Core i5 or i7?
 

Was wondering which is best for prime at standard clockspeed. The i7 supports HT but that doesn't boost prime so isn't a core i5 760 about the same power as an equal clocked i7?
Hope someone has some info on this.

Thanx,
Ferdy

You can start by checking out the benchmarks page....

[url]http://www.mersenne.org/report_benchmarks[/url]

Same speed, same performance
 

At the same speed, the i5 and i7 deliver pretty much the same throughput on Prime95. The i7 has a small edge because it usually comes with triple channel memory compared to the i5's dual channel.

On the other hand, overclocking i7's is fun and significant in terms of Prime95 speed. My original i7-920 is overclocked to 3.8 GHz with the assistance of an aftermarket heatsink.

[QUOTE=Rhyled;235928]At the same speed, the i5 and i7 deliver pretty much the same throughput on Prime95. The i7 has a small edge because it usually comes with triple channel memory compared to the i5's dual channel.

On the other hand, overclocking i7's is fun and significant in terms of Prime95 speed. My original i7-920 is overclocked to 3.8 GHz with the assistance of an aftermarket heatsink.[/QUOTE]
Hmm...do i7's overclock significantly better than i5's? I thought they were pretty much the same except for hyperthreading.

@Ferdy: If overclocking is out of the question, then definitely go with an i5 if you're planning to do mostly LL tests. It will be nearly the same speed as an i7, as Rhyled mentioned, but a good $100 cheaper.

A friend of mine at the "No Prime Left Behind" project (farther down the forum) has an i7 and finds that the hyperthreading gives a very big boost on sieving (analogous to TF at GIMPS). I don't know whether the same goes for TF, but would guess it might.

Actually, though, you may want to consider looking into an AMD 6-core--you can get them for the same price as a 4-core i5 and though it will be a little slower per-core, it will beat the socks off of either an i5 or i7 in terms of raw processing power because of the two extra cores (real cores, not hyperthreads). I would recommend either the [url=http://www.newegg.com/Product/Product.aspx?Item=N82E16819103851]1055T[/url] or [url=http://www.newegg.com/Product/Product.aspx?Item=N82E16819103849]1090T[/url]. (The 1075T, which appears to be the only other AMD 6-core available at this time, is more expensive than the 1090T but lower clocked, hence why I left it out.)

[FONT=Arial]Ferd,

A few examples:[/FONT] [FONT=Arial]

1090T@3.6GHz[/FONT] [FONT=Arial]

69*2^1030003-1 is not prime. LLR Res64: 63DDEBEC28078615 Time : 824.101 sec.[/FONT] [FONT=Arial]

Q6600@2.8 GHz[/FONT] [FONT=Arial]

69*2^1030003-1 is not prime. LLR Res64: 63DDEBEC28078615 Time : 840.805 sec.[/FONT] [FONT=Arial]

Core i5 750@3.4GHz[/FONT] [FONT=Arial]

I don't have the benchmark but all k*2^n-1 test I have done so far shows that the core i5 is at least 30 % faster than the Q6600.[/FONT] [FONT=Arial]As n increases the gap speed increases due to better speed and cache memory for the core i5.

So, go for the Core i5 instead of the 1090T, the 4 cores of the core i5 beats the crap of the six cores from the AMD processor. You can reach 4 GHz for the core i5 with a better cooler than the one I use, the Artic Cooling Freezer 7 Pro. Go for the Noctua NH-D14.[/FONT]

[QUOTE=em99010pepe;235951][FONT=Arial]Ferd,

A few examples:[/FONT] [FONT=Arial]

1090T@3.6GHz[/FONT] [FONT=Arial]

69*2^1030003-1 is not prime. LLR Res64: 63DDEBEC28078615 Time : 824.101 sec.[/FONT] [FONT=Arial]

Q6600@2.8 GHz[/FONT] [FONT=Arial]

69*2^1030003-1 is not prime. LLR Res64: 63DDEBEC28078615 Time : 840.805 sec.[/FONT] [FONT=Arial]

Core i5 750@3.4GHz[/FONT] [FONT=Arial]

I don't have the benchmark but all k*2^n-1 test I have done so far shows that the core i5 is at least 30 % faster than the Q6600.[/FONT] [FONT=Arial]As n increases the gap speed increases due to better speed and cache memory for the core i5.

