System Performance: Multi-Tasking
One of the key drivers of advancements in computing systems is multi-tasking. On mobile devices, this is quite lightweight - cases such as background email checks while the user is playing a mobile game are quite common. Towards optimizing user experience in those types of scenarios, mobile SoC manufacturers started integrating heterogeneous CPU cores - some with high performance for demanding workloads, while others were frugal in terms of both power consumption / die area and performance. This trend is now slowly making its way into the desktop PC space.
Multi-tasking in typical PC usage is much more demanding compared to phones and tablets. Desktop OSes allow users to launch and utilize a large number of demanding programs simultaneously. Responsiveness is dictated largely by the OS scheduler allowing different tasks to move to the background. Intel's Alder Lake processors work closely with the Windows 11 thread scheduler to optimize performance in these cases. Keeping these aspects in mind, the evaluation of multi-tasking performance is an interesting subject to tackle.
We have augmented our systems benchmarking suite to quantitatively analyze the multi-tasking performance of various platforms. The evaluation involves triggering a ffmpeg transcoding task to transform 1716 3840x1714 frames encoded as a 24fps AVC video (Blender Project's 'Tears of Steel' 4K version) into a 1080p HEVC version in a loop. The transcoding rate is monitored continuously. One complete transcoding pass is allowed to complete before starting the first multi-tasking workload - the PCMark 10 Extended bench suite. A comparative view of the PCMark 10 scores for various scenarios is presented in the graphs below. Also available for concurrent viewing are scores in the normal case where the benchmark was processed without any concurrent load, and a graph presenting the loss in performance.
Following the completion of the PCMark 10 benchmark, a short delay is introduced prior to the processing of Principled Technologies WebXPRT4 on MS Edge. Similar to the PCMark 10 results presentation, the graph below show the scores recorded with the transcoding load active. Available for comparison are the dedicated CPU power scores and a measure of the performance loss.
The final workload tested as part of the multitasking evaluation routine is CINEBENCH R23.
After the completion of all the workloads, we let the transcoding routine run to completion. The monitored transcoding rate throughout the above evaluation routine (in terms of frames per second) is graphed below.
Across all the different workloads, we actually find the ASRock Industrial NUC(S) BOX systems having significant drop in performance compared to similar UCFF systems. It leads one to suspect that Thread Director is simply not able to do the appropriate thread allocation in the systems. Whether this is related to any BIOS configuration is something for the company to look into.
ASRock NUCS BOX-1360P/D4 ffmpeg Transcoding Rate (Multi-Tasking Test) |
Task Segment |
Transcoding Rate (FPS) |
Minimum |
Average |
Maximum |
Transcode Start Pass |
2 |
9.6 |
43.5 |
PCMark 10 |
0 |
8.37 |
31.5 |
WebXPRT 4 |
2.5 |
9.18 |
18 |
Cinebench R23 |
0.5 |
8.4 |
29.5 |
Transcode End Pass |
2 |
9.51 |
30.5 |
ASRock NUCS BOX-1360P/D4 (In-Band ECC) ffmpeg Transcoding Rate (Multi-Tasking Test) |
Task Segment |
Transcoding Rate (FPS) |
Minimum |
Average |
Maximum |
Transcode Start Pass |
1.5 |
9.28 |
39.5 |
PCMark 10 |
0 |
8.03 |
27.5 |
WebXPRT 4 |
2 |
8.9 |
17.5 |
Cinebench R23 |
0.5 |
8.16 |
27 |
Transcode End Pass |
1.5 |
9.21 |
29 |
On the positive side, the drop in transcoding frame rate for the NUCS BOX configurations is not as heave as what was seen for other systems.
30 Comments
View All Comments
mode_13h - Tuesday, February 14, 2023 - link
I also don't agree that W680 boards are scarce. At least Supermicro boards seemed to be easy enough to find since the end of last year. Now DDR5 ECC UDIMMs have been a much bigger challenge, but they're thankfully now readily available too.mode_13h - Tuesday, February 7, 2023 - link
Thanks for the review, but my ideal microserver would be fanless and support a 2.5" SATA SSD. Does anyone know if any of their fanless boxes support in-band ECC? I couldn't find any indication that they do.https://www.asrockind.com/en-gb/fanless-embedded-b...
ganeshts - Wednesday, February 8, 2023 - link
ASRock Industrial took notice of your comment and requested that this be posted in response.mode_13h - Thursday, February 9, 2023 - link
Thanks for the follow-up!Now, if I could just find an ASRock Rack X570D4U-2L2T Mini-ATX board in stock somewhere in the US. I can never seem to find it or the newer /BCM version.
mode_13h - Monday, February 27, 2023 - link
Just wanted to follow up on the ASRock Rack X570D4U-2L2T. It's finally back in stock @ newegg! Shipped & sold by newegg, too (i.e. not just some scalper).For those not familiar with this product, it's a micro-ATX AM4 server board with dual 10G Ethernet, ECC RAM support, and remote management via BMC. I'm excited, because there are no other products like it, to my knowledge. ASRock Rack has validated ECC memory on it, which you tend to see on other AM4 boards. You can find professional reviews of it, on other sites.
I'm about to order mine, now.
mode_13h - Monday, February 27, 2023 - link
Sorry, I meant to say that I _haven't_ seen ECC memory fully validated and supported, on other AM4 boards. This is one of the preferred boards of the homebrew NAS community.sjkpublic@gmail.com - Monday, February 13, 2023 - link
Nice NUC. But I am waiting on the 7735U.sjkpublic@gmail.com - Monday, February 13, 2023 - link
$690 barebones.sjkpublic@gmail.com - Monday, February 13, 2023 - link
Silly people posting on ECC for a end user desktop/kiosk device - trying to put a square peg in a round hole. I like the idealistic attitude. But the realistic says otherwise.sjkpublic@gmail.com - Tuesday, February 14, 2023 - link
Silly me! I retract. ECC support is a great idea.