They probably weren’t inspired by [Jeff Dunham’s] jalapeno on a stick, but Intel have created the Movidius neural compute stick which is in effect a neural network in a USB stick form factor. They don’t rely on the cloud, they require no fan, and you can get one for well under $100. We were interested in [Jeff Johnson’s] use of these sticks with a Pynq-Z1. He also notes that it is a great way to put neural net power on a Raspberry Pi or BeagleBone. He shows us YOLO — an image recognizer — and applies it to an HDMI signal with the processing done on the Movidius. You can see the result in the first video, below.
At first, we thought you might be better off using the Z1’s built-in FPGA to do neural networks. [Jeff] points out that while it is possible, the Z1 has a lower-end device on it, so there isn’t that much FPGA real estate to play with. The stick, then, is a great idea. You can learn more about the device in the second video, below.
Continue reading “Neural Networks… On a Stick!”
How would you sell a computer to a potential buyer? Fast? Reliable? Great graphics and sound? In 1956, you might point out that it was somewhat smaller than a desk. After all, in those days what people thought of as computers were giant behemoths. Thanks to modern FPGAs, you can now have a replica of a 1956 computer — the LGP-30 — that is significantly smaller than a desk. The LittleGP-30 is the brainchild of [Jürgen Müller].
The original also weighed about 740 pounds, or a shade under 336 kg, so the FPGA version wins on mass, as well. The LGP-30 owed its relative svelte footprint to the fact that it only used 113 tubes and of those, only 24 tubes were in the CPU. This was possible, because, like many early computers, the CPU worked on one bit at a time. While a modern computer will add a word all at once, this computer — even the FPGA version — add each operand one bit at a time.
Continue reading “Another New Old Computer on an FPGA”
This is about the time of the year you realize you aren’t going to keep all of those new year’s resolutions you made. However, if one of them was to learn VHDL and FPGAs, you might be in luck. Vicilogic has a free course in Fundamentals of Digital Systems. You do have to register, but it didn’t even verify our e-mail address, so it shouldn’t be too onerous to sign up.
Associated with the National University of Ireland Galway, the training is high quality and offers animated demos in your browser of the digital circuitry. You can even control the demos yourself. You’d think the work was occurring in some browser script, but according to the site, the demos are tied to real FPGA boards. You can supposedly look in on them as you use them with a video stream, but we never saw that working so your mileage may vary. If you want a preview of what it looks like, check out the video below. There’s guided exercises and also quizzes where you have to interact with the demos.
Continue reading “Veni, Vidi, ViciLogic Teaches You Digital Logic Interactively”
[Robert Baruch] wanted to tackle a CPU project using an FPGA. One problem you always have is you can either mimic something that has tools and applications or you can go your own way and just build everything from scratch (which is much harder).
[Robert] took the mimic approach–sort of. He built a CPU with the express idea of running Infocom’s Z-machine virtual machine, which allows it to play Zork. So at least when you are done, you don’t have to explain to your non-tech friends that it only blinks an LED. Check out the video, below, for more details.
Continue reading “Zork Comes to Custom FPGA CPU (Again)”
FPGAs (like Xilinx’s Spartan series) are great building blocks. They often remind us of the 100-in-1 electronic kits we used to get as kids. Lots of components you can mix and match to make nearly anything. However, like a bare microcontroller, they usually don’t have much in the way of peripheral devices. So the secret sauce is what components you can surround the chip with.
If you are interested in retro computing, you ought to have a look at the ZX-Uno board. It hosts a Spartan 6 FPGA. They are for sale, but the design is open source and all the info is available if you prefer to roll your own or make modifications. You can see a video of the board in action, below (as explained in the video, the color issues are due to the capture card trying to deal with the non-standard sync rate).
Here are the key specifications:
- FPGA Xilinx Spartan XC6SLX9-2TQG144C
- Static Memory 512Kb, AS7C34096A-10TIN
- 50MHz Oscillator
- Video output (composite)
- PS/2 keyboard
- Stereo audio jack
- EAR jack connector (for reading cassette tapes)
- Connectors for JTAG and RGB
- Slot for SD Cards
- Expansion port with 3 male pin strips
- Micro-USB power connector
- PCB Size: 86×56 mm. (Compatible with Raspberry Pi cases)
Continue reading “Retro ZX Spectrum Lives a Spartan Existence”
Around here we love technology for its own sake. But we have to admit, most people are interested in applications–what can the technology do? Those people often have the best projects. After all, there’s only so many blinking LED projects you can look at before you want something more.
[Landingfield] is interested in astrophotography. He was dismayed at the cost of commercial camera sensors suitable for work like this, so he decided he would create his own. Although he started thinking about it a few years ago, he started earnestly in early 2016.
The project uses a Nikon sensor and a Xilinx Zynq CPU/FPGA. The idea is the set up and control the CMOS sensor with the CPU side of the Zynq chip, then receive and process the data from the sensor using the FPGA side before dumping it into memory and letting the CPU take over again. The project stalled for a bit due to a bug in the vendor’s tools. The posts describe the problem which might be handy if you are doing something similar. There’s still work to go, but the device has taken images that should appear on the same blog soon.
Continue reading “Custom Zynq/CMOS Camera Unlocks Astrophotography”
If you are from the United States and of a certain age, it is very likely you owned some form of Commodore computer. Outside the US, that same demographic was likely to own an Amstrad. The Z80-based computers were well known for game playing. [Freemac] implemented a working Amstrad CPC6128 using a Xilinx FPGA on a NEXYS2 demo board.
The wiki posting is a bit long, but it covers how to duplicate the feat, and also gives technical details about the design. It also outlines the development process used ranging from starting with a simple Z80 emulation and moving on to more sophisticated attempts. You can see a video of the device below.
Continue reading “Amstrad on an FPGA”