Next-Gen AMD Bobcat and Bulldozer CPU Deep Dive

Article Index:   
Brooding Over Bulldozer
AMD still isn't talking about release dates when it comes to the company's next-generation server / workstation / enthusiast processor, but we now know much more than we did about the inner workings of the 'dozer core. This is AMD's first complete redesign since it built the K7 in 1999, and that's an inherently risky process. AMD refers to Bulldozer as a "third-way" between symmetric multithreading (Hyper-Threading) and Core Multi-Processing (multiple discrete cores on one die). Specifically, AMD started with two discrete cores, as shown in the left hand slide below, then fused them together into a single, mostly shared design. This paid off handsomely as far as design efficiency was concerned; Bulldozer's second ALU unit increased the die size by just 12 percent.


Two discrete cores on the left; AMD's Bulldozer combination on the right.

We're dubious as to whether or not AMD's approach qualifies as a "third way," perhaps it's more aptly characterized as "Hyper-Threading, Evolved." Intel's Hyper-Threading technology improves core efficiency by scheduling multiple threads for simultaneous execution. Alternatively, in a situation where the processor is waiting for code from Thread A, the scheduler is more than happy to crunch away on Thread B. This keeps the processor's execution units busier than they'd otherwise be, but standard Hyper-Threading doesn't provide the CPU with any additional execution hardware.



With Bulldozer, AMD has taken the concept of SMT and added a second independent integer unit. The following block diagram illustrates which sections of the new chip are shared and which are not. According to AMD, the company aggressively researched which core blocks needed to be duplicated and which could be combined before arriving at the present balance. We're going to circle back around to the ramifications of this decision, but let's take a closer look at the core first.

Under The Hood



Unlike all of AMD's processors since K7, Bulldozer has four x86 decoders. That puts it on par with Nehalem; previous products had just three. As we saw with Bobcat, Bulldozer's branch predication unit has been aggressively tuned for high performance as well—the branch prediction and instruction fetch logic has been decoupled, which means that an incorrect branch prediction won't stall the fetch unit (and vice versa). Again, that's different than Phenom, where these two units were tied to each other. The CPU's L1 instruction cache is 64K, but the associated data cache is much smaller. Each Bulldozer module has two independent 32K L1 data caches for a total of 96K (down from Shanghai's 128K).

If Bulldozer's FPU lives up to its promise on paper, AMD's new core could be a floating-point gorilla.  The joint FPU unit is capable of tracking two hardware threads (one from each core) and has two MMX integer units and two 128-bit FMAC units. On paper, this looks more-or-less identical to Phenom II's FPU, but AMD assures us that the FPU at the heart of Bulldozer is more capable. What we do know is that Bulldozer adds support for SSE4.1, SSE4.2, and Intel's AVX extensions.



As far as the OS is concerned, each Bulldozer module will appear as a dual-core processor, just as an Intel Hyper-Threaded processor is treated as having 2x its actual number of physical cores. This leads us back to the question of exactly how many cores each Bulldozer module contains. AMD claims that one Bulldozer module delivers 80 percent of conventional dual-core performance "with much less area and power." This strikes us as decidedly optimistic and is undoubtedly highly dependent on workload. It's by no means certain that 'dozer will be able to deliver what it promises; AMD's next-generation SMT will only function optimally if the company has nailed its cache ratios, execution unit distribution, branch prediction, and available memory bandwidth.

An Uncertain Future
Designing microprocessors is like playing Russian roulette. You put a gun to your head, pull the trigger, and find out four years later if you blew your brains out.

-- Robert Palmer, former CEO of Digital Equipment Corporation.

On paper, Bulldozer looks good. It's a notable jump forward for AMD, it adds features that will help equalize the playing field against Intel, and it incorporates power-saving technologies AMD hasn't previously adopted.  If some of the bets AMD has taken pay off, the company could be in a position to compete for the performance crown for the first time in years.

The problem with brand-new architectures, however, is that they often don't turn out as expected. In the past 29 years, Intel has released five separate architectures that either ultimately failed (iAPX 432, i860, Netburst), captured just a fraction of their originally intended markets (IA-64), or were repurposed for a different use (i960). In each case, the company sank years of work and vast amounts of capital into its design efforts. Palmer's quote doesn't just apply to Intel—the last thirty years are littered with the bones of once-powerful companies brought low, at least in part, by betting on the wrong microarchitectural horse.

With Bulldozer, AMD is taking two significant risks. First, the company has chosen to build its first Bulldozer processor on brand-new 32nm production lines. Most companies try to avoid this—Intel's entire Tick-Tock model was deployed after Prescott's simultaneous core debut and process shrink resulted in a power-sucking Netburst furnace as opposed to a Northwood 2.0. The danger here is that problems at the foundry level can cause significant product delays. To be fair, AMD may not have felt it had much choice, given Intel's already substantial process transition lead.

The second risk has to do with just how much of a performance boost Bulldozer can actually deliver compared to Phenom II. When AMD's Phenom core debuted in 2007, it was instantly obvious that the desktop version of  Barcelona would be hard-pressed to match Intel's 65nm Conroe Core 2 parts, much less the then-new 45nm Penryn chips. Given what they had to work with, Shanghai—Phenom II—was probably the best core it could've been; it definitively surpassed Conroe and matched up well against Penryn.

