# Macro Placement on adaptec3 (HPWL and Congestion)

Source: [Macro Placement on adaptec3 (HPWL and Congestion)](<https://www.sota2.com/research/sota/macro-placement-on-adaptec3-hpwl-and-congestion>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-19T07:29:00.407Z

Evaluation of Macro Placement algorithms on the adaptec3 dataset, focusing on quality metrics such as Half-Perimeter Wire Length (HPWL) and Congestion.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Macro Placement |
| Dataset (including any stated split) | adaptec3 |
| Metric | HPWL (x10^5) |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 13 of 13 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [HPWL (x10^5)](<https://www.sota2.com/research/sota/macro-placement-on-adaptec3-hpwl-and-congestion.md?metric=HPWL%20(x10%5E5)>): Lower is better; unit: SCALAR.

- [Congestion](<https://www.sota2.com/research/sota/macro-placement-on-adaptec3-hpwl-and-congestion.md?metric=Congestion>): Lower is better; unit: SCALAR.

- [Std HPWL (x10^5)](<https://www.sota2.com/research/sota/macro-placement-on-adaptec3-hpwl-and-congestion.md?metric=Std%20HPWL%20(x10%5E5)>): Lower is better; unit: SCALAR.

- [Best HPWL (x10^5)](<https://www.sota2.com/research/sota/macro-placement-on-adaptec3-hpwl-and-congestion.md?metric=Best%20HPWL%20(x10%5E5)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | HPWL (x10^5) | Result date | Report paper |
| --- | --- | --- | --- |
| VeoPlace + ChiPFormer | 24.1 | Not recorded | 69cb558b0636e5bf4afca4ef |
| ChiPFormer | 25.64 | Not recorded | 69cb558b0636e5bf4afca4ef |
| ChiPFormer | 26.31 | Not recorded | 69cb558b0636e5bf4afca4ef |
| WireMask-EA | 56.56 | Not recorded | 68fa71091e209131cea4ece8 |
| WireMask-BO | 58.67 | Not recorded | 68fa71091e209131cea4ece8 |
| WireMask-RS | 60.91 | Not recorded | 68fa71091e209131cea4ece8 |
| MaskPlace | 79.32 | Not recorded | 68fa71091e209131cea4ece8 |
| SP-SA | 122.3 | Not recorded | 68fa71091e209131cea4ece8 |
| DREAMPlace | 153.3 | Not recorded | 6a0bee5edbc836b87d82c1ae |
| MacroDiff+ | 163.9 | Not recorded | 6a0bee5edbc836b87d82c1ae |
| ChipDiffusion | 165.2 | Not recorded | 6a0bee5edbc836b87d82c1ae |
| WireMask-BBO | 180.8 | Not recorded | 6a0bee5edbc836b87d82c1ae |
| MaskPlace | 185.3 | Not recorded | 6a0bee5edbc836b87d82c1ae |

### VeoPlace + ChiPFormer

HPWL (x10^5): 24.1. Result ID: 69cbc10147f34ce924b56c99.

[Reporting paper](<https://www.sota2.com/research/paper/69cb558b0636e5bf4afca4ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb558b0636e5bf4afca4ef.md>)

Recorded evaluation configuration: {"LLM Backbone":"Gemini 2.5 Flash","Context Length (C)":"1"}. This record does not assert independent reproduction.

### ChiPFormer

HPWL (x10^5): 25.64. Result ID: 69cbc10147f34ce924b56c9a.

[Reporting paper](<https://www.sota2.com/research/paper/69cb558b0636e5bf4afca4ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703c1e209131cea49cd6.md>)

Recorded evaluation configuration: {"Fine-tuning":"No-FT"}. This record does not assert independent reproduction.

### ChiPFormer

HPWL (x10^5): 26.31. Result ID: 69cbc10147f34ce924b56c9b.

[Reporting paper](<https://www.sota2.com/research/paper/69cb558b0636e5bf4afca4ef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703c1e209131cea49cd6.md>)

Recorded evaluation configuration: {"Fine-tuning":"FT"}. This record does not assert independent reproduction.

### WireMask-EA

HPWL (x10^5): 56.56. Result ID: 6991903b3a6c31484908ff93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Implementation](<https://github.com/lamda-bbo/WireMask-BBO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WireMask-BO

HPWL (x10^5): 58.67. Result ID: 6991903b3a6c31484908ff92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Implementation](<https://github.com/lamda-bbo/WireMask-BBO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WireMask-RS

HPWL (x10^5): 60.91. Result ID: 6991903b3a6c31484908ff91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Implementation](<https://github.com/lamda-bbo/WireMask-BBO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MaskPlace

HPWL (x10^5): 79.32. Result ID: 6991903b3a6c31484908ff90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0a1e209131cea3d9b7.md>)

[Implementation](<https://www.sota2.com/laiyao1.github.io/maskplace>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SP-SA

HPWL (x10^5): 122.3. Result ID: 6991903b3a6c31484908ff8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DREAMPlace

HPWL (x10^5): 153.3. Result ID: 6a0c113bfbc373592c01c02e.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1ae.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MacroDiff+

HPWL (x10^5): 163.9. Result ID: 6a0c113bfbc373592c01c032.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1ae.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ChipDiffusion

HPWL (x10^5): 165.2. Result ID: 6a0c113bfbc373592c01c031.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa793a1e209131cea7cb84.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WireMask-BBO

HPWL (x10^5): 180.8. Result ID: 6a0c113bfbc373592c01c030.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ece8.md>)

[Implementation](<https://github.com/lamda-bbo/WireMask-BBO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MaskPlace

HPWL (x10^5): 185.3. Result ID: 6a0c113bfbc373592c01c02f.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee5edbc836b87d82c1ae.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0a1e209131cea3d9b7.md>)

[Implementation](<https://www.sota2.com/laiyao1.github.io/maskplace>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
