Open Optimization Challenge: Cut TensorFrost Wave Equation Runtime Below 1e-6 Max Error
Michael_Moroz_ · x · 2026-09-09
frostcompute kicked off an optimization challenge targeting TensorFrost's wave equation simulation: lower the runtime as much as possible while keeping maximum error below 1e-6, with a baseline repo published as the starting point. A hands-on kernel/tuning contest for GPU and numerical simulation enthusiasts.
More from Research
- Mordatch: robot experiments reveal intentionality and awareness in current models — IMordatch · 2026-09-09
- BlackboxNLP 2026 announces keynotes from Ivan Titov, Sheridan Feucht and Michael Hahn — gsarti_ · 2026-09-09
- Schmidhuber: long-context autoregression was cool long before 2016, cites pioneer-credit survey — SchmidhuberAI · 2026-09-09
- System Design Interview book notes hit 17k stars, +910 in a day — liquidslr · 2026-09-09
- Singapore switches on biological data center with 20 CL1 units of living human neurons — Olivier__OG · 2026-09-09
- 2-billion-line Lean proofs: mathematicians debate proof without understanding — Singularitarian · 2026-09-09