---
title: "Microcosmos avoids quadratic-scaling operations by design — local fluid updates and grid-based steric repulsion instead of pairwise checks — to reach GPU-scale populations"
type: "claim"
status: "seedling"
audit_status: "capture-verified for the design principle (the capturing hop session read arxiv.org/html/2607.02954v1, Tier 1); the specific benchmark figures below are held [unverified-quant] — the capture itself flagged that exact numbers and methodology must be checked against the paper's own figures, and this headless promotion has no web tool to re-fetch. Routed to [[question-verify-microcosmos-benchmarks-and-experiments]]. | AUDIT 2026-07-09 (claude-opus-4-8, cross-model): arXiv HTML re-fetched directly. Design principle confirmed (LBM local updates; grid-based steric repulsion via density field deposited on a grid + FFT-convolved Gaussian, no all-pairs; JAX). Benchmark confirmed against the paper's Figure 5: wall-clock scales LINEARLY with particle count, tested to ~500k particles on a single NVIDIA L40S GPU (1000 steps). [unverified-quant] resolved — figure matches the note."
source_url: "https://arxiv.org/html/2607.02954v1"
source_title: "Microcosmos: Reimagining Artificial Life for the GPU Era"
source_author: "Mark Tensen, Ciaran Regan, Bert Wang-Chak Chan, Mizuki Oka, Kenneth O. Stanley, Grisha Szep"
source_date: "2026-07"
source_quote: "designed from the ground up for modern GPU hardware and end-to-end differentiable simulation"
source_tier: 1
provenance: "Promotion from 10-inbox/raw/2026-07-09-hop-microcosmos-gpu-alife.md, 2026-07-09"
origin: "batch"
derived_from: ["20260709-1602-hop-microcosmos-gpu-alife"]
date_created: "2026-07-09T00:00:00.000Z"
tags: ["gpu-simulation","computational-scaling","artificial-life","jax","differentiable-physics"]
---


The organizing constraint behind Microcosmos (arXiv:2607.02954) is that every
component avoids operations that scale quadratically with the number of interacting
elements, because quadratic cost is what caps population size on a GPU. Two design
choices carry this: the **Lattice Boltzmann fluid solver uses only local updates**
(no all-pairs force computation), and **self-avoidance is handled by grid-based
steric repulsion** rather than pairwise collision detection. The whole engine is
implemented in **JAX**, giving [[entity-automatic-differentiation|automatic differentiation]] over the physics for free
([[claim-microcosmos-elastic-filaments-differentiable-gpu-fluid]]).

The capture records the paper's performance claim — runtime scaling **linearly with
particle count, tested to ~500k particles on a single NVIDIA L40S GPU** — but that
specific figure is held under `[unverified-quant]`. The capture author explicitly
noted that "exact benchmark numbers/methodology beyond this summary should be checked
against the paper's own figures before reuse," so the number is recorded, not treated
as settled. Under the vault's sourcing floor a specific benchmark figure is a
Tier 1–2 quantitative claim that should be confirmed against the primary source's
own plots before going load-bearing; the verification is routed to
[[question-verify-microcosmos-benchmarks-and-experiments]] and the note stays
`seedling`.

The durable content here is the *design principle* — trade pairwise exactness for
local/grid approximations to buy linear scaling — not the exact particle count. This
"kill the quadratic term to hit hardware scale" pattern is a recurring theme in
GPU-era ML systems work, adjacent to the throughput-oriented engineering in
[[claim-gift-2026-gradient-anisotropy-isotropic-transform]].