ROCK 5 in ITX form factor

#35

It’s an ASM1164 instead :slight_smile:

#36

Ah, good to know :+1: Thanks for the heads up!

#37

I have this beauty now on my desk:

rock5-itx-2
rock5-itx-2.jpg2703×2746 993 KB

I used a preliminary OS image from Radxa to check some stuff by running sbc-bench -r: https://github.com/ThomasKaiser/sbc-bench/blob/master/results/reviews/Radxa-Rock-5-ITX.md

Forget about the performance numbers present there since there’s something wrong with DRAM initialization. While the two SK Hynix 32Gb LPDDR5 modules should be faster than the LPDDR4X on Rock 5B (4224 vs. 5472 MT/s) memory bandwidth hasn’t improved and latency is worse compared to LPDDR4X.

The good thing to report is that the board is lying flat on a table at 23°C ambient temp with neither heatsink nor fan and not even the rather demanding cpuminer benchmark led to throttling since temps remained below 76°C :slight_smile:

As for the hardware just as quick addendum to sbc-bench -r info collected above: there’s a Genesys Logic GL3523 USB3 hub on the board and also a Terminus Technology Inc. USB2 hub.

Idle consumption with all governors set to powersave and nothing connected except TF card, the (optional) PoE module and one Ethernet jack at GbE speed is 4.00W according to my ODROID SmartPower 3 (5.3W with governors set to performance).

But just like the benchmark scores above this is BS at this point in time since settings haven’t matured yet.

4 Likes
#38

It looks really nice and high quality. I’m also noticing a chip marked “Radxa” there. It reminds me the first time I saw “Asus” marked on a chip several decades ago :slight_smile:

What we really need nowadays will be to make interchangeable DRAM modules based on LPDDR so that even if the SoC cannot support standard SODIMM, it should be possible to design an alternative. I initially thought that a tiny PCB with two chips on top and tin balls underneath could be pressed using screws against the main board, but after all, there are plenty of connectors that could probably support multi-chip LPDDR frequencies and make such SBCs much more modular.

#39

It looks really nice and high quality. I’m also noticing a chip marked “Radxa” there. It reminds me the first time I saw “Asus” marked on a chip several decades ago

#40

LPCAMM will be evaluated for Rock 6 ITX.

#41

Yeah exactly something like this. Good to see they’re evaluating it. the only thing is that LPCAMM seems “large” to me, I mean, we’re talking about SOCs supporting only 2 32-bit chips or 4 16-bit ones, but maybe this will permit interleaving and improved average latencies. We’ll see.

#42

Few more pictures can be seen where my journey with this board within the next weeks will be documented: https://github.com/ThomasKaiser/Knowledge/blob/master/articles/Quick_Preview_of_ROCK_5_ITX.md

1 Like
#43

My sample arrived this morning too (only 4 days late thanks to UPS!) and I took a bunch of pictures for a quick close-up of the board. The photos likely do it zero justice but it’s a really pretty-looking board, as tkaiser said!

2 Likes
#44

Review update: MMC storage, USB-C, SATA power and 1st real problem identified: SATA write performance sucks

4 Likes
#45

Great photos, thanks

#46

Review update: Testing 2.5GbE networking, OS defaults vs. optimal settings, achieving weird iperf3 results.

1 Like
#47

Review update: Testing today’s b1 Radxa build, more recent boot BLOBs and Armbian defaults.

TL;DR: newer DRAM initialization BLOBs do not solve the problem that LPDDR5 @ 2736 MHz is not significantly faster than LPDDR4X @ 2112 MHz, Radxa’s b1 builds from today don’t solve the reported problems and someone at Armbian managed to ruin NAS/server performance by choosing an inappropriate cpufreq governor

Or maybe better TL;DR: grab an Alder Lake-N x64 box when you want to run an energy efficient server

1 Like
#48

And another one: SMB Multichannel.

TL;DR: 600 MB/s over two 2.5GbE connections, don’t buy an Alder Lake-N x64 box

#49

Really interested in one of these to replace my aging NAS, watching this with interest.

I’m curious if the board-powered fan is controllable with a temperature sensor on the board itself?

#50

Hi, @tkaiser

After we read your post, we put it in high priority and did the test immediately:

https://gist.github.com/RadxaStephen/88b6a5e09699017d04a2299192104232

We also reported this with Rockchip and worked with them closely and got a shocking fact from Rockchip’s engineer:

The LPDDR5 latency is expected to be slower than LPDDR4x. Just like LPDDR4 latency is slower than LPDDR3.

We also checked with AI, first, we asked:

is lpddr5 latency higher than lpddr4?

AI answered: No, LPDDR5 has lower latency compared to LPDDR4.

Then we asked:

why real world test shows lpddr5 has higher latency?

Here is the answer:

Based on the provided search results, there are a few key points explaining why real-world tests may show higher latency for LPDDR5 compared to LPDDR4:

  1. Current LPDDR5 implementations have higher rated latencies (CAS latencies around CL40) compared to typical LPDDR4 latencies (CL20 or lower).13 While LPDDR5’s higher data rates can offset some of this latency penalty, the raw latency numbers are still higher initially.
  2. Benchmarking tools like AIDA64 may not accurately measure LPDDR5 latency yet, as the technology is new. Some users have reported AIDA64 showing unexpectedly high latency numbers for LPDDR5 that don’t match real-world performance.2
  3. LPDDR5 operates at an effective lower clock speed (800MHz x4 channels) compared to the rated “data rate” speed of 6400MT/s. This can make latency appear higher when measured by tools not optimized for LPDDR5.2
  4. While LPDDR5 reduces command/address latency through architectural changes, the data transfer latency itself may still be higher in early LPDDR5 implementations compared to mature LPDDR4 modules.4

So in summary, the higher rated CAS latencies of initial LPDDR5 chips combined with potential benchmarking tool inaccuracies can make LPDDR5’s real-world latency appear higher than LPDDR4, even though LPDDR5 reduces other latency components.1234 As LPDDR5 matures, its latency is expected to improve.

Full answer:

https://www.perplexity.ai/search/is-lpddr5-latency-KDYiMM5MQiS8L3Qy5LiZQg

We are still investigating this, will update here after more findings.

#51

Well, somehow expected but I would’ve thought 2736 MHz vs. 2112 MHz would compensate for that. Obviously wrong or hopefully RK revisits the topic and is maybe able to improve timings?

We’ll see but at least for now we might conclude that workloads that benefit from lower memory latency (not that much) run better off LPDDR4X with RK3588.

Edit: though Geekbench on other platforms than x86 more being a joke than a reputable benchmark here are numbers comparing Rock 5B (LPDDR4X @ 2112 MHz) and Rock 5 ITX (LPDDR5 @ 2736 MHz):

Basically same performance at the moment (until maybe Rockchip sends out a new DRAM initialization BLOB that improves performance)

#52

Yes, since it’s a ‘12V PWN enabled fan header’ you can then combine with any thermal source you want.

But for RK3588 you won’t need a fan unless you cramp the board with a few pieces of hot spinning rust into a small enclosure w/o any ventilation since this SoC is pretty energy efficient.

#53

My glorious plan involves a Jonsbo N2 case, the rock5 ITX, and four HDDs. So if the disks are busy I may well need a case fan.

#54

Review update: Settings matter for performance

TL;DR: how Armbian guys managed to halve performance of one specific use case with the snip of a finger, w/o even noticing of course and w/o doing any evaluation prior or after.