Single-Threaded Integer Performance: SPEC CPU2006

Even though SPEC CPU2006 is more HPC and workstation oriented, it contains a good variety of integer workloads. Running SPEC CPU2006 is a good way to evaluate single threaded (or core) performance. The main problem is that the results submitted are "overengineered" and it is very hard to make any fair comparisons.

So we wanted to keep the settings as "real world" as possible. We welcome constructive criticism to reach that goal. So we used:

  • 64 bit gcc: most used compiler on Linux, good all round compiler that does not try to "break" benchmarks (libquantum...)
  • -Ofast: compiler optimization that many developers may use
  • -fno-strict-aliasing: necessary to compile some of the subtests
  • base run: every subtest is compiled in the same way.

The ultimate objective is to measure performance in applications where for some reason – as is frequently the case – a "multi thread unfriendly" task keeps us waiting.

Nobody expect the ThunderX to be a single threaded performance wonder. Cavium clearly stated that they deliberately went for a high core count with pretty simple cores. As a result, single threaded performance was not a priority.

However, Facebook and other hyperscalers have indicated that they definitely prefer to get the single threaded performance of a Xeon D. So any competitor challenging Intel should try to keep up with the Xeon D in single threaded performance and offer a throughput-per-dollar/watt bonus. So it is very interesting to measure what single threaded performance the current ThunderX can offer.

Subtest
SPEC CPU2006
Integer
Application Type Cavium
ThunderX
2 GHz
Xeon D-1557
1.5-2.1
Xeon D-1587
1.8-2.4
Xeon E5-2640 v4
2.4-2.6
Xeon E5-2690 v3
2.6-3.5
Xeon E5-2699 v4
2.2-3.6
Xeon E5-2699 v4
2.2-3.6
(+HT)
400.perlbench Spam filter 8.3 24.7 29 33.4 39 32.2 36.6
401.bzip2 Compression 6.5 15.1 17.2 19.8 24.2 19.2 25.3
403.gcc Compiling 10.8 23.1 27.2 30 37.2 28.9 33.3
429.mcf Vehicle scheduling 10.2 32.6 38.4 40.4 44.8 39 43.9
445.gobmk Game AI 9.2 17.4 20.2 22.7 28.1 22.4 27.7
456.hmmer Protein seq. analyses 4.8 19 21.7 25.1 28 24.2 28.4
458.sjeng Chess 8.8 19.8 22.8 25.6 31.5 24.8 28.3
462.libquantum Quantum sim 5.8 47.9 58.2 60.3 78 59.2 67.3
464.h264ref Video encoding 11.9 32 36.6 41.9 56 40.7 40.7
471.omnetpp Network sim 7 17.3 23 23.6 30.9 23.5 29.9
473.astar Pathfinding 7.9 14.7 17.2 19.8 24.4 18.9 23.6
483.xalancbmk XML processing 8.4 27.8 33.3 36.2 45.1 35.4 41.8

Although some of you have a mathematical mind and are able to easily decipher these kinds of tables, let the rest of us be lazy and translate this into percentages. We make the Xeon D-1581 the baseline. The Xeon D-1557's performance is more or less the single threaded performance some of the important customers such as Facebook like to have.

Subtest
SPEC CPU2006
Integer
Application Type Cavium
ThunderX
2 GHz
Xeon D-1557
1.5-2.1
Xeon D-1581
1.5-2.1
Xeon E5-2640
2.4-2.6
400.perlbench Spam filter 29% 85% 100% 115%
401.bzip2 Compression 38% 88% 100% 115%
403.gcc Compiling 40% 85% 100% 110%
429.mcf Vehicle scheduling 27% 85% 100% 105%
445.gobmk Game AI 46% 86% 100% 112%
456.hmmer Protein seq. analyses 22% 88% 100% 116%
458.sjeng Chess 39% 87% 100% 112%
462.libquantum Quantum sim 10% 82% 100% 104%
464.h264ref Video encoding 33% 87% 100% 114%
471.omnetpp Network sim 30% 75% 100% 103%
473.astar Pathfinding 46% 85% 100% 115%
483.xalancbmk XML processing 25% 83% 100% 109%

First of all, single threaded is somewhat better than we expected when we received the first architectural details (a very simple dual issue core with high latency shared L2). However, this is still a fraction of the Xeon D's single threaded performance, which means that ThunderX doesn't look very impressive to companies which feel that single threaded performance should not be lower than a low end Xeon D. The latter is 2 to 4 times faster. On average, the Xeon D-1581 delivers 3 times faster single threaded performance than the ThunderX, but not 5!