So, go for the Core i5 instead of the 1090T, the 4 cores of the core i5 beats the crap of the six cores from the AMD processor. You can reach 4 GHz for the core i5 with a better cooler than the one I use, the Artic Cooling Freezer 7 Pro. Go for the Noctua NH-D14.[/FONT][/QUOTE]
Actually, as a matter of fact I get a slight advantage for the AMD with those numbers. Using 824 seconds/test for the 1090T and .7*840=588 seconds/test for the i5, I get 24.49 tests/hour for the i5 and 26.21 tests/hour for the AMD. It seems that the 6 cores just slightly more than compensates for the slower individual cores.

(I imagine the difference would be even more pronounced without overclocking: the 1090T is stock clocked to 3.2Ghz, not much below the 3.4Ghz you tested with, whereas the i5 750 is significantly lower at 2.66Ghz.)

[FONT=Arial]Ferd,

You also need to watch for the overclock capability vs energy efficiency. Core i5 is better.

EDIT: Anyway, what's your current machine?
[/FONT]

[QUOTE=em99010pepe;235958][FONT=Arial]Ferd,

You also need to watch for the overclock capability vs energy efficiency. Core i5 is better.
[/FONT][/QUOTE]


Sounds a bit like a Intel fanboy!
Only the i7 980X would be significantly better than the AMD 1090T, but the price is clearly too elitist for me!

[QUOTE=moebius;235982]Sounds a bit like a Intel fanboy!
Only the i7 980X would be significantly better than the AMD 1090T, but the price is clearly too elitist for me![/QUOTE]

I had both types of processors (AMD K5, K6, Athlon 2200+, AMD 64 3000+) and I found on Intel a higher potential...do you see a Mac using an AMD?

I thought about upgrading the Q6600 to a AMD 1090T because I could use the DDR2 memory but after the latter output on LLR I was very disappointed. I was not going to make an investment on a new CPU, cooler and motherboard just for having more 47 % more work when I could have the same by upgrading the Q6600 to a Q9650 for less.

Anyway, give me some numbers on i7 980X vs AMD 1090T at the same GHz running LLR although the intel cost 3x than the AMD.

A question to all, why the motherboards manufactures like Asus, MSI, etc don't make dual sockets motherboards for usual standards (not servers)? It is something I can't understand.

[QUOTE=em99010pepe;235989]I had both types of processors (AMD K5, K6, Athlon 2200+, AMD 64 3000+) and I found on Intel a higher potential...do you see a Mac using an AMD?
[/QUOTE]

So, what does that prove exactly? In a normal case Apple has some pretty cheap (in the sense of performance and price worthiness) cpu included. Exceptions are in the high price area Macs.

No doubt that the Intel 980x Hex Core from Intel is faster but for what price? At least 800 Euro and the mainboard is expensive.

I own a Q6600 as well and I'm thinking about upgrading to the 2,8 GHz Hex Core from AMD. No way I will spend at least 5 times that much money for an Intel Hex Core with a mainboard.

With exception of those who really need it (heavy programmers) I call the Intel Hex Core price a tax for 'idiots who are bad in math' ;=).

And don't forget, Mr. Prime95 has and wants to improve the AMD64 processor optimization.

[QUOTE=em99010pepe;235989]I had both types of processors (AMD K5, K6, Athlon 2200+, AMD 64 3000+) and I found on Intel a higher potential...do you see a Mac using an AMD?

I thought about upgrading the Q6600 to a AMD 1090T because I could use the DDR2 memory but after the latter output on LLR I was very disappointed.

Anyway, give me some numbers on i7 980X vs AMD 1090T at the same GHz running LLR.[/QUOTE]
Note that Intel vs. AMD clock speeds are not usually comparable; I would compare by price instead (since the primary consideration is how much crunching power you can get for a given price).

[QUOTE=joblack;235991]So, what does that prove exactly? In a normal case Apple has some pretty cheap (in the sense of performance and price worthiness) cpu included. Exceptions are in the high price area Macs.
[/QUOTE]

Why they choose Intel instead of an AMD?

[QUOTE=joblack;235991]
No doubt that the Intel 980x Hex Core from Intel is faster but for what price? At least 800 Euro and the mainboard is expensive.[/QUOTE]

Totally agree. Here it cost more than 1000 Euros.

[QUOTE=joblack;235991]
I own a Q6600 as well and I'm thinking about upgrading to the 2,8 GHz Hex Core from AMD. No way I will spend at least 5 times that much money for an Intel Hex Core with a mainboard.[/QUOTE]

Did you think about a Q9650 instead of an AMD?

