- Učlanjen(a)
- 12.07.2000
- Poruke
- 6,934
- Poena
- 800
ako sam ja dobro razumeo nije ono Coolaer testirao vec neko sa njegovog foruma?! Ispravi me ako gresim.Ma nećemo verovati Coolaer-u i ako je jedan od najvećih testera na svetu.![]()
ako sam ja dobro razumeo nije ono Coolaer testirao vec neko sa njegovog foruma?! Ispravi me ako gresim.Ma nećemo verovati Coolaer-u i ako je jedan od najvećih testera na svetu.![]()
ako sam ja dobro razumeo nije ono Coolaer testirao vec neko sa njegovog foruma?! Ispravi me ako gresim.
zanimljivo je da s jedne strane imamo fantasticne rezultate o kojima piste theInq i s druge strane imamo katastrofalne rezultate o kojima pise Coolaer...
Tebi koji imas 1 CPU u masini naravno da nije preterano bitno![]()
Da naravno, R600 je bolji chip i bolje se prodaje od G80.:dTo bi bilo extra! R600 se prodaje k'o ćetenalva
Ako zeli da ostane na trzistu morace da skrati ciklus i proba da prati Intelov tempo.AMD samo zatvara ciklus koji je bio standard do sada - 4 godine za jezgro.
Ni Intel do prosle godine nije davao prelimiranrne rezultate, pa kada su imali sta da pokazu, a trebalo im je, odmah su promenili strategiju.Pa ni sa prethodnim procesorima uverljivih preliminarnih rezultata nije bilo, zasto bi se to menjalo sa K10?
Osim ako samo to istices, znaci da cisto perf rezultati i nisu sjajni.Verovao ti ili ne perf/watt je ono sto trziste danas trazi. Sta vise konkurencija jos agresivnije gura tu mantru!
To vazi za interne price u kompaniji. Kada pricas sa medijima onda se hvalis, ako imas cime naravno.Pa samo ako budu realni moci ce da kreiraju realnu biznis strategiju
The simple fact is, this core needs clock speed and until 2.4GHz or so, it is not that impressive in my opinion on the desktop. Certain transactions/operations will be noticeable/improved over some of the Core 2 family processors on a performance/wattage aspect from an enterprise overview, but this chip design is going to require clock speed before you start seeing some numbers that make sense in the consumer/workstation market. That is why Phenom will launch at higher clock speeds, different core configurations, and with chipsets designed to take full advantage of the core changes with consumer applications. That is my guesstimate based on performance up to this point, several of the larger OEMs received their final silicon chips this past week, most noticed another improvement in performance, how much, we will find out shortly but do not expect a leap frog over the Blue Bunnies yet.
AMD mora da bude brži najmanje 20 posto od Kentsfilda klok za klok, da bi se IOLE suprotstavio
Priseti se 1999. i izlaska prvog K7 Athlona. Na http://www.firingsquad.com/hardware/k7550preview/page9.aspAMD mora da bude brži najmanje 20 posto od Kentsfilda klok za klok, da bi se IOLE suprotstavio Penryn derivatima koji će u kombinaciji sa X38 ići 10ak posto brže od Kentsfild+P35 kombinacije na istom kloku, i pored toga debelo pregaziti 3 GHz.. I meni ovo nažalost sve više liči na R600 priču, čak i posle čitanja onog što je Gary Key napisao na Anand forumu:
na sledecem screenshotu ima nesto cudno
http://www.muenster.de/~e30pics/Bilder/Computer/K10-Intel/k10-3.jpg
radi se o Win 2003 Server X64 operativnom koji cist trosi normalno kod 2GB memare nekih
300-350MB stim sto je ovdje u pitanju 4GB tako da sistem jos vise Cache'a rezervise.
Druga stvar sto smrdi je da Cinebench pri prikazivanja rezultata zauzima dodatnih 170MB
Pa Cak i Pagefile bi trebao da bude veci kod aplikacija koje rade.
Cenim da bi trebalo da bude oko 500MB Commit Charge a ne polovina .....
FAKE ????
Broj otvorenih procesa u Taskmanageru 26 -> a Commit Charge samo 255MB , hmhmmhmh ????
