Memory Frequency Scaling in SFF Systems: An Investigation with SO-DIMMs and Coffee Lakeby Ganesh T S on November 28, 2018 8:00 AM EST
BAPCo SYSmark 2018
The different ASRock DeskMini Z370 GTX configurations were evaluated using our Fall 2018 test suite for small-form factor PCs. In the first performance section, we will be looking at SYSmark 2018.
BAPCo's SYSmark 2018 is an application-based benchmark that uses real-world applications to replay usage patterns of business users in the areas of productivity, creativity, and responsiveness. The 'Productivity Scenario' covers office-centric activities including word processing, spreadsheet usage, financial analysis, software development, application installation, file compression, and e-mail management. The 'Creativity Scenario' represents media-centric activities such as digital photo processing, AI and ML for face recognition in photos and videos for the purpose of content creation, etc. The 'Responsiveness Scenario' evaluates the ability of the system to react in a quick manner to user inputs in areas such as application and file launches, web browsing, and multi-tasking.
Scores are meant to be compared against a reference desktop (the SYSmark 2018 calibration system, a Dell Optiplex 5050 tower with a Core i3-7100 and 4GB of DDR4-2133 memory to go with a 128GB M.2 SATA III SSD). The calibration system scores 1000 in each of the scenarios. A score of, say, 2000, would imply that the system under test is twice as fast as the reference system.
Other than the responsiveness workload, the DDR4-2933 configuration ends up with the best scores. This correlates well with the minimum latency observed in the AIDA64 Cache and Memory Benchmark testing. The scores generally follow the expected trend, and in cases where they don't, they are within the margins of variation observed in multiples runs with the same configuration.
SYSmark 2018 also adds energy measurement to the mix. A high score in the SYSmark benchmarks might be nice to have, but, potential customers also need to determine the balance between power consumption and the efficiency of the system. For example, in the average office scenario, it might not be worth purchasing a noisy and power-hungry PC just because it ends up with a 2000 score in the SYSmark 2014 SE benchmarks. In order to provide a balanced perspective, SYSmark 2018 also allows vendors and decision makers to track the energy consumption during each workload. In the graphs below, we find the total energy consumed by the PC under test for a single iteration of each SYSmark 2018 workload. For reference, the calibration system consumes 5.36 Wh for productivity, 7.71 Wh for creativity, 5.61 Wh for responsiveness, and 18.68 Wh overall.
The energy consumption is not reflective of the average power consumption at load or idle. Rather, the faster the benchmark is able to complete, the lesser is the energy recorded for the workload. This is the reason for the DDR4-3066 configuration (expected to be the most power-hungry of the lot) consuming the least energy in the 'Responsiveness' workload. Overall, the DDR4-2400 configuration fares the worst due to the workloads needing a longer time to complete. The DDR4-2666 configuration seems to achieve the best balance of power consumption and speed.
Post Your CommentPlease log in or sign up to comment.
View All Comments
BedfordTim - Wednesday, November 28, 2018 - linkIt would have been interesting to see some bargain basement memory in the comparison. Is there a specification below which we start to see a difference?
goatfajitas - Wednesday, November 28, 2018 - linkI dunno, I think it gets the job done. The takeaway is the same as it has been for a decade... Higher bandwidth memory with higher latency provides very little actual performance improvements.
qlum - Wednesday, November 28, 2018 - linkTo add some qualifiers to what you said:
In regards to cpu performance
on intel's core achitecture
IGP performance, AMD, certain memory limited workloads tell a different story.
goatfajitas - Wednesday, November 28, 2018 - link"on intel's core achitecture"
Flunk - Wednesday, November 28, 2018 - linkNo, not really. The slowest and faster RAM here aren't that far off. What it really tells us is that minimal increases in RAM performance can bring noticeable performance improvements but only in memory-heavy applications. Which is pretty much exactly what you'd expect.
goatfajitas - Wednesday, November 28, 2018 - link"No, not really. The slowest and faster RAM here aren't that far off."
That is what I said. Barely noticeable even in synthetic benchmarks.
BedfordTim - Wednesday, November 28, 2018 - linkThere is a difference in two memory heavy applications. The RAM drive shows a ~20% benefit and one of the image processing benchmarks shows ~10% benefit.
There will be a tiny number of people doing very specific applications who might notice the difference.
peterfares - Wednesday, November 28, 2018 - linkNot sure what other games it applies to but in Overwatch the RAM speed actually has a pretty significant impact on FPS when you start going very high FPS.
Not sure what what speed the benefits stop, but improvements were still easily seen at 3200MHz.
Death666Angel - Wednesday, November 28, 2018 - linkIt just seems a bit weird to test those speeds. G.Skill RipJaws SoDIMM DDR4-3200 CL18-18-18-43 are available in 8GB form for the same price as regular DDR4-3200 RAM and the 16GB variant is only slight more expensive (would be 5th in the price ranking with regular DDR4-3200 RAM). Is that just a weird German price thing? I was even considering buying them with an adapter just so I can have some more potential usability for the future. :D
deil - Wednesday, November 28, 2018 - linkIMHO small things that does not even make the cpu leave lower power state happens faster, page loading, folder browsing etc...
might be just bias or simple "better timings" that was also the case for me. Still I feel something different in day-to-day stuff.