Why Barton will be a better OC'er

Reading various OC reports on the new T-bred seems to indicate that heat is it's Achilles heel. This is not exactly what one would expect, as a die-shrink normally results in lower temperatures. And the T-Bred actually does have a lower power-consumption than the Palomino, but it also has difficulties in getting rid of the heat, due to the reduced surface of the small core and lack of heat-spreader. This is why I believe that the added L2 cache of Barton, which will result in a larger core, will allow for better heat dissipation, and thus, higher clock-speeds than the T-bred is currently showing.

Notice how extreme cooling helps the T-bred to reach very high frequencies.

Wonder if the large core of the P4 was something Intel designed "on purpose", in order to improve heat dissipation at very high frequencies.

<i>/Copenhagen - Clockspeed will make the difference... in the end</i> :cool:
74 answers Last reply
More about barton
  1. Personally I was also predicting Barton's OCing will be better. The core design and layout will be improved and maybe AMD can do a Palomino-style rearrangement, resulting in lower temps and possibly lower voltage?
    But I am more positive that Barton will have better OCing.

    --
    :smile: Intel and AMD sitting under a tree, P-R-O-C-E-S-S-I-N-G! :smile:
  2. You may be right about this.

    I have used an AthlonXP 1600+ and a Duron 1000(Morgan) on almost (but not exactly) the same system and the Duron was hitting higher temps.
    I believe the analogy might be similar with the Duron having less cache, although I haven't really checked the die sizes.
    So maybe the smaller die size is really the issue with the Tbred.

    I wonder what Texas Techie & Matisaro might have to say on the subject.
  3. I donot think so.
    CPU with larger cache normally donot oc well, though perform better at the same frequency.
    Besides, AXP has quite large 128K L1, so doubling its L2 wouldnot help the performance as efficiently as it does to P4.
  4. the bigger L2 cache will boost higher Cache-Hit rates and thus the new processor will access the memory less.
    this should bring down temps becouse memory access creates an effect of Capacitance and thus lifts core tempertures.


    This post is best viewed with common sense enabled
  5. the P4 L1 and the AMD L1 actualy work differently, so it might give more of a benifit than you think.

    Also, if CPUs with a larger cache don't OC well, then how do you explain the P4 NW overclock compaired to the P4 Willy?

    The cache should have little to do with the OC by itself, however, with the increased surface area, that should help heat disapate better, which could help.

    So, better heat disapation + lower initial clock on the same basic architecture should = better OCability.

    One other thought. It's also posable that the extra cache on the CPU could help with heat by simply not letting the CPU heat up as much because the CPU works more efficiently. Not sure if that would work, just a curious thought. (Less heat because the CPU does less to get the same ammount of work done, so less electricity flowing through places where it can heat up.)

    English is phun.
  6. Quote:
    Also, if CPUs with a larger cache don't OC well, then how do you explain the P4 NW overclock compaired to the P4 Willy?


    Because it was a die shrink. Tbred -> Barton will not be. And he's right, processors with more cache typically OC less.

    <font color=blue>Hi mom!</font color=blue>
  7. "This is why I believe that the added L2 cache of Barton, which will result in a larger core, will allow for better heat dissipation"

    this makes no sense, sure a larger surface area dissipates heat better, but the extra core area (the extra 256 kb of cache) will produce its own heat surely? adding to the total heat output, therefore the heat dissipated per unit area will remain the same. There is more heat but more surface area to compensate.

    You are assuming that the extra 256kb of cache doesnt produce any heat.

    I predict you are wrong and we will be disapointed once again, but i really hope you are right.

    I need a 1.5 Ghz Athlon + 512mb ddr ram to write emails......honestly
  8. <blockquote><font size=1>Svar på:</font><hr><p>I donot think so.
    CPU with larger cache normally donot oc well, though perform better at the same frequency.
    Besides, AXP has quite large 128K L1, so doubling its L2 wouldnot help the performance as efficiently as it does to P4.<p><hr></blockquote><p>You missed my point, which was that the T-Bred core seems to have problems dissipating heat, due to its small size. A heatspeader or a larger core surface would improve heat dissipation.

