Qualcomm Debuts 10nm FinFET Centriq 2400 Processor With 48 Cores
Qualcomm and its Qualcomm Datacenter Technologies subsidiary announced today that the company has already begun sampling its first 10nm server processor. The Centriq 2400 is the second generation of Qualcomm server SOCs, but it is the first in its new family of 10nm FinFET processors. The Centriq 2400 features up to 48 custom Qualcomm ARMv8-compliant Falkor cores and comes a little over a year after Qualcomm began developing its first-generation Centriq processors.
Qualcomm's introduction of a 10nm server chip while Intel is still refining its 14nm process appears to be a clear shot across Intel's bow--due not only to the smaller process, but also its sudden lead in core count. Intel's latest 14nm E7 Broadwell processors top out at 24 cores.
Qualcomm isn't releasing more information, such as clock speeds or performance specifications, which would help to quantify the benefit of its increased core count. The server market commands the highest margins, which is certainly attractive for the mobile-centric Qualcomm, which found its success in the relatively low-margin smartphone segment. However, Intel has a commanding lead in the data center with more than a 99% share of the world's server sockets, and penetrating the segment requires considerable time, investment, and ecosystem development. Qualcomm unveiled at least a small portion of its development efforts by demonstrating Apache Spark and Hadoop on Linux and Java running on the Centriq 2400 processor. The company also notes that Falkor is SBSA compliant, which means that it is compatible with any software that runs on an ARMv8-compliant server platform.
"The Qualcomm Centriq 2400 series processors will drive high performance, power-efficient ARM-based servers from concept to reality," said Anand Chandrasekher, senior vice president and general manager, Qualcomm Datacenter Technologies, Inc. "Qualcomm requires the leading edge of integrated circuit technology to deliver high performance at low power for the newest premium smartphones. We are first in 10nm IC technology for mobile, and leveraging our expertise in ARM processors and system on chip design, we are the first with our Qualcomm Centriq family of server processors to bring the leading edge to the data center."
Qualcomm's move to a 10nm server chip isn't entirely surprising; the company recently unveiled the Snapdragon 835 SoC, which is its first processor built on Samsung's 10nm process. True to form, Qualcomm designed the Snapdragon 835 SoC for the mobile market. However, many of the same features that make ARM processors attractive, such as low power and cost, are coveted characteristics in the data center--a few fewer watts per chip can lead to millions in savings when deployed at scale.
Qualcomm isn't revealing which company is fabbing its new chips, but it indicated that the Snapdragon's 10nm process allowed it to increase area efficiency by 30% and enables either 27% more performance or up to 40% less power consumption than the 14nm process. These metrics surely won't apply directly to the benefits seen with the Centriq 2400, but it gives us some view of the advantages of the smaller node. Samsung is currently working with its 10nm (Low Power Early) process, which is the leading edge, but it also has its second-generation 10nm LPP (Low Power Plus) process on the horizon, which might give us an indication of future Qualcomm chip enhancements.
Just as with any announcement of a new process, we have to view the 10nm measurement with some hesitation. At times, only portions of a chip are constructed with the smaller geometry, while other portions will employ legacy nodes. The various semiconductor vendors also employ different measurement methodology, which leads to some lithography confusion at times. Many claim that Samsung's 10nm process is more akin to Intel's 14nm, but even if that is the case, just reaching parity with Intel is a big step for Qualcomm. Intel isn't slated to bring its 10nm Cannonlake chips to the market until late 2017, and we may not see 10nm Xeons until 2018 (or later). Intel has the intermediary 14nm+ process that will likely step into the Xeon market before the 10nm generation.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Meanwhile, Qualcomm plans to ship to the commercial market in Q2 2017. This is a bit off on the horizon, but it will certainly make Intel's next launch even more interesting. Qualcomm hasn't released many details of its new chip, such as memory controllers or cache alignments, but we expect more details to emerge as the company moves closer to the full launch. For now, Qualcomm will need to focus on technology enablement and ecosystem development that will likely begin with hyperscale customers, which are the true ingredients needed for a successful data center strategy.
Paul Alcorn is the Managing Editor: News and Emerging Tech for Tom's Hardware US. He also writes news and reviews on CPUs, storage, and enterprise hardware.
-
Nintendork When just money can't provide intel the competitive part, intel is in a pinch. The 3D Nand joint venture with micron is a huge fail, 3D-Xpoint/Optane failed the promises.Reply
AMD coming big with Zen, AMD-SAMSUNG coming big with their own version of non-volatile ram. -
manleysteele 18972735 said:When just money can't provide intel the competitive part, intel is in a pinch. The 3D Nand joint venture with micron is a huge fail, 3D-Xpoint/Optane failed the promises.
AMD coming big with Zen, AMD-SAMSUNG coming big with their own version of non-volatile ram.
Intel is scared of AMD and Samsung the same way I'm scared of shrews. Not at all. Besides that, what does your post have to do with the subject?
