back to article Sockets, cores and threads, oh my

Intel gave us lucky hacks a post-Nehalem launch briefing to outline aspects of its near-term processor roadmap. Here's a fast-paced tour through the briefing content. Intel reassured us that it could see Moore's Law progression being maintained for another ten or so years with the process shrinks and other developments in its …

COMMENTS

This topic is closed for new posts.
  1. David Halko
    Happy

    Projected Intel, IBM, AMD, and Oracle/SUN/Fujitsu processors

    Chris Mellor writes, "Eight-core Xeon 7400s will be its latest battering RAM to assault the RISC castle keep doors. Whether it will be enough depends on IBM (Power 6+) and Oracle with whatever the Oracle-ised SPARC people come up with."

    The question is... when will any of these things come out???

    SUN - 8 core (T1) processor in 2005

    SUN - 8 core (T2) processor in 2007

    AMD - 6 core (Opteron) processor in 2009? (1st half, June)

    SUN - 16 core (T3) processor in... 2009? (2nd half)

    SUN - 16 core (RocK) processor in... 2009? (2nd half)

    Intel - 8 core (Xeon) processor in... 2009? (2nd half)

    AMD - 12 core (Opteron) processor in 2010?

    IBM - 2 core (Power6+) processor in... ?????

    IBM - 16 core (Power7) processor in... 2010?

    With the SUN SPARC T series traditionally being released on-time or early since 2005, that looks like a sure bet. With SUN SPARC RocK being late for years, Power being late for years, and Xeon being behind the core-curve for years (until recently) - it looks like it could be anyone's game.

    The Power6+ may already be done, waiting for SUN to release SPARC T3 and/or RocK, so as not to canibalize Power6 system profits, and to try to spoil the SPARC marketing announcement.

    The throughput of those cores and speed of a single thread on those cores are wildly different between architectures - meaning applications will perform wildly differently on each of these architectures and software licensing will vary wildly different between architecture.

    Considering new CPU and Computers are projected to be released within months from now, the consumer must stay nimble. These issues do not make it simple for the systems architect who is trying to project into the future processor availability, system performance, and system cost.

    The RISC market continues to be assaulted, but as long as there are workloads which perform superior in some form-factor or reduced system complexity, the market may continue to shrink, but retain a significant stronghold.

    High single threaded throughput under POWER and high multi-threaded encrypted throughput under SPARC are two examples of specific workloads with superior price/performance to competing processors.

  2. Bounty

    Moore's law... really?

    First it was 12 months, then 18 months. Wikipeida now reads 24 months. I propose Bounty's Law. The number of months cited as "Moore's Law" increases by at least 6 moths every decade.

  3. Bounty

    dang it

    someone beat me to to it:

    "Dave Epstein, a longtime member of the Microprocessor Report editorial board, has proposed a solution he modestly calls Epstein’s amendment: “Starting in 1970 with the predicted doubling every 12 months, the interval will increase by six months every ten years.”

    "

  4. Anonymous Coward
    Boffin

    Beware the ARMy

    With AMD set to copy ARMs success by separating fab from design, there could be plenty of surprises in store for Intel. Imagine for instance a third party combining AMD and ARM on the same piece of silicon with AMDs super duper hyper transport.

    Or, how about a 32core ARM based CPU. We've already got the distros. So therefore it wouldn't be difficult for some newbie company to knock out some really powerful kit based on them.

    Gigabyte are fairly good with their motherboards at the moment - they seem to have the google contract tied up. Mind you though, Google would be idiots to use a single company so there's bound to be another one. (The 2oz copper idea didn't come from nowhere and probably has something to do with Google.) So anyway, with Gigabytes inventiveness, they could in theory create their own supercomputers based on ARM. No need to sell the processor, expensive sockets and coolers. The CPUs would be so cheap they could be treated like any other chip and placed on the boards with a regular cheap heatsink. With the amount of space being saved by not having those huge heatsinks, you could even consider putting two or more computers onto one board in a server. Who knows, perhaps that is what Google are already doing. Google ain't gonna show us the latest gear and your an idiot if you believe they did.

    Iphones use ARM because they are low power, in fact, really really low power. It's the same reason why almost every phone in the world seems to use ARM. If netbooks grow up from the phone, ARM will win. If netbooks grow down from the notebook, Intel and AMD win. If AMD and ARM get together in some kind of hybrid solution, then intel doesn't stand a chance unless they figure out a way to do something similar. (eg multi cores with different power ratings, powerful high speed cores for use in the office, low power efficient cores for battery use)

    If Intel are scared of RISC it's with good reason. If ARM wasn't a threat they wouldn't bother, wouldn't care.

  5. Quirkafleeg
    Coat

    Frame rates

    “The system will automatically detect playback of 24fps recorded video”… what? There are people who don't use 25fps?

