Around 15 months ago, AMD announced that it would be building 64-bit ARM based SoCs for servers in 2014. Less than a month into 2014, AMD made good on its promise and officially announced the Opteron A1100: a 64-bit ARM Cortex A57 based SoC.

The Opteron A1100 features either 4 or 8 AMD Cortex A57 cores. There's only a single die mask so we're talking about harvested die to make up the quad-core configuration. My guess is over time we'll see that go away entirely, but since we're at very early stages of talking about the A1100 there's likely some hedging of bets going on. Each core will run at a frequency somewhere north of 2GHz. The SoC is built on a 28nm process at Global Foundries.

Each pair of cores shares a 1MB L2 cache, for a total of up to 4MB of L2 cache for the chip. All cores share a unified L3 cache of up to 8MB in size. AMD designed a new memory controller for the Opteron A1100 that's capable of supporting both DDR3 or DDR4. The memory interface is 128-bits wide and supports up to 4 SODIMMs, UDIMMs or RDIMMs. AMD will be shipping a reference platform capable of supporting up to 128GB of Registered DDR3 DIMMs off of a single SoC.

Also on-die is an 8-lane PCIe 3.0 controller (1 x8 or 2 x4 slot configurations supported) and an 8-port 6Gbps SATA controller. AMD assured me that the on-chip fabric is capable of sustaining full bandwidth to all 8 SATA ports. The SoC features support for 2 x 10GbE ports and ARM's TrustZone technology. 

AMD will be making a reference board available to interested parties starting in March, with server and OEM announcements to come in Q4 of this year. 

It's still too early to talk about performance or TDPs, but AMD did indicate better overall performance than its Opteron X2150 (4-core 1.9GHz Jaguar) at a comparable TDP:

AMD Opteron A1100 vs. X2150
  CPU Core Configuration CPU Frequency SPECint_rate Estimate SPECint per Core Estimated TDP
AMD Opteron A1100 8 x ARM Cortex A57 >= 2GHz 80 10 25W
AMD Opteron X2150 4 x AMD Jaguar 1.9GHz 28.1 7 22W

AMD alluded to substantial cost savings over competing Intel solutions with support for similar memory capacities. AMD tells me we should expect a total "solution" price somewhere around 1/10th that of a competing high-end Xeon box, but it isn't offering specifics beyond that just yet. Given the Opteron X2150 performance/TDP comparison, I'm guessing we're looking at a similar ~$100 price point for the SoC. There's also no word on whether or not the SoC will leverage any of AMD's graphics IP.

The Opteron A1100 is aimed squarely at those applications that either need a lot of low power compute or tons of memory/storage. AMD sees huge demand in the memcached space, cold storage servers and Apache web front ends. The offer is pretty simple: take cost savings on the CPU front and pour it into more DRAM.

Early attempts at ARM based server designs were problematic given the lack of a 64-bit ARM ISA. With ARMv8 and the Cortex A53/A57 CPUs, that's all changed. I don't suspect solutions like the Opteron A1100 to be a knockout success immediately, but this is definitely the beginning of something very new. Of all of the players in the ARM enterprise space, AMD looks like one of the most credible threats. It's also a great way for AMD to rebuild its enterprise marketshare with a targeted strike in new/growing segments. 

AMD's Andrew Feldman included one of his trademark reality check slides in his Opteron A1100 presentation today:

Lower cost, high volume CPUs have always won. That's how Intel took the server market to begin with. The implication here is that ARM will do the same to Intel. Predicting 25% of the server market by 2019 may be feasible, but I'm not fond of making predictions for what the world will look like 5 years from now. 

The real question is what architecture(s) AMD plans to use to get to a leadership position among ARM CPUs and a substantial share of the x86 CPU market. We get the first hint with the third bullet above: "smaller more efficient x86 CPUs will be dominant in the x86 segment".

POST A COMMENT

124 Comments

View All Comments

  • FwFred - Wednesday, January 29, 2014 - link

    I challenge you on pricing. Intel has shown in the tablet market that they won't be beat on price. Could be the same in microservers if there was a perceived strategic threat.

    Avoton is no more a client design than Seattle is a phone SOC. 8 cores, 4x GBE, 64GB RAM, no GPU. Come on, can you be any more of a shill?
    Reply
  • KenLuskin - Wednesday, January 29, 2014 - link

    Fred, Intel has almost ZERO market share in Tablets, so they can LOSE money on every chip sold in order to BUY market share.

    Intel has 95% server chip market share.. If they discount, the DESTROY their biggest profit center!!!

