except we have no undeniable facts about K8L, the same could be said about a good few unreleased products. But we have rumors from reliable sources which are probably correct.Quote:
Originally Posted by ksimp88
Printable View
except we have no undeniable facts about K8L, the same could be said about a good few unreleased products. But we have rumors from reliable sources which are probably correct.Quote:
Originally Posted by ksimp88
Yes . thats what I am basing it on the 45 should scale higher. It not a magic cpu. But it should get Intel closer to the C2D's wall .
Also its been said many times and in many articles that Intel is going to use highk and metal gates on the 45nm process. If true that should give Intel a little head room . As you know Penryn A0 chip booted into windows thats a very promising sign . That 45 nm is going to be good for intel.
On the normal 3.2 to 3.5 O/C your talking about most those guys are using 6600 and 6400 and running into a chipset wall. 6700 & 6800 do very well.
well I admit it may be the chipset or the CPU, though in the past couple years for AMD you could use a $50 mobo and $100 Ram to hit the 3GHZ wall (or 2.6 depending on the core)Quote:
Originally Posted by Turtle 1
True AMD M/B are cheaper than Intels because of the chipset and its a more complex M/B . But a 1.83 ghz c2d scales a lot higher than an amd 2.0 ghz. cpu. Now the e4300 bring a whole new pricing into the game as they will scale high with cheap M/B and ram. The one thing that must be remembered is c2d is still rather new. as time passes they are going to get cheaper and cheaper. When the e-4300 drop to $113 in 2nd qt. you will have a intel product that can do 3.2 -3.4 ghz with a $90 M/B and cheap DDR2 667 cheap memory. Its going to be a wonderful low buck system .
actually if I remember correctly lately people have been having troubles overclocking the E4300. Not to mention the fact that the E6300 is actually cheaper than the E4300 right now and actually supports virtualization which is actually very useful.Quote:
Originally Posted by Turtle 1
Could you link to were people are having problems O/C 3.2 seems to be very stable. at lower V. .Who wants virtualization for a budget gamer?
As I said when the price settles @ $113 these are going to great budget gamers. You can bet Dell and HP are going to buy tons of these. I am impressed with the performance so far for the first batch.
Back on topic . What do you exspect the first K8L released to be clocked at?Also How high of an o/c you exspecting?
That is for the low end E6300/E6400.Quote:
Originally Posted by nn_step
E6600 is 3.5-4 GHz.All on air of course.
I think you should pay a visit to the Intel side of the forum and see the light...
http://blogs.business2.com/utilitybe...rimming_w.html
Quote:
AMD's brimming with quad-core confidence
AMD (AMD) remains confident that the quad-core Barcelona chip for enterprise servers, due at the middle of this year, will deliver a 40 percent performance boost over what's available today – an advantage Intel (INTC) won't be able to match.
I had lunch on Tuesday with Randy Allen, AMD's corporate vice president for servers and workstations, and had a wide-ranging talk about the status of AMD's server business and competition with Intel. Undeterred by the disappointing financial results AMD announced that day, Allen made some bold statements about the company's upcoming quad-core server chip. Here are some key points from our conversation:
AMD gains in 2006 chip rankings
AMD will begin shopping the Barcelona chip around to customers in the April-June time frame (so, in about three months).
Allen thinks Barcelona's advances in virtualization and power management (and other technologies) are so significant that to compete, Intel will have to significantly change its front side bus or micro-architecture – no simple task.
AMD decided two years ago to pursue the current Barcelona strategy, even though it would take six months longer than other options and Intel would almost surely come to market with a quad-core product first. (Intel did, with Clovertown.) AMD believes its quad-core Barcelona design is far more efficient, and that customers will notice.
AMD is hopeful that customers are holding off on purchasing Intel's quad-core product, released in November, based on the fact that Intel didn't say much about it in its most recent earnings call. Yesterday, however, CNET quoted a Mercury Research analyst saying Intel's Clovertown chip is already contributing a meaningful amount of business to Intel.
Allen said Q4 2007 will be when the first real impact of Barcelona comes through in AMD's financial statements. I noted that if the chip does well, it will provide very flattering comparable sales figures to the Q4 results AMD announced this week, which were short of Wall Street's expectations.
Barcelona will have healthy margins, Allen predicted – AMD seems confident that because it will provide such a performance advantage over Intel, price competition won't be as intense.
While he doesn't expect customer uptake to be as quick as the shift from single- to dual-core, Allen said because AMD has made it easy for customers to drop the quad-core solution into their existing equipment, customer acceptance will be rapid and broad-based.