[QUOTE=joblack;235991]

With exception of those who really need it (heavy programmers) I call the Intel Hex Core price a tax for 'idiots who are bad in math' ;=).

And don't forget, Mr. Prime95 has and wants to improve the AMD64 processor optimization.[/QUOTE]

I hope he does improve.

Let's put it in this way.
Running both processors the same type of work 24/7 during a year, like LLR. Which one, i7 980X vs AMD 1090T, will cost you less and make more work? Think about the investment, the energy consumed by both, the price of energy....

Much conjecture in this thread but little information.
[URL="https://spreadsheets.google.com/ccc?key=0AqpmCkfx1ywadHk2NnY3aGRyM2l6Nks2REtpRExiM1E&hl=en&authkey=CLTqrBg"]Here's some data to consider[/URL]. (Google spreadsheet)

[QUOTE=em99010pepe;235995]Let's put it in this way.
Running both processors the same type of work 24/7 during a year, like LLR. Which one, i7 980X vs AMD 1090T, will cost you less and make more work? Think about the investment, the energy consumed by both, the price of energy....[/QUOTE]

The difference will be around 1-3 Euro / month (actual power prices and the performance surplus for the 980x).

Let's assume it's 3 Euro difference so you would have to wait 750 Euro / 3 Euro = 250 months or 20,8 years to get even. And you have no interest included in your saved money for the AMD.

[QUOTE=em99010pepe;235994]Why they choose Intel instead of an AMD?[/QUOTE]

Who knows. Maybe Intel gave a special rebate (wouldn't be the first time) or Steve Jobs doesn't like the CEO of AMD, ... the point is we don't know the reason but you can't take Apple's decision for Intel cpus as an argument for their superiority.

[QUOTE=em99010pepe;235994]Did you think about a Q9650 instead of an AMD?[/QUOTE]

No, the Q6600 and Q9650 aren't 'real' quad cores. They are two double cores glued together (with all the consequences like suboptimal memory controller). Don't get me wrong, at the time I bought it (almost 4 years ago) they were state of the art and price worthy for the performance. That point has changed.

The 6 Core AMDs are real hex cores and are very cheap for that category.

And not to forget I have done an extensive web search about that topic. You should do the same. ^^



[QUOTE=em99010pepe;235994]I hope he does improve.[/QUOTE]

He has already done so. If you give him (temporary) access to a new installed amd hex core (via ssh) he might optimize it, too.

[QUOTE=em99010pepe;235958][FONT=Arial]Ferd,

You also need to watch for the overclock capability vs energy efficiency. Core i5 is better.

EDIT: Anyway, what's your current machine?
[/FONT][/QUOTE]
My current machine is a Conroe E6750 sat 2,66Ghz.

Ferdy

Sandy Bridge
 

Why don't you wait for Intel's Sandy Bridge architecture next January?
By the way, my Core i5 750 costed me 150 Euros in November 2009 and runs Prime stable at 3700 MHz on all 4 cores with air cooling...
Formerly, I had always preferred AMD...

[QUOTE=Brain;236152]Why don't you wait for Intel's Sandy Bridge architecture next January?
By the way, my Core i5 750 costed me 150 Euros in November 2009 and runs Prime stable at 3700 MHz on all 4 cores with air cooling...
Formerly, I had always preferred AMD...[/QUOTE]

A friend of mine overclocked his 6 core AMD from 2.8 to 3.5 ghz (aircooled). Price is around 160 euro and you got 2 more cores.

[QUOTE=joblack;236188]A friend of mine overclocked his 6 core AMD from 2.8 to 3.5 ghz (aircooled). Price is around 160 euro and you got 2 more cores.[/QUOTE]My air -cooled AMD 6-core is currently clocked at just under 3.8MHz and running very stably. Here is a snippet from /proc/cpuinfo:
[code]
[pcl@anubis ~]$ cat /proc/cpuinfo
processor : 0
vendor_id : AuthenticAMD
cpu family : 16
model : 10
model name : AMD Phenom(tm) II X6 1090T Processor
stepping : 0
cpu MHz : 3780.838
cache size : 512 KB
physical id : 0
siblings : 6
core id : 0
cpu cores : 6
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 6
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc rep_good nonstop_tsc extd_apicid pni monitor cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt npt lbrv svm_lock nrip_save
bogomips : 7351.62
TLB size : 1024 4K pages
clflush size : 64
cache_alignment : 64
address sizes : 48 bits physical, 48 bits virtual
power management: ts ttp tm stc 100mhzsteps hwpstate [9]

[/code]I've been an AMD fan for quite a few years now.

