Monday: Intel teases 48-core Xeon. Tuesday: AMD whips covers off 64-core second-gen Epyc server processor

Chipzilla more like Tyrannosaurus Rekt


AMD said on Tuesday it's going to roll out a 7nm 64-core second-generation Epyc server processor, dubbed Rome, in 2019.

Samples of the processor are in the hands of selected organizations for testing and evaluation. This comes a day after Intel promised on Monday a 14nm 48-core Cascade Lake AP Xeon chip also for 2019.

AMD's Rome will sport PCIe 4.0 interfaces, and the usual PCIe-based Infinity Fabric that interconnects processor sockets and any GPU accelerators. With up to 64 physical Zen 2 CPU cores, the chips can run up to 128 hardware threads. This is double the number of cores and hardware threads as 2017's 14nm first-generation Zen 1 Epyc, dubbed Naples.

As such, AMD CEO Lisa Su told journos and industry analysts in San Francisco on Tuesday that Rome will have double the performance of Naples, due to this core count leap and switch to 7nm.

Competition

The physical x64 core count blows away Intel's Xeon compute family, which only just set itself a high-water mark of 48 cores with Cascade Lake AP. Also, that line is still on Intel's 14nm process, whereas AMD is nudging ahead with TSMC's 7nm. AMD also claimed a single-socket Rome can match or outperform a dual-socket Intel Xeon Scalable 8180M setup, when running the ray-tracing C-Ray benchmark, at least.

If you've already splashed out on Naples chips, Rome processors are socket compatible with its previous generation, and are forward compatible with Milan: the third-generation Zen-based server part that will use TSMC's 7nm+ node and is due in 2020. As a whole, AMD hopes to get its 7nm+ Zen 3 chips, from Ryzen to Epyc, out that year. Zen 4 is in design, we're told.

Interestingly enough, the Rome processor package contains a central 14nm I/O die that interfaces with up to 2TB of external RAM per socket, and its PCIe 4.0 channels, and multiple dies of 7nm CPU core clusters connected to that I/O block. This way, whenever a CPU core wants to talk to outside memory, it can access it right out through the I/O die, as opposed to the NUMA approach of Zen 1 Epyc chips, where multiple internal dies had their own memory controllers and memory domains.

Amazon Web Services is also offering AMD generation-one Epyc-powered virtual machines in its cloud, which work out 10 per cent cheaper than Intel-based instances.

Click here to read more about AMD's Rome processor on our high-performance computing sister site, The Next Platform.

Similar topics

Broader topics


Other stories you might like

  • AMD bests Intel in cloud CPU performance study
    Overall price-performance in Big 3 hyperscalers a dead heat, says CockroachDB

    AMD's processors have come out on top in terms of cloud CPU performance across AWS, Microsoft Azure, and Google Cloud Platform, according to a recently published study.

    The multi-core x86-64 microprocessors Milan and Rome and beat Intel Cascade Lake and Ice Lake instances in tests of performance in the three most popular cloud providers, research from database company CockroachDB found.

    Using the CoreMark version 1.0 benchmark – which can be limited to run on a single vCPU or execute workloads on multiple vCPUs – the researchers showed AMD's Milan processors outperformed those of Intel in many cases, and at worst statistically tied with Intel's latest-gen Ice Lake processors across both the OLTP and CPU benchmarks.

    Continue reading
  • Intel says Sapphire Rapids CPU delay will help AMD catch up
    Our window to have leading server chips again is narrowing, exec admits

    While Intel has bagged Nvidia as a marquee customer for its next-generation Xeon Scalable processor, the x86 giant has admitted that a broader rollout of the server chip has been delayed to later this year.

    Sandra Rivera, Intel's datacenter boss, confirmed the delay of the Xeon processor, code-named Sapphire Rapids, in a Tuesday panel discussion at the BofA Securities 2022 Global Technology Conference. Earlier that day at the same event, Nvidia's CEO disclosed that the GPU giant would use Sapphire Rapids, and not AMD's upcoming Genoa chip, for its flagship DGX H100 system, a reversal from its last-generation machine.

    Intel has been hyping up Sapphire Rapids as a next-generation Xeon CPU that will help the chipmaker become more competitive after falling behind AMD in technology over the past few years. In fact, Intel hopes it will beat AMD's next-generation Epyc chip, Genoa, to the market with industry-first support for new technologies such as DDR5, PCIe Gen 5 and Compute Express Link.

    Continue reading
  • AMD to end Threadripper Pro 5000 drought for non-Lenovo PCs
    As the House of Zen kills off consumer-friendly non-Pro TR chips

    A drought of AMD's latest Threadripper workstation processors is finally coming to an end for PC makers who faced shortages earlier this year all while Hong Kong giant Lenovo enjoyed an exclusive supply of the chips.

    AMD announced on Monday it will expand availability of its Ryzen Threadripper Pro 5000 CPUs to "leading" system integrators in July and to DIY builders through retailers later this year. This announcement came nearly two weeks after Dell announced it would release a workstation with Threadripper Pro 5000 in the summer.

    The coming wave of Threadripper Pro 5000 workstations will mark an end to the exclusivity window Lenovo had with the high-performance chips since they launched in April.

    Continue reading

Biting the hand that feeds IT © 1998–2022