Become a fan of Slashdot on Facebook

 


Forgot your password?
Close
typodupeerror
×
Intel Power Hardware Technology

Intel Launches Xeon Scalable CPUs: Dual Xeon Platinum 8176, 112 Threads Tested (hothardware.com) 54

Posted by BeauHD from the family-reunion dept.
MojoKid writes: Intel announced its new Xeon Scalable processor family based on the 14nm Skylake-SP microarchitecture a few weeks back, though today marks the official launch of the platform. Not only do these processors feature a new microarchitecture, but Intel has also revamped the naming convention and arrangement of the Xeon product stack, branding them with Platinum, Gold, Silver, and Bronze model families. Intel Xeon Scalable series processors feature core counts ranging from 4 to 28, with varied frequencies and cache configurations. Workstation processors and lower-core count server chips top out in the 3.2GHz -- 3.6GHz range, while the higher-core count products typically fall in the 2GHz -- 2.7GHz range. Six memory channels are supported and the chips have 48 lanes of integrated PCIe 3.0 connectivity. Power envelopes range all the way from 70W on up to 205W. The Xeon Scalable series also introduces new security, virtualization, and storage-related features, more memory bandwidth, support for AVX-512 extensions, a mesh interconnect, and enhanced hardware controlled power management, among a host of other architectural improvements. Testing of a 2P Xeon Platinum 8176 system, sporting 56 physical cores / 112 threads shows significantly increased performance and bandwidth, with only moderately higher power consumption versus a previous-gen 2P Xeon E5-2679 v4-based system.
This discussion has been archived. No new comments can be posted.

Intel Launches Xeon Scalable CPUs: Dual Xeon Platinum 8176, 112 Threads Tested More

Intel Launches Xeon Scalable CPUs: Dual Xeon Platinum 8176, 112 Threads Tested

Comments Filter:
  • 8176+112=8288. nerd stuff.

  • Imagine a Beowulf cluster... (Score:5, Funny)

    by Red Herring ( 47817 ) on Tuesday July 11, 2017 @05:24PM (#54789703)

    Too old a joke? Anyone? Anyone? This thing on?

    • Re: (Score:2, Troll)

      by sl3xd ( 111641 )

      Beowulf is an ancient story, whether we're talking about literature or technology.

      It was too old in 2005.

      At least in 2005, AMD had a processor that was genuinely faster than anything from Intel. Those were heady days.

      Now we just get fanbois droning on endlessly about how awesome it is that AMD's next generation will be slower but cheaper than Intel's latest offering.

      • Now we just get fanbois droning on endlessly about how awesome it is that AMD's next generation will be slower but cheaper than Intel's latest offering.

        Actually, AMDs newest chip is pretty good. Earlier today, Anandtechan article comparing Intel and AMDs latest offerings [anandtech.com], and puts the 8176 up against AMDs best CPU. The overall takeaway is that the AMD system is faster in a lot of workloads (databases being the one big notable area where it loses badly) than the Intel system and at a much lower cost. It isn't a complete ass-whooping to the degree it was in the Opteron days, but now AMD actually has a product that won't be relegated to the bargain bin.

        • Databases (Score:4, Insightful)

          by nojayuk ( 567177 ) on Tuesday July 11, 2017 @07:40PM (#54790445)

          The overall takeaway is that the AMD system is faster in a lot of workloads (databases being the one big notable area where it loses badly) than the Intel system and at a much lower cost.

          Databases are what the Big Iron servers live to support so AMD losing badly against Skylake on that front means they've lost the sales war. Web servers are databases, order processing systems are databases, pretty much everything that's computationally intensive has a database or six on the backend.

          High Performance Computing (HPC) is shiny and prominent but the sales are limited and a lot of new HPC kit is based around non-CPU computation elements derived from GPUs rather than general-purpose CPUs so even good performance in that area won't save AMD in the datacentre markets.

          • Re: (Score:3)

            by epine ( 68316 )

            Databases are what the Big Iron servers live to support so AMD losing badly against Skylake on that front means they've lost the sales war.

            Big language. Been watching too much Bruno Ganz lately?

            I appears Ars tested MySQL Percona Server 5.7.0 as their chosen representative for the entire category. I wouldn't recall Rommel's tanks just yet.

            Typically when high response times were reported, this indicated low single threaded performance. However for EPYC this is not the case. We tested with a database that is

          • All of those things you've listed (and many you haven't) might connect to a database, but they're not always running on the same system or even the same hardware as the database. Pick Intel where it makes the most sense based on performance and choose AMD when they're better suited to the task. The only difference is that AMD hasn't had a server chip suited to any task beyond space heater for over half a decade, whereas now there's a compelling reason to buy AMD for some workloads.

  • Hilarious (Score:5, Informative)

    by Anonymous Coward on Tuesday July 11, 2017 @05:25PM (#54789709)

    Very expensive (the top one is $11722) and very fragmented portfolio. There actually is a review comparing one of the top Xeon Platinums 8176 ($8719) to the AMD EPYC 7601 (4200$) - http://www.anandtech.com/show/11544/intel-skylake-ep-vs-amd-epyc-7000-cpu-battle-of-the-decade

    The results might be surprising and speak of desperation in pushing the Core-derived architectures too far. Another indicator is the recent HEDT platform's problems on Tom's Hardware - http://www.tomshardware.com/reviews/-intel-skylake-x-overclocking-thermal-issues,5117.html

    Not to mention another security nightmare on the level of Intel ME/AMT:

    "The chipset will also include a new feature called Intel’s Innovation Engine, giving a small embedded core into the PCH which mirrors Intel’s Management Engine but is designed for system-builders and integrators. This allows specialist firmware to manage some of the capabilities of the system on top of Intel’s ME, and is essentially an Intel Quark x86 core with 1.4MB SRAM."