Paul

How about some real life, hard numbers.
The Benchmarks page is a very good start but it only reports the calculated potential thruput of one core running solo. It won't tell you the impact of loading all cores.

So in our example here, if an AMD 1090T 6-core and an i5-750 are equally clocked (or over clocked) and all 6 or 4 cores are fully loaded equally how many total GIMPS GhzDays per day can it process?

My personal experience for example:
I have a Q9550 (2.83 Ghz) and a i5-750 (2.66Ghz).
My own benchmarks page entries show that for a 2560 FT I can do an LL iteration at 38.22 and 35.30 ms respectively. Hmm looks pretty close.
HOWEVER, if I load them each with 4 2560 LL then the iteration times change to about 53-57 and 37-38 Ghz respectively. A BIG DROP for the Q9550 simply because it is well documented that it has memory channel / bandwidth / sharing issues.

My earlier post has a bit of what you are looking for.
[URL="https://spreadsheets.google.com/ccc?key=0AqpmCkfx1ywadHk2NnY3aGRyM2l6Nks2REtpRExiM1E&hl=en&authkey=CLTqrBg#gid=0"]Link to spreadsheet[/URL]

[QUOTE=sdbardwick;236255]My earlier post has a bit of what you are looking for.
[URL="https://spreadsheets.google.com/ccc?key=0AqpmCkfx1ywadHk2NnY3aGRyM2l6Nks2REtpRExiM1E&hl=en&authkey=CLTqrBg#gid=0"]Link to spreadsheet[/URL][/QUOTE]

So if I try to extrapolate: 2240 is a new FFT size but allow me to assume the exponent in question is 40,000,001.

Each i5-750 core at 0.034 ms will take 15.74 days.
In 63 days this CPU will complete 16 exponents.

Each 1090T core at 0.44 ms will take 20.37 days.
In 61 days this CPU will complete 18 exponents.

Round 1 goes to AMD with a small disclaimer that it is OC'd to 3.2 vs 3.0 for Intel. Assuming a linear OC to speed increase Intel at 3.2 would process 17 exponents. Still an edge to AMD.

Minor note: 1090T is not OC'd (3.2GHz is stock); 750 OC'd from 2.66 to 3 GHz.
But your conclusion is correct.

Intel has ability to clock higher than AMD; a heavily OC'd 750 can probably beat a 1090T.
Personally, I won't do high overclocks (on either Intel or AMD) as you start getting 'silent' errors. Silent errors are what I call errors that are not detected by Prime95 during the LL run (error codes are all 0 ) but later residues don't match. The boxes generating silent errors can pass days of Prime95 torture tests.

PrimeScore
 

[QUOTE=sdbardwick;236299]Silent errors are what I call errors that are not detected by Prime95 during the LL run (error codes are all 0 ) but later residues don't match. The boxes generating silent errors can pass days of Prime95 torture tests.[/QUOTE]
I'm scared. Is this commonly agreed? Solution? (Run always a DC on one core..?)

By the way, I suggest a PrimeScore feature in Prime95. This would be a positive integer describing a (CPU) performance index that is easily comparable and generated after benchmarking. This could also make Prime95 a test reference in hardware online magazines.

Formula (naive) suggestion, given no helper threads: PrimeScore = Theoretical CPU throughput = Sum(FFT size*(1/Iteration time))*Number of possible workers

Let me do a bit more research before jumping to conclusions (or into a panic). A fair portion of those errors occurred fairly long ago using old versions of Prime95 (all the way back to v19). Also, IIRC, all but one or two were from OC'd processors. I'll pull up my bad LL results and check.

Not going to be very precise, because this is based on me manually counting numbers as they scroll by on the screen (computer I'm using right now is not mine and has limited resources).

Quick check of my LL tests reveals that since 04 Apr 2008 I have had (about)
38 Bad results with all 0s in the error code field.
Of those 38, 24 are from OC'd boxes.
Of the remaining 14, 6 were from non-OC'd boxes with NVidia integrated video (I've had problems with NVidia drivers in the past).
Of the remaining 8, 2 were from a box where the RAM went bad later that month.
The last 6 cannot be tied to either bad RAM, OC, or faulty drivers (some results are missing a computer name, some I don't remember details about the boxes).

