Visit additional Tabor Communication Publications
August 17, 2007
Being in the x86 processor space has always been a double-edged sword for AMD. The market for this architecture, probably the most widely used ISA for general-purpose computing, is enormous. But so is the competition.
Intel dwarfs AMD by any measurement. In 2006, Intel's net revenue was $35.38 billion, compared to $5.65 billion for AMD. In fact, last year Intel's R&D spending alone -- $5.87 billion -- was larger the AMD's entire revenue stream. This disparity is manifesting itself as AMD gets ready to release its much-anticipated "Barcelona" quad-core processor and Intel prepares to launch its new 45nm Penryn family.
On Tuesday, DailyTech reported that Intel is planning to release its first 45nm Penryn server chips on November 11, just nine weeks after the expected September 10 Barcelona release (and just in time for the 2007 Supercomputing Conference and Expo). Apparently the Penryn information was inadvertently placed on an unprotected Intel website. The 45nm shrink represents the next "tick" in Intel's "tick-tock" processor development strategy.
With AMD just beginning its 65nm Opteron deliveries at almost the same time that Intel is introducing its 45nm Xeon chips, it looks like AMD will be nearly a full process technology cycle behind its rival. While transistor size and technology isn't everything, it does offer the leader some fundamental advantages. For example, getting to 65nm ahead of AMD helped Intel deliver quad-core processors almost a year in advance of its rival. AMD is quick to remind us that the Intel designs are not "true" quad-core processors, since they rely on plugging two dual-core chips into a single socket. But that's of little consequence to customers. The dual-dual chips achieve respectable performance numbers. The new Xeon L5335 Intel just announced this week is a 2.0GHz quad that consumes only 50 watts -- a mere 12.5 watts per core.
While AMD is still ahead of the game in system design, using HyperTransport and an integrated memory controller to achieve better multicore integration and energy efficiency, the lack of a quad-core offering over the last ten months created an opportunity for Intel to retake market share, especially in the server space. With the quad-core Barcelona, AMD has a chance to recover some lost momentum. To its detriment, the company has over-hyped its new product and its vision of dealing a death blow to the Intel quads will not be realized. AMD scaled back the initial chip to a modest 2.0GHz, which is significantly less that the original target of 2.6GHz.
Because of the slower clock, AMD has backed away from claims of integer performance superiority for its initial Barcelona offering. However, the company still expects to beat the current raft of Xeons in floating point performance. It's all but impossible to get an apples-to-apples comparison of processors these days, given the variation of CPU caches, clocks and power envelopes. But assuming the first Opteron quad-core will be a 2.0GHz processor at 95 watts, a comparable chip in the Intel stable might be the 2.6GHz Xeon X5355 quad-core, but which runs a hotter at 120 watts (and that doesn't include the off-chip memory controller). AMD is claiming a 2.0GHz Barcelona should yield a peak SPECfp_rate2006 result of 69.5; Intel reports 58.9 for the Xeon X5355. So if the first quad-core Opteron out of the chute can put up these kinds of numbers against a comparable Xeon and use less power, that bodes well for the new Opteron line, especially in the floating-point-loving high performance technical computing market.
But if Intel does release Penryn-based Xeons a couple of months after the Barcelona launch, AMD's performance edge will be in jeopardy. Because the Penryn processors will use the advanced high-K dielectric and metal gate transistor design for its 45nm manufacturing technology, these chips will be able to achieve significantly better performance within a given power envelope compared to their 65nm counterparts. I'm guessing that the Penryn launch will nullify any floating point performance advantage AMD will achieve with their first quad-core Opterons and widen Intel's integer performance advantage. AMD, of course, will not be sitting still. They're expected to come out with both higher performing and lower power versions of their quad offering following the initial September introduction. So by the time November rolls around, we could have a real horse race.
But being an entire process technology iteration behind their rival will be a heavy burden for AMD. Intel will have a lot of latitude in targeting performance or energy consumption with the new transistor technology. If we can believe the Penryn information leaked by Intel, the top of the line X5460 quad-core will clock in at 3.16GHz and dissipate 120 watts; the low-end quad-core L5410 will run at 2.33GHz and use just 50 watts. Until AMD can move to 45nm, which it plans to do in 2008, it will have to be content to find design tradeoffs where it can tweak the clock speed or exploit energy savings on the 65nm chips.
The only good news for AMD is that the Penryn chips will still rely on the antiquated Front Side Bus (FSB) and off-chip memory controllers. However, this will not be the case for Intel's next-generation Nehalem microarchitecture due in 2008 -- the next "tock" in the tick-tock strategy. Nehalem is expected to jettison the FSB in favor of a more HyperTransport-like system interconnect and use an integrated memory controller. There's even talk of including a GPU on some Nehalem processors. The fact that Intel is following in its smaller rival's footsteps is probably of little consolation to AMD at this point.
For AMD to compete effectively in the x86 server market, it has to be on par with Intel's semiconductor technology. That doesn't mean AMD has to embrace the same technologies or have the same manufacturing structure as Intel, but if Opteron transistors are always going to be bigger and leakier than Xeon transistors, that seems unsustainable in the long run.
Since AMD relies heavily on IBM for its process technology R&D, maybe it's time to invest more heavily in that partnership -- or develop a larger alliance of companies that it can use for both semiconductor research and manufacturing. Big Blue itself would not appear to be as motivated as AMD is in outgunning Intel chips, since IBM's own Power and PowerPC processors aren't in direct competition with the Xeons. (Itaniums, of course, are another matter.) Indeed, IBM manufactures both Xeon- and Opteron-based servers. That means AMD itself needs to find a way to drive the process. But time is not on their side. Tick-tock.
As always, comments about HPCwire are welcomed and encouraged. Write to me, Michael Feldman, at email@example.com.
Posted by Michael Feldman - August 16, 2007 @ 9:00 PM, Pacific Daylight Time
Michael Feldman is the editor of HPCwire.
No Recent Blog Comments
The Xeon Phi coprocessor might be the new kid on the high performance block, but out of all first-rate kickers of the Intel tires, the Texas Advanced Computing Center (TACC) got the first real jab with its new top ten Stampede system.We talk with the center's Karl Schultz about the challenges of programming for Phi--but more specifically, the optimization...
Although Horst Simon was named Deputy Director of Lawrence Berkeley National Laboratory, he maintains his strong ties to the scientific computing community as an editor of the TOP500 list and as an invited speaker at conferences.
Supercomputing veteran, Bo Ewald, has been neck-deep in bleeding edge system development since his twelve-year stint at Cray Research back in the mid-1980s, which was followed by his tenure at large organizations like SGI and startups, including Scale Eight Corporation and Linux Networx. He has put his weight behind quantum company....
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 15, 2013 |
Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
May 10, 2013 |
Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
May 09, 2013 |
The Japanese government has revealed its plans to best its previous K Computer efforts with what they hope will be the first exascale system...
May 08, 2013 |
For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.
The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.