stock use. After market HSF/Watercooling allows users a much higher CPU speed. Likewise the reduction in current running through a processor is necessary because of the decreasing size of circuitry on a chip which has ever decreasingly sized of the space between the micro circuitry. So decreasing voltage and power is a logical progression to solve a problem.

Reducing the TDP to 77W is not because keeping it the same would have not been technically feasible. From AnandTech review:

I would say the reduction in TDP is the main reason why the specifications (not performance) are so similar to Sandy Bridge. If Intel had kept the 90W TDP, higher frequencies would have been likely and we might have even seen a hex-core part without a loss in frequency...

The driver for reducing TDP is almost certainly about having sufficient market demand for such a hex-core chip vs. a similarly performing chip that's significantly more energy efficient.

---

In 3 years desktops would die down to half billion, laptops would die down too while smartphones most likely jump to 3 billion. This is what Boinc community should be aware of it. At that time total smartphones might reach 1-2 petaflop of power or more no one can deny.

---

Mandtugai!

In 3 years desktops would die down to half billion, laptops would die down too while smartphones most likely jump to 3 billion. This is what Boinc community should be aware of it. At that time total smartphones might reach 1-2 petaflop of power or more no one can deny.

Phones won't be crunching they will be talking sending text getting on the web etc but not crunching and it will not be the death of the pc you are simply silly so it like saying a horse is better than a car.

---

In 3 years desktops would die down to half billion, laptops would die down too while smartphones most likely jump to 3 billion. This is what Boinc community should be aware of it. At that time total smartphones might reach 1-2 petaflop of power or more no one can deny.

I don't know where you get these figures from but from what I've seen desktops for the last 6yrs have remained fairly static (no gaining or loosing) though in the mobile market is where things are very different (I just wish that I could find the 10yr stats that I saw a few weeks back which is why I haven't replied to this thread earlier).

Mobile computing is where things are changing in a big way and its laptops that are now loosing out to tablets and smart phones but people who require full on processing power will always stay with desktops as no other format can provide that.

Sorry Orgil but I find the stats that you've throwing around aren't very accurate but if you want to carry on with that is up to you. There may be 490 million smart phones around but I doubt that very many of those people will want to use them for crunching anything, though it would be interesting to see just how long they will last doing it and if any injuries or accidents happen while doing this (I don't even like the idea of laptops doing this though some people do).

I'm also with skildude, James Sotherden, PaulDHarris, HAL9000 and msattler on this topic, smart phones, and tablets, just aren't designed with this type of use in mind.

Cheers.

---

I'm also with skildude, James Sotherden, PaulDHarris, HAL9000 and msattler on this topic, smart phones, and tablets, just aren't designed with this type of use in mind.

I agree too, I see them to be more useful running Non-CPU-intensive applications where they monitor one of their sensors, than all out crunching,

Claggy

Because mostly people in this forum are solely desktop generation so for you it is just incomprehensible to accept that something different form of hardwares to take over pc's. It is coming much faster than you sense.

Ok then, take your smart phone (or tablet) and video/sound edit/encode a couple of hours worth while running a fairly large and complex spreadsheet as well as having a couple of browser windows with a few active tabs in each and still chat to your friends at the same time (and I won't even mention doing all this while crunching as well), see how long that takes you (if you even could). I know that this will bring even the best of laptops to their knees (and I won't even mention about running all that over 2-3 monitors just so that you can see everything that's going on). :D

No one believed when thumb/flash drives to take over floppies so fast but it happened.

I certainly wasn't 1 of those people as I welcome new technology. LOL

Cheers.

---

I know that this will bring even the best of laptops to their knees (and I won't even mention about running all that over 2-3 monitors just so that you can see everything that's going on).

Sorry for going off topic but have you seen what you can get in a notebook lately? I am not looking for an argument or a debate but my i7 975 lappy is still standing.

Example:
http://www.sagernotebook.com/index.php?page=product_info&model_name=NP9270
Video: Dual Nvidia GeForce GTX 580M GPU 2GB GDDR5
CPU: 2nd Generation Intel® Core™ i7-3960X Processor Extreme Edition (15MB L3 Cache, 3.90GHz, 6 Cores)
Memory: 32GB Quad Channel DDR3 SDRAM at 1333MHz
Storage: RAID-0 3 X Intel 520 Series SATA3 SSD

Most of my farm are notebooks. Sorry I can not run it full bore 24/7 anymore with my fixed income these days but I have an old Alienware notebook that ranked "#62" a few years back. My current Sager i7 975 - GeForce GTX 280M got into the top #100 when I first got it.