-
bit_user Unless it's Samsung, I think the quoted process node isn't truly superior to Intel's 14+ node.Reply
The more important point will be to focus on benchmarks & real-world performance. In those areas, I think they'll have a tough fight on their hands.
I think it's safe to say that per-core performance won't match Broadwell. I also wonder whether they have multiple threads, since such a high core-count means there will be a lot of stalls while waiting for memory reads/writes. So, even if the cores were more comparable to Broadwell, there might be little real-world benefit from having 48 of these vs. the 24-core/48-thread Xeons.
On the other hand, perhaps these cores are more comparable to the Silvermont Atom cores found in the latest Xeon Phi (with up to 72 cores / 288 threads). And unless the Centriq has HBM2 or HMC2, I think it's no match for the KNL Xeon Phi. -
InvalidError
That's what I was thinking too.18972688 said:Wouldn't the Xeon Phi be the logical comparison for this Tech?
Having twice the core count isn't that impressive when each core is less than half as powerful on its own. Simpler cores do tend to be more power-efficient when the workload scales well with core count though, which is usually the case for datacenters. -
manleysteele 18973221 said:
That's what I was thinking too.18972688 said:Wouldn't the Xeon Phi be the logical comparison for this Tech?
Having twice the core count isn't that impressive when each core is less than half as powerful on its own. Simpler cores do tend to be more power-efficient when the workload scales well with core count though, which is usually the case for datacenters.
Certainly, power costs over time are important in server farms. The obvious question is power cost at a level of compute performance. If it takes 3 or 4 of these SOC's to make similar levels of performance your cost savings are out the window.
I've been watching this all play out for 40 years. The superior replacement for the Intel architecture has come and gone too many times to easily count. The big problem is a huge installed base of critical software that won't run on anything else without huge investments of redesigning and reprogramming. I'll wait until someone solves that problem before I worry too much about it.
-
bit_user
But we don't know how they compare.18973221 said:Having twice the core count isn't that impressive when each core is less than half as powerful on its own.
Facebook explicitly rejected that approach, hence the Xeon D:18973221 said:Simpler cores do tend to be more power-efficient when the workload scales well with core count though, which is usually the case for datacenters.
https://www.nextplatform.com/2016/03/14/xeon-d-shows-arm-can-beat-intel/
The TL;DR is that single-thread performance still matters. Their point is that ARM can beat Intel, if someone can deliver cores that are sufficiently fast.
For datacenters, power costs typically overshadow initial purchase price. If the performance disparity were that great, then this product would've been killed before it even saw the light of day.18973356 said:Certainly, power costs over time are important in server farms. The obvious question is power cost at a level of compute performance. If it takes 3 or 4 of these SOC's to make similar levels of performance your cost savings are out the window.
While you weren't looking, ARM built up pretty much all the software support they need, in order to unseat Intel. All that's left is for silicon like this to provide truly competitive implementations. They own mobile, they're assaulting the datacenter, and products like Chromebooks are even encroaching into the laptop market. Desktops will be the last holdout, but maybe within a decade...18973356 said:I've been watching this all play out for 40 years. The superior replacement for the Intel architecture has come and gone too many times to easily count. The big problem is a huge installed base of critical software that won't run on anything else without huge investments of redesigning and reprogramming. I'll wait until someone solves that problem before I worry too much about it.
If we're talking about the cloud, then OpenPOWER is another one to watch. -
manleysteele 18973524 said:
But we don't know how they compare.18973221 said:Having twice the core count isn't that impressive when each core is less than half as powerful on its own.
Facebook explicitly rejected that approach, hence the Xeon D:18973221 said:Simpler cores do tend to be more power-efficient when the workload scales well with core count though, which is usually the case for datacenters.
https://www.nextplatform.com/2016/03/14/xeon-d-shows-arm-can-beat-intel/
The TL;DR is that single-thread performance still matters. Their point is that ARM can beat Intel, if someone can deliver cores that are sufficiently fast.
For datacenters, power costs typically overshadow initial purchase price. If the performance disparity were that great, then this product would've been killed before it even saw the light of day.18973356 said:Certainly, power costs over time are important in server farms. The obvious question is power cost at a level of compute performance. If it takes 3 or 4 of these SOC's to make similar levels of performance your cost savings are out the window.
While you weren't looking, ARM built up pretty much all the software support they need, in order to unseat Intel. All that's left is for silicon like this to provide truly competitive implementations. They own mobile, they're assaulting the datacenter, and products like Chromebooks are even encroaching into the laptop market. Desktops will be the last holdout, but maybe within a decade...18973356 said:I've been watching this all play out for 40 years. The superior replacement for the Intel architecture has come and gone too many times to easily count. The big problem is a huge installed base of critical software that won't run on anything else without huge investments of redesigning and reprogramming. I'll wait until someone solves that problem before I worry too much about it.
If we're talking about the cloud, then OpenPOWER is another one to watch.
I'll believe it when I see it. This is not the first time by a long shot that the POWER architecture has attempted a head to head battle with x86. So far, it's Intel 3 Power 0. I'll wait.
Edit: Or make that 3-1. IBM does use their own processors in their own servers.