Allen downplayed the significance of Intel's partnership announcement with Sun Microsystems (SUNW) on Monday. Though he admitted that AMD liked being Sun's exclusive provider of x86 chips, he said it seemed to him that the partnership was more about getting Intel to back Solaris than it was about selling a whole lot of servers. He also said this doesn't mean AMD won't still see Sun as a great customer.
My take: Chip makers are, without exception, confident about their upcoming products – so I take everything Allen said with a grain of salt. Still, Allen laid down some very specific claims and projections, particularly the 40 percent performance boost. (When I pressed him on what exactly that 40 percent includes, it was slightly less clear; he mentioned a number of metrics, including performance per watt.)
The future of password security: no easy answers
Also, it is obviously in AMD's interest to drum up customer curiosity about Barcelona, in hopes that some will hold off on purchasing Intel's quad-core offering, and at least do an Intel/AMD bake-off later this year.
Is Allen's confidence in Barcelona warranted, or is it an attempt to spread anti-Intel FUD (fear, uncertainty and doubt)? Time will tell.
Conroe isn't forever. It will reach a limit where a cpu will surpass the desine one day. Like the Power 6/7. Or cell. IBM is the top cpu manufactuer when this comes out. Nobody can denie that fact even if AMD is able to take the number 1 spot in the eyes of the desktop. The server market will be taken by IBM if performance was everything. Intel would be 2nd or 3rd after this happens, but who cares. if you challenge this fact it really shows how loyle you really are as a dog.
Where is AMD and K8L?
Intel can show running systems on 45nm to the people and press:
1) 45nm dual core mobile processor in a notebook with Microsoft Vista running Microsoft Office 2003 applications.
2) 45nm dual-core desktop processor running high definition video content (1080P) under Microsoft Vista. 2.13 GHz
3) 45nm quad-core desktop processor running Ubisoft Rainbow Six Las Vegas game under Microsoft Vista. 1.86 GHz
4) Two 45nm dual-core processors running Glaze Workstation application under Microsoft Windows 2000 Advanced Server. 2.13 GHz
5) Two 45nm quad-core processors encoding a video in Adobe Premier under Microsoft Vista. 2.13 GHz
http://www.anandtech.com/cpuchipsets...spx?i=2915&p=1
Double...
Shintai why you bolded quad-core :stick: ??
It is logical that if Penryn (dual-core) is functional then 2xPenryn on one substrate will work as well.
Shintai,the master of the off-topic is on the road again!
PS Actually the Turtle1 is the master,the one above mentioned is the 2nd place :D.
45nm quadcores should not be bolted like 65nm.Quote:
Originally Posted by Lightman
Not really, itīs more a statement on what AMD lacks with their announcement. Since K8L should be about 6-8 weeks infront of Penryn. But maybe itīs because AMD dont have anything to show...Quote:
Originally Posted by informal
Also the ES samples are nowhere to be seen, even tho its a serverchip and the boards and new chipsets will require extensive testing and validation.
AMD doesn't send out "mass" ES shipments like Intel does. Instead, they do most of their testing in-house. K8L does not require any new chipsets as it'll be a "drop-in" replacement for current socketF Opties. As long as the mobo manufacturers have built their boards according to AMD's guidelines, testing for compatibility issues will take very little time.Quote:
Originally Posted by Shintai
Shintai thinks that the whole world should function as intel corp(tm).Quote:
Originally Posted by s7e9h3n
Thank God it's not the case.AMD operates in a different manner,and unlike intel they plan their moves carefully and smart,not giving away what they have too early.It's been that way in the past and it will be that way in the future.
Oooh, yay, they showed off a dumb shrink. Its not that big of a deal.Quote:
Originally Posted by Shintai
Oh yea , they plan their moves so right , that's why they have a path laid with past blunders....;)Quote:
Originally Posted by informal
Penryn isn't a dumb shrink.It has almost 20% more logic transistors than Conroe.Quote:
Originally Posted by ether.real
There is more in that chip than what was revelead until now.
Yeah it's a wonder chip,we all know that :rolleyes:Quote:
Originally Posted by savantu
Really mysterious one :rolleyes:Quote:
Penryn, the first 45nm processor (shown above), is largely a Core2 Duo, with some minor enhancements that boost the transistor count to 410M, from 293M for Woodcrest. The most obvious use of transistors will be an extra megabyte of L2 cache, bringing it up to 3MB for desktop parts, while high-end desktop and server designs will use 6MB. In a quad core configuration, using dual chip packaging, this would translate to 6 or 12MB of L2 cache. Penryn will also sport ~50 new SSE4 instructions that are targeted at HPC and media applications. Of these new instructions, roughly 80-90% will be executed in hardware. The remainder, mainly the CRC and string instructions, will be microcoded.
in other words....a slightly enhanced dumb shrink.
kinda like VeniceQuote:
Originally Posted by ether.real
Some people hear should really post under the Intel Section
THIS IS AN AMD THREAD
so stop talking about 6300/4300/6400/Penryn INTEL CRAP
this is a thread about K8L
K8L will use intel's SSE4 instructions later anyway ... so it's kinda related. Plus, we like to go bring back reality to some amd fanboys to make them stay normal.
I hope some of you guys get K8Ls soon in like april.
I may get Barcelona if they have an AM2+ version that supports unbuffered memory. otherwise I will wait for Agena.
There should be one early on,along with the socket F versions.Quote:
Originally Posted by ether.real
The price will probably be high in the beginning.
Indeed. Like when AMD carefully and smartly hid their last new core (K8) from the public until 4 years before it's launch and the first ES benchmarks didn't hit the web until 16 months before the launch. :DQuote:
Originally Posted by informal
Fred, will you please stop trolling the AMD threads....I barely visit here and I am sick of you already.
You wouldn't notice the obvious even if it struck you in the head...Quote:
Originally Posted by informal
Oh yes , 20% more transistors for SSE4 , who would have thought of that ?Quote:
Really mysterious one :rolleyes:
What about improved FP performance or VT2 or the possibility of HT ?
:slap:
If you have any relevant facts concerning K8L that you'd like to share, I'd be very happy to hear them. I only visited this thread to learn something about K8L but all I've seen so far is a lot of rumor based speculation, zealous optimism and the fallacious "K8L is ready to go but AMD is keeping it top secret like they always do" argument.Quote:
Originally Posted by ether.real
Just read the realworldtech article ,D. Kanter explained it all pretty well.It's not that hard.HT is a possibility?More like a long shot to me.What improved FP?Minor core revisions don't yield the FP improvement.VT2 is in the line of minor improvement,just like RevF for AMD did bring that one(in pacifica version).Quote:
Originally Posted by savantu
If you base your claims on rumor mill information,you will end up like your smiley.
Here's some recent K8L news that may be of interest:
http://www.dailytech.com/article.aspx?newsid=5874
Quote:
The desktop equivalent of Barcelona, codenamed Agena, is the 65nm flagship of AMD's next-generation desktop processors. Launch frequencies were quoted at "2.4 - 2.6GHz." Previous roadmaps had indicated Agena would debut at 2.7 to 2.9 GHz. Agena will have a 2MB L2 and 2MB L3 cache per CPU. AMD's internal guidance denotes this as a 125W TDP processor. As the flagship, Agena will be the first next-generation desktop launch and is scheduled for Q3'07.
Kuma, the dual-core mainstream next-generation desktop processor was quoted as having launch frequencies of "2.0 - 2.9GHz." Unlike the quad-core Agena processors, Kuma will feature 1MB of L2 and 2MB of shared L3 cache. Kuma will launch with both 89W and 65W TDP variants, but Energy Efficient models scheduled for 35W TDP will follow shortly after.
Rana, the next-generation Sempron successor codename, will launch with frequencies in the 2.1 to 2.3 GHz range. The dual-core CPUs will feature 1MB of total L2 cache, but no L3 cache. Rana's TDP is rated at 65W. Rana will not launch with the Agena flagship; AMD roadmaps have the processor launching at the same time as the Energy Efficient Kuma processors, or approximately Q4'07 if the launch schedule holds together.
Good news that semprons are going the way of dual cores with Stars,was about time.Quote:
Originally Posted by Fred_Pohl
And your trolling is making this thread any better? If you have some relevant facts, share them or shut the hell up.Quote:
Originally Posted by Fred_Pohl
http://amd-barcelona.com/Quote:
Originally Posted by ether.real
At least I'm trying to contribute... how about you? :D
the day you are contributing something usefull in this thread i will buy you one 1000l of good belgian beerQuote:
Originally Posted by Fred_Pohl
so thats not going to happen because you are full of BS
That was pretty funny. :DQuote:
Originally Posted by GoThr3k
Here is news from the Analyst Day event in New York today. AMD see the end of the Homogeneous Multicore CPU and the rise of the Heterogeneous Multicore CPU - what they call the Accelerated Processing Unit. This will include not just the usual computing core but several cores dedicated to specialized functions such as graphics, JAVA acceleration, and video encoding/decoding. Having said that, they also said that they are currently working on an 8-core homogeneous multicore CPU.