Neznam mozda su gasili neke servise ali onda bi morali imati manje aktivnih procesa
zanimljivo zapazanje...jel' moze neko da simulira na 2003 x64 serveru sa 4GB i upaljenom Cinebenchu ovo isto??? cisto da vidimo da li je ovo uopste moguce ili je bilo malo photoshopa
ili je ovo neka ultra-tweakovana 2003 edicija![]()
Priseti se 1999. i izlaska prvog K7 Athlona. Na http://www.firingsquad.com/hardware/k7550preview/page9.asp
adresi mozes da vidis preview test gde su rezultati prilicno traljavi. Takodje su ljudi iz Intela *****li kako doticni K7 nece preci 650 Mhz ! :d
Svi znamo sta je posle bilo.
Prema tome, nemojte mnogo da se lozite na to sta su tamo neki Japanci, Tajvanci ili ko zna vec ko na nekom forumu testirali.
K10 nema sanse da je klok za klok isti kao K8 ili cak losiji. Uostalom, to nije netburst, pa tesko da moze biti takvih penala.
Ja ne verujem da ona Phenom masina pravi 30K markova 06, ali verujem da ce performanse biti ok.
Da li si ti bilo gde procitao da ja R600 poredim sa G80? Da negde isticem koji je bolji i koji se bolje prodaje? Ako ne umes da procitaqs samo cu ti napomenuti da sam replicirao na tvoju negativnu konotaciju u vezi R600. R600 se odlicno prodaje... provereno! Da li su te kolicine vece ili manje u odnosu na G80 nemam informaciju, tako da nisam to ni pominjao.Da naravno, R600 je bolji chip i bolje se prodaje od G80.:d
Pa nije li Bulldozer najavljen za dve godine nakon Barcelone?Ako zeli da ostane na trzistu morace da skrati ciklus i proba da prati Intelov tempo.
OK, slazem se (konacno), ali kakve veze promena celokupne Intelove marketinske strategije ima sa K10?Ni Intel do prosle godine nije davao prelimiranrne rezultate, pa kada su imali sta da pokazu, a trebalo im je, odmah su promenili strategiju.
Nemam repliku za ovu liniju rezonovanja...Osim ako samo to istices, znaci da cisto perf rezultati i nisu sjajni.
A ti si exper za PR & HR?To vazi za interne price u kompaniji. Kada pricas sa medijima onda se hvalis, ako imas cime naravno.
Kako moze K10 da ti lici na bilo sta kad ga jos nisi ni video?K10 pocinje da mi lici na nesrecni Preshot. I on bi bio super procesor da je postigao planiranih 5GHz. Valjda Barsa nece proci kao i doticni.
Pa prvi K7 i nije nešto leteo, ako mislimo na Slot A varijantu, kojoj je keš radio na 50 ili 33% takta CPU-a. Tek je T-Bird bio dobar i konkurentan.
Ni ja ne verujem da je K10 ovoliko spor, ali pravo stanje stvari ćemo znati tek kad neki od ozbiljnijih sajtova ili review-era odradi posao kako treba.
E cekaj kada pricamo o ovom. Da li stvarno ima neko ko veruje da je K10 sporija od K8 arhitekture? Taj ko to misli (a ima ih ovde dosta) nemaju veze sa zivotom i pojam realnosti im je izgubljen u bagovima C2D procesora, sa AM2 platformom prosle godine AMD je odlicno unapredio mem bandwith, K10 je tu da donese isto takva unapredjenja u IPC domenu i sve to da se nastavi sa sledecom generacijom njihovih procesora, nema mnogo filozofije, uostalom u zadnjih 7 godina Intel je uvek stagnirao sa arhitekturom, Netburst je picen do krajnjih granica brzine i disipacije toplote
kroz nekoliko verzija jednog te istog jezgra, C2D je iako dobar pomak opet u fazi stagnacije jer Penyrin po testovima radi malo brze od Conroe verzije, to nije slucaj kod AMD-a, oni su uvek prvo izbacivali najgoru mogucu varijantu jezgra i u kratkom periodu ga unapredjivali do maximuma (pogledajte njihov 90nm proces danas), ovo mi izgleda kao poredjenje DV i Mpeg2 formata
![]()
Ma da, sve u svemu snajper ce se i dalje brze dodavati u COD2 samo, ako imas AMD procesor u masini![]()
![]()
lol
Kao ona cuvena "Moj drug je presao na AMD-u Wolfenstein brze nego ja na Intel-u."![]()
Prvi K7 je razbijao PIII Katmai kako oces, tek kad je Intel izbacio Coppermine, onda su bili tu negde i to u integer operacijama, samo zahvaljujuci brzom keshu na Cumine procesoru i boljim cipsetovima.Pa prvi K7 i nije nešto leteo, ako mislimo na Slot A varijantu, kojoj je keš radio na 50 ili 33% takta CPU-a. Tek je T-Bird bio dobar i konkurentan.
