# limbo018/DREAMPlace

Deep learning toolkit-enabled VLSI placement

Repository: https://github.com/limbo018/DREAMPlace
Canonical: https://ross.abutalabs.com/products/dreamplace
Language: C++
License: BSD-3-Clause
License Family: permissive
Topics: vlsi-physical-design, deep-learning, pytorch, vlsi, vlsi-placement, gpu-acceleration
Last push: 2026-07-18T08:53:32+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 100
- inputs: {"age_days": 2743, "days_push": 46, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1044, forks 280 (observed 2026-08-28T04:03:21.280559+00:00)

## What it is
DREAMPlace is a GPU-accelerated VLSI placement tool that reformulates placement as a deep-learning-like optimization using PyTorch. It supports global, legalization, and detailed placement with large speedups over CPU-based placers.

## Use cases
- place standard cells in a VLSI design
- run GPU-accelerated global placement and legalization
- benchmark placement algorithms on ISPD contest benchmarks
- accelerate detailed placement of million-cell designs
- experiment with deep-learning-based physical design

## When to choose
- you need fast placement of large netlists on GPU hardware
- you want a flexible PyTorch-based research platform for placement algorithms

## When to avoid
- you need a full commercial P&R flow with routing and signoff
- you have no GPU and very large designs where CPU performance is insufficient

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, gpu-computing, simulation
- domain: hardware, machine-learning
- platform: python
- tags: vlsi, placement, eda, pytorch, physical-design, linux, gpu, docker

## Member repositories
- limbo018/DREAMPlace (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.280559+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:14.319589+00:00, confidence not recorded.
  - readme: https://github.com/limbo018/DREAMPlace (fetched 2026-08-28T04:03:21.280559+00:00, sha daad81855617)
- Data as of 2026-08-30T08:39:29.467469+00:00.