---

...

I know that this will bring even the best of laptops to their knees (and I won't even mention about running all that over 2-3 monitors just so that you can see everything that's going on).

Sorry for going off topic but have you seen what you can get in a notebook lately? I am not looking for an argument or a debate but my i7 975 lappy is still standing.

Sorry but you'll get no argument out of me either but I have tried it doing all that on a mate's Alienware lappy (he just had to brag to much about it beating any desktop) and I did bring it to a slow motion crawl, not to mention that it had to throttle itself down 5 minutes later due to heat (my 2500K was still cruising).

Cheers.

---

Gentlemen, Lets keep this civil.

---

[/quote]

Old James

Gentlemen, Lets keep this civil.

What are you talking about?

I was talking about a mate of mine over here who likes to brag to much. ;)

Cheers.

---

As there was interest in this thread, Lets try it once more.

Keep it civil or its gone.

---

[/quote]

Old James

Recently AnandTech posted a review of Qualcomm's Krait CPU, a 1.5 GHz ARM-compatible dual-core CPU on 28nm process that should appear in handsets later this year. Benchmarks show a substantial jump in scores from current smartphone chips.

Linpack results (stresses FPU and memory subsystem):

Single threaded: 106.794 MFLOPS
Multi threaded: 218.197 MFLOPS

To put into perspective with x86 CPUs.

Phenom II @ 3.0 GHz: 1412.83 MFLOPS
Core i7 860: 2004.31 MFLOPS

(source)

---

I'm not sure where you got your numbers

This is the info on an amd 965 @ 3.4Ghz

Measured floating point speed 2792.47 million ops/sec
Measured integer speed 8573.71 million ops/sec

and my Athlon II 630 @ 2.8Ghz

Measured floating point speed 2310.81 million ops/sec
Measured integer speed 7157.31 million ops/sec

Notice that my 965 is nearly double and my 630 clear does more work that your supposed Phenom II @3.0Ghz. I'm getting in the line that says someone is intentionally shorting these numbers to make the handheld device look much better.

IIRC the Mflops are measured per core. which means not only are they attempted to shorthand an very fast Chip but also ignore that there are 4 cores running.
I think you've fallen into the realm of writer not understanding his hardware and reader believing it.

just for the sake of arguements. I just ran a benchmark on my FX-8150 using the AMD overdrive tool. It recorded a FLoPs of 16540 Amazing but you realize that it is taking all 8 cores into account and only uses 4 FPU's. The point is that divide by 8 to get your Mflops. thats something like 2067/core.

Now lets take another look at that dual core ARM chip that gets 100Mflops
That really isn't impressive. As pointed out in previous posts thats really really slow. We are talking 20X slower than an average CPU.

20 Freaking times slower. Then we can take a look at the average speed for an average WU on a CPU. lets say 2 hours for giggles, VLARs will take much longer, about 40 hours. That's 40 hours of crunch time on a device that likely has less than a 2 hour battery for active use.

Active being the difficult to determine quantity because most if not all apps do not stress a chip at all. So we are looking at maybe 1 hour of life on battery which means you are either constantly plugging in just to keep the battery from draining. Best case is that the battery isn't repeated drained which eventually shortens its life. Meaning again you are always plugged into to a wall socket which defeats the purpose of a mobile device.

I'm not even counting your added cost for your bandwidth usage, etc that you'd incur because of the download/uploads that you'd encounter. figuring about 14 WU's a month comes out to 5.1Mb which is pretty much beyond the standard smartphone contracted bandwidth usage.

For all that money wasted on a smartphone you could just as easily bought a cheap laptop and beaten your smartphone handily.

---

In a rich man's house there is no place to spit but his face.
Diogenes Of Sinope

You are right that LINPACK may not offer the best method for comparison. I just looked up more benchmark results on x86 from LINPACK and found another two wildly different numbers.

Core i7-3960X (Stock, HT On) - 64.9275 GFLOPS
[url=http://www.xbitlabs.com/articles/cpu/display/core-i7-3960x-3930k_12.html]Core i7-3960X (4.5 GHz, HT On) - 133.9831 GFLOPS

There is an OC in the second case but it wouldn't account for that much difference. I suspect different setups or benchmark settings prevent it from being a good apples-to-apples comparison to use when different people are running the benchmark.

