Does the 6258R Make Sense for Intel?

For this test, I wanted to compare the difference between Intel’s Xeon Platinum 8280 and Intel’s Xeon Gold 6258R. These processors are practically identical on paper for any regular 1P or 2P server, offering up 28 cores at 2.7-4.0 GHz, however the Gold 6258R has a list price that saves over $6000 compared to the Platinum 8280.

As per our regular testing procedure, I put both CPUs in our 1P LGA3647 test system and ran through our performance benchmarks. We also took power measurements, latency measurements, and idle-to-turbo measurements. Everything came out the same. Without the name of the CPU on the heatspreader, or a different CPU string when probed, no-one would be able to tell the difference in a 1P or 2P environment.

So if anyone is thinking of deploying Intel’s high-end Xeon Platinum 8280s in anything less than a eight-socket system, don’t bother. Save a few grand per CPU and gain the plaudits of your boss – unless they start asking questions about why the infrastructure doesn’t have the latest ‘Xeon Plutonium’ things they’re heard about.

Jokes aside, the pragmatic question to ask is:

Has Intel shot itself in the foot with the 6258R?

Intel often repeats (as does AMD) that the majority of its server customers exist in that 1P and 2P spectrum. An offering like the 6258R replaces the 8280 in all aspects for that, giving Intel an effective performance-per-dollar improvement of 2.5x, while at the same time lowering its selling price - when we compare the prices, Intel stands to lose $6000 per processor sold.

 

However, Intel launched the 8280 in April 2019 as the flagship – the 6258R only came out in February 2020. Anyone who wanted the perfromance of the 8280 in that time frame already purchased one. At the same time, a few months later, the company has launched its 3rd Generation Xeon Scalable platform, known as Cooper Lake. We’ve covered Cooper Lake in detail, but the short information is that it is an OEM platform designed for 4-socket and 8-socket servers. Any customer who needs servers that large are now going to look at Cooper Lake as the leading product, meanwhile the 1-socket and 2-socket customers are still on the Cascade Refresh options.

At this point, the 8280 is a dead product for Intel.

  • Users who want the 4-8 socket compatibility and performance can now get the 8380H/HL.
  • Users who want the 1-2 socket compatibility and performance will go for the 6258R.

If you’re wondering where the 6258R stacks up against AMD, we’re in the process of re-testing the parts we have on hand as we go through our regression testing. The EPYC 7542 is probably the best comparison point (32C, 2.9-3.4 GHz, 225W, $3400), however we’ll have to look into getting one of those.

 

Test Bed and Benchmarks
POST A COMMENT

82 Comments

View All Comments

  • MrVibrato - Friday, August 7, 2020 - link

    You are probably right. It is very likely a sales tactic. Those CPUs are not sold in retail (at least not in quantities), but as part of enterprise/complex sales, where contracts (including prices) are negotiated. It is good negotation tactic for a seller to start with a high(er) price. Everyone who ever visited a bazar and haggled with a merchant knows how it goes.And despite having no evidence or experience of Intels approach to sales and negotation, i doubt that anyone who buys more than a handful of those puppies would pay anything close to the listed price... Reply
  • yankeeDDL - Friday, August 7, 2020 - link

    I agree, in general. It is the same practice that most specialized SW vendors use: list prices are insane, and then you get a massive discount. Trouble is: when things get rough these discounts tend to shrink rapidly, because they can. Reply
  • Spunjji - Friday, August 7, 2020 - link

    Exactly that. It's also a way of applying paradoxically high price penalties to smaller and/or less tech-literate buyers. I used to work for an IT reseller and it was amazing how many customers we picked up who had previously been paying list price for all of their purchases - hardware *and* software. Reply
  • Revv233 - Friday, August 7, 2020 - link

    *this*

    When you are selling that new server to the end user you can show a discount under Intel's published price even after you've got your markup in there.
    Reply
  • mrvco - Friday, August 7, 2020 - link

    Definitely. Street price for any given entity is what matters or should matter. I doubt there is a reliable way to smoke out the actual price paid for the 8280 without violating enterprise NDAs, but I have to assume that the 6285 price is a reflection of the competitive pressure being applied by AMD and Epyc and the 8280 pricing has been similarly on a per account basis, just in case there are still some suckers out there. Reply
  • mrvco - Friday, August 7, 2020 - link

    similarly --> adjusted <-- on a Reply
  • Duncan Macdonald - Friday, August 7, 2020 - link

    There is one reason for the 6258R - Intel needs something at least remotely competitive to the EPYC Rome CPUs. For 1 or 2 socket servers the 8280 is far more expensive than AMD's EPYC 7742 while having less performance (due to 28 cores vs 64 and 38.5MB L3 cache vs 256MB) Reply
  • yankeeDDL - Friday, August 7, 2020 - link

    So, instead of lowering the price they make a crippled sku at 40% of the price.
    I said in a previous comment: they do it because they can. Hopefully though, not for so much longer.
    Reply
  • danbob999 - Friday, August 7, 2020 - link

    AMD doesn't have anything in the 8 socket configuration. That leaves Intel pretty much a monopoly. In a typical monopolistic behavior, they raise prices. Nothing new here.
    The only thing is that a dual socket EPYC might outperform a 4 socket Xeon. So Intel need 8 sockets to take the performance crown.
    Reply
  • SSNSeawolf - Friday, August 7, 2020 - link

    Articles like this are important, to help validate that the chips do, in fact, perform similarly. Appreciate that you went through the work to run the tests.

    One small noteworthy difference is that the 6358R has one less UPI link, to go along with the 2P support. I'm curious about the power cos of each UPI link at idle (here in 1P configuration), but eyeballing the y-cruncher chart at the start it appears trivial.
    Reply

Log in

Don't have an account? Sign up now