Search results

  1. J

    AMD Bulldozer architecture "update"

    Idontcare you're not exactly one of those laypeople, are you? Do you know what cluster based multithreading is? Bulldozer presumably is going to make us of that and it's supposed to be 'better' than SMT according to those slides. Is this the correct description: "These patent application...
  2. J

    Intel process roadmap...

    No, reason to roll eyes. Photonics and the use of light is a serious avanue of research, at least when it comes to interconnects. http://en.wikipedia.org/wiki/S...cs#Physical_properties http://techresearch.intel.com/...es/Tera-Scale/1419.htm
  3. J

    Intel Core i5

    So you're saying there's no way they can implement it in a modified K10.5 version e.g. Magny Cours or some other version slated for launch in 2010? That might hurt a lot..
  4. J

    AMD vs Intel at the high end in the future

    Yes, Wikipedia is unrivaled, outstanding and a pretty reliable encyclopedia. Yes, they even happen to use actual sources which everyone can reliably check. In this case the article is based on some rumours from the far east -- what did you expect? Rumours are rumours. At this stage there is...
  5. J

    AMD vs Intel at the high end in the future

    Not if we can trust that CPU-Z read-out (I'm quite sure we can trust JC. he was the first one to leak & publish nehalem numbers). Doesn't changing L2 involve a major redesign? http://www.dvhardware.net/article34782.html According to Wikipedia, however, Sandy Bridge is going to have 512KB L2.
  6. J

    AMD vs Intel at the high end in the future

    If we know how well westmere fares we might be able to better extrapolate what AMD will be up against, as - correct me if I'm wrong - sandy bridge will be a heavily tweaked westmere chip. I'm expecting them to deliver the 5-10% IPC increase that we came to expect from Intel die shrinks, but...
  7. J

    AMD vs Intel at the high end in the future

    When's AMD supposed to launch 32nm? There's a lot of talk of AMD 'closing the gap' or Intel losing their process tech advantage, but is there any official or reliable data to substantiate such rumours? Does anyone know what we can expect from westmere IPC and feature wise? (there is that one...
  8. J

    AMD 6-core Opteron in May and 16core CPU in 2 years

    In the strictest sense I believe most known encryption standards are broken from the beginning. They're merely working because decryption takes too much time. AFAIK correctly implemented encryption via one time pads is the only de facto unbreakable encryption algorithm. Just wondering if this is...
  9. J

    Phenom II > i7

    I got what you mean; but if software is optimisied I'd assume it will scale to n threads (as well as possible). If it uses n threads the gap will surely widen because of HT. Other than that (at 4 threads) both systems should benefit more or less the same, I agree.
  10. J

    Phenom II > i7

    I'm not sure if it is that clear cut and I would bet my money i7 anyway. You have seen the server benchmarks? Both are "sever CPUs" and "similar" as you say, but nehalem completely annihilates shanghai clock for clock in most server tasks, which are generally well-threaded. I remember from...
  11. J

    The Best Server CPUs part 2: the Intel "Nehalem" Xeon X5570

    Great review. Nemesis did you forget to take your meds today? And does anyone know what happened to xtremesystems.org? (haven't they been down for days; someone over there also wanted to review a gainestown rig so I wanted to check it out - see I'm not off topic)
  12. J

    Phenom II x3 710 run with 4 core!

    Wow. That's pretty insulting. IDC's comments are the only reason I regularly visit this board and I've never seen him make an unreasonable statement. MarcVenice, one could ask "what makes you sure they are functional"? I believe there are parts of the core which are not stressed by prime...
  13. J

    AMD prepares dualcore 45nm surprise - Callisto

    Wake up, PhII is slower than 65nm Core 2s. Anything else is speculation on your part (maybe you're right - maybe not).
  14. J

    Intel developing optical chip-to-chip interconnects

    Are you sure QPI will be necessarily replaced with a completely new optical interconnect and it can't just replace our current QPI implementation without major changes? Dkanter said: "Clock encoding and clock and data recovery are prerequisites for optical interconnects, which will eventually...
  15. J

    why Core i7 is not overclockable as Phenom II and Core 2 ?

    Cherry picked i7 975 did 5ghz on air IIRC (over at xtremesystems). Some golden i7 do 4,5-4,6 ghz on air/water, how many PhII and penryn QC can do it these days? I am not sure. No, actually I didn't mean what I said in this case. I was thinking about L1 latency (3->4 cycles). It is generally...
  16. J

    why Core i7 is not overclockable as Phenom II and Core 2 ?

    Idontcare, actually I have been led to believe that i7 can overclock better than Core 2 and Ph II quadcores on high-end air and water, but on sub-zero cooling it seems to top out earlier. I can understand why people are surprised, increased L2 latency and more stages, normally allow higher...
  17. J

    Official Phenom 2 Review Thread

    Your comment is as simple-minded and wrong as if I said "AMD going chapter 11 won't affect Intel at all". Please consider both sides of the argument, Intel dominates already, interestingly their biggest competitor is Intel, i.e. their own install and customer base, inventories, etc. Then there's...
  18. J

    AMD announces petaflop supercomputer

    How can they use GPGPUs (and even desktop cards at that?!) for rendering? I thought GPUs are not there yet when it comes to data integrity/security/RAS features. On the other hand maybe rendering does not require 100% data integrity? But the applications for GPGPUs should be still pretty...
  19. J