Fusion will be put on Desktops in this config later after moble units with lesser cores are released. APU's are much more powerful then the CPU's of today and can not be compared.
http://rubyworks.net/forumz/viewtopic.php?t=363
Ummmmmm... I liek Belgian beer! Can my contribution be factually based or must I sing K8L rumors in unison and key with the AMD fanboi choir? :DQuote:
Originally Posted by GoThr3k
Quote:
Originally Posted by Fred_Pohl
Lol, Belgian beer taste too sweaty. How bout a Sam Adam's winter brew...
Ply
Sam Adams is another fav but sometimes nothing quenches my thirst like a good Belgian White. Not to mention that 1000L of free Belgian beer is quite an enticing offer. :DQuote:
Originally Posted by Plywood99
Well you can dismiss the added transitors as NN did. But 1mb of cache more doesn't quit added up to 1 million extra transistor.Its a lot more.Quote:
Originally Posted by informal
http://techreport.com/etc/2006q4/fall-idf/index.x?pg=1
Here is a quote from this article
The bulk of SSE4's 50 or so instructions is comprised of new compiler vectorization primitives, which should make it easier for compilers to translate software written in high-level languages into effectively parallelized code and data structures. These new instructions encompass both integer and floating-point operations, and include provisions for dual- and quad-word multiplication, blending, and format conversions. SSE4 also has some related "media accelerator" functions that expand SSE's capabilities. Among them are four instructions that round floating-point values to integers and a floating-point dot product capability that should prove especially useful for graphics. Taken together, Intel expects these new instructions to help further the traditional promise of SSE as an accelerator for multimedia, 3D gaming, graphics, and scientific computing.
I doubt very much the the effectively parallelized code means any thing but H/T useing to cores to run 1 thread. Meaning penryn is effectively doubling it performance.
turtle it is 14.2M transisters per 256kB of Cache :Fact:
Wow man,just wow :clap: .You sure could help intel marketing dep.Quote:
Originally Posted by Turtle 1
QFA( "A" is for arguing :D,in the future :) j/k)Code:Meaning penryn is effectively doubling it performance.
The cache l1 doesnt matter . penryn uses the same amount of cache L1 . There is 62 million transitors in 1mb of l2 cache x 6 = 372 million transitors in l2 cache. That leaves 38 million transitors of core logic. That means penryn has 5 million less transitors in it for core logic than conroe.. that would mean penryns transitor logic is smaller than conroes. unless the number of transitors it takes to make 1mb cache in conroe is differant than the number of transitors it takes to make 1 mb of cache in penryn which i am sure is the case. That said no one knows how many transitors has been added to the core logic of penryn unless you work at Intel in engineering. FIXEDQuote:
Originally Posted by nn_step
Umh no...6MB of L2 using 6T cells needs 288 million transistors.Logic,L1+everything else for L2 needs 122 million for Penryn.Quote:
Originally Posted by Turtle 1
Conroe has 4MB of L2 , 192 million transistors.99 million left.
Even if we assume that for each MB of L2 you need 3 million extra transistors , that leaves 104 million for Penryn and 87 for Conroe in logic only.
17 million transistors is 2 P3 cores ( I mean the entire core , with 256KB L2 ) .It is obvious Penryn is much more than a simple shrink.
Quote:
Originally Posted by savantu
Amazing how amd threads end up about intel if i wanna read about intel il do so in the intel section can people please keep this thread on topic so when some good k8l news is out we dont have to start a new thread as this one is closed.
the second barcelona photo i've ever seen
http://www.watch.impress.co.jp/akiba...age/nvis36.jpghttp://www.overclockers.ru/images/ne.../30/k8l_01.jpg
+1 ..mercy..Quote:
Originally Posted by pocketbikeuk
For those interested nn-step pawned me pretty good on the core transitor count. Penryn increased it core logic transitor count by 17.8% . Still thats not bad if it increases performance.
Some discuss technical details and others :banana::banana::banana::banana::banana: about the weather :slap:Quote:
Originally Posted by pocketbikeuk
AMD isn't alone in the marketplace , as lons as there is a competitor comparisons will be made.What's your problem after all ? Need a pure AMD cheering ground ? Go to sharikou's blog and become one of his followers.
Give me Mod-Privlages and I'll delete all the Intel posts since this IS my thread and in a AMD forum is it not? =P
So physical proof of a real chip has been found. Must be a (ES).
I believe you would do a heck of alot more damage with Mod power than the Intel Fanboys could ever do:p:Quote:
Originally Posted by Serge84
Quote:
Originally Posted by Savantu
It's got nothing to do with a cheering ground.