Ni ja ne verujem da je K10 ovoliko spor, ali pravo stanje stvari ćemo znati tek kad neki od ozbiljnijih sajtova ili review-era odradi posao kako treba.
Prvi K7 je razbijao PIII Katmai kako oces, tek kad je Intel izbacio Coppermine, onda su bili tu negde i to u integer operacijama, samo zahvaljujuci brzom keshu na Cumine procesoru i boljim cipsetovima.
Link koji sam postovao sa firingsquad-a je samo ilustracija kako rani sample-ovi umeju da daju prilicno lose rezultate. Zvanicna verzija K7 @550 je imala mnogo bolje performanse od onog preview-a na firingsquad-u.
U bilo kojoj Floating Point aplikaciji K7 je solidno drao Coppermine-a, a da ne pricamo o Katmai-u. Usput, K7 je bio izradjen u 0.25u, a Coppermine u 0.18u. U doticnih 0.25 mikrona su izvukli cak 750 Mhz iz K7, iako su Intelashi tvrdili da nema sanse da predje nikako 600 Mhz u 0.18u procesu.
Coppermine se pojavio u oktobru 1999. U junu 2000. je AMD izbacio Thunderbird i Spitfire jezgra, a krajem 2001. pojavljuju se Palomino i Morgan jezgra. PIII se vrlo tesko nosio sa ovim procesorima, narocito kada su poceli da se uparuju sa DDR memorijom i kada se pojavio prvi pristojan cipset, VIA KT266A.
Jedini nacin na koji su im parirali tada je brutalna sila proizvodnih kapaciteta i sitniji proizvodni proces. Zahvaljujuci tome Intel je pre AMD-a imao kesh na procesoru i manju disipaciju toplote.
Cinjenica je i to da je AMD izvuakao cak 1733 Mhz iz svog 0.18u procesa, Intel sa svojim PIII nije ni u 0.13u izvukao toliko.
Prema tome da rezimiram, prvi sample-ovi i nisu najbolji pokazatelj kako ce procesor stvarno raditi.
http://www.tomshardware.com/2003/02/17/benchmark_marathon/page23.html
Na zalost, Srpsko trziste nije za poredjenje. Narocito iz onog vremena, dugo posle izlaska K7, u Srbiju bukvalno nije usao ni jedan Athlon, narocito zbog uvrezenog tadasnjeg misljenja da je AMD nekompatibilan sa postojecim softverom, sto je naravno ordinarna glupost.<OT>
K7 je u Srbiji bio Vaporware, to pod jedan - maltene si pre mogao da kupiš CUmine nego K7, tako da poređenje K7 sa Katmai-em i nema nekog smisla. Pod dva, ne znam da li si ti taj računar imao, ili si čitao testove, pošto sam ja na par nedelja imao Slot A mašinu u ono vreme i to je bilo agonija što se stabilnosti u raznim aplikacijama tiče. Dok se išta sredilo sa drajverima za ploču i bios-ima izašao je T-Bird koji je bio zmaj, ali prateća FOP 32 ili 38 artiljerija nikako nije bila za mene na duže staze. Inače u aplikacijama koje su imale optimizovan SSE kod T-Bird je naravno bio slabiji klok za klok. Jedno vreme sam imao dve mašine: Cumine 650@866 i T-Bird 900@950 i bile su potpuno jednake u video kompresiji.
</OT>
Naravno! U onim testovima nesto gadno "smrdi" ! :d :smoke:Što se tiče preliminarnih rezultata tu si skroz u pravu, posebno pošto se valjda iz cpuz validacije videlo da nešto nije u redu sa HT linkom.. Kada izađe retail onda ćemo da pljujemo ili da hvalimo. Još par dana.
secam se samo da kad se pojavio prvi k7 (znaci slot A), iz amd-a su nudili 100$ za bilo koji test gde ce p3 (tada jos katmai) biti brzi... u svakom testu ga je k7 drao debelo
I am not saying that increases in the CPU core frequency yield a linear performance gain greater than 1:1. My example as stated was crude and too simple, in this case the cubic inches, compression ratio, and gearing are static, the supercharger simply lets the engine perform more efficiently (from a power output perspective) by taking greater advantage of the fuel/air intake mixture (plus aggressive timings) it has available as RPMs rise.
Probably a very bad example, but I was trying to make the point that the changes in the architecture of this processor and the new chipsets (HT 3.0, etc) do not provide any advantages (in most cases) over the current platforms in performance until the core clock speed increases and we start to notice that around 2.4GHz (see below for other reasons at this time). I think I have said this several times since Computex, AMD desperately needs to get the core speeds on this processor architecture improved (above 2.4GHz or so, privately a few people at AMD agree) for it to be really competitive and to take full advantage of their processor/platform improvements.
I do not think AMD ever intended or even believed this CPU would launch at the speeds it will (1.8~2.0, possibly 2.2 in Q4) as the processor simply does not perform as efficiently as it should (appears capable of) based upon the architecture changes. A lot of the early information we had was that Barcelona would launch in the 2.2~2.4 range and then scale quickly, with a potential to 4GHz in the end. The early performance expectations and claims of performance improvements over current platforms were based on simulations at 2.4~2.6GHz and then scaling upwards. The CPU was designed with these speeds and above in mind, it simply is too slow right now not to mention several core improvements have been flipped on/off or just are not as efficient as they should be in early testing.
At least with the early samples we have seen, there are improvements against current processors on a clock for clock basis as the core speed improves, this does not mean a linear performance gain that is greater than 1:1, it simply means the chip is operating more efficiently as the core speed improves. There could be a wide variety of reasons for this as we have seen dramatic changes in the platform performance almost week to week as new steppings, chipet revisions, and BIOS code were changed. We have seen HT not working or set at 1.0, 2.0, 3.0 specifications depending upon core speed and chipset, secondary caches turned off or even gated based upon core speed (L3 cache and L2 prefetchers as late as July), floating-point instructions flipped on or off, out of order execution of load algorithms flipping from conservative to aggressive and back depending upon core speed, and even translation lookaside buffers being tinkered with during this time not too mention a dozen other changes.
Also remember that the DRAM controller is now split into two separate 64-bit controllers. Each controller can be operated independently by the chipset and there can be some significant improvements in efficiency, especially where the individual cores are working on independent threads and each have their own memory access patterns, yet another area where core speeds could create variable results. Added to this is the fact that the data prefetcher now brings data directly into the low latency L1 data cache, as opposed to the L2 cache in the K8. K10 also increased the ability of its L1 instruction cache prefetcher to handle two outstanding requests to any address. These two areas plus the new DRAM prefetcher on the revised memory controller are the control mechanisms that we have noticed having the greatest impact on performance, especially with the increase in core speed. It is also the area that believe has been most "tinkered" with during the prototype and pre-production phases. We have noticed the processors only needing DDR2-667 in June to really being responsive with DDR2-1066 as the core speeds have increased along with the other improvement/additions to the processor, BIOS, and chipsets.
When I said that certain features were "idle" in some cases, this is what I was talking about. Until we see production level silicon and final BIOS code, it is extremely difficult to determine what is occurring inside Barcelona/Phenom and what is not on a clock for clock basis. Throw into that mix, a whole new generation of chipsets (ie...RD790) that take further advantage of these changes and you have a situation that is very fluid as the initial performance results will be on older HT 2.0 chipsets that are designed for the enterprise environment. There is not a consumer level board available that is tuned for this processor series yet, trying to use it on one is like using a QX6850 on a VIA PT880, yeah it works, but look at the results.
That is why we do not want to guesstimate the performance or even provide tangible numbers until we have had a chance to test released product. For whatever reason, in the early tests, the processor operated more efficiently as the core speed increased, we will find out shortly why it did. I hope this helps and if I could speak in greater detail, I would, but September 10th is getting close. Like I said in my previous message, some people will be happy, some will not, and most will realize that certain hype does not directly translate into expected performance improvements, not until we see some speed. In the end, this processor lays the groundwork for what comes next, sort of like how the Core Series did for the Core 2.
Like I said in my previous message, some people will be happy, some will not, and most will realize that certain hype does not directly translate into expected performance improvements, not until we see some speed. In the end, this processor lays the groundwork for what comes next, sort of like how the Core Series did for the Core 2.
Pre bih rekao da je covek dao poentu u poslednjem pasusu (koliko kapiram Anandtech je imap pristup retail verziji procesora, koja bi, iako to do sada nikada nije bio slucaj, trebalo da radi bolje i "dosta brze" od razvojnih verzija)...
Koliko kapiram, Phenom ispada "Core" (medjukorak), a Buldozer ce biti "Core 2".
Follow along with the video below to see how to install our site as a web app on your home screen.
Napomena: this_feature_currently_requires_accessing_site_using_safari