The Pursuit of Clock Speed

Thus far I have pointed out that a number of resources in Bulldozer have gone down in number compared to their abundance in AMD's Phenom II architecture. Many of these tradeoffs were made in order to keep die size in check while adding new features (e.g. wider front end, larger queues/data structures, new instruction support). Everywhere from the Bulldozer front-end through the execution clusters, AMD's opportunity to increase performance depends on both efficiency and clock speed. Bulldozer has to make better use of its resources than Phenom II as well as run at higher frequencies to outperform its predecessor. As a result, a major target for Bulldozer was to be able to scale to higher clock speeds.

AMD's architects called this pursuit a low gate count per pipeline stage design. By reducing the number of gates per pipeline stage, you reduce the time spent in each stage and can increase the overall frequency of the processor. If this sounds familiar, it's because Intel used similar logic in the creation of the Pentium 4.

Where Bulldozer is different is AMD insists the design didn't aggressively pursue frequency like the P4, but rather aggressively pursued gate count reduction per stage. According to AMD, the former results in power problems while the latter is more manageable.

AMD's target for Bulldozer was a 30% higher frequency than the previous generation architecture. Unfortunately that's a fairly vague statement and I couldn't get AMD to commit to anything more pronounced, but if we look at the top-end Phenom II X6 at 3.3GHz a 30% increase in frequency would put Bulldozer at 4.3GHz.

Unfortunately 4.3GHz isn't what the top-end AMD FX CPU ships at. The best we'll get at launch is 3.6GHz, a meager 9% increase over the outgoing architecture. Turbo Core does get AMD close to those initial frequency targets, however the turbo frequencies are only typically seen for very short periods of time.

As you may remember from the Pentium 4 days, a significantly deeper pipeline can bring with it significant penalties. We have two prior examples of architectures that increased pipeline length over their predecessors: Willamette and Prescott.

Willamette doubled the pipeline length of the P6 and it was due to make up for it by the corresponding increase in clock frequency. If you do less per clock cycle, you need to throw more clock cycles at the problem to have a neutral impact on performance. Although Willamette ran at higher clock speeds than the outgoing P6 architecture, the increase in frequency was gated by process technology. It wasn't until Northwood arrived that Intel could hit the clock speeds required to truly put distance between its newest and older architectures.

Prescott lengthened the pipeline once more, this time quite significantly. Much to our surprise however, thanks to a lot of clever work on the architecture side Intel was able to keep average instructions executed per clock constant while increasing the length of the pipe. This enabled Prescott to hit higher frequencies and deliver more performance at the same time, without starting at an inherent disadvantage. Where Prescott did fall short however was in the power consumption department. Running at extremely high frequencies required very high voltages and as a result, power consumption skyrocketed.

AMD's goal with Bulldozer was to have IPC remain constant compared to its predecessor, while increasing frequency, similar to Prescott. If IPC can remain constant, any frequency increases will translate into performance advantages. AMD attempted to do this through a wider front end, larger data structures within the chip and a wider execution path through each core. In many senses it succeeded, however single threaded performance still took a hit compared to Phenom II:


Cinebench 11.5 - Single Threaded

At the same clock speed, Phenom II is almost 7% faster per core than Bulldozer according to our Cinebench results. This takes into account all of the aforementioned IPC improvements. Despite AMD's efforts, IPC went down.

A slight reduction in IPC however is easily made up for by an increase in operating frequency. Unfortunately, it doesn't appear that AMD was able to hit the clock targets it needed for Bulldozer this time around.

We've recently reported on Global Foundries' issues with 32nm yields. I can't help but wonder if the same type of issues that are impacting Llano today are also holding Bulldozer back.

The Architecture Power Management and Real Turbo Core
Comments Locked


View All Comments

  • actionjksn - Thursday, October 13, 2011 - link

    AMD Nailpuller? That was some funny shit right there HA HA HA
  • Spam not Spam - Wednesday, October 12, 2011 - link

    Just skimmed the review; not as awesome as I had hoped for, sadly. That being said, I'm thinking it might well be a nice improvement for the stock, C2D Q6600 in my Dell. I could go Intel, obviously, but... I dunno. I've got an odd fascination with novel things, even if they are rough to begin with. Hell, I've even got a WP7 phone :p
  • wolfman3k5 - Wednesday, October 12, 2011 - link

    Then make sure to get a quality power supply and motherboard to go with it. Also, your power bill will increase, but not directly from the Bulldozer CPU, nope, but from all the heat that it will make... you will need to run your air conditioner which is a power hog.

