Intel 3rd Gen Xeon Scalable (Ice Lake SP) Review: Generationally Big, Competitively Smallby Andrei Frumusanu on April 6, 2021 11:00 AM EST
- Posted in
- Xeon Scalable
- Ice Lake-SP
Test Bed and Setup - Compiler Options
For the rest of our performance testing, we’re disclosing the details of the various test setups:
Intel - Dual Xeon Platinum 8380
For our new Ice Lake test system based on the Whiskey Lake platform, we’re using Intel’s SDP (Software Development Platform 2SW3SIL4Q, featuring a 2-socket Intel server board (Coyote Pass).
The system is an airflow optimised 2U rack unit with otherwise little fanfare.
Our review setup solely includes the new Intel Xeon 8380 with 40 cores, 2.3GHz base clock, 3.0GHz all-core boost, and 3.4GHz peak single core boost. That’s unusual about this part as noted in the intro, it’s running at a default 205W TDP which is above what we’ve seen from previous generation non-specialised Intel SKUs.
|CPU||2x Intel Xeon Platinum 8380 (2.3-3.4 GHz, 40c, 60MB L3, 270W)|
|RAM||512 GB (16x32 GB) SK Hynix DDR4-3200|
|Internal Disks||Intel SSD P5510 7.68TB|
|Motherboard||Intel Coyote Pass (Server System S2W3SIL4Q)|
|PSU||2x Platinum 2100W|
The system came with several SSDs including Optane SSD P5800X’s, however we ran our test suite on the P5510 – not that we’re I/O affected in our current benchmarks anyhow.
As per Intel guidance, we’re using the latest BIOS available with the 270 release microcode update.
Intel - Dual Xeon Platinum 8280
For the older Cascade Lake Intel system we’re also using a test-bench setup with the same SSD and OS image as on the EPYC 7742 system.
Because the Xeons only have 6-channel memory, their maximum capacity is limited to 384GB of the same Micron memory, running at a default 2933MHz to remain in-spec with the processor’s capabilities.
|CPU||2x Intel Xeon Platinum 8280 (2.7-4.0 GHz, 28c, 38.5MB L3, 205W)|
|RAM||384 GB (12x32 GB) Micron DDR4-3200 (Running at 2933MHz)|
|Internal Disks||Crucial MX300 1TB|
|Motherboard||ASRock EP2C621D12 WS|
|PSU||EVGA 1600 T2 (1600W)|
The Xeon system was similarly run on BIOS defaults on an ASRock EP2C621D12 WS with the latest firmware available.
AMD - Dual EPYC 7763 / 7713 / 75F3 / 7662
In terms of testing the new EPYC 7003 series CPUs, unfortunately due to our malfunctioning Daytona server, we weren’t able to get first-hand experience with the hardware. AMD graciously gave us remote access to one of their server clusters – we had full controls of the system in terms of BMC as well as BIOS settings.
|CPU||2x AMD EPYC 7763 (2.45-3.500 GHz, 64c, 256 MB L3, 280W) /
2x AMD EPYC 7713 (2.00-3.365 GHz, 64c, 256 MB L3, 225W) /
2x AMD EPYC 75F3 (3.20-4.000 GHz, 32c, 256 MB L3, 280W) /
2x AMD EPYC 7662 (2.00-3.300 GHz, 64c, 256 MB L3, 225W)
|RAM||512 GB (16x32 GB) Micron DDR4-3200|
|Motherboard||Daytona reference board: S5BQ|
Software wise, we ran Ubuntu 20.10 images with the latest release 5.11 Linux kernel. Performance settings both on the OS as well on the BIOS were left to default settings, including such things as a regular Schedutil based frequency governor and the CPUs running performance determinism mode at their respective default TDPs unless otherwise indicated.
