Introduction
It seems as if an eternity has passed since the excitement around AMD’s Hammer technology took feverish hold of enthusiasts. However, the discussion has often been marred or confused by the fact that the all-embracing term Hammer applied to two completely different products – Clawhammer, and Seldgehammer.
Well, Clawhammer is now an Athlon, and will maintain that brand’s recognition in the market. Sledgehammer has been anointed with a completely new brand to signal AMD’s intentions of getting serious in the enterprise server and corporate markets. That name, the feature of the day, is Opteron.
Cue fanfare and fireworks.
At WinHEC 2002, Microsoft didn’t have anything to say about AMD and 64-bit operating systems, but today the announcement finally came – Microsoft will of course support Opteron’s x86-64 64-bit instruction set.
Goodbye to Duron Apaloosa
In addition to the new branding on Hammer chips, AMD has revamped its product roadmap and effectively consigned Duron to a slow death.
The Opteron makes its appearance on AMD’s new roadmap. Notice how the Duron Apaloosa core has disappeared from the roadmap to be replaced by Athlon Thoroughbred.
It’s simple, sharp, and clear cut. It cuts out the deadwood, and frees AMD’s resources to go into Opteron.
AMD’s official line on the new roadmap is:
AMD designed the “Thoroughbred” core of the AMD Athlon XP processor so that we could produce a single family of products that meets the needs of our OEM customers, benefits end users, and serves all system price bands. AMD plans to make AMD Athlon XP processors available for more system price points, including those occupied by the AMD Duron processor. We plan for the AMD Duron processor to be available in the market into 2003. More business and home consumers can now enjoy the benefits of the award-winning AMD Athlon XP processor. Consolidating on the AMD Athlon XP processor brand also provides a single performance scale which makes PCs easier to purchase for home and business users.
With this brand consolidation, AMD also can apply valuable engineering and design resources to other critical development areas, such as our 8th-generation processor family, codenamed “Hammer.”
Opteron – Latin is Cool and AMD is Smart
Opteron is a very smart move on AMD’s part. Although there are still many questions that remain to be answered about the product. We’ll look at some of the plus points and negatives, and also bring you pictures of the first demonstration Opteron system from AMD, something that was being paraded in a back room at WinHEC 2002 last week.
So, say it again, Opteron. Opteron from the Latin optimus meaning best. But, we won’t bore you with the marketing pitch, or push you to imagine the pictures the word Opteron is supposed to conjure up. Obviously, optimal comes to mind. Like it or lump it, people in marketing get paid good money to come up with this stuff, and while it takes some getting used to initially, it does eventually sit well. That’s enough fretting about the name.
The name isn’t the thing. Opteron isn’t as much about the branding as it is about positioning AMD to do what it has not been able to do with great success in the past – get those Tier One OEMs, and corporate buyers to jump on the bandwagon. Despite having definite benefits and advantages, AMD’s processors have remained firmly entrenched in the Systems Integrator channels, and among resellers, but have not found as much favor with the establishment of the PC industry.
Premium Branding and Pricing – A Discussion with John Crank of AMD
With Opteron, AMD has a shot at creating marketing programs and impetus behind a product to move it into the rarified atmosphere of the enterprise. We sat down and discussed the branding issues with John Crank, AMD’s senior brand associate.
The details on Opteron are sketchy, at best, and little has been said to add to what was already said at CeBIT and IDF in February, 2002.
“We will not be disclosing specific information.” Said John Crank, firmly.
In terms of positioning Opteron, Mr. Crank said, “We feel a new brand, the Opteron brand, is the best way to get into the mutli-way server market; a back-room solution.
“Right now we have the Athlon MP for a 1 or 2 way server solution. Most of the server market, 80%, is a 1 or 2 way market, and most of those systems have only 1 CPU in them.
“Opteron will go from the front-end to the mid-tier to the back-room database servers, what’s called the big iron market. It’s targeted against Itaniums, Xeon MPs, Xeon scalable solutions.”
One area that we were particularly concerned with was the value proposition for Opteron. Mr. Crank allayed our fears by saying, “Opteron is not a mainstream product. It is an Enterprise class product. It will have a premium.” However, he also added, “AMD will continue to compete on price.”
This is going to be where AMD’s detailed marketing efforts and programs have to come into play. Things that we have no information on presently. AMD is fighting Intel, with its deep pockets, entrenchment in the enterprise and among Tier One OEMs.
There needs to be a clear distinction on AMD’s part, backed up with successful penetration of the enterprise market, that Opteron is a premium product, with premium margins, and one that will not have to undercut its rivals in price alone to remain competitive.
This is not the commodity desktop market, and it is essential that AMD’s strategy results in Tier One adoption of Opteron in multi-way server product lines.