SPEC CPU2006 allows us to characterize the ThunderX core a bit better. We ignore libquantum because it has a very special profile: you can triple the score with specific compiler settings, but those settings reduce performance by 2-30%(!) in some other subtests. Those compiler settings optimize cache utilization by splitting records of an array in separate arrays. Combine this with software loop prefetching and libquantum numbers can indeed double or triple. Since libquantum is hardly relevant for the server world and is known for being a target for all kind of benchmark trickery, we ignore it in our comparison.

Mcf exhibits a large amount of data cache misses and memory controller usage. Mcf is also "horribly low IPC" software, so beefy execution backends do not help. Despite those facts, the ThunderX does not do well in mcf. Mcf does a lot of pointer chasing, so the high latency L2-cache and the high latency DRAM access are slowing things down. That is probably also true for XML processing and the network simulator: those subtests have the highest data cache misses.

The shallow pipeline and relatively powerful gshare branch predictor make the ThunderX a better than expected performer in the chess (sjeng), pathfinding (astar), compiling (gcc) and AI (gobmk). Although the gobmk has a relatively high branch misprediction rate on a gshare branch predictor (the highest of all subtests), the ThunderX core can recover very quickly thanks to its 9 stage pipeline. Notice also that gobmk and gcc have relatively large instruction footprints, which gives the ThunderX and its 78 KB I-cache an advantage.

That is also true for the perl, but that benchmark has a relatively high IPC and needs a beefier execution backend. Indeed, the more compute intensive (and thus high IPC sub tests) perlbench and hmmer perform badly relative to the Intel core. In these benchmarks, the wide architecture of the Intel cores pays off.

Benchmarks Versus Reality Multi-Threaded Integer Performance: SPEC CPU2006
POST A COMMENT

82 Comments

View All Comments

  • Daniel Egger - Wednesday, June 15, 2016 - link

    I could hardly disagree more about the remote management of SuperMicro vs. HP. Remote management of HP is *the horror*, I've never seen worse and I've seen a lot. It's clunky, it requires a license to be useful (others do to but SuperMicro does not have such nonsense), the BCM tends to crash a lot (which is very annoying for a remote management solution), boot is even slower than all other systems I know due to the way they integrate the BIOS and remote management on the system and it also uses Java unless you have Windows machines around to use the .NET version.

    For the remote management alone I would chose SuperMicro over most other vendors any day.
    Reply
  • JohanAnandtech - Thursday, June 16, 2016 - link

    I found the .Net client of HP much less sluggish, and I have seen no crashing at all. I guess there is no optimal remote management client, but I really like the "boot into firmware" option that Intel implemented. Reply
  • rahvin - Thursday, June 16, 2016 - link

    Not only that but Supermicro actually releases updates for their BCM's. I had the same shocked reaction to the HP claim. Started to wonder if I was the only one that thought supermicro was light years ahead in usability.

    I should note that Supermicro's awful Java tool works on Linux as well as windows. Though it refuses to run if your Java isn't the newest version available.
    Reply
  • pencea - Wednesday, June 15, 2016 - link

    All these articles and yet still no review for the GTX 1080, while other major sites have already posted their reviews of both 1070 & 1080. Guru3D already has 2 custom 1080 and a custom 1070 review up. Reply
  • Ryan Smith - Wednesday, June 15, 2016 - link

    It'll be done when it's done. Reply
  • pencea - Wednesday, June 15, 2016 - link

    Unacceptably late for something that should've been posted weeks ago. Reply
  • Meteor2 - Thursday, June 16, 2016 - link

    Will anyone read it though? Your ad impressions are going to suffer. Reply
  • Ryan Smith - Thursday, June 16, 2016 - link

    Maybe. Maybe not. But it's my own fault regardless. All I can do is get it done as soon as I reasonably can, and hope it's something you guys find useful. Reply
  • name99 - Thursday, June 16, 2016 - link

    Give it a freaking rest. No-one is impressed by your constant whining about this. Reply
  • pencea - Thursday, June 16, 2016 - link

    Not looking to impress anyone. As a long time viewer of this site, I'm simply disappointed that a reputational site like this is constantly late for GPU reviews. Reply

Log in

Don't have an account? Sign up now