AMD - Dual EPYC 7742
Our local AMD EPYC 7742 system, due to the aforementioned issues with the Daytona hardware, is running on a SuperMicro H11DSI Rev 2.0.
|CPU||2x AMD EPYC 7742 (2.25-3.4 GHz, 64c, 256 MB L3, 225W)|
|RAM||512 GB (16x32 GB) Micron DDR4-3200|
|Internal Disks||Crucial MX300 1TB|
|PSU||EVGA 1600 T2 (1600W)|
As an operating system we’re using Ubuntu 20.10 with no further optimisations. In terms of BIOS settings we’re using complete defaults, including retaining the default 225W TDP of the EPYC 7742’s, as well as leaving further CPU configurables to auto, except of NPS settings where it’s we explicitly state the configuration in the results.
The system has all relevant security mitigations activated against speculative store bypass and Spectre variants.
Ampere "Mount Jade" - Dual Altra Q80-33
The Ampere Altra system we’re using the provided Mount Jade server as configured by Ampere. The system features 2 Altra Q80-33 processors within the Mount Jade DVT motherboard from Ampere.
In terms of memory, we’re using the bundled 16 DIMMs of 32GB of Samsung DDR4-3200 for a total of 512GB, 256GB per socket.
|CPU||2x Ampere Altra Q80-33 (3.3 GHz, 80c, 32 MB L3, 250W)|
|RAM||512 GB (16x32 GB) Samsung DDR4-3200|
|Internal Disks||Samsung MZ-QLB960NE 960GB
Samsung MZ-1LB960NE 960GB
|Motherboard||Mount Jade DVT Reference Motherboard|
The system came preinstalled with CentOS 8 and we continued usage of that OS. It’s to be noted that the server is naturally Arm SBSA compatible and thus you can run any kind of Linux distribution on it.
The only other note to make of the system is that the OS is running with 64KB pages rather than the usual 4KB pages – this either can be seen as a testing discrepancy or an advantage on the part of the Arm system given that the next page size step for x86 systems is 2MB – which isn’t feasible for general use-case testing and something deployments would have to decide to explicitly enable.
The system has all relevant security mitigations activated, including SSBS (Speculative Store Bypass Safe) against Spectre variants.
The system has all relevant security mitigations activated against the various vulnerabilities.
For compiled tests, we’re using the release version of GCC 10.2. The toolchain was compiled from scratch on both the x86 systems as well as the Altra system. We’re using shared binaries with the system’s libc libraries.
Post Your CommentPlease log in or sign up to comment.
View All Comments
Oxford Guy - Sunday, April 11, 2021 - link'The faulty logic I see is that you seem to believe it's the review's job to...'
'I think it could be appropriate to do that sort of thing, in articles that...'
Don't contradict yourself or anything.
If you're not interested in knowing how fast a CPU is that's ... well... I don't know.
Telling people to go for marketing info (which is inherently deceptive — the entire fundamental reason for marketing departments to exist) is obviously silly.
mode_13h - Monday, April 12, 2021 - link> Don't contradict yourself or anything.
I think the point of confusion is that I'm drawing a distinction between the initial product review and subsequent follow-up articles they often publish to examine specific points of interest. This would also allow for more time to do a more thorough investigation, since the initial reviews tend to be conducted under strict deadlines.
> If you're not interested in knowing how fast a CPU is that's ... well... I don't know.
There's often a distinction between the performance, as users are most likely to experience it, and the full capabilities of the product. I actually want to know both, but I think the former should be the (initial) priority.
ballsystemlord - Thursday, April 8, 2021 - linkSpelling and grammar errors (there are a lot!):
"At the same time, we have also spent time a dual Xeon Gold 6330 system from Supermicro, which has two 28-core processors,..."
Nonsensical English: "time a duel". I haven't the faintest what you were trying to say.
"DRAM latencies here are reduced by 1.7ns, which isn't very much a significant difference,..."
Either use "very much", or use "a significant":
DRAM latencies here are reduced by 1.7ns, which isn't a very significant difference,..."