    Nice try... but you get an F= FAIL!
    Reply
  • FwFred - Wednesday, January 29, 2014 - link

    If they hit their 40m target for tablets in 2014, it will not be insignificant.

    Do you really think AMD can undercut Intel when AMD and GF both take their margin on a lower volume part? (+ royalties to ARM)

    Intel has competed with AMD for years and kept a 60% margin. I don't see what changes here.
    Reply
  • extide - Wednesday, January 29, 2014 - link

    A57 is also a 'Client Design' here. At least call a spade a spade man. Reply
  • iwod - Wednesday, January 29, 2014 - link

    Expensive? Yes on Mobile. Did you just read the AMD SoC chip cost $100+? The Intel Avoton cost less then $150. @ Ken, Their biggest profit center are on Xeon, Not Atom Servers.

    Again, this would have been great if it came out 1 year earlier. But with Xeon SoC and Denvonton on the flag AMD offering doesn't sound too exciting for me.
    Reply
  • tcube - Saturday, August 02, 2014 - link

    try again that atom is "TRAY: $171.00" on intels site about the chip. Yeah sure if you buy 1000 you get a discount but so you do also for any AMD.

    BTW: Don't compare with tables prices with it's newest form of Intel bribes called "contra-revenue" (because "marketing-funds" was already taken from some years before). Intel is a crime syndicate and has been fined as such by the EU courts(1.5bn$ - highest fine ever in EU history).

    Buying Intel chips is just as dangerous as buying natural fur or blood diamonds, you feed a crime syndicate!! Get informed & get educated and buy an alternative if there is one if not sustain the creation of alternatives. Never in the history of IT was there a company as crime involved and as toxic to the environment and fair and open markets as Intel is right now! Get informed and understand the risks and don't give into any of this! You see a tablet powered by Intel - don't buy it! Same goes for anything Intel else but at least don't feed this "contra-revenue" thing or you'll feed a new monster! Show intel it can't bribe itself into any market! You the customer have the final say in this!
    Reply
  • Krysto - Wednesday, January 29, 2014 - link

    Avoton was obsolete from the day they announced it. Intel keeps being behind ARM competition no matter what they do - even when they are AHEAD in process node being utilized. No wonder they're considering getting out of the mobile market in 2015. They're already losing money with Atom, trying to enter a market where they have no chance of even being competitive, let alone "winning". Reply
  • factual - Wednesday, January 29, 2014 - link

    That's completely untrue. When Intel's silvermont core (used in avoton) came out, it beat virtually every ARM CPU in the market in terms of perf/watt.The 14nm atom core will widen the gap even further. The reason why Intel is having problems in the mobile market has little to do with ARM CPUs, and has a lot to do with Intel's ability to put together a well-integrated world-class SOC (with integrated cpu, gpu, lte baseband, sensors, etc.).

    I have little doubt that Intel will keep widening the perf/watt gap and destroy ARM CPUs in that regard. What remains to be seen is if intel can design a well-integrated SOC (something that only Qualcomm has been able to do so far).
    Reply
  • ancientarcher - Thursday, January 30, 2014 - link

    Intel will destroy this... Intel will destroy that
    and how much market share does the bestest of the best mobile chip silvermont have?? It beat all ARM chips but still has a 0.001% market share in smartphones. that's the example you want to trot out? seriously???

    The next thing thats gonna get destroyed is Intel's margins and marketshare in servers
    Reply
  • factual - Thursday, January 30, 2014 - link

    There is no doubt that Intel is struggling in the mobile market (it only has 3% of the tablet market share and practically has no presence in the smartphones market). But Intel's problems in the mobile market has little to do with ARM and has a lot to do with lack of a leading mobile solution which is a well-integrated, world-class SOC.

    Intel faces the same barrier that has prevented Nvidia (which uses ARM) from having a significant presence in the mobile market, the same barrier that forced TI (which used ARM) to drop out of the mobile race and the same barrier that has prevented AMD from entering the mobile market at all. Qualcomm dominates the mobile market because they have the best SOC (which has cpu, gpu, cellular baseband, gps, wi-fi, sensor hub, bluetooth, etc. all on the same die), not the best CPU or even GPU.

    If Intel dropped x86 in favor of ARM today, it wouldn't help its chances of penetrating the mobile market, it would probably hurt them.

    But in the server space, it's only the cpu performance that matters not the soc! so yes Intel's leading perf/watt cpu solution, will most likely destroy ARM's chances of gaining any significant market share in the low-power server space.
    Reply

Log in

Don't have an account? Sign up now