    About whether large cache OC well or not: Look at the Northwood, it doesn't seem to have any problems in that respect.


    <i>/Copenhagen - Clockspeed will make the difference... in the end</i> :cool:
  9. <blockquote><font size=1>Svar på:</font><hr><p>You are assuming that the extra 256kb of cache doesnt produce any heat.<p><hr></blockquote><p>You are assuming that L2 cache generates the same amount of heat per unit area as, say, a FPU unit or an ALU. I'm almost sure that it is not the case.


    <i>/Copenhagen - Clockspeed will make the difference... in the end</i> :cool:
  10. I dont like the fact that evryone disregarded my post about the Barton being cooler as a result of a highe Cache-Hit rates and less access to memory per amount of time.


    This post is best viewed with common sense enabled
  11. think about it logically, heatsink would be closer to core than extra cache, heat from core is not magically going to transfer into the extra area cache provides.

    I need a 1.5 Ghz Athlon + 512mb ddr ram to write emails......honestly
  12. Just because nobody commented on that directly doesn't mean everybody ignored it.

    <font color=blue>Hi mom!</font color=blue>
  13. Don't compare apple and orange. T-Bred=> Barton is just (or mostly) L2 change, while Willemette => Northwood is so much more.
    Plus, if Athlon architecture won't go high freq at all, nothing could help oc.
  14. Quote:
    You are assuming that L2 cache generates the same amount of heat per unit area as, say, a FPU unit or an ALU. I'm almost sure that it is not the case.

    Cache is actually one of the most active portions of the chip. Execution pipelines can and do stall quite frequently, but cache is almost always being accessed and updated, even when the CPU is "idle." So the extra die space used by cache will probably put out <i>more</i> heat...

    <i>I can love my fellow man...but I'm damned if I'll love yours.</i>
  15. but they didn't.

    anyway Cache is hardly that active - it holds many many adresses and is required to store/load only a few of them in the same clockcycle + it has a latncy of a few clockcycles in which only the controling mechminzem of the cache works. the cache is self - which is the larger part - has really low usage...


    This post is best viewed with common sense enabled
  16. i have a BIG question here...

    Will Barton outperfor thoughbred so much, to even wait before buying, lets say, an athlon xp 2200???
  17. most esstimates go for around ~7% improvement.
    and my guess is that the desktop version of the barton would lunch at the begining of Q4' at the earlyest.
    then you'd be wanting to wait for somthing else..

    This post is best viewed with common sense enabled
  18. That's not a big question, yes and no, it will gain from the additional L2, but not as much as the Northwood, considering the Athlon is less sensitive to mispredicted branches. It won't have a large gain, but comparable to the Willy to NW

    "When there's a will, there's a way."
  19. Personally I found your theory and fact to be very realistic, and I didn't disregard it at all, I just read it!

    It makes sense that the more the helping components, the less the CPU has to heat up. I would suppose that the Willy has a large idle-load delta compared to NW's, but we'd need proof. So for one: The added cache will increase die space, therefore cooling is more reaching. The cache will also serve as less time to do an operation, thus less heat. In overall the delta should be reduced and the OCing just might be better. Hell we've seen recent Tbreds doing better and better in new steppings. Fugger has an interesting 2.6GHZ Tbred on LN2.(I really wish the guy would stop being so anti-AMD, he has really good info)Granted, it's extreme and no SSE, but it sure as hell shows the Tbred CAN get there soon, and that maybe Gigabyte's 2.6GHZ Tbred OC is not so farfetched. In any case, we'll just have to wait and see how Barton turns out, but for now, IIB's claim is pretty logical and if he's experienced in this, I guess his credentials are less to be debatable if someone who hasn't taken a course in such was disagreeing.

