Draft:Untether AI
| Submission declined on 12 June 2025 by KylieTastic (talk). This submission is not adequately supported by reliable sources. Reliable sources are required so that information can be verified. If you need help with referencing, please see Referencing for beginners and Citing sources. This draft's references do not show that the subject qualifies for a Wikipedia article. In summary, the draft needs multiple published sources that are:
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
| Submission declined on 12 June 2025 by CanonNi (talk). This draft's references do not show that the subject qualifies for a Wikipedia article. In summary, the draft needs multiple published sources that are: Declined by CanonNi 3 days ago.
| |
| Submission declined on 12 June 2025 by CF-501 Falcon (talk). This draft's references do not show that the subject qualifies for a Wikipedia article. In summary, the draft needs multiple published sources that are: Declined by CF-501 Falcon 3 days ago.
| |
Comment: In accordance with Wikipedia's Conflict of interest policy, I disclose that I have a conflict of interest regarding the subject of this article. Rhg2 (talk) 23:47, 11 June 2025 (UTC)
Untether AI was a Canadian technology company that developed microchips and compilers for neural net processing. The patented computational memory[1][2] architecture (also known as at-memory compute [3] ) was built largely on standard silicon processes with some customization of memory cells and processing elements. The $125 million dollars raised in Series B funding in July 2021[4] led to a top MLPerf disclosure in August 2024[5][6][7] and a launch of its speedAI-240 product in October 2024.[8] The MLPerf results indicated the at-memory architecture could achieve 3X to 6X the power efficiency of competing approaches. Despite the early success, Untether AI was shut down in June 2025[9]
References
[edit]- ^ Elliott, Duncan; Snelgrove, Martin; Stumm, Michael (1992). "Computational Ram: A Memory-simd Hybrid And Its Application To Dsp". Proceedings of the IEEE Custom Integrated Circuits Conference. doi:10.1109/CICC.1992.591879. