Hardware Acceleration In The Cloud

Computers are great at a lot of things. However, general-purpose computers can benefit from help on certain tasks, which is why your video card and sound card both have their own specialized hardware to offload the CPU. If Accelize has its way, some of your hardware acceleration will be done in the cloud. Yes, we know. The cloud is the buzzword of the week and we are tired of hearing about it, too. However, this service is a particularly interesting way to add FPGA power to just about any network-connected CPU.

Currently, there are only four accelerators available, including a hardware-assisted random number generator, a GZIP accelerator, an engine for rapidly searching text, and a BMP to JPEG converter. The company claims, for example, that the search engine can find 2500 entries in the 60 GB Wikipedia archive in 6 minutes. They claim a traditional CPU would take over 16 days to do the same task. The BMP to JPEG converter can process faster than required to feed real-time HD video.

The cloud, in this case, is FPGA resources hosted in the Amazon cloud or in the OVH public cloud. They’ll clearly charge for the service at some point using a “coin” system. However, right now they are letting you sign up with nothing more than an e-mail address and crediting your account with 50,000 coins. Apparently, coins are 1,000 for one dollar.

Continue reading “Hardware Acceleration In The Cloud”

Tiny Arduino + FPGA = Sno

Alorium rolled out a new product late last year that caught our attention. The Sno (pronounced like “snow”) board is a tiny footprint Arduino board that you can see in the video below. By itself that isn’t that interesting, but the Sno also has an Altera/Intel Max 10 FPGA onboard. If you aren’t an FPGA user, don’t tune out yet, though, because while you can customize the FPGA in several ways, you don’t have to.

Like Alorium’s XLR8 product, the FPGA comes with preprogrammed functions and a matching Arduino API to use them. In particular, there are modules to do analog to digital conversion, servo control, operate NeoPixels, and do floating point math.

Continue reading “Tiny Arduino + FPGA = Sno”

Neural Networks… On A Stick!

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!”

Universal Chip Analyzer: Test Old CPUs In Seconds

Collecting old CPUs and firing them up again is all the rage these days, but how do you know if they will work? For many of these ICs, which ceased production decades ago, sorting the good stuff from the defective and counterfeit is a minefield.

Testing old chips is a challenge in itself. Even if you can find the right motherboard, the slim chances of escaping the effect of time on the components (in particular, capacitor and EEPROM degradation) make a reliable test setup hard to come by.

Enter [Samuel], and the Universal Chip Analyzer (UCA). Using an FPGA to emulate the motherboard, it means the experience of testing an IC takes just a matter of seconds. Why an FPGA? Microcontrollers are simply too slow to get a full speed interface to the CPU, even one from the ’80s.

So, how does it actually test? Synthesized inside the FPGA is everything the CPU needs from the motherboard to make it tick, including ROM, RAM, bus controllers, clock generation and interrupt handling. Many testing frequencies are supported (which is helpful for spotting fakes), and if connected to a computer via USB, the UCA can check power consumption, and even benchmark the chip. We can’t begin to detail the amount of thought that’s gone into the design here, from auto-detecting data bus width to the sheer amount of models supported, but you can read more technical details here.

The Mojo v3 FPGA development board was chosen as the heart of the project, featuring an ATmega32U4 and Xilinx Spartan 6 FPGA. The wily among you will have already spotted a problem – the voltage levels used by early CPUs vary greatly (as high as 15V for an Intel 4004). [Samuel]’s ingenious solution to keep the cost down is a shield for each IC family – each with its own voltage converter.

Continue reading “Universal Chip Analyzer: Test Old CPUs In Seconds”

Apple One, On FPGA

Today, Apple is known for iPhones, iPads, and a commitment to graphical user interfaces. But that wasn’t how it all started. The original Apple was a single board computer built around a 6502. In 1976, you could snag one for $666.66, but you needed to supply your own TV, power supply, and keyboard. [Alangarf] didn’t have an Apple 1, but he did have a 6502 CPU core for FPGAs from [Andrew Holme] that he fleshed out to an Apple I clone with a VGA output and PS/2 keyboard port. The project works with either an iCE40 board or a Terasic DE0 board. You could probably port it to other similar FPGAs.

This is much more practical than trying to find an original, as Apple bought a lot of the old boards back and destroyed them. According to the Apple-1 Registry there are only about 71 of the boards still in existence, and that’s with the annotation that 4 of those may be lost and 8 might be duplicates. We’ve heard that of those there are only six that actually still work.

Continue reading “Apple One, On FPGA”

A DIY Nine Channel Digital Scope

Have you ever found yourself in the need of a nine channel scope, when all you had was an FPGA evaluation board? Do not despair, [Miguel Angel] has you covered. While trying to make sense of the inner workings of a RAM controller core, he realized that he needed to capture a lot of signals in parallel and whipped up this 9-channel digital oscilloscope.

The scope is remote-controlled via a JavaScript application, and over Ethernet. Graphical output is provided as a VGA signal at full HD, so it is easy to see what is going on. Downloading sampled data to the controlling computer for analysis is in the works. [Miguel] runs his implementation on an Arty A7 development board which is currently available for around a hundred dollars, but the design is transferable to other platforms. The code and some documentation is available on GitHub and there is a demo video after the break.

Continue reading “A DIY Nine Channel Digital Scope”

Reverse Engineer An X-Ray Image Sensor

If you think of a medical x-ray, it is likely that you are imagining a photographic plate as its imaging device. Clipped to your tooth by your dentist perhaps, or one of the infamous pictures of the hands of [Thomas Edison]’s assistant [Clarence Madison Dally].

As with the rest of photography, the science of x-ray imaging has benefited from digital technology, and it is now well established that your hospital x-ray is likely to be captured by an electronic imaging device. Indeed these have now been in use for so long that their first generation can even be bought by an experimenter for an affordable sum, and that is what the ever-resourceful [Lucy Fauth] with the assistance of [Jana Marie Hemsing], has done. Their Trophy DigiPan digital x-ray image sensor was theirs for around a hundred Euros, and though it’s outdated in medical terms it still has huge potential for the x-ray experimenter.

The write-up is a fascinating journey into the mechanics of an x-ray sensor, with the explanation of how earlier devices such as this one are in fact linear CCD sensors which track across the exposed area behind a scintillator layer in a similar fashion to the optical sensor in a flatbed scanner. The interface is revealed as an RS422 serial port, and the device is discovered to be a standalone unit that does not require any commands to start scanning. On power-up it sends a greyscale image, and a bit of Sigrok examination of the non-standard serial stream was able to reveal it as 12-bit data direct from the sensor. From those beginnings they progressed to an FPGA-based data processor and topped it all off with a very tidy power supply in a laser-cut box.

It’s appreciated that x-rays are a particularly hazardous medium to experiment with, and we note from their videos that they are using some form of shielding. The source is a handheld fluoroscope of the type used in sports medicine that produces a narrow beam. If you remember the discovery of an unexpected GameBoy you will be aware that medical electronics seems to be something of a speciality in those quarters, as do autonomous box carriers.

Continue reading “Reverse Engineer An X-Ray Image Sensor”