Mats, how can you know which pins are used in current am3 processors? maybe there is some pins already for future use.
PS. you have awesome avatar... i know it is building on front of sun, but it really always looks like something differrent first
Mats, how can you know which pins are used in current am3 processors? maybe there is some pins already for future use.
PS. you have awesome avatar... i know it is building on front of sun, but it really always looks like something differrent first
Mech Man: Honestly, I don't know. I'm sure there's some doc about that at amd.com
Yeah, it's and awesome building!
I don't think there is unused pins anymore.
First K8 was socket 940 & DDR1 dual channel. AM3 is 941 pins with DDR3 dual channel with advanced power management.
So i think there is no pins available from a long time ^^.
It might very well be that there is no free pins anymore. But, there is som space for pins in current processor. So additional pins could be added without loosing compability with older processors. It is shame still that they did not introduce it with 800 series chipsets.
I guess you missed the reviews that showed how irrelevant hyper threading is in the desktop world, more times hurting that doing good, or else you wouldn't be praising SB 16 threads.Originally Posted by terrace215
And what will stop AMD from bringing 16 threads to desktop other then the lack of need to do so?
Actually, first K8 was 754, then 939 came along. 940 was multi-CPU Opteron parts
The Cardboard Master Crunch with us, the XS WCG team
Intel Core i7 2600k @ 4.5GHz, 16GB DDR3-1600, Radeon 7950 @ 1000/1250, Win 10 Pro x64
First FX chips were 940.Actually, first K8 was 754, then 939 came along. 940 was multi-CPU Opteron parts
No, 940 came first, in April 2003, and it wasn't for Opterons only since Athlon FX used it as well (although it came later), with server RAM. S754 came in September.Actually, first K8 was 754, then 939 came along. 940 was multi-CPU Opteron parts
940 - 939 - AM2 - AM2+ - AM3 - AM3+
Yeah i remember this old days, when we was overclocking AthlonXP 2600+ mobile @ 2.9ghz and when AMD released the first Hammer chip. It was insane
Socket 940 had 3 HT links; Socker AM3 only has a single link; so there have to be alot of spare pins; count in that power consumption on those parts is still the same and you have plenty of pins left for power distribution
Core i7 2600k|HD 6950|8GB RipJawsX|2x 128gb Samsung SSD 830 Raid0|Asus Sabertooth P67
Seasonic X-560|Corsair 650D|2x WD Red 3TB Raid1|WD Green 3TB|Asus Xonar Essence STX
Core i3 2100|HD 7770|8GB RipJawsX|128gb Samsung SSD 830|Asrock Z77 Pro4-M
Bequiet! E9 400W|Fractal Design Arc Mini|3x Hitachi 7k1000.C|Asus Xonar DX
Dell Latitude E6410|Core i7 620m|8gb DDR3|WXGA+ Screen|Nvidia Quadro NVS3100
256gb Samsung PB22-J|Intel Wireless 6300|Sierra Aircard MC8781|WD Scorpio Blue 1TB
Harman Kardon HK1200|Vienna Acoustics Brandnew|AKG K240 Monitor 600ohm|Sony CDP 228ESD
Please point out such reviews. Secondly, I suppose you realize HT improves through-output. Testing only the amount of time needed to complete a job and not the actual work done will give a false impression on HT.
For example : task 1 takes 30s to complete and processes 100 work units. I activate HT and now I get 34s. From your POV HT is hurting. In reality you have another task, task 2 which did some actual work in that timeframe besides task 1. Let's say task 2 did 30 work units.
Overall we have : 13% more time wrts to task 1, but 30% more work done overall.
Reviews fail miserably at pointing out this. They only show you : in game X with HT enabled you go from 180 fps to 170s. Conclusion : HT sucks. Maybe their brain sucks, not HT.
A socket the size of your palm ?And what will stop AMD from bringing 16 threads to desktop other then the lack of need to do so?
sorry but that would be a fail. a loss in FPS is exactly that, a loss in FPS
1. SB has significantly improved hyperthreading.
2. Reread the exchange. I didn't mention HT, the other guy objected that HT made it unfair to compare Zambezi (8 core) with desktop Sandy (8 core).
3. Interlagos on the desktop... there would be some concerns with cost, the socket / mem bandwidth, low power devices vs turbo frequency, size of that segment. I doubt it, but not impossible.
Yes, HT sucks in that example workload where the wanted result is most FPS. HT sucks/not sucks is not black and white, in some workloads it gives boost, and sometimes it "sucks".
It goes both ways really. It depends on if throughput or latency is more important to your workload. Game engines aren't going to benefit much from more parallel throughput at the cost of latency. They need a lot of serial tasks done in sequence on the CPU side of things. A video encoder on the other hand probably couldn't care less since its workload can be broken up nicely into independent blocks of data and will probably see an improvement overall even if each work unit takes longer than it otherwise would.
Particle's First Rule of Online Technical Discussion:
As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.
Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.
Rule 2:
When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.
Rule 2A:
When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.
Rule 3:
When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.
Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!
Random Tip o' the Whatever
You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.
Fair enough, but that situation is becoming increasingly rare since most if not all the new games benefit from HT/multicores.
if the review is about gaming, then the conclusion could be for people making a gaming rig. sure an i7 might just flat out rock, but what if you wanted a 2c/4t cpu, in some games its fine, in others its not going to be as good as 4c/4t cpus.
im simply replying to the example and how its possible that the conclusion is relevant.
my personal feelings, HT is a bandaid that is well used, it should not be around forever, but long enough to have a purpose.
Don't get me wrong, I don't particularly care for hyperthreading either. I'm just trying to keep things objective.
As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.
Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.
When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.
When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.
When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.
Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!
Random Tip o' the Whatever
You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.
Bandaid ? It is a technology for improving through output by increasing the utilization of a CPU's compute capacity. How can that be a bandaid ? Bandaid is throwing more and more cores at a problem, hoping somehow that they will be used.
there are many ways to look at and evaluate a problem that is constantly evolving.
first we had single or duel cores. it was a simple black and white difference. now that we have some programs still begging for more mhz, and some that have been optimized for every core available. the answer isnt so clear what will provide the best performance for every situation. and every meaning more than just single threaded and unlimited threaded.
i say bandaid because i honestly believe that a better solution will be found within a few years and intel will no longer rely on HT (like reverse HT sounds pretty awesome if it can get working). i did say it has a point and a purpose in the current scheme of things. so dont think i hate it.
lulz just about every Nehalem review where the comparison was made. You asking for them like they didn't exist is hilarious and pathetic at the same time
Can i ask you what other imaginary task are you referring to? And what imaginary 30% more work done? And if it made so much more work how come it ends up encoding in more time in a multithreaded app?
roflocopter...
So what has HT done for the game beside dropping the playable rating? 30% more work in a imaginary task that still led to less fps? HT is adorable.
It at least doesn't hurt games as much as adding two cores in Thuban.
you must be comparing different speed bins
Well, yeah adding more cores means a reduction of frequency. Same basic idea of Hyperthreading, sacrificing performance in a single thread to potentially gain throughput benefits by doing work in a second thread.
This doesn't make any sense as both HT and more cores require the software to do precisely the same thing in order for either to be used. One could say Intel was applying a bandaid hoping the extra threads would be used with the same argument you've supplied for more cores if the assertion were true in the way you've put forth.
As a thread about any computer related subject has its length approach infinity, the likelihood and inevitability of a poorly constructed AMD vs. Intel fight also exponentially increases.
Likewise, the frequency of a car pseudoanalogy to explain a technical concept increases with thread length. This will make many people chuckle, as computer people are rarely knowledgeable about vehicular mechanics.
When confronted with a post that is contrary to what a poster likes, believes, or most often wants to be correct, the poster will pick out only minor details that are largely irrelevant in an attempt to shut out the conflicting idea. The core of the post will be left alone since it isn't easy to contradict what the person is actually saying.
When a poster cannot properly refute a post they do not like (as described above), the poster will most likely invent fictitious counter-points and/or begin to attack the other's credibility in feeble ways that are dramatic but irrelevant. Do not underestimate this tactic, as in the online world this will sway many observers. Do not forget: Correctness is decided only by what is said last, the most loudly, or with greatest repetition.
When it comes to computer news, 70% of Internet rumors are outright fabricated, 20% are inaccurate enough to simply be discarded, and about 10% are based in reality. Grains of salt--become familiar with them.
Remember: When debating online, everyone else is ALWAYS wrong if they do not agree with you!
Random Tip o' the Whatever
You just can't win. If your product offers feature A instead of B, people will moan how A is stupid and it didn't offer B. If your product offers B instead of A, they'll likewise complain and rant about how anyone's retarded cousin could figure out A is what the market wants.
Posting Permissions
Reply With Quote
Bookmarks