Developing a custom microarchitecture is difficult. Even with all the standards in place and licensing an instruction set such as ARM, the actual development takes time and the right people to put together, then the infrastructure to deploy at scale.

In the mobile space, we’ve seen custom cores – most notably from Apple – deviating from the regular ARM design, but also Samsung and Qualcomm are playing in that space. Qualcomm however is going one further by developing a custom core for the server and enterprise market, focusing purely on typical enterprise workloads. The current commercial ARM success in the data center comes from companies such as Cavium, who use ARM architecture licenses in a custom SoC. By developing its own high-performance core, Qualcomm is hoping to offer something different in the data center, and they’ve lifted the lid on a good chunk of the core.

The Qualcomm Centriq 2400 SoC Family, with the Falkor CPU

Back in December 2016, Qualcomm announced that it has developed its own SoC for the data center, all the while also reveaing details such as the fact that it is a custom core and that Qualcomm will be involved in the Open Compute Project (and is based on the latest version of Microsoft’s Project Olympus). We knew that Qualcomm has been aiming for a 48 core design, using ARM’s instruction set, and is aiming for the data center and enterprise markets. The goal is to carry forward knowledge of the ARM instruction set and custom core design into markets that could potentially leverage it – it also helps that the data center market has a very interesting TAM (total addressable market, in USD) of which even a small slice could reap rewards. Back in December, they were beginning to sample cloud partners and potential future customers. 

The first set of products to come out will be the Qualcomm Centriq 2400 family of SoCs. The top parts will feature 48 cores, and while today Qualcomm is ultimately communicating about said 48-core model, they have stated that the 2400-series will be a range of parts segregated by core count, performance, and power. The CPU cores, code named Falkor, will be ARMv8.0 compliant although with ARMv8.1 features, allowing software to potentially seamlessly transition from other ARM environments (or need a recompile). The Centriq 2400 family is set to be AArch64 only, without support for AArch32: Qualcomm states that this saves some power and die area, but that they primarily chose this route because the ecosystems they are targeting have already migrated to 64-bit. Qualcomm’s Chris Bergen, Senior Director of Product Management for the Centriq 2400, stated that the majority of new and upcoming companies have started off with 64-bit as their base in the data center, and not even considering 32-bit, which is a reason for the AArch64-only choice here.

The design team behind the Centriq, as explained to us, was partly formed from the custom core team from the mobile side. On the mobile side we have seen Qualcomm custom cores based on ARM’s instruction set in the form of Krait and Kryo, although this new Falkor design is not derived from either. Qualcomm states that Falkor is their 5th generation of custom CPU core design, and has been a complete ground up design specifically for the data center. The focus, we were told, was on high overall performance, high performance per watt, but also the ability to run at low power. To do this, the Centriq 2400 is set to be the first major data center design built on a 10nm process.

We already know that it will be fabbed on a 10nm process, and various media/analysts have postulated which foundry will be playing that role. Qualcomm currently has 10nm volume with Samsung through the Snapdragon 835, which is shipping in the millions. Samsung’s 10nm processes are more mature than the competition at this point, however Samsung does not have much experience with large silicon dies, tending to favor smaller SoCs due to the naturally higher yields and helping to keep fab production at a high level. The other alternative is TSMC, whose CLN10FF process was technically available for select customer orders later than Samsung, but is currently being used by Apple's A10X in the iPad Pro 2. TSMC also has experience with larger silicon, which would be of considerable benefit. Qualcomm is not announcing who their foundry partner is at this time unfortunately, although it would likely depend on relations, volume, pricing and performance.

Enterprise Features: Security, QoS, and Secure Boot
POST A COMMENT

43 Comments

View All Comments

  • DanNeely - Sunday, August 20, 2017 - link

    Mobile CSS needs fixed. Bulleted lists need to wrap, instead of overflowing into horizontal scroll as they currently do on Android. Reply
  • twotwotwo - Sunday, August 20, 2017 - link

    The things I most wonder about the chip itself are, how much worse will single-thread speed be, and how much better will throughput/$ be?

    For serial speed, there's sort of a sliding scale of "good enough"; you can certainly find uses for chips that are slower than Intel's large cores, but as single-thread perf gets worse and worse, more types of app become tricky to run on it because of latency. So you want latency stats for typical enterprisey Java or C# (or, heck, Go) Web app or widely used databases or infrastructure tools. That's also a test of how well compilers and runtimes are tuned for ARMV8, the chip, and live with may cores, but since early customers will have to deal with the ecosystem that exists today, that's reasonable.

    For cost-effective throughput I guess we need to have an idea of at least price and power consumption, and parallel benchmarks that will hit bottlenecks a single-threaded one might not, like memory bandwidth. And the toughest comparison is probably against Intel's parts in the same segment, Xeon D and their server Atom chips. Something that makes it harder to win big on throughput/$ is that the CPU's cost and power consumption are only a piece of the total: DRAM, storage, network, and so on account for a lot of it. Also, the big cloud customers Qualcomm wants to win probably aren't paying the same premiums as you and I are to Intel.

    Then, aside from questions about the chip itself, there are questions about the ecosystem and customers. There are the questions above of how well toolchains and software are tuned. Maybe the biggest question is whether some big customer will make the leap and do some deployments on lots of slower cores. It might be a strategic long-term bet for some big cloud company that wants more competition in the server chip space, but I bet they have to be willing to lose real money on the effort for a generation or two first.
    Reply
  • name99 - Monday, August 21, 2017 - link

    Intel sells 28 core CPUs that run at 2.1 GHz (and turbo up to 3.8GHz but see below).
    Hell, they sell 16 core systems that run at 2.0 GHz and only turbo up to 2.8 GHz.

