I'm testing Adlink's Ampere Altra Developer Platform. This machine has a 96-core Arm CPU, but now they sell a 128-core version. Apple also recently released the M2 Ultra Mac Pro, so the model I'm testing isn't the "fastest in the world" like I could boast a couple months ago... but it's close, and I actually doubled my performance from last time—I'll show how later.
This week I finally moved my gaming/Linux PC into my little office rack—it's that 2U box above the UPS at the bottom:
I remembered seeing Linus Tech Tips' 4U build in a video a couple years ago—but he has a full 42U rack in his basement. I don't have that much space—just 2U (technically 3U if I wanted) in my little under-desk studio rack.
So after working with them last year on a similar build (but with a prototype case), I got in touch with MyElectronics and they sent over their new production Mini ITX short-depth 2U PC case.
In October 2020, after Raspberry Pi introduced the Compute Module 4, I started out on a journey to get an external graphics card working on the Pi.
At the time, it'd been over a decade since the last time I'd built a PC, and I had a lot to learn about PCI Express, the state of graphics card drivers in Linux, and PCI Express support on various ARM SoCs.
I recently got an Nvidia Jetson Nano 2GB Developer Kit, and I read through and followed the Developer Kit Getting Started Guide straight from Nvidia's website.
I downloaded the 7 GB(!) microSD card from their website, and flashed it to a 128 GB microSD card using Balena Etcher.
Then I popped the microSD card into my dev kit board, plugged in HDMI and a USB-C 3A power supply, and waited... I kept seeing a giant NVIDIA logo on my display, and after about 20 seconds, it would seemingly reboot to black screen, then the logo... and repeat forever.
Searching around the Nvidia forums, I eventually found this issue: Nano 2GB boot looping, and finally found the problem: apparently the default image download is only for the 4GB Nano model.
Earlier today I did a livestream on my YouTube channel to attempt using an Nvidia GeForce GTX 1080 on a Raspberry Pi Compute Module 4.
As with all my testing, I'm documenting everything I learn in this GitHub issue, which is part of the Raspberry Pi PCI Express Card Database website.
It's only been a few hours, but I've already gotten good suggestions for better debugging than I was able to do on the stream. And someone pointed out it might be the case, due to 32-bit memory limitations on the BCM2711's PCIe bus, that no GPU with more than 4 GB of onboard RAM could work. Though it's hard to confirm there'd be no software workaround—even 1 and 2 GB graphics cards (AMD and Nvidia) are crashing the kernel in similar ways.
The full livestream is available on replay and is embedded below:
Last year I tested two older graphics cards—a Radeon 5450 and a GeForce GT710—on a Raspberry Pi Compute Module 4.
This year, I've been testing three more graphics cards—a GeForce GTX 750 Ti, a Radeon RX 550, and the diminutive ASRock Rack M2_VGA.
The Compute Module 4, if you didn't know already, exposes the BCM2711's single PCI express lane, and the official IO Board has a nice, standard, 1x PCIe slot into which you can plug any PCI express device.
The Raspberry Pi Compute Module 4 eschews a built-in USB 3.0 controller and exposes a 1x PCI Express lane.
The slightly older Raspberry Pi 4 model B could be hacked to get access to the PCIe lane (sacrificing the VL805 USB 3.0 controller chip in the process), but it was a bit of a delicate operation and only a few daring souls tried it.
Watch this video for more detail about my experience using these GPUs on the CM4:
GPUs on a Raspberry Pi Compute Module 4!
Over the weekend, Nvidia confirmed it would purchase ARM from Softbank for $40 billion.
Now, what is ARM, why is Nvidia buying it, and what does any of this have to do with the Raspberry Pi?
Well, let's start with ARM.
This blog post also has a video version to go along with it.
ARM can refer to a number of things, but let's start by talking about the company, Arm Holdings. They have lineage dating back to Acorn computers, a British computer manufacturer founded in the late 1970s that designed the first 'Acorn RISC Machine architecture' chips, AKA 'ARM'.
I've had a few friends report strange issues with their MacBook Pro laptops. Often they would report that the video signal on either an internal or external display becomes 'glitchy' or 'jumpy'. I initially thought it could be a connection issue, as I've seen many a VGA cable that becomes loose cause weird sync issues. However, they also reported that the cursor continued to work normally, moving around when they were moving the mouse/trackpad.
Doesn't look too nice...
I typically recommend people take these sorts of issues to the Genius Bar at an Apple Store, especially since the problem isn't easy to replicate when I take a minute or two to look at the laptop—often the problem only happens after constantly using the computer for more than half an hour.
However, I finally got to experience the problem first-hand, when my sister brought me her laptop and I used it for an evening of blogging and browsing. After half an hour or so, the screen started getting quite jittery (click through to view video and read more):