    --
    :smile: Intel and AMD sitting under a tree, P-R-O-C-E-S-S-I-N-G! :smile:
  20. Let the overhype start again

    1 more cache do not result in less speed for the cpu(mghz)
    2 Actual speed of a chip is a combination of many factor
    R300 107 million transitor 350 mghz core speed 0.15 micron
    Pharelia 512 80 million transitor 220 mghz core speed 0.15 micron

    That off topic but prove that micron prosces alone is not the only factor for speed.

    cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie <P ID="edit"><FONT SIZE=-1><EM>Edited by juin on 06/25/02 11:49 PM.</EM></FONT></P>
  21. I dunno why an added cache would need less speed, I thought as we add things, we also increase clock?

    --
    :smile: Intel and AMD sitting under a tree, P-R-O-C-E-S-S-I-N-G! :smile:
  22. <blockquote><font size=1>Svar på:</font><hr><p>think about it logically, heatsink would be closer to core than extra cache, heat from core is not magically going to transfer into the extra area cache provides.<p><hr></blockquote><p>You certainly have a point there.

    I don't know exactly how a CPU is build. Between the inner core and the heatsink there is some kind of protective material, but I guess its heat conductivity must be pretty good. It could however turn out to have less conductivity than the heat conductivity within the core itself. This makes the whole arrangement of the die very important. You would like to place very hot spots near cold ones, instead of hot spots next to other hot spots. I'm sure AMD has already optimized the die in this respect. Question is whether the added L2 cache will allow a better die arrangement with respect to heat.


    <i>/Copenhagen - Clockspeed will make the difference... in the end</i> :cool:
  23. IIB, if I don't comment on a post it doesn't mean that I disregard that post. It could of course be the case, but in your case it didn't.


    <i>/Copenhagen - Clockspeed will make the difference... in the end</i> :cool:
  24. Sorry, but I disagree. I would like to see Barton as a good overclocker, but right now Tbred has some problems, that, maybe, are due to lower contact with HSF so more difficult to transmit heat. Ok, more L2 cache can help. Now another point.

    Barton will be initially out at 2400+ or something like this, isn't it? So bearing in mind that the frecuency will be higher and, from my point of view, there is an arquitecture limitation in the K7 core, there will be less room to overclock, simply because we will be near the limits of the CPU.

    Also I don't think AMD will spend money and time to rearrange the core to allow higher frecuencies, because they are focused on Hammer.

    For all this reasons I'm affraid that Barton won't be a good overclocker. Better we stay in the low spectations range, or we will be disappointed again.

    DIY: read, buy, test, learn, reward yourself!
  25. Quote:
    I don't know exactly how a CPU is build. Between the inner core and the heatsink there is some kind of protective material, but I guess its heat conductivity must be pretty good.


    Usually is sog(spin on glass) or silicon dioxide, neither of which has very good thermal properties, but its damn thin.

    :wink: The Cash Left In My Pocket,The BEST Benchmark :wink:
  26. Quote:
    Barton will be initially out at 2400+ or something like this, isn't it? So bearing in mind that the frecuency will be higher and, from my point of view, there is an arquitecture limitation in the K7 core, there will be less room to overclock, simply because we will be near the limits of the CPU.


    Whatever is causing the bad ocing, it isnt a core design limitation(on a grand scale I have no doubt of some issue).

    The p3 core was slated to retire at 1ghz or thereabouts, and the shrink+copper extended it to 1.7ghz and counting. Not the core design, no sir.

    :wink: The Cash Left In My Pocket,The BEST Benchmark :wink:
  27. i think the barton will be better just due to time.
    judging by the newer batch of tbreds around the 0.13 die is still being refined. so by the time barton comes out it should be as mature as it can ever be... if not then it spells trouble for 0.13 and hammer.

    <font color=green>Proud member of THG's</font color=green> <font color=blue>Den Of Thieves</font color=blue> :lol:
  28. First of all guys it is NOT the 0.13m yeilds that are bad. You can ask Texas_techie for the real reason (I dunno if I can divulge it here).

    Second, if adding cache largely makes the core bigger, it should reach a bit less than the Palomino. Assuming Palomino was a core rearrangement, and it overclocked better, a 0.13m Barton core looking like a Palomino, AND a rearrangement SHOULD in a way give us even better overclocking than the Palomino did. Look at it this way, I think it might be working, since the added cache will change the Tbred layout core. (THG has pics of the silicons)

    EDIT: <A HREF="http://www.tomshardware.com/cpu/02q2/020610/thoroughbred-04.html" target="_new">http://www.tomshardware.com/cpu/02q2/020610/thoroughbred-04.html</A>
    --
    :smile: Intel and AMD sitting under a tree, P-R-O-C-E-S-S-I-N-G! :smile: <P ID="edit"><FONT SIZE=-1><EM>Edited by Eden on 06/26/02 10:19 AM.</EM></FONT></P>
  29. Quote:
    Because it was a die shrink

    The t-bred was a die shrink and it doesn't OC too much better...

    I'm not saying that Barton will OC like a NW, but I think it could help the CPU OC better than the current T-bread.

    English is phun.
  30. Quote:
    <i>Eden says:</i>
    First of all guys it is NOT the 0.13m yeilds that are bad. You can ask Texas_techie for the real reason (I dunno if I can divulge it here).

    I personally don't care. If he doesn't feel like sharing, so be it. But I'm not going to rush to believe him or whoever else for no reason.

    Quote:
    <i>Bront says:</i>
    The t-bred was a die shrink and it doesn't OC too much better...


    Because the Athlon was never designed to scale in clockspeed like the P4 is.

    <font color=blue>Hi mom!</font color=blue><P ID="edit"><FONT SIZE=-1><EM>Edited by FatBurger on 06/26/02 12:02 PM.</EM></FONT></P>
  31. Well, then I suppose you need to reduce the heat produced by the CPU. I mean, how can't go too far if heat rises at current rate. I know that maybe lowering the voltage can help, but it will be enough? Will the added L2 cache help the heat issue and by how much?

    For this reason I feel the Tbred and also Barton can go up to a limit that seems not so high. Maybe 2800+? I'm just guessing.

    DIY: read, buy, test, learn, reward yourself!
  32. They will behave like TBreds except:

    O/C pros:
    - Larger area die to remove heat from

    O/C cons:
    - The extra cache will generate more heat.
    - Yield will be lower (harder to make).

    - JW
  33. Unless you have a need to have the latest and greatest instantly, there is no reason to rush out and buy a new AXP if you already have one unless the price drops to rediculous levels ($100 for an AXP 2200+). Wait for Barton, and wait for the t-bred to be refined. Generation 2 might be better for them anyway.

    English is phun.
  34. On the face of it, Athlon may not have been designed to clock to huge speeds, but if you look at where it started, compared to P4, it's done well. I dare say that relatively speaking, Athlon has ramped in speed equal to what Intel plans for P4. Athlon started at 5 or 550mhz compared to P4's 1.7ghz.

    Athlon is now at 1.8ghz compared to P4's 2.5ghz. So, AMD will quadruple in clockspeed over the life of the chip. P4 will quad, or perhaps quintuple over it's life. That's pretty close and considering the greater IPC of Athlon I think that gives Athlon a similar or perhaps slightly better performance scaling over the life of the chip.

    Mark-

    <font color=blue>When all else fails, throw your computer out the window!!!</font color=blue>
  35. Just to play Ye Olde Devil's Advocate...

    Quote:
    and considering the greater IPC of Athlon I think that gives Athlon a similar or perhaps slightly better performance scaling over the life of the chip.


    That would be if, and only if, Intel didn't improve the IPC of the P4 significantly in Prescott and/or whatever future revisions to the P4 core Intel might make before the core's lifespan has ended.

    Now back you your regularly scheduled re-programming.

    <pre>The computer is your friend.
    The computer is good.
    The computer only wants to help.
    Be friends with the computer.
    Join us.
    Join us.</pre><p>

    Tech support said take a screen shot.
    Putting it down with my .22 was the humane thing to do.
  36. I don't necessarily agree with you there Silvr and here's why.

    Athlon started out with higher IPC than P4. Since Athlon was released AMD has regularly improved IPC. AMD is continuing to improve IPC with Barton. So, while P4 IPC will improve in IPC, I doubt it will improve more in IPC than Athlon has.

