←
Edmund Humenberger28,151 posts
Edmund Humenberger avatar

Edmund Humenberger

@ico_TC

mostly about open source FPGA tools and chip design tools

◷ Joined January 2016▧ 2,605 Photos and videos
Mehdi avatar
⟳ Edmund Humenberger retweeted
Mehdi@MehdiHacks·49m

For comparison, here's my Rigol MHO98. 1 GHz, 4 channels, 12-bit, compact, and USB-C powered. All for around €1,300. Hard to beat that value for money.

Post attachment
Hasan avatar
⟳ Edmund Humenberger retweeted
Hasan@hasanunlu9·Oct 6

We’re building the Apex GPU alongside our AI accelerator. Our open-source Mesa driver just achieved Vulkan 1.3 conformance on our Alveo U50 FPGA prototype. This is the first FPGA-prototype GPU capable of running Vulkan while rendering the entire Ubuntu desktop. We built the entire stack, from the GPU microarchitecture and RTL all the way up to the Mesa driver and Vulkan. The entire Linux desktop is rendered and driven by the Apex GPU at up to 4K 120 Hz on FPGA. @VulkanAPI

Post attachmentPost attachmentPost attachment
Edmund Humenberger avatar
Edmund Humenberger@ico_TC·11h

In 2016 people told me that it will never be possible to design a working chip with open source EDA tools. I think we achieved to make chip design fun again. youtu.be/iZ-hEF7Yf1s?si=Llch… The community made quite some progress since then. This is a Bluetooth beacon.

Post attachment
Andrea Bernardi avatar
⟳ Edmund Humenberger retweeted
Andrea Bernardi@atomozero·Nov 17

For a few weeks I have been porting Haiku, and its fork @RenkuOS, to the Milk-V Mars. It is a #RISC-V board, built around the StarFive JH7110 SoC with 4 SiFive U74 cores at 1.5 GHz; mine has 4 GB of RAM. I wanted to share the progress, because the board is usable.

Post attachment
Enjoy Digital avatar
⟳ Edmund Humenberger retweeted
Enjoy Digital@enjoy_digital·Nov 16

Keeping our dev methodology but with AI assistance, we've finally stabilized the USB3-PIPE project, implemented a proper USB3 Core, added support for Gowin/ECP5/Xilinx FPGAs and USB 3.2 Gen 1 (5Gbps) and Gen 2 (10Gbps). This will also be an enabler for other projects: SLogic16U3, M2SDR, etc... github.com/enjoy-digital/usb…

0:16
Machdyne UG avatar
⟳ Edmund Humenberger retweeted
Machdyne UG@machdyne·Nov 17

New project: Mach86 is a 386DX/486SX-class PC-compatible SOC for #FPGA computers; it boots FreeDOS and can run thousands of apps and games. mach86.org

1:11
Edmund Humenberger avatar
Edmund Humenberger@ico_TC·Nov 17

For those who want to play with a FPGA with the open source FPGA tools, but do not have yet access to a real FPGA. Here is a simulated iceBreaker FPGA board with the @latticesemi ice40UP5k and two simulated PMOD runnning in your browser. And the open source FPGA tool chain to generate the bitstream run in the Browser too. senolgulgonul.github.io/soft…

Post attachment
John Carmack avatar
⟳ Edmund Humenberger retweeted
John Carmack@ID_AA_Carmack·Nov 16

Both NeXT and 3DFX tried to “do the right thing” with color spaces, and it wound up generally making them look worse than competing options. I didn’t really understand it properly until years later. It is natural to think that a pixel with a value of 1.0 is emitting twice the photons as a pixel with a value of 0.5, so you can do the obvious linear math to calculate partial pixel coverage, blending a foreground over a background, or interpolating between colors in a texture. If displays are “linear”, that is correct. NeXT and 3DFX were much closer to linear than other contemporary displays. NeXT had crossover from the deep graphics understanding at Pixar, and 3DFX had the SGI heritage. They did this intentionally. If you have 10+ bits per channel like the professional rendering systems, linear displays are The Right Thing. Unfortunately, NeXTStation Colors were 4 bits per channel and 3DFX was 5 or 6 bits per channel, and there… it was not the right thing. Human eyes aren’t linear intensity sensors. We mostly register relative changes in intensity, so we can tell the difference between 0.01 and 0.02 as a huge doubling, while 0.99 to 1.00 is almost imperceptible. This distribution of intensities is often referred to as the “gamma” of the display system, but the actual curves like sRGB are a bit more complicated. If you only have a small number of discrete pixel values, you definitely don’t want to spread them evenly from 0 to 1! If you do, you will have good precision in the brights, but very stark “intensity bands” in the dark colors. If everything was authored specifically for 3DFX, you would still have the fundamental problem with the dark bands, but more accurate blending and filtering. The problem was that artists made all of their textures in paint programs on conventional non-linear displays, so when they were drawn by 3DFX cards, they got the characteristic “washed out color” look. You can mathematically correct textures for differences in display gamma, but I didn’t really understand the issue back in the glQuake days, and we were so enthralled by the absolute performance of 3DFX that the color fidelity didn’t get as much attention as it should have. Even today, tons of games don’t properly handle gamma across their textures and render targets. High resolutions and 24 bit color masks most of it, but you still see it in some slight shimmerings in high contrast textures and edges.

Does anybody know why 3DfX 1 cards had such a washed out color output? In my research, circa '97 I found many people complaining about the colors. Is it gamma? 16-bit color? What can it be?

Post attachment
Kenta IDA avatar
⟳ Edmund Humenberger retweeted
Kenta IDA@ciniml·Nov 16

TangPrimer20Kに入れたRISC-V CPU上でLinux動かしてる状態で、差動ペア1本でCPUのトレース出力を700Mbpsくらいで出して、TangPrimer25Kで受けてトレース解析して画面作って解析結果をDVI出力できるようになった。 この前の同人誌のEasyCDRトレースツールの応用。便利。booth.pm/ja/items/9034048

Post attachment
0:19