    Official Phenom 2 Review Thread

    You couldn't be more mistaken, Nehalem is performing (or rather will be if it ever launches) more than stellar in the high margin server market and PII is <10% faster than PI while Nehalem is more than 10% faster clock for clock on average. Yes, AMD has earned at least some level of...
  20. J

    Intel Nehalem HPC performance

    Oh snap. You are right. Maybe it is just the typically better Intel support for reviewers, they seem to be giving away ES rather easily, but if the testers work at LANL they shouldn't have had much of a problem with acquiring AMD chips too... Ok, I am puzzled.
  21. J

    Intel Nehalem HPC performance

    I think it is obvious why they did not use Shanghai (which launched only very recently), generating all the data most certainly took quite some time. Still why they only used a 2.0ghz K10 escapes my imagination.
  22. J

    First Phenom II review + New review 26th

    Just did some number crunching. It's a comparison of CPUs, so I excluded the heavily GPU limited runs and the 3d Mark composite scores whenever they showed the CPU scores. I included 03 and 05, even though I believe those were composite scores, not showing the true speed of the CPU (if this is...
  23. J

    Question about AMD

    AFAIK AMD is already way, way below that.
  24. J

    First Phenom II review + New review 26th

    piesquared, whether it will be turned on or off by default doesn't matter. A correctly implemented hardware overclocking feature will always be superior to a software feature. So it will be benfical to a bigger crowd by default, even if it's still a small crowd. I think anyone challanging IDC...
  25. J

    Phenom II 940 3GHz reviewed

    I do not trust the FUDzilla provided Iranian review myself, but I am pretty sure, if we were talking about this one, it was the one not showing spectecular stock-performance (20% more perf. for 15% clock).
  26. J

    First Phenom II review + New review 26th

    A software feature is only benefical to a very small number of customers. Forget the server, workstation, HPC world and any linux users. Forget all the end-users who do not install the necessary software (if it really needs software and not just a bios). You are left with a crowd that probably...
  27. J

    Phenom II 940 3GHz reviewed

    I am, because.. ..my calculator tells me you are wrong. How can we trust your prediction if you did not even calculate an IPC estimate from this review? The 15% higher clocked ph II does not perform 20% better than ph I across the board, how is it supposed to perform 20% better per clock then?
  28. J

    Phenom II 940 3GHz reviewed

    Depending on market segment there might be some truth to it. Server, no *hints at SAP*. Desktop? Remains to be seen, but apparently they cannot compete with the higher-end of Intel processors if the prices are indeed correct, sub 300$ for ph IIs IIRC. Either one needs to be wrong. Intels top...
  29. J

    First Phenom II review + New review 26th

    Both tests have their merits, I think it's as simple as that.
  30. J

    First Phenom II review + New review 26th

    Where is the review? Somehow I only see text describing some GPU-limited games where the phenom set-up is clearly edged out by the competition: it's worse in cinebench, crysis gpu limited, CoJ gpu limited, Lost Planet probably within margin of error, fear gpu limited, 18% slower in doom3...
  31. J

    Intel 22nm - Multigate FETs: A Risky Proposition

    I'm just wondering where does die-stacking come into play? Or is this completely out of the equation now? Or was it just left out from this report, because they focused on process features, whereas die-stacking is not dependant on process but a way to assemble chips? It seems it's not...
  32. J

    Intel Xeon 5570: Smashing SAP records SCOOP

    How important is SAP-SD in the server-world? What would this mean to AMD's server share if Nehalem is twice as fast per clock in this application? Are there any ways to "cheat" on SAP-SD? Does the benchmark fit into RAM or does it access the hard drives too? (maybe they used SSDs as proposed by...
  33. J

    Is AMD mounting a successful comeback with Phenom II and others?

    Nah, just talking about 48xx, because only those enabled them to actually make a profit. I think Q3'08 was the first quarter AMD/ATI made a profit sinse the obnoxious R600. IIRC the earnings reports. When talking about AMD I'm alwys trying to think in terms of mid- and long-term survival i.e...
  34. J

    Is AMD mounting a successful comeback with Phenom II and others?

    Now that this thread has turned to a discussion about speculation and leaks - which I prefer anyway - I want to add that this recent rumour gives a lot credibility to the good ol' leaks from the far east. They showed 5% IPC gains on early ES months ago (so we could expected some minor...
  35. J

    Is AMD mounting a successful comeback with Phenom II and others?

    Huh? Deneb is not competing with i7 FWIW. As I like to point out it's competing with very mature 45nm, 2*107mm^2 chips that clock equally well - no even better going by the current data. As of yet we do not have enough data to fully predict the performance of Deneb (Desktop), but it's not...
  36. J

    Is AMD mounting a successful comeback with Phenom II and others?

    On page 3, there was some confusion about the influence of process vs architecture on yields. I think it's an interesting issue worth some discussion. Based on my limited understanding of semi manufacturing I'd assume there are two types of defects affecting yields (not talking about packaging...
  37. J

    Is AMD mounting a successful comeback with Phenom II and others?

    Well the SPEC numbers published on spec.org and discussed at RWT show it to be superior in bandwidth heavy _rates, where K10 and K10.5 normally could rule against penryns. Over at techreport they wrote that even their 1P nehalem (I know it was differently configured) outperformed 2P Shanghai and...
  38. J

    Is AMD mounting a successful comeback with Phenom II and others?

    They've earned it I guess, but just to play devil's advocate. Your calculations are based on the unofficial (?) TDP of an unreleased AMD CPU on an unreleased socket/platform targeting a june'09 launch, right? Those are many variables that could yield a mid 3ghz part in Q3'09, close to someone...