I have a nice armbian image on an SSD on a rock5b board. I want to copy it to an sd card for cloning on other boards. Does anyone know how this can be done? It doesn't come out via dd

Hello, congratulations for your achievement! I wonder if you had the chance to give a shot to the ssv6051 sibling... the original drivers (one for ssv6051 and another for ssv6x5x) were really a mess that @ilmich and me did a lot of work at the time to cleanup and fix things in the past time. We concentrated against the ssv6051 driver at the time and in fact the ssv6051 driver already works in mainline kernel (it is in the rockchip 32bit patch directory), although it is still quite a mess. Here it is the repository if you want to take a look to the commits. We also started an attempt to do a clean and proper reimplementation of the ssv6xxx driver, but actually never went over firmware loading (the repo is private since it was a heavy WIP, but can share if you have enough will to take a look to that)

Lately, I've been playing around a bit with computer vision detection. I managed to patch together a PoC script with which I conducted some tests. The results are quite promising. The frame rate is just based on the round trip time of my test script, so it only roughly reflects the inference time. The throughput includes all additional overhead but is sufficiently informative for a relative comparison. Inference on a single CPU core delivers an image throughput of about 4 images: Inference on a single NPU core delivers an image throughput of about 17 images: Inference on eight CPU cores delivers an image throughput of about 21 images. But all eight cores run over 80% during this, and after a short time the fan kicks in. The headroom is also quite limited, for e.g., to perform other tasks concurrently. Running several similar inference tasks concurrently immediately results in a proportional drop in frame rate per task. When six similar inference tasks are executed simultaneously with NPU delegates, they are distributed across the three available NPU cores, and the SoC utilization is moderate enough that the fan doesn't even turn on. The throughput does not degrade and the CPU cores remain available for other tasks as well: For my tests, I used a random video clip. For the inference, I used a model pre-trained with the COCO dataset. With its 4.1MB memory size and its 80 object classes, it delivers surprisingly good results. Using the NPU hardware not only reduces the load on the CPU cores but also provides additional acceleration of processing. But the best part is that only current mainline code is required for use. No dependencies on proprietary implementations or outdated software stacks. It just works out-of-the-box, you just need to know how to use it.

That "rvdisplay" string is found in the following files: libVK_IMG.so, libsutu_display.so, and libpvr_dri_support.so. When comparing the OpiRV2 versions of these files with https://gitee.com/spacemit-buildroot/img-gpu-powervr I got 9a640=spacemit vs 9a2d0=rvdisplay. Thus, Xunlong has source code for these (different offsets, rvdisplay is one char longer). So no need to hack Armbian kernel, I presume GPU works if we use *.so from gitee repo. HTH // Sven-Ola

@c0rnelius then the GPU probably works, since without GPU e.g the Bianbu first time wizard (language, kbd, timezone, user) needs 20 minutes while uptime reports load=10. I'm damn sure you have noticed an extraslow GUI