    Because we all know the motherboard manufacturers are known for stable and secure code, so let's let them botch yet another thing.

    It's high time AMD kicked Intel's butt into actually trying and not milking their customers constantly.

    • Re:Hilarious (Score:4, Interesting)

      by gweihir ( 88907 ) on Tuesday July 11, 2017 @06:34PM (#54790059)

      I think this is a sign of pretty extreme desperation: They do not have anything on par with what AMD offers and they will not have anything for years to come, as developing new architectures takes a lot of time, regardless of how much money you throw at it. AMD, meanwhile can optimize their new design for the next 5 years or more before they are even remotely threatened by Intel. Will take all the mindless sheep a while to understand, but eventually it might even dawn on them how thoroughly Intel has fucked them over the last few years..

      • Re: (Score:1)

        by kfh227 ( 1219898 )

        And your source from Intel's R&D department saying they having started years ago is?

      • Re: (Score:2)

        by tlhIngan ( 30335 )

        I think this is a sign of pretty extreme desperation: They do not have anything on par with what AMD offers and they will not have anything for years to come, as developing new architectures takes a lot of time, regardless of how much money you throw at it. AMD, meanwhile can optimize their new design for the next 5 years or more before they are even remotely threatened by Intel. Will take all the mindless sheep a while to understand, but eventually it might even dawn on them how thoroughly Intel has fucked

    • Not to mention another security nightmare on the level of Intel ME/AMT:

      Yeah sorry but no one cares about this in this given market. Pretty much every Xeon chip ever sold has been put into a motherboard with some equivalent of this as a value added extra, and at a premium price too.

      If you're in the market for these and you're trying to control access at this level then you're doing your security wrong.

  • Threads, system buses
    It's time for networked processors (not ethernet)
    You give each processor its own memory space with a large amount of the space dedicated to its own private ram. Other sections of this memory space can intersect the memory space of a set of neighboring processors, shared ram. Get rid of the cashing and swapping and thrashing. Extremely complex operations can pipeline from processor space to processor space. One could make Neural networks, Function networks, Data flow programs as they wis

    • So basically the Inmos Transputer [wikipedia.org] from the 1980s?

    • Shared memory is superior in general because the code can simply avoid sharing to avoid nearly all of the negatives. Its called Non-Uniform Memory Access (NUMA) .. maintaining cache coherency with simple algorithms while giving each thread its own pool of fast memory.

      The advantage is that when you do need to share, its not nearly as bad as trying to push data across a cluster.

    • Re: (Score:2)

      by gweihir ( 88907 )

      That bullshit again. Yes, again, it was up around 20 years ago, complete failure, and it might have been up before that, also complete failure if it was.

    • WTF? Up to 205W, man that would glow without liquid cooling.
      Fully agree they're stuck on a track of blindly making it bigger.
      networked processors
      http://www.greenarraychips.com... [greenarraychips.com]
      144 separate processors in a chip, all running, well under 1W
      Chuck Moore's been doing it for years, nothing new, and it doesn't glow in the dark.

      • Looks cool. Are these available? It seems the nodes are separated by comports and not shared ram buffers. I was hoping for in addition to local ram for each processor core, a few shared memory ranged with a group of other processors. Maybe in a bipartite graph configuration.

    • Read up on the AS/400 architecture. Makes much more sense than the 8088 kludge we've had for decades.

  • and really shitty for everyone else who runs servers on a reasonable budget. It still appears AMD is going to take the server market.

  • how do the amd EPYC systems hold up?

    With Intel you need 3 cpus to get the same pci-e as 1 amd.

    Also that 1 AMD cpu has more ram channels then 1 intel cpu.

  • software Virtual (AKA fake) RAID for pci-e?? does that only work with intel pci-e ssd? and does it work with drives behind pci-e switches? hot swap?

    At least AMD gives you the pci-e lanes to do a system with lot's of pci-e storage and stuff like ZFS / CEPH / etc works good with storage in HBA mode not with all kinds of overhead like JBOD or 1 disk raid 0 setups.

  • With 112 threads, can you compile Chrome ans still use the mouse in Windows 10?

  • ... build Chrome [slashdot.org].

    Moreover, the problem gets worse the more cores you have.

  • Xeon Scalable processor family is now designated by Platinum, Gold, Silver, and Bronze categories, with a single model number.

    This naming shift gives me the major heebs. It can't possibly be designed to aid comprehension. It's the end of an era, for sure.

    I'd buy AMD almost for that reason alone, once I'm sure AMD is solid in the ZFS camp (the story there has been spotty for some while).

    But more likely, I'll run my current dual E5-2620 NAS convergence box into the dirt (I figure on another five to seven ye

Slashdot Top Deals

Children begin by loving their parents. After a time they judge them. Rarely, if ever, do they forgive them. - Oscar Wilde

Close