It's a K8L thread, I assume here so one can post and one can find information about K8L as it comes to hand, not sift through pages and pages and pages of intelvs amd flamewars.
Quote:
Originally Posted by savantu
No
This is an Amd forum not a generally Intel vs Amd thread. You have no right to come here and spam like you do. You sir are a troller of the worst sort .Im so sick of your imature behaviour::stick:
Fair enough and I am sure your staement fits me also. But we pretty much know everthing we can know about K8L .Quote:
Originally Posted by Teroedni
Everyone is a little ansie to see some es chips and bench marks that would help a lot. Right now all we have on K8l is that its going to be 40% than conroe. If its true why didn't AMD give us a real Demo in DEC?
You can't blame the intel side for standing up and saying hay show us the benchmarks instead of the marketing hype can ya.
It really adds more tension to the water now that intel has shown real demo's of Penryn Running with AO cores thats 20% faster with the same voltage and freq, as conroe. Add to that 17% increase in core logic. Anand says 20%. So I am assuming that translates to even more of a preformance boost. Than add into the fact these chips will like O/C to 4.75 ghz.
Its hard for the Intel side to stay outside when AMD has shown us nothing other the marketing hype. Wouldn't you agree?
I for one want to debate with the AMD side . I don't want to argue wth the amd side. Debate leads to more understanding . Argueing leads to flaming and closed threads. As insults strart fling around.
Intel side vs amd side LOL.... I just felt like pointing out how ridiculous this kind of mind set is. Are you sub 15yo ? Jeez....Quote:
Originally Posted by Turtle 1
I have to ask : do you even know what trolling is ?Quote:
Originally Posted by Teroedni
Since when are technical facts trolling ? I ask again : how should an AMD only thread look like ?
In Internet terminology, a troll is a person who enters an established community such as an online discussion forum and intentionally tries to cause disruption, often in the form of posting messages that are inflammatory, insulting, or off-topic, with the intent of provoking a reaction from others.Quote:
Originally Posted by savantu
This thread is about Amd next generation processor. What makes you think that this thread is for Amd versus Intel or Penryn vs K8l:confused: . Sure you may post technical info, buts that info is not about K8l:stick:
Im just so sick of certain people invading the Amd K8l thread all the time just to post how much better this and that from Intel is. 2 Threads is allready been locked because of this :mad:
Here is 2 threads from the Intel forum which i had to search for in order to locate them. Why is it that a Thread made for an Future Amd processor get plenty of babble and such for Intel processor , while in the Intel forum theres almost no discussion at all?
And you have not posted in any of those threads either. Why is that Savantu?
http://www.xtremesystems.org/forums/...ight=yorkfield
http://www.xtremesystems.org/forums/...ight=yorkfield
I think it's because savantu fits the description you gave :).Quote:
Originally Posted by Teroedni
He conveniently avoided those topics,but he somehow managed to post here :D.Really interesting:)
Please stop spamming MY Thread. God! You can ONLY talk about K8L nothing else off topic besides AMD related. This flaming has got to stop. Just ignore people from the other side ok? We are here for info about K8L we could care less what Intel can do.
(YOU REALLY SHOULD POST IN THE INTEL FORUMS IF YOU WANT TO TALK ABOUT A INTEL TOPIC, ITS GREAT AND ALL TO BRING UP USEFUL INFO BUT IN THE WRONG FORUMS IT'S USELESS. WE DON'T CARE ABOUT INTEL IF WE DID WE WOULD POST IN THE INTEL FORUMS "THAT WOULD MAKE SENSE". IF YOU CAN READ LAST TIME WE ALL CHECKED THIS WAS THE !!!AMD FORUMS!!! CAN'T SAY IT MUCH CLEAR THEN THAT... NOT A INTEL FORUM HELLO, MAKES NO SENSE WHAT SO EVER TO POST UNRELATED INFO IN A FORUM ABOUT A TOTALLY DIF CPU COMPANY, YA THINK... DURRHURR!?)
:D what do u wanna hear here except flood?Quote:
Originally Posted by Serge84
i see people drawing Kuma screenshots :)
Quote:
Originally Posted by w0mbat
:slobber: Could it be true? :confused:
Quote:
Originally Posted by Serge84
Serge I will do as you asked. But if I see AMD K8L will be 40% than intel without showing the benchmarks . That invites me or anyone else in to thread. The moment Intel is mentioned. In those terms without proof. Its all hype which= fud. SHOW US THE BENCHMARKS before saying K8l will be 40% faster at the same clock.