    /* Patiently waiting for AMD's next gen architecture codenamed "Bendover" */
  • ckryan - Wednesday, October 12, 2011 - link

    Is 'ScrewdOver' next on the roadmap after 'Bendover'? I'll have to look in the official AMD leaked slide repository.

    I still think some intrepid AMD faithful will try BD out just because they're wired that way, and many of the are going to like it. I bet it compares better to Lynnfield than Sandy Bridge... Except Ivy Bridge is closer in the future than SB's launch is in the past. This could be an interesting and relevant product after a few years, but the need is dire now. AMD is going to kill off the Phenom II as fast as possible.
  • themossie - Wednesday, October 12, 2011 - link

    Bendover -> ScrewdOver -> Screwdriver (I'll bring the OJ) -> Piledriver.
    Courtesy of numerous internal leaks at AMD.
  • themossie - Wednesday, October 12, 2011 - link

    My apologies, didn't realize Piledriver was real.
  • bill4 - Wednesday, October 12, 2011 - link

    AKA, the reason all of us who are commenting are reading this review. Gaming performance. And AMD chose not to even compete there. Bunch of monkey overs at AMD CPU engineering?

    It's now a non starter in the enthusiast market.

    I've often though recently that AMD (or any manufacturer really, but AMD as a niche filler would be a more obvious choice given their market position) would do well to try to position itself as the gamers choice, and even design it's CPU's to excel in gaming at the expense of some other things at times. I really suspect this strategy would lead to a sales bonanza. Because really the one area consumers crave high performance is pretty much, only gaming. It's the one reason you actually want a really high performance CPU (provided you dont do some sort of specialized audio/video work), instead of just "good enough" which is fine for general purpose desktoping.

    Instead they do the exact opposite with Bulldozer, facepalm. Bulldozer is objectively awful in gaming. Single handedly nobody who posts at any type of gaming or gaming related forum will ever buy one of these. Unbelievable.

    Perhaps making it even more stinging is there was some pre-NDA lift supposed reviewer quote floating around at about how "Bulldozer will be the choice for gamers" or something like that. And naturally everybody got excited because, that's all most people care about.

    Combine that with the fact it's much bigger and hotter than Intel's, it's almost a unmitigated disaster.

    This throws AMD's whole future into question since apparently their future is based on this dog of a chip, and even makes me wonder how long before AMD's engineers corrupt the ATI wing and bring the GPU side to disaster? The ONLY positive thing to come out of it is that at least AMD is promising yearly improvements, key word promising. Even then absolute best case scenario is that they slowly fix this dog in stages, since it's clearly a broken architecture. And that's best case, and assumes they will even meet their schedule.

    Anand lays so much of the blame at clockspeed, hinting AMD wanted much more. But even say, 4.3 ghz Bulldozer, would STILL be a dog in all important gaming, so there's little hope.
  • shompa - Wednesday, October 12, 2011 - link

    I have used many AMD systems. Have deployed 1000 of AMD CPU inside Unix workstations at my old work. I cheer for AMD.
    AMD is going to have a hard time ahead. Selling its fabs to Global foundries was the biggest mistake of them all.

    We are in the post PC world. If Tablets are computers: 2012 20% of PCs will use ARM. This is many lost CPU sales for AMD/Intel.

    I predict that AMD will be gone within 3 years. Maybe someone buys them? After the settlement with Intel, AMD now can transfer its X86 license to the next buyer. (pending Intels approval)

    Maybe Google could buy AMD and build complete computers ?
  • wolfman3k5 - Wednesday, October 12, 2011 - link

    I see two things that might happen to AMD
    1) They will transform in to a GPU manufacturer completely (and of course they will make those silly APUs)
    2) If that damn x86 license is transferable, they could merge with NVidia. Neither of these two companies looks to hot these days, so they might as well work together.
  • philosofool - Thursday, October 13, 2011 - link

    We may be in the "post PC" era, but don't count x86 out. Recent studies indicate there's a corollary to Moore's law that applies to compute power per watt; the study goes back to 1961. This suggests that x86 is only a few years away from running on mobile devices, which is what MS and Intel are betting on. And frankly, it makes sense. Ultimately, I don't want two different things (a mobile device and a PC), I want a PC in my pocket and one on my desk.

Log in

Don't have an account? Sign up now