Branding is good, but Mr. Crank and his colleagues have their work cut out for them in every aspect of their marketing activities, and evangelism of AMD’s technology.
Positioned to Dominate
The Opteron triumverate of chipsets. No change in the chipsets and feature sets available from when Opteron was codenamed Sledgehammer.
2P value server configuration. This segment of the server market accounts for about 80% of the total server market, and many 2P configurations don’t even have the second CPU installed. This may be AMD’s easiest target, but not necessarily the best from a strategic point of view.
4P server configuration. Mutli-way server configurations, the holy grail of ‘Big Iron’ is what AMD hopes to get to with Opteron. 4P and up is where AMD really wants to go with Opteron.
The Workstation Conundrum
AMD freely admitted that the workstation market wasn’t a primary target for the Opteron, which makes perfect sense for a number of reasons. AMD’s strength seems to be in Systems Integrator channel, and in the digital content creation (DCC) market, the company has made inroads into production houses were price sensitivity exists. However, the big special effects houses, such as DreamWorks and Sony, are sill primarily Tier One brand name buyers.
However, if AMD manages to create a large enough installed base of 64-bit platforms with Opteron and Clawhammer, it should find it easier to get the support of workstation applications developers in key market areas such as DCC, simulation, and finance to port their software to AMD’s 64-bit platform.
The one question mark that hangs over the Opteron in the workstation segment is the 8151 chipset and the way it works with AGP. AMD uses the term APG tunneling.
The 8151 with AGP Tunneling.
Into this mix you have to add an AGP Bridge: this connects the two contrasting buses of the HyperTransport interface and the AGP interface. The AGP tunnel from AMD allows AGP 8x to hook up to the Opteron HyperTransport FSB. Is this a good idea? It is logical since Opteron integrates the memory controller. This is the next best thing for an AGP attach. But, will it have issues? It could. It is more complex to convert from parallel data (AGP) to packetized data (HyperTransport). Packets are not pure data; they have overhead (commands, addresses, ECC, etc. that establish each packet of information and define its transport). This overhead can cause over-runs or under-runs that may impact performance and cause bugs.
While AMD readily admits that the workstation market is not going to be the major target for Opteron, it’s worth noting that there is a slight question mark hanging over the approach taken with the 8151 chipset.
To get AMD’s point of view we talked to Gabriele Sartori, Director of Technology Evangelism at AMD and President of the HyperTransport Consortium, who believes that HyperTransport is a very effective solution. He told us, “HyperTransport is very low latency, and very fast. The problem with AGP today is that it is plugged in directly to the memory controller. When you get a transaction from AGP the data may or may not be available. We don’t have that problem with HyperTransport.”
In addition, Mr. Sartori stressed that the greater bandwidth of HyperTransport can be calibrated depending on the application. With other bus solutions that require an embedded clock, the overhead can eat up as much as 20% of the bandwidth of the bus, further reducing the efficacy of the bus.
At the end of the day, this is all conjecture until we get our hands on real silicon and test it, yet, the issue of competing and contrasting buses is not going to go away. For instance, Intel, ServerWorks, AMD, VIA, et. al. all have their own favorite board-level interconnects; some proprietary, and some open. PCI Express and HyperTransport are both an open standard, so competition and customer demand will dictate what chip-level interconnect chipsets will choose. This issue mustn’t be overlooked in assessing AMD’s positioning statements.
Optimal Technology (Section provided by Thomas Pabst)
Thinking up a kewl name is one thing, but equipping the new processor with the ‘optimum’ technology is another. There is no reason to worry, however. AMD was able to pack some really nifty stuff into its upcoming new “Opteron” processor.
- Integrated Memory Controller (!!)
The probably most promising feature of AMD’s Opteron processors will be the integrated memory controller. Unlike what’s found in x86 systems today, Opteron does not require to go through the chipset’s “north bridge” when accessing memory. Rather than that, the Opteron processor hooks up directly to the memory, and because it is a 64-bit (as well as 32-bit) processor, it also comes with a wider memory bus of 128-bit width – something we so far knew from 3D chips only. What you get is a direct connect from Opteron to two parallel 64-bit wide memory interfaces as we know them today. This doubles the memory bandwidth and the omission of a north bridge chip in between reduces latency as well. Things get even better. In SMP (multi processor) systems, each Opteron has its own memory interface and its own memory. This might have been overkill in the past, but with memory prices as low as today, this solution is feasible and most certainly the best way to go in terms of performance, as it offers a whopping bandwidth of up to 5.3 GB/s per processor.