"Inspecting Intel's prior disclosures about Ice Lake SP in last year's HotChips presentations, one point sticks out, and that's is the "SpecI2M optimisation" where the system is able to convert traditional RFO (Read for ownership) memory operations into another mechanism"
"Inspecting Intel's prior disclosures about Ice Lake SP in last year's HotChips presentations, one point sticks out, and that's the "SpecI2M optimisation" where the system is able to convert traditional RFO (Read for ownership) memory operations into another mechanism"
"It's a bit unfortunate that system vendors have ended up publishing STREAM results with hyper optimised binaries that are compiled with non-temporal instructions from the get-go, as for example we would not have seen this new mechanism on Ice Lake SP with them"
You need to rewrite the sentance or add more commas to break it up:
"It's a bit unfortunate that system vendors have ended up publishing STREAM results with hyper optimised binaries that are compiled with non-temporal instructions from the get-go, as, for example, we would not have seen this new mechanism on Ice Lake SP with them"
"The latter STREAM results were really great to see as I view is a true design innovation that will benefit a lot of workloads."
Exchange "is" for "this as":
"The latter STREAM results were really great to see as I view this as a true design innovation that will benefit a lot of workloads."
Or discard "view" and rewrite as a diffinitive instead of as an opinion:
"The latter STREAM results were really great to see as this is a true design innovation that will benefit a lot of workloads."
"Intel's new Ice Lake SP system, similarly to the predecessor Cascade Lake SP system, appear to be very efficient at full system idle,..."
"Intel's new Ice Lake SP system, similarly to the predecessor Cascade Lake SP system, appears to be very efficient at full system idle,..."
"...the new Ice Lake part to most of the time beat the Cascade Lake part,..."
"to" doesn't belong. Rewrite:
"...the new Ice Lake part can beat the Cascade Lake part most of the time,..."
"...both showcasing figures that are still 25 and 15% ahead of the Xeon 8380."
"...both showcasing figures that are still 25% and 15% ahead of the Xeon 8380."
"Intel had been pushing very hard the software optimisation side of things,..."
Poor sentance structure:
"Intel had been pushing the software optimisation side very hard,..."
"...which unfortunately didn't have enough time to cover for this piece."
"...which unfortunately we didn't have enough time to cover for this piece."
"While we are exalted to finally see Ice lake SP reach the market,..."
"excited" not "exalted":
"While we are excited to finally see Ice lake SP reach the market,..."
Thanks for the article!
Oxford Guy - Sunday, April 11, 2021 - linkPerhaps Purch would be willing to take you on as a volunteer unpaid intern for proofreading for spelling and grammar?
I would think there are people out there who would do it for resume building. So... if it bothers you perhaps you should make an inquiry.
evilpaul666 - Saturday, April 10, 2021 - linkAre the W-1300s going to use 10nm this year?
mode_13h - Saturday, April 10, 2021 - linkYou mean the bottom-tier Xeons? Those are just mainstream desktop chips with less features disabled, so that question depends on when Alder Lake hits.
I'd say "no", because the Xeon versions typically lag the corresponding mainstream chips by a few months. So, if Alder Lake launches in November, then maybe we get the Xeons in February-March of next year.
The more immediate question is whether they'll release a Xeon version of Rocket Lake. I think that's likely, since they skipped Comet Lake and there are significant platform enhancements for Rocket Lake.
AdrianBc - Monday, April 12, 2021 - linkNo, the W-1300 Xeons will be Rocket Lake. The top model will be Xeon W-1390P, which will be equivalent to the top i9 Rocket Lake, with 125 W TDP and 5.3 GHz maximum turbo.
rahvin - Tuesday, April 20, 2021 - linkAndre does some of the best server reviews available, IMO.
KKK11 - Tuesday, May 11, 2021 - linkThat is a curious-looking wafer. I thought it was fake at first but then I noticed the alignment notch. Actually, I'm still not convinced it's real because I have seen lots and lots of wafers in various stages of production and I have never seen one where partial chips go all the way out to the edges. It's a waste of time to deal with those in the steppers so no one does that.