Do you think this would be fair Serge. I for one don't want to see this thread closed . Some good stuff in year. Just leave Intel out of it and I see zero problems.
yes it couldQuote:
Originally Posted by Malkec
Somebody is trying to tease us with a Kuma's L3 cache (ES).Quote:
Originally Posted by w0mbat
http://img220.imageshack.us/img220/1...ircpuidfr8.png
More teasing? Pic of a CPUz shot of a X4.
****
Well to the other guy I didn't say K8L would be 40% faster. AMD did and its prob only in FPU because they did physically double it's size. But for everything else who knows, all we know is the specs say to expect similar speed performance to conroe because of the new cycle speeds of K8L.
I am just going by the sources, I don't go by anything else. I have just as much idea whats in store as the next guy. We just don't know yet. However AMD looks pretty excited about something to be braging about it. They usouly don't do a intel style show off. Its too early for benchmarks, I'm sure people have the (ES) but are waiting for the OK from AMD to show the Star processors. We never really see them until they come out or close to it like a month or 2 before, its usouly done only in the FAB's for testing is how AMD has always been.
@Serge84
You know that pic showing CPU-Z shot of Altair is FAKE.
w0mbat pic is also FAKE...
Why are you doing this?
If u know that its fake, then u also know where im from and why i should fake such a pic? Its funny, everyone is screaming fake just because u dont believe :nono:Quote:
Originally Posted by Lightman
And maybe im a fake too and just existing in ur brain? Like kindergande here, fake, fake, fake, fake, fake, ...
If we presume it's not fake, could you please tell us what processor is on that cpu-z right corner shot? Kuma (sempron successor?) :confused:Quote:
Originally Posted by w0mbat
Nobody knows if they been edited or not because for one I just came across it, I didn't make the thing. It Could it be true. Maybe. Could it be a fake. Maybe. Who cares, and 1st of all there are (ES)'s out there of K8L there is physical proof these things have been made into a working CPU so why not?Quote:
Originally Posted by Lightman
Thats like saying the other companies cpu was fake when ppl showed specs on it when they where real (ES)'s how can this be any dif? Tell me how can we know for sure or not when K8L EXISTS AS A REAL CPU not just a peice of silcon on a die wafer. Its as bad as AMD showing it working in a task manager. You could say that was fake too. *Shrugs* If its fake or not it doesn't really matter, your just being inamaginative. Because thats not the point at all. Why am I doing WHAT? I didn't do anything I just showed what could be proof of (ES)'s. Next are you going to tell us the shots of the real physical cpus are also fakes?
The 1st K8L's come out in April or may. why wouldn't (ES)'s exist? Expecting it to come out much later? it was more like 9 months we saw the special (ES)'s of that other companies cpu. Did we challange the reliability of the 1st CPU-Z shots? Prob, then they ended up being real. So why hate on K8L so much, I'm not even starting.
It is a pic from a friend working at AMD. He said its a K8L Antares dualcore. Maybe i can please him for validation.
Kuma is the X2 K8L's, Rana is the dual core semprons, Agena is the X4's and AFX K8L's, Altair is a older star name they used but recently changed it to Agena. Spica is a single core K8L with very low performance. Information is unknown on the core speeds they will use.Quote:
Originally Posted by Malkec
So your serious?Quote:
Originally Posted by w0mbat
********
http://www.xfastest.com/redirect.php...8&goto=newpost
Some more info.
Core Enchancements:
128 Bit floating point:
Applies only to Agena & Kuma
New SSE4A instructions:
Advanced Bit manipulation
MWAIT & MONITOR instructions
Misaligned SSE Mode
Additional Features:
Power management state invariant time stamp counter (TSC)
increased number of TLB Page entries
1GB large paging support
Physical address space increased to 48 bits
IMC Enhancements
DDR2 Dimms in products variations:
32 iFetch
Larger(OoO) Buffers
Socket AM2+: Dual Channel unbuffered 1066 support
Socket 1207+ Dual Channel unbuffered 1066 support
Memory Controller enhancements
Write Burst & DRAM prefetching performance improovements
DRAM writes can be buffered in the memory controller before being opportunistically bursted into DRAM controler to improve DRAM interface efficiency
Read prefetcher detects stride paterns and issues prefetch requests based on confidence level
Channel Interleaving
Roadmap:
Agena FX(K8L):
Q3 2007:
2.7-2.9GHz
4x512kB L2 cache
2MB shared L3 cache
Socket 1207+, 1207 compatible
4000MHz hypertransport Bus
TDP not determined yet
65nm SOI
Agena(K8L):
Q3 2007:
2.4-2.6GHz
4x512kB L2 cache
2MB shared L3 cache
Socket AM2+, AM2 compatible
4000MHz hypertransport Bus
TDP 125W
65nm SOI
Kuma(K8L):
Q3 2007:
2.0-2.9GHz
2x512kB L2 cache
2MB shared L3 cache
Socket AM2+, AM2 compatible
4000MHz hypertransport Bus
TDP 89W, 65W
65nm SOI
Kuma EE(K8L):
Q4 2007:
2.0-?GHz
2x512kB L2 cache
2MB shared L3 cache
Socket AM2+, AM2 compatible
4000MHz hypertransport Bus
TDP 35W
65nm SOI
Rana(K8L):
Q4 2007:
2.1-2.3GHz
2x512kB L2 cache
No shared L3 cache
Socket AM2+, AM2 compatible
2000MHz hypertransport Bus, HTT1
TDP 65W
65nm SOI
Sources:
Chilehardware
Dailytech
Just wanted to recap but most know this already.