Prior to 4 Apr 2008 (or without a completion date), I had about 72 bad results with all 0s in the error code field.
70 were from OC'd processors. Those were mostly P4 processors, and the ones giving bad results were mostly Prescott based IIRC.

PrimeNet throws a CGI time out so I can't give a total number of tests, but I completed about 600 LL and DC in the past 365 days.
Edit: In the past 365 days, I've had 8 silent errors, 6 from 1 non OC'd box that has been since rebuilt (might have had bad RAM), the other 2 from non-OC'd boxes that had incorrect memory timings and/or bad RAM.

I have I7-920 and i7-930 here at home. Both I like.

I tend to agree with this statement:

[QUOTE=Brain;236152]Why don't you wait for Intel's Sandy Bridge architecture next January?
[/QUOTE]

January is not that far away. If you can wait until then, I think that's the better option.

-- Craig

[QUOTE=nucleon;237235]I have I7-920 and i7-930 here at home. Both I like.

I tend to agree with this statement:



January is not that far away. If you can wait until then, I think that's the better option.

-- Craig[/QUOTE]

In my experience "available" and "affordable" are about one or two years apart.

[QUOTE=nucleon;237235]I have I7-920 and i7-930 here at home. Both I like.

I tend to agree with this statement:



January is not that far away. If you can wait until then, I think that's the better option.

-- Craig[/QUOTE]

With January only two months away I thought we would have heard something more official from Intel by now??? Or at least so good leaks.

[QUOTE=petrw1;237243]In my experience "available" and "affordable" are about one or two years apart.[/QUOTE]
That is quite true but when new cpus are introduced the price of current cpus might go down. :smile:

[QUOTE=nucleon;237235]I have I7-920 and i7-930 here at home. Both I like.

I tend to agree with this statement:



January is not that far away. If you can wait until then, I think that's the better option.

-- Craig[/QUOTE]


Based upon what I have read Sandy Bridge will not be any faster/more
powerful than the current i7's.

I have a thought.......:smile:

Rather than concentrate on new architectures, smaller dies, etc., I think
it would be marvelous if they just gave us a new chip with the same
architecture as the current i7, but with 1 Gbyte of L2 cache per core. :smile:

We'd really see some performance improvements!

Give us cache, lots of cache in the sunny skies above....

[QUOTE=petrw1;237263]With January only two months away I thought we would have heard something more official from Intel by now??? Or at least so good leaks.[/QUOTE]

I have seen some "official" discussions. I am less than impressed.

AVX?
 

[QUOTE=R.D. Silverman;237345]Based upon what I have read Sandy Bridge will not be any faster/more
powerful than the current i7's.[/QUOTE]
There's AVX. I don't know exactly how Prime95 is affected (speed doubled?).

[QUOTE=Brain;236316]I'm scared. Is this commonly agreed? Solution? (Run always a DC on one core..?)

By the way, I suggest a PrimeScore feature in Prime95. This would be a positive integer describing a (CPU) performance index that is easily comparable and generated after benchmarking. This could also make Prime95 a test reference in hardware online magazines.

Formula (naive) suggestion, given no helper threads: PrimeScore = Theoretical CPU throughput = Sum(FFT size*(1/Iteration time))*Number of possible workers[/QUOTE]

Silent Errors are almost not possible if you enable all error corrections (needs around 4 - 6 per cent more time). Check your overclocked hardware with a torture test over 1- 3 days.

[QUOTE=R.D. Silverman;237345]Rather than concentrate on new architectures, smaller dies, etc., I think it would be marvelous if they just gave us a new chip with the same architecture as the current i7, but with 1 Gbyte of L2 cache per core. :smile:

We'd really see some performance improvements![/QUOTE]As I said to Ernst recently in another thread in another context: "Who is this we white-man?". In other words, to whom would they sell this device in quantities sufficient to make it affordable?

A few weirdos, many of the inhabitants of this forum for example, would really love such a chip. Almost the entire population would have little or no use for it.

Over 10 years ago I contributed to an IEEE workshop devoted to trends in high-performance computing in its various guises. Present were Intel and AMD hardware guys. I, and several others, said that what they would really like is a significant amount of memory as fast as the cpu could use it. Registers, in other words, or[B] L1 [/B]cache at a pinch. "Significant" meant somewhere between 100Mbyte and 1Tbyte (may as well be optimistic!).

Still waiting.

