vector addition kernel
HoldTechniques
A simple GPU kernel that computes c[i] = a[i] + b[i] with one thread per element.
Why it's here
Placed in Hold: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 4Hacker News·8/21/2026researchHow a GPU Reads Memory
This article reverse-engineers the path a GPU global load takes on an RTX 4090, from register reads and warp scheduling through the load/store unit, coalescer, cache hierarchy, and memory controller. It uses timing experiments and SASS inspection to explain how a simple vector-add kernel moves data through the hardware for performance analysis.