There is one rather serious disadvantage of this integrated memory controller though. It is only designed for one type of memory. It is not surprising that AMD chose a DDR-SDRAM interface (clocked at 266-333 MHz), which is clearly showing the best future right now. However, RDRAM or QDR-SDRAM will not be supported. It would require a redesign of Opteron’s processor die. Still, it might well be possible that future Opteron processors come in different flavors for different memory types. - x86-64 Technology
Much has already been said about the Sledgehammer core and AMD’s approach to 64-bit processing, so I will keep myself short on this. Unlike Intel’s “Itanium” processor, which ‘understands’ only IA64 software and which is not backwards compatible to the Pentium1-4 32-bit processors of today and yesterday, Opteron will “understand” today’s 32-bit software as well as future x86-64 64-bit software. Opteron executes both software types natively and thus with full speed. This gives users the opportunity to stick with 32-bit software for the time being, saving the costs of a complete software revamp and still leaves the chance for a future ‘upgrade’ to 64-bit software without having to buy a new platform. Microsoft has just announced that it will support x86-64, so there will be WindowsXP and MS Office for Opteron’s 64-bit instruction set as well. - HyperTransport Technology
HyperTransport itself is not new whatsoever and latest since NVIDIA put Hypertransport into its nForce chipset, everyone with a technical interest is well aware of its virtues. With Opteron, AMD is taking the usage of HyperTransport to a new level. 16 CAD HyperTransport (16-bit wide, CAD=Command, Address, Data) will be used as the interface for processor-to-processor and processor-to-chipset, providing a bandwidth of up to 6.4 GB/s and thus about 50% more than what the latest Pentium 4 or Xeon processors with 533 MHz processor bus clock are able to provide. For the techies of you, the 6.4 GB/s are exactly 3.2 GB/s in each direction, while the 16-bit wide interface is clocked at 800 MHz and transporting data at double data rate. Sounds all very ‘Rambus’ to me, but it’s not a memory interface after all. 8-bit wide HyperTransport (bandwidth up to 1.6 GB/s with 400 MHz clock) will be used to interconnect Opteron-system components that don’t require the ultra-high bandwidth provided by the 16-bit version, such as normal I/O-Hubs. - Large 2nd Level Cache
It is not suprising that AMD will offer Opteron with up to 1 MB of L2 cache, which is particularly useful in enterprise server systems. Workstations are usually not able to benenfit too much from L2 caches of that size.
AMD predicts that Opteron will have a nominal performance gain over Athlon of about 25% (at equal clock speeds), where 20% are coming from Opteron’s new intergrated low-latency memory interface and 5% from improvements to Opteron’s core.
Pictures! Wow! Of Working Opteron System
It seems to be obligatory these days to do sightings of products. Sometimes they get to be a bit like the grainy images of Big Foot.
The mighty, might Opteron server in a 2P value server configuration. That’s a mighty Big Footprint.
But, in this case, AMD is pulling out all the stops. The company has already begun the seeding process with developers. AMD is running a little behind with Intel on this one, but the more they show the silicon is there, or getting there, the more they can get leverage to win applications support from 64-bit developers. Of course, it’s worth noting that Intel has had a bit of a head start with McKinley, to say the least. However, the more Opteron sees daylight, the better it has to be for AMD.
Clawhammer system running on the Opteron server’s network. Clawhammer will is going to be the Athlon desktop flagship CPU for AMD by end of 2002.
In the meantime, Clawhammer/Athlon 8th Generation is going to be the first product we will get to test drive. So, why the pre-pre-pre-release sightings? That is a mystery of the Web phenomenon that is AMD.
Finally
Opteron is just the first piece of the puzzle. AMD has a lot more work to do on the marketing and promotion of its platform. The development cycle is going to be long for 64-bit applications, irrespective of how quickly AMD gains support. Even the announcement from Microsoft doesn’t necessarily accelerate that process. It’s was an absolutely necessary step.
Application developers are going to want a lot more convincing before they invest development resources, and AMD can’t match Intel’s clout here so, the question is, will Opteron’s build an installed base as 32-bit platforms? Or, will it be the Clawhammer/Athlon that will actually give AMD an installed base of 64-bit computer users that it can flaunt in the face of its developers.
If AMD wants the server market and the enterprise and the Tier One OEMs that serve that enterprise, it needs to find a way to gain acceptance for Opteron with what is out there. Linux, 32-bit apps, etc. all figure. On top of that, AMD has to be very aggressive in it evangelism and mustn’t end up losing the premium pricing and positioning on Opteron.
A volume server solution is not what AMD needs with Opteron. AMD needs Big Iron wins. Opteron may be just a branding exercise for now, but it matches Intel toe-to-toe on Xeon and Itanium. That’s not a bad way for AMD to go about winning blue chip customers.