The Ampere Altra Review: 2x 80 Cores Arm Server Performance Monster
by Andrei Frumusanu on December 18, 2020 6:00 AM EST- Posted in
- Servers
- Neoverse N1
- Ampere
- Altra
SPEC - Single-Threaded Performance
Starting off with SPECint2017, we’re using the single-instance runs of the rate variants of the benchmarks.
As usual, because there are not officially submitted scores to SPEC, we’re labelling the results as “estimates” as per the SPEC rules and license.
We compile the binaries with GCC 10.2 on their respective platforms, with simple -Ofast optimisation flags and relevant architecture and machine tuning flags (-march/-mtune=Neoverse-n1 ; -march/-mtune=skylake-avx512 ; -march/-mtune=znver2).
While single-threaded performance in such large enterprise systems isn’t a very meaningful or relevant measure, given that the sockets will rarely ever be used with just 1 thread being loaded on them, it’s still an interesting figure academically, and for the few use-cases which would have such performance bottlenecks. It’s to be remembered that the EPYC and Xeon systems will clock up to respectively 3.4GHz and 4GHz under such situations, while the Ampere Altra still maintains its 3.3GHz maximum speed.
In SPECint2017, the Altra system is performing admirably and is able to generally match the performance of its counterparts, winning some workloads, while losing some others.
In SPECfp2017 the Neoverse-N1 cores seem to more generally fall behind their x86 counterparts. Particularly what’s odd to see is the vast discrepancy in 507.cactuBSSN_r where the Altra posts less than half the performance of the x86 cores. This is actually quite odd as the Graviton2 had scored 3.81 in the test. The workload has the highest L1D miss rate amongst the SPEC suite, so it’s possible that the neutered prefetchers on the Altra system might in some way play a more substantial role in this workload.
The Altra Q80-33 ends up performing extremely well and competitively against the AMD EPYC 7742 and Intel Xeon 8280, actually beating the EPYC in SPECint, although it loses by a larger margin in SPECfp. The Xeon 8280 still holds the crown here in this test due to its ability to boost up to 4GHz across two cores, clocking down to 3.8, 3.7, 3.5 and 3.3GHz beyond 2, 4, 8 and 20 cores active.
The Altra showcases a massive 52% performance lead over the Graviton2 in SPECint, which is actually beyond the expected 32% difference due to clock frequencies being at 3.3GHz versus 2.5GHz. On the other hand, the SPECfp figures are only ahead of 15% for the Altra. The prefetchers are really amongst the only thing that come to mind in regards to these differences, as the only other difference being that the Graviton2 figures were from earlier in the year on GCC 9.3. The Altra figures are definitely more reliable as we actually have our hands on the system here.
While on the AMD system the move from NPS1 to NPS4 hardly changes performance, limiting the Altra Q80-33 from a monolithic setup to a quadrant setup does incur a small performance penalty, which is unsurprising as we’re cutting the L3 into a quarter of its size for single-threaded workloads. That in itself is actually a very interesting experiment as we haven’t been able to do such a change on any prior system before.
Facebook
Twitter
RSS
148 Comments
View All Comments
Wilco1 - Monday, December 21, 2020 - link
Why would they introduce Graviton if it would run at a loss??? A significant percentage of AWS is already Graviton (probably 20% by now). If anything Graviton increases profitability due to vertical integration and other cost reduction.mode_13h - Monday, December 21, 2020 - link
First, there's a fundamental disparity between an in-house CPU and a 3rd Party one, where Amazon can cut out some overheads by building their own. So, that already skews the price-comparison.The other question is whether Amazon is partially-subsidizing the price of their Graviton2 instances as an incentive to get more people to switch. For a business, the least risky thing is to stay on x86, so Amazon needs to present an immediate and significant cost savings to get people to switch. After they've switched and ARM server cores have had more time to mature, Amazon can charge more and make back a good return on investment.
I obviously don't know if that's what they're doing, but we don't know that it's not. So, you really can't read much into their current pricing. That's all I'm saying.
mode_13h - Sunday, December 20, 2020 - link
Finally, I guess you missed this part, in the discussion of SPECjbb:> One thing that did come to mind immediately when I saw the results was SMT.
> Due to this being a transactional data-plane resident type of workload,
> SMT will undoubtedly help a lot in terms of performance,
> so I tested out the EPYC chip figures with SMT disabled,
> and indeed max-jOPS went down to 209.5k for the 2S THP enabled results,
> meaning that SMT accounts for a 29.7% performance benefit in this benchmark.
...
> It’s generally these kinds of workloads that SMT works best on,
> and that’s why IBM can deploy SMT4 or SMT8 processors,
> and the type of workloads Marvell’s ThunderX was trying to carve a niche or itself with SMT4.
mode_13h - Sunday, December 20, 2020 - link
As the article mentions, Marvell’s ThunderX did support SMT on ARMv8-A.Were SMT's reputation not bruised by all the recent side-channel exploits, perhaps it would be showing up in some of ARM's own cores. Maybe their V-series will get it, since that's a much larger core.
Wilco1 - Monday, December 21, 2020 - link
ThunderX2/X3 and Neoverse E1 have SMT, but neither has been hugely successful. SMT doesn't provide a significant benefit across a wide range of workloads, so adding another core remains simpler and cheaper. And yes, security is another nail in the coffin.EthiaW - Saturday, December 19, 2020 - link
The performance of Graviton2 meets our expectation for Neoverse N1 (or Cortex A76) better. How can Q80 manage to deliver so much higher IPC with the same architecture? Incredible.Brutalizer - Saturday, December 19, 2020 - link
One old Oracle SPARC T8 cpu does 153.500 Java max-JOPS SPECjbb2015. And the crit-JOPS value is 90.000. Easily smashing all cpus here.https://blogs.oracle.com/bestperf/specjbb2015:-spa...
satai - Saturday, December 19, 2020 - link
Benchmarked by Oracle... Definitely trustworthy.zepi - Saturday, December 19, 2020 - link
SPECJBB graphs kill me.For the love of god, please keep the axis scaling identical!
Same applies to every single metric always. If you provide separate graphs for different products, please make sure that axis-scaling is the same in all images!
Andrei Frumusanu - Sunday, December 20, 2020 - link
The graphs are generated by the benchmark itself.