So, tonight's goal is to continue with ngscopeclient performance work.
I started out by doubling the speed of the eye pattern *again* by moving index buffer calculation from CPU to GPU.
Next up is going to be getting the 100baseTX decoder to not be so slow. Right now of the 43 seconds of CPU time in the current 1-minute benchmark, 26.9 is spent sampling the MLT-3 waveform on rising edges of the recovered clock.
The thing is, we already *know* the sample values at the re…
Relevant paper btw: https://pmc.ncbi.nlm.nih.gov/articles/PMC7828932/
from my link log —
Don't Panic! Better, fewer, syntax errors for LR parsers.
https://soft-dev.org/pubs/html/diekmann_tratt__dont_panic/
saved 2020-07-07
Our Christmas tree didn't drink water this year. It's been pretty much dead for the past 2 weeks. Every time you get near it, needles fall off. It's been quite a mess.
Today was the day it came down. I really wasn't looking forward to having to pick needles out of everything we own between the living room and the door for the next year, so… I went Full Dexter on it. (And it actually worked.)
Large drainage systems produced half of Mars’ ancient river sediment: #Mars’ Large River Drainage Systems for First Time: https://www.jsg.utexas.edu/news/2025/12/scientists-map-mars-large-river-drainage-systems-for-first-time/
I'm still figuring out beta-blockers. And yes, they still suck when running. I don't think I'll be able to escape that.
I have been on the treads more lately; my tolerance for cold weather has been pretty bad. Getting older, post covid crud, who knows 🤷♂️
Grateful to be able to run and enjoy this weather today.
#running
Organic geochemical evidence for life in Archean rocks identified by pyrolysis–GC–MS and supervised machine learning: #life in ancient rocks: https://gizmodo.com/ai-uncovers-evidence-of-life-in-3-3-billion-year-old-rocks-2000687539 / https://www.reuters.com/science/new-method-spots-signs-earths-primordial-life-ancient-rocks-2025-11-18/ - a machine-learning-enhanced approach to chemical analysis is drastically expanding the chemical record of life on Earth, and it could help us find evidence of life on other planets too.
I think this is progress.
I fixed the typoed atu_unr_limit and now the ATU is working, translating accesses to the 0x1000_0000 AXI space to configuration reads and writes in the PCIe bus.
But the data is always zero. I'm trying to write 0x41410000 to the BAR and it comes out as zeroes, and while the protocol analyzer shows me successfully reading 1327:1c5c which is the VID/PID of my test SSD, it comes out as zero on the AXI side.