Slash Boxes

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 16 submissions in the queue.
posted by chromas on Saturday July 28 2018, @01:28AM   Printer-friendly
from the epyc-story dept.

AMD "Rome" EPYC CPUs to Be Fabbed By TSMC

AMD CEO Lisa Su has announced that second-generation "Rome" EPYC CPU that the company is wrapping up work on is being produced out at TSMC. This is a notable departure from how things have gone for AMD with the Zen 1 generation, as GlobalFoundries has produced all of AMD's Zen CPUs, both for consumer Ryzen and professional EPYC parts.

[...] As it stands, AMD seems rather optimistic about how things are currently going. Rome silicon is already back in the labs, and indeed AMD is already sampling the parts to certain partners for early validation. Which means AMD remains on track to launch their second-generation EPYC processors in 2019.

[...] Ultimately however if they are meeting their order quota from GlobalFoundries, then AMD's situation is ultimately much more market driven: which fab can offer the necessary capacity and performance, and at the best prices. Which will be an important consideration as GlobalFoundries has indicated that it may not be able to keep up with 7nm demand, especially with the long manufacturing process their first-generation DUV-based 7nm "7LP" process requires.

See also: No 16-core AMD Ryzen AM4 Until After 7nm EPYC Launch (2019)

Related: TSMC Holds Groundbreaking Ceremony for "5nm" Fab, Production to Begin in 2020
Cray CS500 Supercomputers to Include AMD's Epyc as a Processor Option
AMD Returns to the Datacenter, Set to Launch "7nm" Radeon Instinct GPUs for Machine Learning in 2018
AMD Ratcheting Up the Pressure on Intel
More on AMD's Licensing of Epyc Server Chips to Chinese Companies

Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 3, Interesting) by bzipitidoo on Saturday July 28 2018, @04:50AM (1 child)

    by bzipitidoo (4388) on Saturday July 28 2018, @04:50AM (#713930) Journal

    I try to get more years out of my computers than a mere 5, but such rapid and large upgrades make it hard to justify keeping old boxes plugged in. Plus, hard drives these days have about a 5 year life span. I'm still getting a little use out of decade old 45nm and 65nm stuff, and (assuming marketing hasn't perverted die size measurements to make them worthless) here we are with 14nm and talking of 10nm and 7nm, and in another few years, 5nm. 5nm is such a gigantic upgrade from 14nm, I suppose in 2 years they too won't be worth the electricity it takes to run them.

    • (Score: 2) by takyon on Saturday July 28 2018, @05:43AM

      by takyon (881) <{takyon} {at} {}> on Saturday July 28 2018, @05:43AM (#713935) Journal

      It's useful for as long as you find it useful.

      If the stuff you are typically doing doesn't feel sluggish, then you don't need more speed. If the machine is idling most of the time and not under load, then you don't need the greater power efficiency.

      Keep the hard drive contents backed up frequently. Swap in an SSD when it dies.

      [SIG] 10/28/2017: Soylent Upgrade v14 []
  • (Score: 2) by takyon on Saturday July 28 2018, @06:49AM (1 child)

    by takyon (881) <{takyon} {at} {}> on Saturday July 28 2018, @06:49AM (#713945) Journal

    Seen this in the past couple of days? []

    No boost in core count for Cascade Lake-SP. AMD could drop 64 core server chips onto Intel's measly 28 cores.

    But there is Cascade Lake-AP at the bottom. Maybe an attempt at making Xeon Phi into the flagship product?

    [SIG] 10/28/2017: Soylent Upgrade v14 []
    • (Score: 2) by opinionated_science on Saturday July 28 2018, @12:21PM

      by opinionated_science (4031) on Saturday July 28 2018, @12:21PM (#713974)

      that lack of AVX512 on AMD is a sticking point. Some calculations benefit considerably from the density.

      Plus, I suspect some twiddling could turn the AVX machinery into "Machine Learning" units...