From info based on what spec info we have I will try to make up a ALU and FPU chart of K8L on each processor speed if I have time. Just think that would be intresting just for fun to speculate performance.
Yes i am. Im not a kiddie who wants attention, i say its not my CPU. I will ask him for validation. If i get a link i will post it here, if not i cant proove that this pic is real. Then i have to excuse me and try to have a validation with me next time. But im shure that he isnt liying to me cause i know him good and hes over 40 years old.
K8L ALU & FPU Performance
Agena X4 & AFX(K8L):
2.9GHz Quad Core
ALU:46,800(80%/X2) Or 52,000(100%/X2)
FPU:40,320(80%/X2) Or 44,800(100%/X2)
Kuma X2(K8L):
2.9GHz Dual Core
ALU: (K8)21,000 If K8L=26,000(25%+)
FPU: (K8)16,000 If K8L=22,400(40%+)
According to this if Sandra scores are used to compare K8 with K8L specs we can see how K8L might perform agenst it's last gen parts. If these ALU & FPU numbers are true the Semperons will be even faster then some of the fastest FX's of today.
"This is just estimated" So it all depends on how well they OC and if L3 as well as other arc enhancments will make the difference. There will be double the bandwidth on memory and system. It could be very close. But FPU performance will be superior with SSE4A.
I hope we have some final proof. :D I can't wait to get the thing.Quote:
Originally Posted by w0mbat
BTW thats a good OC on your rig.
Guys, no offense but on this small corner you're showing w0mbat it's clearly visible that 'Level 3' is moved compared to 'Level 2' and is brighter as well (means 'tweaked').
Then pic from Serge84 is definitely 'tweaked' coz CPU-Z doesn't have 'Altair' name and 'AM2(+)' in file (you can view cpu-z.exe and check, there is only global 'K8L' signature). On top of that clocks are misplaced. CPU-Z always is centering text in boxes but on this pic they are biased to left. There is more to that like version of this tester, etc....
I would like to see any screens from AMD Quads and if you w0mbat will succeed with CPU-Z validation (or other informations) I will be more that happy ;)
Just how can you "VIEW" into the CPU-Z exe code?Quote:
Originally Posted by Lightman
here is an extract from cpu-z 1.38 data segment
Quote:
SledgeHammer Athens E4 Venus (UP) EE HE AMD Opteron 1%2d Lancast
er AMD Turion 64 ML-%d AMD Turion 64 MT-%d SH8-E5 Newark Oakville Odessa
Mobile AMD Athlon 64 %2d00+ Toledo AMD Athlon 64 FX-%2d JH-E6 AMD Athlon
64 X2 %2d00+ BH-E4 Manchester DH-E3 DH-E6 Venice SH-E4 San Diego DH7
-CG NewCastle CH7-CG Paris SH7-B0 SH7-C0 SH7-CG ClawHammer AMD Athlon
64 %2d00+ BH-F2 AMD Turion 64 X2 Mobile TL-%d AMD Turion 64 X2 Mobile Tay
lor AMD Turion 64 Mobile ML-%d AMD Turion 64 Mobile Keene Mobile AMD
Sempron AMD Opteron 82%d SE AMD Opteron 82%d AMD Opteron 82%d HE AMD Optero
n 82%d EE AMD Opteron 22%d SE AMD Opteron 22%d AMD Opteron 22%d HE AMD Optero
n 22%d EE AMD Opteron 12%d EE AMD Opteron EE AMD Opteron 12%d HE AMD Opteron HE
Manila SH-F0 DH-F2 Orleans JH-F1 Windsor Brisbane ╕▲Е=AMD Athlon 64
X2 Mobile AMD Athlon 64 X2 %2d00+ Mobile AMD Athlon 64 X2 AMD Opteron 12%d
JH-F2 Santa Rosa AMD Opteron 12%d SE AMD Opteron SE AMD K8L Attached devic
e PCI device at bus %d, device %d, function %d
K8 Revision ID %d.%d
K8 Thermal sensor %s
so are there real screenshots of cpu-z running on a K8L system? or are these fake...
