Intel dealt a blow to AMD and ARM this week with the introduction of the Xeon Processor D Product Family of low power server SoCs. The new Xeon D chips use Intel’s latest 14nm process and top out at 45W. The chips are aimed at low power high density servers for general web hosting, storage clusters, web caches, and networking hardware.
Currently, Intel has announced two Xeon D chips, the Xeon D-1540 and Xeon D-1520. Both chips are comprised of two dies inside a single package. The main die uses a 14nm process and holds the CPU cores, L3 cache, DDR3 and DDR4 memory controllers, networking controller, PCI-E 3.0, and USB 3.0 while a secondary die using a larger (but easier to implement) manufacturing process hosts the higher latency I/O that would traditionally sit on the southbridge including SATA, PCI-E 2.0, and USB 2.0.
In all, a fairly typical SoC setup from Intel. The specifics are where things get interesting, however. At the top end, Xeon D offers eight Broadwell-based CPU cores (with Hyper-Threading for 16 total threads) clocked at 2.0 GHz base and 2.5 GHz max all-core Turbo (2.6 GHz on a single core). The cores are slightly more efficient than Haswell, especially in this low power setup. The eight cores can tap into 12MB of L3 cache as well as up to 128GB of registered ECC memory (or 64GB unbuffered and/or SODIMMs) in DDR3 1600 MHz or DDR4 2133 MHz flavors. Xeon D also features 24 PCI-E 3.0 lanes (which can be broken up to as small as six PCI-E 3.0 x4 lanes or in a x16+x8 configuration among others), eight PCI-E 2.0 lanes, two 10GbE connections, six SATA III 6.0 Gbps channels, four USB 3.0 ports, and four USB 2.0 ports.
All of this hardware is rolled into a part with a 45W TDP. Needless to say, this is a new level of efficiency for Xeons! Intel chose to compare the new chips to its Atom C2000 “Avoton” (Silvermont-based) SoCs which were also aimed at low power servers and related devices. According to the company, Xeon D offers up to 3.4-times the performance and 1.7-times the performance-per-watt of the top end Atom C2750 processor. Keeping in mind that Xeon D uses approximately twice the power as Atom C2000, it is still looking good for Intel since you are getting more than twice the performance and a more power efficient part. Further, while the TDPs are much higher,
Intel has packed Xeon D with a slew of power management technology including Integrated Voltage Regulation (IVR), an energy efficient turbo mode that will analyze whether increased frequencies actually help get work done faster (and if not will reduce turbo to allow extra power to be used elsewhere on the chip or to simply reduce wasted energy), and optional “hardware power management” that allows the processor itself to determine the appropriate power and sleep states independently from the OS.
Being server parts, Xeon D supports ECC, PCI-E Non-Transparent Bridging, memory and PCI-E Checksums, and corrected (errata-free) TSX instructions.
Ars Technica notes that Xeon D is strictly single socket and that Intel has reserved multi-socket servers for its higher end and more expensive Xeons (Haswell-EP). Where does the “high density” I mentioned come from then? Well, by cramming as many Xeon D SoCs on small motherboards with their own RAM and IO into rack mounted cases as possible, of course! It is hard to say just how many Xeon Ds will fit in a 1U, 2U, or even 4U rack mounted system without seeing associated motherboards and networking hardware needed but Xeon D should fare better than Avoton in this case since we are looking at higher bandwidth networking links and more PCI-E lanes, but AMD with SeaMicro’s Freedom Fabric and head start on low power x86 and ARM-based Opteron chip research as well as other ARM-based companies like AppliedMicro (X-Gene) will have a slight density advantage (though the Intel chips will be faster per chip).
Which brings me to my final point. Xeon D truly appears like a shot across both ARM and AMD’s bow. It seems like Intel is not content with it’s dominant position in the overall server market and is putting its weight into a move to take over the low power server market as well, a niche that ARM and AMD in particular have been actively pursuing. Intel is not quite to the low power levels that AMD and other ARM-based companies are, but bringing Xeon down to 45W (with Atom-based solutions going upwards performance wise), the Intel juggernaut is closing in and I’m interested to see how it all plays out.