    Mark-

    <font color=blue>When all else fails, throw your computer out the window!!!</font color=blue>
  37. Quote:
    AND a rearrangement SHOULD in a way give us even better overclocking than the Palomino did.

    Except they only rearangement should be where they add the extra 256KB Cache. The rest is layed out as it will be in barton already in the t-bred.

    English is phun.
  38. Quote:
    1 more cache do not result in less speed for the cpu(mghz)

    No, but it does mean that you need a slower speed to get the same performance, so AKA PR rating, at least I would think.

    English is phun.
  39. I think Intel could've clocked their P3 T's to where the Athlon is right now. Athlon was to compete w/ P3s, not P4's. Intel changed cores (and names..P4) a little prematurely. Had they released a 1.8a at first, and maybe took the P3 to 1.5ghz, there would probably be no complaints from anyone.....well the AMD fans would find something to dislike, but there wouldve been no disgraceful willamette.
    " Athlon started at 5 or 550mhz compared to P4's 1.7ghz."
    P4s started at 1.2ghz.

    I sold my sig for $50.
  40. IIRC the barton will have a rearranged core.

    The goal is to get all the fab equipment ready to make hammers. So they are setting up the core of barton similar to hammer.
    disclaimer: NO - i dont mean the architecture, i mean where things physically sit on the silicon.

    That way when hammer roles, it will be any easy transition from Barton. Also, the Athlon architecture doesnt benefit too much from more cache. SO i dont see how Barton would be any different. ALso, IIRC Barton is supposed to have SOI, we will see if that helps any.
    The Hammer architecture, on the other hand, apparently benefits a fair amount from extra cache. IIRC there was about a 10% improvement in speed (execution) with larger cache.
    Once again, I dont think T-bred will overclock well. IF, a big if, hammer does REALLY well. They may go back and make t-bred a better overclocker (fix its issues). But why bother? Why not avoid the t-bred probs when making Barton and discontinue t-bred.

    my 2 cents

    Benchmarks are like sex, everybody loves doing it, everybody thinks they are good at it.
  41. barton soi as been cancel a month ago.
    Anyway hammer will be release in 6 month

    cheap, cheap. Think cheap, and you'll always be cheap.AMD version of semi conducteur industrie
  42. Quote:
    I personally don't care. If he doesn't feel like sharing, so be it. But I'm not going to rush to believe him or whoever else for no reason.


    Burger, texas has shown me things which make me BELIEVE him when he says he has sources, I am not the type to believe someone blindly, but I have seen evidence to back up texas's claims.

    :wink: The Cash Left In My Pocket,The BEST Benchmark :wink:
  43. Thats a bummer about SOI. I swear I wanna kick someone at AMD in the family jewels for:

    1. not executing hammer sooner
    2. the t-bred fiasco.
    3. dropping SOI from barton


    Benchmarks are like sex, everybody loves doing it, everybody thinks they are good at it.
  44. You knew so much inside AMD news, but didn't know about SOI? Talk about bummer!

    Oh and for LED, the P4 began at 1.3GHZ, and beleive me it's as painful as it gets, so please don't make us think of a 1.2GHZ version!

    However as for IPC-wise, I have to disagree with Zengeos here. P4 IPC recently has been much better. In tests with SSE2 optimization such as After Effects, the P4 1.6GHZ was able to compete the XP2000, which signals the P4 CAN be optimized over its IPC and Athlon's. Prescott may or may not reclaim the P4's true performance that was first talked of, however the IPC HAS become much more competitive, even if currently at Q3, the NW As are NOT higher per clock, for example. I think the NWBs however do now, but I wish someone could underclock a NWB to 1.6GHZ with a 533MHZ FSB and RAM, then we'd see the real deal against Palominos. Strange how the Tbird had excellent competition, but with the AXP it feels like it's now weak! I dunno why, but looking at benches, my XP1600+ barely itches the 1.8A...