    Remember QC is not TRYING to sell these to amateurs, or even as office servers. They are targeted at data warehouse tasks where the job they're doing will be pretty well defined, and it's expected for the most part that ALL the cores will be running (ie when the work load lightens, you shut down entire dies and then racks, you don't futz around with just shutting down single cores).
    For environments like that, turbo'ing is of much less value. QC doesn't have to (and isn't) targeting the entire space of HPC+server+data warehouse, just the part that's a good match to what they're offering.
    Reply
  • Threska - Tuesday, August 22, 2017 - link

    Well there is the small developer virtualization market like Ansible. Reply
  • prisonerX - Monday, August 21, 2017 - link

    A preoccupation with single thread performance is the domain of video game playing teenagers and not terribly important, neither is the "latency" you refer to. This sort of high-core, efficient processor is going to be used where throughput and price/power/performance ratio (ie, all three, not just any one of those), are the key metric.

    Latency is mostly irrelevant since processing will be stream oriented and bandwidth limited rather than hamstrung by latency (thus features such as memory bandwidth compression). Gimmicks like "turbo" (which should be called by its proper name: "throttling") and favoring single thread performance are counterproductive in this mode. Being able to deploy many CPUs in dense compute nodes is what is required and memory, storage and networking are minor parts here.

    I don't know why you think compilers or runtimes is a concern, 99.9% of code is common across archs, so if you've supported a lot of x86 cores your code is going to function well for a lot of ARM cores with a small amount of arch specific configuration. The compilers themselves, namely GCC and LLVM are mature as is their support for ARM.

    Finally the new ARM CPUs don't have to beat Intel, just stay roughly competitive, because the one thing the tech industry hates more than a monopoly is a monopoly that has abused its monopoly powers, and Intel is it. Industry is itching for an alternative, and near enough is good enough.
    Reply
  • deltaFx2 - Thursday, August 24, 2017 - link

    "Industry is itching for an alternative": While this is true, is the industry truly interested in an alternative ISA, or alternative supplier? Because there is one now in the x86 space, and is very competitive, and in some metrics better than Intel. Also, your argument about single threaded performance being irrelevant in servers is false. A famous example of this is a paper in ISCA by google folks arguing in favor of high IPC machines (among other things). They also note that memory bandwidth is not as critical as latency. Now this is specific to google, but in plenty of other cases too, unless you have a very lopsided configuration, bandwidth doesn't get anywhere near saturation. There are also plenty of server users who provide extra cooling capacity to run at higher than base frequencies because it's cheaper than scaling out to more nodes. Obviously, your workloads should scale with freq.

    "Finally the new ARM CPUs don't have to beat Intel," -> change intel to AMD. AMD is hugely motivated to compete on price and has the performance to match intel in many workloads. And AMD's killer app is the 1P system, exactly where Qualcomm intends to go. You also have to add the cost of porting from x86->ARM (recompile, validation, etc). Time is money and employees need to be paid. So the question is, why ARM? More threads/socket? Nope. More memory/socket? Nope. More perf/thread? Probably not based on the architecture described but we'll see. More connectivity then? Nope. Lower absolute power? Maybe. Lower cost? I suspect AMD's MCM design is great for yields. And there's the porting cost if you're not already on ARM.

    There's a lot more work to be done and money to be spent before ARM becomes competitive in the mainstream server space. QC has the deep pockets to stick it out, but I am not sure about cavium.
    Reply
  • Gc - Sunday, August 20, 2017 - link

    Confusing terminology: prefetch vs. fetch

    Prefetch heuristics predict *future* memory addresses based on past memory access patterns, such as sequential or striding patterns, and try to prefetch the relevant cache lines *before* a miss occurs, attempting to avoid the cache miss or at least reduce the delay. A memory fetch to satisfy a cache miss is not a prefetch.

    Slide: "Hardware Prefetch on L1 miss."
    Text: "An L1 miss will initiate a hardware prefetch."
    The initial fetch is after the miss, so the initial fetch is not a 'prefetch'. I assume this means that it is not only fetching the missed cache line but also triggering the prefetchers to fetch additional cache lines.

    Slide: "Hardware data prefetch engine Prefetches for L1, L2, and L3 caches"
    Text: "If a miss occurs on the L1-data cache, hardware data prefetchers are used to probe the L2 and L3 caches."
    The slide is saying that data is prefetched at all three levels of cache. I'm not sure what the text is saying. Probing refers to querying the caches around the fabric to see which if any holds the requested cache line. This is part of any fetch, not specific to prefetching. Maybe the text is trying to say that the prefetchers not only remember past addresses and predict future addresses, but also remember which cache held past addresses and predicts which cache holds fetched and prefetched addresses?
    Reply
  • YoloPascual - Monday, August 21, 2017 - link

    Inb4 fanless data centers near the equator. Reply
  • KongClaude - Tuesday, August 22, 2017 - link

    'however Samsung does not have much experience with large silicon dies'

    I don't remember the actual die size for the DEC Alpha's that Samsung fabbed back in the day, the Alpha was a fairly large CPU even by todays standard. Would they have let go of that knowledge or is Alpha being relegated to low-volume/not much experience?
    Reply
  • psychobriggsy - Tuesday, August 22, 2017 - link

    We should also consider that GlobalFoundries licensed Samsung's 14nm after digging their own 14nm hole and failing to get out of it, and right now AMD are making 486mm^2 Vega dies on that process. The process doesn't have a massive maximum reticle size however, IIRC it's around 700mm^2, whereas TSMC can do just over 800mm^2 on their 16nm. Reply

Log in

Don't have an account? Sign up now