Usually, designing a CPU is a lengthy process, especially so if you’re making a new ISA too. This is something that can take months or even years before you first get code to run. But what if it wasn’t? What if one were to try to make a CPU as fast as humanly possible? That’s what I asked myself a couple weeks ago.
Continue reading “What Happens If You Speedrun Making A CPU?”
I’m sure you all love to see some colorful blinkenlights every now and then, and we are of course no exception. While these might look like coasters at a distance, do not be deceived! They’re actually [bitluni]’s latest project!
[bitluni]’s high-fidelity LED matrix started life as some 8×8 LED matrices lying on the shelf for 10 years taunting him – admit it, we’re all guilty of this – before he finally decided to make something with them. That idea took the form of a tileable display with the help of some magnets and pogo pins, which is certainly a very satisfying way to connect these oddly futuristic blinky coasters together.
It all starts with some schematics and a PCB. Because the CH32V208 has an annoying package to solder, [bitluni] opted to have the PCB fab do placement for him. Unfortunately, though, and like any good prototype, it needed a bodge! [bitluni] had accidentally mirrored a chip in the schematic, meaning he had to solder one of the SMD chips on upside-down, “dead bug mode”. Fortunately, the rest was seemingly more successful, because with a little 3D-printed case and some fancy programming, the tiny tiles came to life in all of their rainbow-barfing glory. Sure, the pogo pins were less reliable than desired, but [bitluni] has some ideas for a future version we’re very much looking forward to.
Video after the break.
Continue reading “Is That A Coaster? No, It’s An LED Matrix!”
[Breaking Taps] has done some lithography experiments in the past, including some test patterns and a rudimentary camera sensor. But now, it’s time to turn it up a notch with 1µm garage semiconductor ambitions.
The e-beam lithography he’s done in the past can achieve some impressive resolutions, but they aren’t very fast; a single beam of electrons needs to scan over the entire exposure area, somewhat like a tiny crayon. That’s not very scalable; he needed a better solution to make 1µm semiconductors.
In his quest, he starts by trying to do maskless photolithography, using a literal projector to shine light on the target area all at once. After hacking a projector devkit apart, replacing blue with ultraviolet and adding custom optics, it’s time for a test. The process works for the most part but can’t produce fine details the way [Breaking Taps] needs. Unfortunately, fixing that would mean tearing the whole set-up apart for the umpteenth time.
Continue reading “Creating 1 Um Features The Hacker Way”
Supercomputers are always an impressive sight to behold, but also completely unobtainable for the ordinary person. But what if that wasn’t the case? [bitluni] shows us how it’s done with his 256-core RISC-V megacluster.
While the CH32V family of microcontrollers it’s based on aren’t nearly as powerful as what you’d traditionally find in a supercomputer, [bitluni] does use them to demonstrate a property of supercomputers: many, many cores doing the same task in parallel.
To recap our previous coverage, a single “supercluster” is made from 16 CH32V003 microcontrollers connected to each other with an 8-bit bus, with an LED on each and the remaining pins to an I/O expander. The megacluster is in turn made from 16 of these superclusters, which are put in pairs on 8 “blades” with a CH32V203 per square as a bridge between the supercluster and the main 8-bit bus of the megacluster, controlled by one last CH32V203.
[bitluni] goes into detail about designing PCBs that break KiCad, managing an overcrowded bus with 16 participants, culminating in a mesmerizing showcase of blinking LEDs showing that RC oscillators aren’t all that accurate.
There’s always an appeal to a cool-looking computer case or cyberdeck – and with authentic-looking Vault-Tec style, [Eric B] and [kc9psw]’s fallout-themed cyberdeck is no exception.
The case looks like it came straight out of one of the Fallout games and acts the part: while (obviously) not capable of withstanding a direct nuclear bomb impact, it can protect the sensitive electronics inside from the electromagnetic pulse and shockwave that follows – if you keep it closed.
And it’s not just the case that’s cool: This cyberdeck is packed full of goodies like long-range radios, SDRs, ADSB receivers, a Teensy 4.1, and dual Raspberry Pis. But that’s just the hardware! It also comes with gigabytes upon gigabytes of Wikipedia, Wikihow, TED talks, and other information/entertainment, for the less eventful days in the wastelands.
If you, too, would like to have one, fret not! The parts list and design files are public, even though some assembly is required.
Have you ever wondered how a GPU works? Even better, have you ever wanted to make one? [Dylan] certainly did, because he made FuryGPU — a fully custom graphics card capable of playing Quake at over 30 frames per second.
As you might have guessed, FuryGPU isn’t in the same league as modern graphics card — those are made of thousands of cores specialized in math, which are then programmed with whatever shaders you want. FuryGPU is a more “traditional” GPU, it has dedicated hardware for all the functions the GPU needs to perform and doesn’t support “shader code” in the same way an AMD or NVIDIA GPU does. According to [Dylan], the hardest part of the whole thing was writing Windows drivers for it.
On his blog, [Dylan] tells us all about how he went from the obligatory [Ben Eater] breadboard CPU to playing with FPGAs to even larger FPGAs to bear the weight of this mighty GPU. While this project isn’t exactly revolutionary in the GPU world, it certainly is impressive and we impatiently wait to see what comes next.
As I’m sure many of you know, x86 architecture has been around for quite some time. It has its roots in Intel’s early 8086 processor, the first in the family. Indeed, even the original 8086 inherits a small amount of architectural structure from Intel’s 8-bit predecessors, dating all the way back to the 8008. But the 8086 evolved into the 186, 286, 386, 486, and then they got names: Pentium would have been the 586.
Along the way, new instructions were added, but the core of the x86 instruction set was retained. And a lot of effort was spent making the same instructions faster and faster. This has become so extreme that, even though the 8086 and modern Xeon processors can both run a common subset of code, the two CPUs architecturally look about as far apart as they possibly could.
So here we are today, with even the highest-end x86 CPUs still supporting the archaic 8086 real mode, where the CPU can address memory directly, without any redirection. Having this level of backwards compatibility can cause problems, especially with respect to multitasking and memory protection, but it was a feature of previous chips, so it’s a feature of current x86 designs. And there’s more!
I think it’s time to put a lot of the legacy of the 8086 to rest, and let the modern processors run free. Continue reading “Why X86 Needs To Die”