  6. Mad Mike

    @David Halko

    Interesting article. However, a few amendments. Power 6+ is already out, at least according to IBM. Power 7 is on target and will be released on time. It's also not a 16 core design. From an enterprise point of view, Itanium is pretty much dead. Where's the differentiator between top end Xeons and Itanium to justify the increased cost? Also, according to Intel, going to the same socket and chipset making this even worse.

    Sparc?? God knows. Over to Oracle. Wouldn't bet on anything sunstantive for a few years yet. Sun don't have a roadmap to mention. It's all very vague and misses all the time, both hardware and software.

    So, in the RISC space, IBM is really where it's at!! Look out for Power 7, it's a beast!!

  7. Matt Bryant Silver badge
    Happy

    RE: Projected Intel, IBM, AMD, and Oracle/SUN/Fujitsu processors

    One problem with old Novatose's marketeering - did he call Larry first to get his approval? Fact is, all the "coming" Sun chips mentioned are waiting on Axeman Larry to decide whether Oracle want them or not, and the evidence so far is not. First off, Oracle haven't committed to ANY current Sun hardware, let alone future products. Wonder what the two-week delay was in Sun announcing the Nehalem kit? It wasn't just Sun being slower to market than the other vendors (as they usually are), it was probably because Sun had to ask Oracle for permission to launch the kit. Until Larry stands up and says Rock and T3 are go they are just vapourware, and even less convincing vapourware than when the SPARC fanclub was running Sun.

    And even if they do get released, Intel and AMD are hardly going to be quaking in their boots. T3 will still have the same scale problems of all the Niagara lines - Xeon and even the old Barcelona Opteron already out-scales and out-perfroms it. And the Nehalem and Barcelona cores are full-bodied cores with a real pipeline to keep those threads spinning, whereas the whole Sun design is a capitulation to the idea that you can't have all the threads going at once, because Sun couldn't design a bus or core powerful enough to. All T1 and T2 did was cannibalise the existing low-end SPARC base, and even then Sun and FSC finally had to produce a single-SPARC64 M-series server (the M3000) as their customers kept screaming at them that Niagara just didn't do what they wanted. And the final nail in T3's coffin - even if Oracle drop the stupid Sun insistance of pitching Slowaris as the OS of choice instead of Linux, it still can't run Windows, which means it can't compete with the cheaper, more flexible and faster x64 options which can Linux, Windows or even Slowaris x86. Niagara's little webserving niche is not going to be enough to keep T3 alive in Oracle.

    Rock? Way too little and far too late, even if they can fix the bugs. Going on the info Sun have released, Rock will be out-performed by the Power5 and old Madison Itanium2 cores it was originally supposed to go up against. Power6 and the latest Montecito Itanium2 cores will comfortably out-perform it, and then there are Power7 and Tukwila Itaniums waiting in the wings. 32-thread Power7 pricing is anyone's guess but likely to be keenly driven as IBM and hp scrap over who gets to migrate all those Sun accounts McNeedy and Ponytail have left in the lurch. Tukzilla-based Integrity servers from hp will come with the big price advantage that Tukwila and Nehalem allow more sharing of components than Power7 and xSeries can, so hp will be able to leverage the economies of scale of that massive ProLiant bizz to keep Integrity costs down. Oracle doesn't have a massive x64 bizz (Galaxy can't be described as a tier1 x64 bizz), and the Galaxy servers don't share components with the Niagara or M-series servers to anything like the same extent. So, Rock and T3 will offer poorer performance and at uncompettive prices. Yeah, I can see Larry jumping with joy at that prospect - not!

    IBM aren't keeping the Power6+ as a spoiler to the Rock/T3 announcements, they don't need to. They are keeping it ready for the arrival of Tukzilla this Summer. With hp's new servers due around this September, IBM will want to throw a spoiler in there to stop hp pointing out to all those Sun customers they can have a shiny new Tukzilla server in September or wait another six months plus for Power7. After all, if IBM play it the same way they did Power6, they could start with just one part of the range and that could mean customers actually waiting for Power7 in the servers they need as late as 2011.

    Interesting though that Novatose is no longer singing the praises of the Fujitsu SPARC64 chips. Are the Sunshiners just sulking because Fujitsu didn't ride in and save their fantasy world like they insisted FSC would? Or is this a silent admission that even the next gen SPARC64 - if it ever arrives - is going to be just as uncompetitive as Rock?

    Larry Ellison isn't blind, unlike McNeedy and Ponytail, and he will know better than to follow their blinkered and comic faith in SPARC. Larry may want the Galaxy servers for his new storage stack, but the rest are just a profits blackhole, and I predict Larry will cut them lose without a second thought.

    /Novatose - the comedy gift that keeps on giving.