I cant see these things. Can u show me them? Because here it looks normal and nothing is brighter or moved. Maybe its ur screen.Quote:
Originally Posted by Lightman
Dude the L3 cache line isn't even centered vertically!Quote:
Originally Posted by w0mbat
fake. Sorry.
http://img479.imageshack.us/img479/4467/duhef5.jpg
So if he works for AMD, why would he supply fake screenshots. So much BS in this thread...and the usual few tries as always to make the 2 eggs into 5 chickens. Just a shame time with catch up soonish. Also I really doubt dualcores will have L3. The L3s benefit is extremely small for such a purpose. But its rather good for cache coherency control.
Serge84: I don´t think K8L got SSE4, but SSSE3. It would be very unlikely due to the fact Intel creates SSE4. (Also why in history AMDs SSE implementation ahve been alittle step behind).
ahh It's been stated for months the dual cores will have 2Mb L3
http://www.xfastest.com/redirect.php...8&goto=newpost (repost)
@mAJORD: Now i will ask him for validation. I mean, i know him good. He has no photoshop skills so maybe he just wanted to make a little joke on me. But i dont think that this is funny.
This was IBM and AMDS news for Dec.
http://www.dailytech.com/article.aspx?newsid=5329
After intel releases info that there new 45nm process uses Highk and metal gates IBM/AMD release news that they to have High K and Metal gates.
I believe in a thread you were saying how the above links info would be better than anything around. Which is it the linked info. or high K or whats actually going on here. The evidence points to market spin and hype.
So nn is it Ultra low K or is it high k . Its says in that article Zram is 15% faster using SS. Yet you say Zram only works on sol. Which is it nn.
Sorry about that guys this wasn't suppose to post in this thread . I had 2 threads open. But I decided to leave it as it does ask a valid qyestion.
make your own damn topic, JUST READ THE TOPIC!, wait I'll make you a paint graph SO YOU CAN SEE WHAT THIS THREAD IS ABOUT:slapass: !Quote:
Originally Posted by Turtle 1
http://img255.imageshack.us/img255/3...turtle1uh7.jpg
IF YOU WANT TO TALK ABOUT 45nm PROCESS AND HOW ADVANCED INTELS IS GO AND MAKE A THREAS IN THE INTEL SECTION, BUT STOP GOING OFFTOPIC IN THIS THREAD!!!
PS: turtle, you know that there is a delete button OK?
PPS: never knew how useful caps lock is :rolleyes:
I asked him for a pic or validation and he replied that he will send me a off screen pic. Now i hope for a good end :)
Hi Turtle 1. If you move your question to the proper thread, I'd be happy to address it.Quote:
Originally Posted by Turtle 1
thanks for remembering to keep the nn lower case :up:Quote:
Originally Posted by generics_user
take a look at my agena :lol:
http://img485.imageshack.us/img485/8...enacpiaos7.jpg
Great! Any hints WHEN this will happen?Quote:
Originally Posted by w0mbat
I think if you get this pic we all will own you couple of :toast:
barcelona is at rev. A3/B0 at the moment right?
I think it will take about one week if he wants a good fake :p:Quote:
Originally Posted by Lightman
No, i think tomorrow :cool:
K8L will be on 65nm Ge-SSOI with low K metal gates in 2007. They will use SGOI 45nm high K metal gates in 2008. What currently IBM uses in there 65nm POWER6 and cell processor when its manufactuered on 65nm later on. AMD will take great advantage of both of these fab processes in the next 2 years. These processes are much more complex and better then bulk silicon ever could.
Here...I'll save you the trouble.....http://www.awardfabrik.de/forum/show...3&postcount=36Quote:
Originally Posted by w0mbat
By the way, those are fake.....
Cool!Quote:
Originally Posted by s7e9h3n
There is no such thing as a 'low-k' metal gate.... 'low-k' is good for the backend processing for decreasing RC (wire) delay. Do you know what you are talking about? And the current gate material AMD is using is actually just plain old vanilla poly silicon, same as the rest of the industry.Quote:
Originally Posted by Serge84