Right now, ARM still has the TDP and customization advantage (where customers can create custom chips and cores to suit their exact needs) and AMD will be able to leverage its GPU expertise by including processor graphics for a leg up on highly multi-threaded GPGPU workloads. On the other hand, Intel has the better manufacturing process and engineering budget. Xeon D seems to be the first step towards going after a market that they have in the past not really focused on.
With Intel pushing its weight around, where will that leave the little guys that I have been rooting for in this low power high density server space?
Very interesting analysis
Very interesting analysis with respect to how these new chips and intel will fare against arm and amd. Thanks.
Thanks. I feel like Intel
Thanks. I feel like Intel keeps forcing AMD into a smaller and smaller corner of the server market. At some point AMD's increasingly focused/smaller niches will not be profitable and AMD will have to fight back or give up that space.
Right now, things are interesting because while Intel is working to get to lower power, ARM is working on moving upwards to higher power and more capable parts. Interesting times, IMO.
AMD is sort of doing their own thing right now and it's working for them but I worry how long Intel will leave them alone in this space. I will keep hope alive for AMD's next gen stuff hehe.
Im sure that fag boy from arm
Im sure that fag boy from arm will tout the merits of ARM and let you know all about custom socs and how anyone who disagrees with him is just rooting for monopolies or something of that sort. And it will be at least 1000 words
Well AMD will have its Zen
Well AMD will have its Zen microarchitecture server SKUs arriving in 2016, and also Its K12 custom ARMv8 core microarchitecture. AMD’s current Opteron server share is small compared to Intel’s. AMD’s Seattle Opteron and skybridge motherboards will have the advantage of having pin compatibility between ARM based and x86 based AMD processor CPU/APUs, that will equal savings for server businesses looking to get the most configurability out of their server motherboard investments. Being able to utilize the same motherboard for x86, and ARM based server deployments, via the dual use Skybridge motherboards will definitely be a plus, and allow for better utilization of server hardware resources. AMD needs to at least maintain enough server revenues to maintain a market presence until 2016 when Zen, and K12 arrive.
There will be much competition for the ARM based server market from other ARM competitors also, But AMD’s Jim Keller has Talked about much sharing of ideas between the custom ARM(K12) and x86(Zen) design teams, so look for some interesting cross pollination of design features in AMDs new ARM and x86 products.
Intel will have to forgo some of its margins, if it really hopes to get a larger share of the low power server market, and the ARM server market is just in its formative stages. Intel’s fab process node lead is shrinking, and most of the ARM based RISC designs are more/just as power efficient on a larger process node. So the closer to fab process node parity the competition gets the harder it will be for the CISC x86 designs to compete in the power usage metrics.
AMD has also done some interesting design layout engineering with its x86 based Carrizo APUs, in that AMD has utilized its GPU layout design libraries in the layout of the Carrizo, and achieved a denser circuit packing on the current 28nm process node, this layout design, and the design libraries will allow AMD to be able to achieve denser/smaller server SKU designs among its x86 offerings, and this is probably applicable to use for the ARM designs also. Being able to pack server boxes more densely is and will be a big selling point in the high density server box designs that the server industry is moving to with the low power server designs.
AMD is not going to go down as easily as some people may think, and 2016 will be a pivotal year for AMD, one way or the other, but pivotal for sure. AMD’s revenue outlooks for the custom console SKUs is looking good also with China opening up as a market for consoles that utilize AMD’s SKUs. AMD’s supposed death knell has been so continuously prophesized over the last decade that it holds very little weight. AMD is definitely not standing still and is actually doing some very creative and innovative engineering.
AMD has other revenue producing divisions, Sea Micoro, and SeaMicro server sales are not totally dependent on AMD’s server SKUs alone, for sure there are SeaMicro customers using Intel SKUs, AND AMD will generate revenues none the less, regardless of the CPU SKUs utilized in its SeaMicro kit, the licensed Power8 products from OpenPower could give AMD some other ISA/IP SKUs with which to apply to their SeaMicro server business, and Give AMD a third option to go along with the ARM, and x86 options that AMD already has. The power8 designs in SeaMicro servers could be a sleeper style move, and allow AMD another entry into the super High end server/HPC market that will compete with the any of Intel’s Xeon SKUs.