I'm not even counting your added cost for your bandwidth usage, etc that you'd incur because of the download/uploads that you'd encounter. figuring about 14 WU's a month comes out to 5.1Mb which is pretty much beyond the standard smartphone contracted bandwidth usage.

For all that money wasted on a smartphone you could just as easily bought a cheap laptop and beaten your smartphone handily.

5.1Mb is not a big deal for many data plans from major carriers in the U.S., but even if so, the smartphone client could give the option to restrict data transfers to only when a WiFi connection is available. In my case my phone uses the router in the house when it's in range and the cell data plan when I'm elsewhere. It probably gets a WiFi connection often enough that a reasonable cache will keep it busy when there is no WiFi.

---

You are right that LINPACK may not offer the best method for comparison. I just looked up more benchmark results on x86 from LINPACK and found another two wildly different numbers.

Core i7-3960X (Stock, HT On) - 64.9275 GFLOPS
Core i7-3960X (4.5 GHz, HT On) - 133.9831 GFLOPS

There is an OC in the second case but it wouldn't account for that much difference. I suspect different setups or benchmark settings prevent it from being a good apples-to-apples comparison to use when different people are running the benchmark.

I'm not even counting your added cost for your bandwidth usage, etc that you'd incur because of the download/uploads that you'd encounter. figuring about 14 WU's a month comes out to 5.1Mb which is pretty much beyond the standard smartphone contracted bandwidth usage.

For all that money wasted on a smartphone you could just as easily bought a cheap laptop and beaten your smartphone handily.

5.1Mb is not a big deal for many data plans from major carriers in the U.S., but even if so, the smartphone client could give the option to restrict data transfers to only when a WiFi connection is available. In my case my phone uses the router in the house when it's in range and the cell data plan when I'm elsewhere. It probably gets a WiFi connection often enough that a reasonable cache will keep it busy when there is no WiFi.

5MB/mo would cost a lot if you were on one of those $1.99/MB rates. Luckily most companies offer unlimited data plans cheap these days. Even thought I get unlimited I have to try if I want to use more than 100mb. So even a 200mb plan would work for me. Oddly if I changed plans it wold cost me more to have a 200mb data plan as the one I have now no longer exists.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

considering the additional cost for the bandwidth its just cheaper and simpler to have a home broadband connection that doesn't limit your usage

also the 3960 has a much higher Mflops than you think. In other words you read the wrong part of the test. What in Gods name would make you think a handle held device had as much or more crunching power as a 6 core CPU



The important things you missed are the 1st and 3rd test on that list. Its hard to read but the numbers look a lot better than you assumed. I think its odd that the amd FX-8150 out ran the 3960X on the FPU. Considering that the 8150 only has 4 FPU's and shares them.

---

In a rich man's house there is no place to spit but his face.
Diogenes Of Sinope

also the 3960 has a much higher Mflops than you think. In other words you read the wrong part of the test. What in Gods name would make you think a handle held device had as much or more crunching power as a 6 core CPU

Nowhere do I even suggest that, in fact I was hoping to show the opposite. Despite the recent innovations in smartphone SoC's there's still a large gap between them and desktop CPUs. What is interesting though is that those chips are quickly advancing and may eventually become powerful enough to be relevant for volunteer computing. Maybe not SETI at first as other projects may be less FP-intensive or have smaller, more manageable WU lengths.

I think its odd that the amd FX-8150 out ran the 3960X on the FPU. Considering that the 8150 only has 4 FPU's and shares them.

That is weird. In most benchmarks I've seen Bulldozer suffer due to the FPU contention even compared to Phenom II. For example:

---

Core i7-3960X (Stock, HT On) - 64.9275 GFLOPS
[url=http://www.xbitlabs.com/articles/cpu/display/core-i7-3960x-3930k_12.html]Core i7-3960X (4.5 GHz, HT On) - 133.9831 GFLOPS

I guess in second case is used Linpack with AVX, this explains the difference.

---

I struck gold! You guys won't believe the date on this thread:

http://setiathome.berkeley.edu/forum_thread.php?id=32889

It's been almost 6yrs and it looks like we still need a couple more, before crunching on a smartphone...

It's been almost 6yrs and it looks like we still need a couple more, before crunching on a smartphone...

Well, eventually not few years more... just found that on Milkyway forums: Boinc Client for Android.
And this smartphone is crunching Milkyway WUs at a performance close to that of my AthlonXP 2000+. And it generates valid results, so it's not just some experimental thing, but actually something that can be used by anyone who wants to.

---