Paul

[QUOTE=R.D. Silverman;237345]Rather than concentrate on new architectures, smaller dies, etc., I think it would be marvelous if they just gave us a new chip with the same architecture as the current i7, but with 1 Gbyte of L2 cache per core. :smile: Give us cache, lots of cache in the sunny skies above....[/QUOTE]
Don't forget the golden rule: The bigger the memory, the slower the speed/access rate. :sad:

[QUOTE=R.D. Silverman;237345]Based upon what I have read Sandy Bridge will not be any faster/more
powerful than the current i7's.

I have a thought.......:smile:

Rather than concentrate on new architectures, smaller dies, etc., I think
it would be marvelous if they just gave us a new chip with the same
architecture as the current i7, but with 1 Gbyte of L2 cache per core. :smile:[/QUOTE]

Aside from some minor matters of architecture and of distribution, this has been done: the higher-end GPUs have aggregate bandwidth (192GB/sec on geforce 580) to the 2GB main memory rather better than the aggregate L2 bandwidth (25.7GB/sec/core) of a Core i7 :smile:

[QUOTE=fivemack;237403]Aside from some minor matters of architecture and of distribution, this has been done: the higher-end GPUs have aggregate bandwidth (192GB/sec on geforce 580) to the 2GB main memory rather better than the aggregate L2 bandwidth (25.7GB/sec/core) of a Core i7 :smile:[/QUOTE]Latency?

Paul

Cisco sell blades with dual xeon processors and 384GB of ram.

RAM on video cards has always been faster than main system ram sold at the time. (To my knowledge)

The reason given was that it was cost reasons. But video cards as cheap as they are now - this reason doesn't seem to hold water these days.

-- Craig

[QUOTE=R.D. Silverman;237345]Based upon what I have read Sandy Bridge will not be any faster/more powerful than the current i7's.[/QUOTE]

What about AVX double-width SSE registers?

Doesn't that have the capability of improving 2x DP FP over current gen? Granted that it requires code development.

-- Craig

50 MB Cache
 

[QUOTE=R.D. Silverman;237345]Rather than concentrate on new architectures, smaller dies, etc., I think
it would be marvelous if they just gave us a new chip with the same
architecture as the current i7, but with 1 Gbyte of L2 cache per core. :smile:

We'd really see some performance improvements!

Give us cache, lots of cache in the sunny skies above....[/QUOTE]

Intel has announced Codename „Poulson“:

An Itanium® processor implemented in 32nm CMOS with 9 layers of Cu contains 3.1 billion transistors. The die measures 18.2×29.9mm². The processor has 8 multi-threaded cores, a ring-based system interface and combined cache on the die is [B]50MB[/B]. High speed links allow for peak processor-to- processor bandwidth of up to 128GB/s and memory bandwidth of up to 45GB/s.

The pricing for Sandy Bridge has vaguely emerged, and it doesn't seem that the higher-end model is going at a painful premium: the i7/2600 (four cores, 3.4GHz, hyperthreading, 8 DP flops per cycle peak using AVX, though only dual-channel DDR3/1600 RAM) is $350 which is about what I paid for my i7/920 shortly after release.

[QUOTE=R.D. Silverman;237345]Rather than concentrate on new architectures, smaller dies, etc., I think it would be marvelous if they just gave us a new chip with the same architecture as the current i7, but with 1 Gbyte of L2 cache per core. :smile:

We'd really see some performance improvements!

Give us cache, lots of cache in the sunny skies above....[/QUOTE]
Just an opinion, but that sort of thing would require some rather exotic cooling. It might even be too hot for helium cooling.


Anyone know how to calculate this sort of thing?

[QUOTE=jasong;238831]Just an opinion, but that sort of thing would require some rather exotic cooling. It might even be too hot for helium cooling.

Anyone know how to calculate this sort of thing?[/QUOTE]Why should it need to run especially hot? As the old saying goes: size doesn't matter, it;s what you do with it that is important. In particular, lowering the clock speed is a good way to reduce the heat output.

The answer to your second question is: yes, they do. Just not me, unfortunately, without an investment in time which I'm presently unwilling to make.

[QUOTE=jasong;238831]Just an opinion, but that sort of thing would require some rather exotic cooling.[/QUOTE]

At last, a video that I saw about a decade ago and which was thereafter hard to find is back on youtube.

Have a look at [url]http://www.youtube.com/watch?v=Tl_RB5Snhr4[/url] for some properly exotic cooling.