Then, of course, came Core i7. AMD has been forced to compete by slashing prices and selling larger chips with higher core counts on a much smaller margin than is healthy. This has helped the company achieve price / performance parity in certain multi-threaded workloads, but Shanghai's single-core performance lags Core i7's by a significant margin. With Sandy Bridge dropping in the next few months, the gap between the two is only going to get wider.

For Bulldozer to win back any of the server / high-end market share AMD has lost in recent years, it has to arrive with a nearly perfect mixture of power efficiency, scalability, base clock frequency, and improved single-thread performance. That's a very tall order for any company; there's simply no guarantee that AMD will be able to deliver a chip that meets such high standards the first time around. We're hopeful, but cautiously optimistic. 

Related content

Comments

Comments
acarzt 4 years ago

I'm hoping this chip(bulldozer) can compete with Intel for the crown in performance.

AMD really needs something that can compete!

I'm suspecting Intels next chip could be a devastating blow to AMD tho.

Also there really needs to be more competition in the netbook market, so i'm really looking forward to seeing what bobcat can do!

Drago 4 years ago

I call shenanigans on the Palmer quote.  That *** hole's only job is to clean out a company and sell it to the highest bidder.  He knows absolutely nothing about technology.  Get your facts straight before you go quoting some lewser who makes money by bankrupting and laying off hundreds of thousands of people.

Joel H 4 years ago

Draco,

So let me get this straight. Because you think Robert Palmer is a meanie, I'm misquoting him? Or are you simply claiming that because you think he's a talentless evil hack, he's also automatically wrong?

This is a quote I first heard during a visit to AMD some years back, where it was anecdotally attributed to Jerry Sanders. Further research on my part turned up the fact that while Sanders has said it, Robert Palmer is generally credited with having said it first. But I wouldn't expect you to take my word for it--how about an eight-year-old article on CNN? 

http://money.cnn.com/magazines/business2/business2_archive/2002/11/01/331620/index.htm

or maybe a smidge of information from the Motley Fool, though the version of the quote there is somewhat different?

http://boards.fool.com/Message.asp?mid=28062739

In fact, this was a difficult quote to track down--in many places it's not attributed to anyone, or to "a high-ranking board member of a microprocessor company." In the few places where it is attributed, it's attributed to Palmer. Please note that I performed this research before I put the quote in the article, as opposed to finding a phrase I liked and slapping it on a random CEO from the mid 1990s.

I hereby dismiss your claim of Shenanigans with prejudice and sentence you to exhaustively review the spelling of the word "loser." This court would also like to remind you that a little judicious Googling can help prevent dreaded foot-in-mouth disease

This court is now adjourned.

Dave_HH 4 years ago

Now Joel, be nice to the members. LOL! Seriously, I love the passionate debates. :)

Joel H 4 years ago

I was nice. You didn't think that was nice? I thought I was angelic.

bigtallsob 4 years ago

i hope this really works for AMD. intel needs some proper competition.

Der Meister 4 years ago

Whats next Steam Roller???? lol... but seriously AMD has not had a big hitting chip since the Athlon and FX series... Intel since the C2D has had the upper had as far a pure performance goes. AMD has become the budget chip

Joel H 4 years ago

Der Meister,


AMD already used SteamHammer--How about Death Mallet? ;)

rapid1 4 years ago

rofl "Death Mallet" (now AMD is proud to introduce to the world our new processor architecture the Death Mallet). I think they should call it the piping hot roll or the cupcake. The cupcake would be my favorite, and of course the triple chocolate chip cupcake would be the best one, the value on would be the strawberry cupcake, and general users would like the Vanilla cupcake.

No seriously I hope these blow some Intel market share to shreds in large chunks. That is how we got the core 2 duo the last time AMD blew some chunks outta Intel's a66. So it is good for the world. These processors all sound nice for the respective markets. The Phenom did to when they first announced it.

So I am excited, but I will wait until my favorite hardware nerds in the whole world Dave and Marco get some test silicone piping hot from the AMD oven!

Marius Malek 4 years ago

I like AMD, I really do. But when I consider computer builds I just seem to always go Intel because it seems like the better choice and more stable with the hardware that I chose.

I REALLY want to use kickass AMD processors but the fact that they are just a little behind in overall performance my OCD always strays away from choosing them.

So, I hope that they can knock Intel off their block. The fiercer the competition the more likely we'll get something great out of it.

Joel H 4 years ago

Marius,

 

I'm guessing you didn't build many systems from 2000-2001, or 2004-2006. Once Hammer hit, AMD led for several years until Intel unleashed Core. From 2006 - Present Day, AMD has actually maintained a decent price/performance ratio overall...but I don't really disagree with your reasons for choosing Intel.

bigtallsob 4 years ago

one thing ilike about amd is how they keep a lot of processors backwards compatible, for example, i had an athlon 5200+ in my old rig, then i got a phenom II 965 and dropped it right in and got a huge performance boost. with intel, most upgrades from intel that would produce a noticable improvement require a board upgrade as well, cause they have 3 different sockets.

animatortom 4 years ago

This is a good foreshadowing of what is going to happen to AMD/ATI stock...It will be bulldozedHmm

Their box store marketing model doesnt work on CPU's. You cant just try and sell a bunch of cheap disposable Chinese products to the masses, without providing quality and good customer service!

Post a Comment
or Register to comment