Retesting AMD Ryzen Threadripper’s Game Mode: Halving Cores for More Performance
by Ian Cutress on August 17, 2017 12:01 PM ESTCPU Office Tests
The office programs we use for benchmarking aren't specific programs per-se, but industry standard tests that hold weight with professionals. The goal of these tests is to use an array of software and techniques that a typical office user might encounter, such as video conferencing, document editing, architectural modeling, and so on and so forth.
All of our benchmark results can also be found in our benchmark engine, Bench.
Chromium Compile (v56)
Our new compilation test uses Windows 10 Pro, VS Community 2015.3 with the Win10 SDK to compile a nightly build of Chromium. We've fixed the test for a build in late March 2017, and we run a fresh full compile in our test. Compilation is the typical example given of a variable threaded workload - some of the compile and linking is linear, whereas other parts are multithreaded.
For our test, we compile a version of v56 under MSVC and report the time in 'Compiles per Day', a more scalable metric to represent over time. Other publications might perfom this test differently (Ars Technica uses a clang-cl compiler with VC++ linking, for example).
One of the interesting data points in our test is the Compile. Because this test requires a lot of cross-core communication and DRAM, we get an interesting metric where the 1950X still comes out on top due to the core counts, but because the 1920X has fewer cores per CCX, it actually falls behind the 1950X in Game Mode and the 1800X despite having more cores.
PCMark8: link
Despite originally coming out in 2008/2009, Futuremark has maintained PCMark8 to remain relevant in 2017. On the scale of complicated tasks, PCMark focuses more on the low-to-mid range of professional workloads, making it a good indicator for what people consider 'office' work. We run the benchmark from the commandline in 'conventional' mode, meaning C++ over OpenCL, to remove the graphics card from the equation and focus purely on the CPU. PCMark8 offers Home, Work and Creative workloads, with some software tests shared and others unique to each benchmark set.
Strangely, PCMark 8's Creative test seems to be failing across the board. We're trying to narrow down the issue.
Facebook
Twitter
RSS
104 Comments
View All Comments
peevee - Friday, August 18, 2017 - link
Of course. Work CPUs must be tested at work. Kiddies are fine with i3s.Ian Cutress - Sunday, August 20, 2017 - link
https://myhacker.net hacking news hacking tutorials hacking ebooksIGTrading - Thursday, August 17, 2017 - link
It would be nice and very useful to post some power consumption results at the platform level, if we're doing "extra" additional testing.It is very important since we're paying for the motherboard just as much as we pay for a Ryzen 5 or even Ryzen 7 processor.
And it will correctly compare the TCO of the X399 platform with the TCO of X299.
jordanclock - Thursday, August 17, 2017 - link
So it looks like AMD should have gone with just disabling SMT for Game Mode. There are way more benefits and it is easier to understand the implications. I haven't seen similar comparisons for Intel in a while, perhaps that can be exploration for Skylake-X as well?HStewart - Thursday, August 17, 2017 - link
I would think disable SMT would be better, but the reason maybe in designed of link between the two 8 Core dies on chip.GruenSein - Thursday, August 17, 2017 - link
I'd really love to see a frame time probability distribution (Frame time on x-axis, rate of occurrence on y-axis). Especially in cases with very unlikely frames below a 60Hz rate, the difference between TR and TR-GM/1800X seem most apparent. Without the distribution, we will never know if we are seeing the same distribution but slightly shifted towards lower frame rates as the slopes of the distribution might be steep. However, those frames with frame times above a 60Hz rate might be real stutters down to a 30Hz rate but they might just as well be frames at a 59,7Hz rate. I realize why this threshold was selected but every threshold is quite arbitrary.MrSpadge - Thursday, August 17, 2017 - link
Does AMD comment on the update? What's their reason for choosing 8C/16T over 16C/16T?> One could postulate that Windows could do something similar with the equivalent of hyperthreads.
They're actually already doing that. Loading 50% of all threads on an SMT machine will result in ~50% average load on every logical core, i.e. all physical cores are only working on 1 thread at a time.
I know mathematically other schedulings are possible, leading to the same result - but by now I think it's common knowledge that the default Win scheduler works like that. Hence most lightly threaded software is indifferent to SMT. Except games.
NetMage - Sunday, August 20, 2017 - link
Then why did SMT mode show differences from Creator mode in the original review?Dribble - Thursday, August 17, 2017 - link
No one is ever going to run game mode - why buy a really expensive chip and then disable half of it, especially as you have to reboot to do it? It's only use is to make threadripper look slightly better in reviews. Imo it would be more honest as a reviewer to just run it in creator mode all the time.jordanclock - Thursday, August 17, 2017 - link
The point is compatibility, as mentioned in the article multiple times. AMD is offering this as an option for applications (mainly games) that do not run correctly, if at all, on >16 core CPUs.