  8. David Halko
    Happy

    RE: Projected Intel, IBM, AMD, and Oracle/SUN/Fujitsu processors

    Matt Bryant says, "And the Nehalem and Barcelona cores are full-bodied cores with a real pipeline to keep those threads spinning"

    But the cores are not always processing, waiting for memory accesses on cache misses.

    Matt Bryant continues, "whereas the whole Sun design is a capitulation to the idea that you can't have all the threads going at once, because Sun couldn't design a bus or core powerful enough to"

    Actually, Sun designed a core powerful enough to run an instruction for every clock cycle, not stalling. The difference is that when the Sun thread stalls, it does not stall the core, while with other processors, the core stalls.

    The Sun design was brilliant, attacking the core not running 100% of the time, using a different strategy to keep it working. It was a very unique solution in the marketplace. It does not work well for all workloads, but it is superior for many workloads. (i.e. on web servers, a single socket T2 processor will handle encrypted traffic almost as well as a quad socket Intel machine!)

    Matt Bryant suggests, "T3 will still have the same scale problems of all the Niagara lines"

    A single socket octal core T2 performing slightly slower than a quad socket hex core Intel is not a bad scaling problem to have - especially when the T2 will scale to 4 sockets... and easily outrun 12 hex-core Intel sockets in encrypted middleware bus or web-server loads.

    http://spec.org/cgi-bin/osgresults?conf=web2005&op=fetch&proj-COMPANY=256&proj-SYSTEM=256&proj-PEAK=256&proj-HTTPSW=256&proj-CORES=256&proj-CHIPS=256&critop-CHIPS=0&crit-CHIPS=1&proj-CORESCHP=256&proj-CPU=0&proj-CACHE1=0&proj-CACHE2=0&proj-CACHE3=0&proj-MEMORY=0&proj-NETNCTRL=0&proj-NETCTRL=0&proj-NNETS=0&proj-NETTYPE=0&proj-NETSPEED=0&proj-TIMEWAIT=0&proj-DSKCTRL=0&proj-DISK=0&proj-SCRIPTS=0&proj-WEBCACHE=0&proj-OS=0&proj-HWAVAIL=0&crit2-HWAVAIL=Jan&proj-OSAVAIL=0&crit2-OSAVAIL=Jan&proj-SWAVAIL=0&crit2-SWAVAIL=Jan&proj-LICENSE=0&proj-TESTER=0&proj-TESTDAT=0&crit2-TESTDAT=Jan&proj-PUBLISH=256&crit2-PUBLISH=Jan&proj-UPDATE=0&crit2-UPDATE=Jan&dups=0&duplist=COMPANY&duplist=SYSTEM&duplist=CORES&duplist=CHIPS&duplist=CORESCHP&duplist=CPU&duplist=CACHE1&duplist=CACHE2&duplist=CACHE3&duplist=NETTYPE&dupkey=PUBLISH&latest=Dec-9999&sort1=PEAK&sdir1=-1&sort2=SYSTEM&sdir2=1&sort3=CORESCHP&sdir3=-1&format=tab

    Matt Bryant predicts, "SPARC... I predict Larry will cut them lose without a second thought."

    So far, both Oracle & SUN indicate that SPARC is staying around... Larry seems to disagree with you on his first thought since merger announcement.

    If RocK is significantly late (again) and T3 is late (CoolThreads have been on-time or early since 2005) - I agree this may be a reasonable prediction. Perhaps Larry's second thought will be align with your prediction under these conditions.

    I guess, we will see!!!

  9. David Halko
    Happy

    @Mad Mike: Power 6+ & 7 will probably be screamers!

    Mad Mike says, "Power 6+ is already out, at least according to IBM. Power 7 is on target and will be released on time. It's also not a 16 core design."

    I have not been able to find any information, outside of speculation on Power6+ or Power7.

    Register suggests the Power6+ is not out, as of "23rd April 2009".

    http://www.theregister.co.uk/2009/04/23/ibm_power6_plus/

    Wikipedia says there are 2 chips per module with 8 cores per chip - which looks like a total of 16 cores per socket, assuming 2 chips in a single multi-chip module per socket. Wikipedia is a little unclear.

    http://en.wikipedia.org/wiki/POWER7

    I look forward to the processor releases, I am sure they will all be screamers!!!

  10. David Halko
    Unhappy

    @Mad Mike: Power 6+ & 7 will probably be screamers!

    I guess I was wrong... The IBM Power6+ was not a screamer...

    http://www.theregister.co.uk/2009/04/28/ibm_shipped_power6_plus_already/comments/

    Silently released, no significant performance boost.

  11. Joan Jacobs

    Itanium taking share from IBM and Sun

    Itanium fills a role at the head of the high-end server class, despite its detractors there is no better option for mission critical computing. Read more at: http://blog.itaniumsolutions.org/

This topic is closed for new posts.

Other stories you might like