    --
    :smile: Intel and AMD sitting under a tree, P-R-O-C-E-S-S-I-N-G! :smile:
  45. Even though AMD dropped plans for SOI, do you believe they will do the same they did from Tbird to Palamino, by changing the core layout, and increasing the IPC through tweaking? Seriously, in the lowerend market, the Athlon is going to have a hard time with the Prescott if the Hammer and Barton don't pull through...

    Quote:
    I think the NWBs however do now, but I wish someone could underclock a NWB to 1.6GHZ with a 533MHZ FSB and RAM, then we'd see the real deal against Palominos. Strange how the Tbird had excellent competition, but with the AXP it feels like it's now weak!


    I'd be willing to bet if you popped an email to Tom, Kyle at [H] or even Anand, you could get some info about unlocked processor benchmarks. Afterall, Tom did mention before, his original samples of the Wilamette 1.4Ghz and Northwood 2.0Ghz were indeed factory unlocked. *shudders in disgust* IMAGINE a Pentium4 Willy at 1.0Ghz...ick, the Palamino MP would rape it at 1.0Ghz...just terrible.


    "When there's a will, there's a way."
  46. I could safely assume a Celeron Tually 1GHZ would do better...

    Yeah I could e-mail Tom, though do they even read them?

    --
    :smile: Intel and AMD sitting under a tree, P-R-O-C-E-S-S-I-N-G! :smile:
  47. Oh yes, I asked Tom a while back if I could use his benchmarks for my 10th grade english term paper, and a week after emailing him, I got a brief, but nice reply...Essentially yes. Ick...A Celeron Tually 1 Ghz beating the Willy...my oh my...

    "When there's a will, there's a way."
  48. Ya, you are correct. Cache doesn't make very much heat, it just takes up quite a bit of space. This will bring down Temps, but not by alot.

    The reason the NW OC's well is because it the way it was designed. It was designed to scale to very high clock speeds, so even with alot of cache, it's a natural overclocker. And also, adding cache to the Tbred won't make a big difference in performance, because the Tbred, I mean Barton, does not really have a problem with hit-rates. In fact, the Athlon architecture was designed to overcome cache misses, and AMD designed the architecture so that the every part of the CPU would be working. In other words, they designed the Athlon to run at 100% efficiency. This is one of the reasons why it runs hotter than a P4, since even current NW's do not run at 100% efficiency (everything in the core isn't used in NW). This is sort of related to an old article I read, where it explained that some of circuitry in the P4 either doesn't do anything, or is simply an early implementation of HT. It seems I'm getting off topic, so I'll stop my blabbering.

    Eden, if it's on LN2 and has no SSE, then I actually might believe that a Tbred can reach 2.6Ghz. But then again, I've seen a 2.5 NW OC'ed to 3.4Ghz. That thing was very unstable, and had to be cooled by a cryofreeze setup! This isn't a huge achievement for the Tbred core, considering it's heat, instability, and lack of SSE. I mean, you COULD push a p4 to 3.4Ghz, but we won't actually see that kind of stock speed for the P4 until next year.

    Zengoes, to set the facts straight (and back up Slvr), first of all, the Athlon debuted at 600mhz, and P4 at 1.5Ghz. And when Intel first released the P4, they bowed their heads high and confidenlty stated that the P4 core will be able to scale as high as <b>10 GHz</b>. Now, the Athlon was beating the Williamette in performance quite noticeably, but when Intel made a little die shrink and core change, the P4's performance jumped up to the level of the Athlon, and has even surpassed it now.

    LED, P4 debuted at 1.5, but Intel dropped the speed later for some strange reason to 1.3.

    ------------------------------------------------
    Montecito & Chivano; Intel's Big Guns.
  49. Quote:
    P4 debuted at 1.5, but Intel dropped the speed later for some strange reason to 1.3.


    No actually, you are wrong, it did appear at 1.3Ghz, just the common benches were at 1.5 (1.3 would have sucked worse anyway). Always was the lowest Willy at 1.3Ghz

    "When there's a will, there's a way."
Ask a new question

Read More

CPUs Core Heat Power Consumption