Excuse my ignorance on arm situation on Windows, but this felt like same situation with third party arm sbc like Orange Pis and rockchip… In Orange Pi 5 and rockship as soon as community develop some stuff on their own, the developer stop providing assistance and pretty much abandon software support and to this day RK3588s (the soc used on OPi 5 and several other sbc) haven’t got Vulkan support meanwhile Raspberry Pi 5 got its VK support 2 weeks after device public release which is shame for rockchip.
I wish Qualcomm competent enough to realise bringing software support boosts the hardware longevity as much as Apple did with their ecosystem which provide both software and hardware supports to make their chips runs at its maximum potential.
A lot of the cheap tablet SoC vendors like Rockchip (whose SoCs end up in low cost SBCs) really only do the bare minimum when it comes to proper linux support. There’s usually next to no effort to upstreaming their patches so oftentimes you’re stuck on their vendor kernel. Luckily for the RK3588(S), Collabora has done a considerable amount of work on supporting the SoC and its peripherals upstream. I run my Orange Pi 5 Plus (RK3588) on a mainline kernel and it works for my needs.
This practice is a lot easier to defend for a low cost SoC compared to something as expensive as a Snapdragon Elite though…
Hey fellow opi 5 owner! iirc some ppl back then managed to run newer ubuntu rk3588 aswell but what makes me quit was the gpu support (Rockchip’s android image have better driver performance and linux neglected which sucks). Also saw that collabora and panfrost stuff but I moved back to x86 mini pc bcuz I need gpu stuff, thought to repurposing them as media server & emulator setup but didn’t worked with linux.
Owned orange pi 5 back then for college project, their NPU really packs a punch but sadly the good story ends there. After finished the project sold mine to friend who need them for computer vision and NN stuffs.
GPU and overall firmware support is always better on x86 systems, so makes sense that you switched to that for your application. Performance is also usually better if you don’t explicitly need low power. In my use case I use the Orange Pi 5 Plus for running an astrophotography rig, so I needed something that was low power, could run Linux easily, had USB 3, reasonable single core performance, and preferably had the possibility of an upgradable A key WiFi card and a full speed NVMe E key slot for storage (preferably PCIe 3.0x4 or better). Having hardware serial ports was a plus too. x86 boxes would’ve been preferable but a lot of the cheaper stuff are older Intel mini PCs which have pretty poor battery life, and the newer power efficient stuff (N100 based) is more expensive and the cheaper ones I found tended to have onboard soldered WiFi cards unfortunately. Accordingly the Orange Pi 5 Plus ended up being my cheapest option that ticked all my boxes. If only software support was as good as x86!
Interesting to hear about the NPU. I work in CV and I’ve wondered how usable the NPU was. How did you integrate deep learning models with it? I presume there’s some conversion from runtime frameworks like ONNX to the NPU’s toolkit, but I’d love to learn more.
I’m also aware that Collabora has gotten the NPU drivers upstreamed, but I don’t know how NPUs are traditionally interfaced with on Linux.
Excuse my ignorance on arm situation on Windows, but this felt like same situation with third party arm sbc like Orange Pis and rockchip… In Orange Pi 5 and rockship as soon as community develop some stuff on their own, the developer stop providing assistance and pretty much abandon software support and to this day RK3588s (the soc used on OPi 5 and several other sbc) haven’t got Vulkan support meanwhile Raspberry Pi 5 got its VK support 2 weeks after device public release which is shame for rockchip.
I wish Qualcomm competent enough to realise bringing software support boosts the hardware longevity as much as Apple did with their ecosystem which provide both software and hardware supports to make their chips runs at its maximum potential.
A lot of the cheap tablet SoC vendors like Rockchip (whose SoCs end up in low cost SBCs) really only do the bare minimum when it comes to proper linux support. There’s usually next to no effort to upstreaming their patches so oftentimes you’re stuck on their vendor kernel. Luckily for the RK3588(S), Collabora has done a considerable amount of work on supporting the SoC and its peripherals upstream. I run my Orange Pi 5 Plus (RK3588) on a mainline kernel and it works for my needs.
This practice is a lot easier to defend for a low cost SoC compared to something as expensive as a Snapdragon Elite though…
Hey fellow opi 5 owner! iirc some ppl back then managed to run newer ubuntu rk3588 aswell but what makes me quit was the gpu support (Rockchip’s android image have better driver performance and linux neglected which sucks). Also saw that collabora and panfrost stuff but I moved back to x86 mini pc bcuz I need gpu stuff, thought to repurposing them as media server & emulator setup but didn’t worked with linux.
Owned orange pi 5 back then for college project, their NPU really packs a punch but sadly the good story ends there. After finished the project sold mine to friend who need them for computer vision and NN stuffs.
GPU and overall firmware support is always better on x86 systems, so makes sense that you switched to that for your application. Performance is also usually better if you don’t explicitly need low power. In my use case I use the Orange Pi 5 Plus for running an astrophotography rig, so I needed something that was low power, could run Linux easily, had USB 3, reasonable single core performance, and preferably had the possibility of an upgradable A key WiFi card and a full speed NVMe E key slot for storage (preferably PCIe 3.0x4 or better). Having hardware serial ports was a plus too. x86 boxes would’ve been preferable but a lot of the cheaper stuff are older Intel mini PCs which have pretty poor battery life, and the newer power efficient stuff (N100 based) is more expensive and the cheaper ones I found tended to have onboard soldered WiFi cards unfortunately. Accordingly the Orange Pi 5 Plus ended up being my cheapest option that ticked all my boxes. If only software support was as good as x86!
Interesting to hear about the NPU. I work in CV and I’ve wondered how usable the NPU was. How did you integrate deep learning models with it? I presume there’s some conversion from runtime frameworks like ONNX to the NPU’s toolkit, but I’d love to learn more.
I’m also aware that Collabora has gotten the NPU drivers upstreamed, but I don’t know how NPUs are traditionally interfaced with on Linux.