AMD 3rd Gen EPYC Milan Review: A Peak vs Per Core Performance Balance
by Dr. Ian Cutress & Andrei Frumusanu on March 15, 2021 11:00 AM ESTTest Bed and Setup - Compiler Options
For the rest of our performance testing, we’re disclosing the details of the various test setups:
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 |
Internal Disks | Varying |
Motherboard | Daytona reference board: S5BQ |
PSU | PWS-1200 |
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 |
Motherboard | SuperMicro H11DSI0 |
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 |
PSU | 2000W (94%) |
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.
Intel - Dual Xeon Platinum 8280
For the 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.
The system has all relevant security mitigations activated against the various vulnerabilities.
Compiler Setup
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.
It’s to be noted that for AMD’s latest Zen3-based EPYC 7003 CPUs, GCC 10.2 did not yet offer compatibility with the relevant -znver3 CPU target. Due to our goal to keep apples-to-apples comparisons between the various systems, we’re resorted to using the same -znver2 binaries on the new EPYC 3rd generation parts.
AMD notes performance benefits using a new LLVM 11 based AOCC 3.0 featuring Zen3 performance optimisations. The new compiler version is to be released at the time of publishing, and thus we hadn’t had the opportunity to verify these claims.
120 Comments
View All Comments
mode_13h - Monday, March 15, 2021 - link
Please don't paint Nvidia as a victim. They are not. All of these guys will have to support each other, for the foreseeable future, and for purely pragmatic reasons.Oxford Guy - Monday, March 15, 2021 - link
They are not 'guys'. They're corporations. Corporations were invented to, to quote Ambrose Bierce, grant 'individual profit without individual responsibility'.mode_13h - Wednesday, March 17, 2021 - link
No disagreement, but I'm slightly disheartened you decided to take issue with my use of the term "guys". I'll try harder, next time--just for you.Oxford Guy - Tuesday, April 6, 2021 - link
People humanize corporations all the time. It doesn't lead to good outcomes for societies.Of course, it's questionable whether corporations lead to good outcomes, considering that they're founded on scamming people (profit being 'sell less for more', needing tricks to get people to agree to that).
chavv - Monday, March 15, 2021 - link
Is it possible to add another "benchmark" - ESX server workload?Like, running 8-16-32-64 VMs all with some workload...
Andrei Frumusanu - Monday, March 15, 2021 - link
As we're rebuilding our server test suite, I'll be looking into more diverse benchmarks to include. It's a long process that needs a lot of thought and possibly resources so it's not always evident to achieve.eva02langley - Monday, March 15, 2021 - link
Just buy EPYC and start your hybridation and your reliance on a SINGLE supplier...eva02langley - Monday, March 15, 2021 - link
edit: Just buy EPYC and start your hybridation and STOP your reliance on a SINGLE supplier...mode_13h - Monday, March 15, 2021 - link
You guys should really include some workloads involving multiple <= 16-core/32-thread VMs, that could highlight the performance advantages of NPS4 mode. Even if all you did was partition up the system into smaller VMs running multithreaded SPEC 2017 tests, at least that would be *something*.That said, please don't get rid of all system-wide multithreaded tests, because we definitely still want to see how well these systems scale (both single- and multi- CPU).
ishould - Monday, March 15, 2021 - link
Yes this seems more useful for my needs as well. We use a grid system for job submission and not all cores will be hammered at the same time