Live data from Hacker News

Viewing profile — fayalalebrun

fayalalebrun

HN member
Joined
Tue, Jan 10, 2023, 7:47 PM UTC
HN karma
262
Public activity
44 items

About fayalalebrun

No profile information was provided.

Recent public activity

  1. story
  2. comment
    Comment #47485758

    Apparently Voodoo cards defaulted to 1.3 gamma instead of the standard 2.2. I wonder why that is, since it theory using a non-standard gamma would just reduce your color range with…

  3. comment
    Comment #47485702

    This fits and runs in a DE-10 Nano without too much difficulty, uses around 70% of the fabric. I've been working on timing closure and just got it to 50 MHz. Note that I also imple…

  4. comment
    Comment #47479258

    You do have a nice point here. Then the compute unit can simply stall the commands coming out of the register bank. Without this I need to stall the write FIFO, which feels less el…

  5. comment
    Comment #47478920

    Thank you! These things do pack in a ridiculous amount of functionality for what they do. Probably why they look so good but also why it took 30 years for a hardware re-implementat…

  6. comment
    Comment #47478895

    Maybe I'm misunderstanding, but that functionality is implemented in another component. The register bank only records the category of each register and implements the memory-mappe…

  7. story
  8. story
  9. comment
    Comment #42827206

    SpinalHDL did not fork from Chisel. You might be able to say that it was inspired by Chisel, but it does not share a commit history. See this comment by the author: https://www.red…

  10. comment
    Comment #41821411

    My favorite dithering algorithm for motion video is Yliluoma dithering: https://bisqwit.iki.fi/story/howto/dither/jy/ It is especially useful for grayscale content, as finding the …

  11. comment
    Comment #41024510

    Do you have any other examples where systolic arrays are suitable other than matrix multiplication? As far as I am aware, other problems require different systolic architectures. S…

  12. comment
    Comment #40919874

    As a result of a flaw in the protocol itself or in its implementation?

  13. comment
    Comment #40332429

    This is a common misconception, but is not the case. For example, look at the Voodoo 1, 2, and 3, which also used fixed point numbers internally but did not suffer from this proble…

  14. story
  15. comment
    Comment #39914543

    A few years ago a friend and I made something similar to universe sandbox, though only with the gravitational simulation part: https://github.com/fayalalebrun/Astraria Surprisingly…

  16. comment
    Comment #39775446

    Even though the newest nvidia drivers have started to support GBM, the Wayland compatibility story is still not great. In my experience on Wayland, several OpenGL programs refuse t…

  17. comment
    Comment #39701145

    I probably don't have nearly as much experience as you do, but I have used VHDL, Verilog, and modern HDLs like Chisel and SpinalHDL. I think the main advantage of a modern HDL is t…

  18. comment
    Comment #39700988

    Chisel does emit FIRRTL. Which can be made into a bitstream directly by Yosys.

  19. comment
    Comment #39372951

    Perhaps already possible via MoltenVK -> Vulkan -> Zink?

  20. comment
    Comment #39344421

    I am surprised no one has yet tried to make a portable shell for the DE-10 Nano (Mister-FPGA's target platform). With a power usage of 10 watts, I think it should be quite feasible…

  21. comment
    Comment #39344108

    What about the actual FPGA specs? Is it more power efficient per LUT? A newer generation or the same generation but a smaller chip?

  22. story
  23. comment
    Comment #39038971

    I am curious, in what ways is WebGPU better than Vulkan or Metal? From my point of view, WebGPU going back to an interpreted shading language like OpenGL makes it conceptually clos…

  24. comment
    Comment #38873131

    With FPGA, unlike with GPUs, you can achieve significant speedup of algorithms where parallelization is very difficult. This is thanks to a technique called pipelining, where you c…

  25. story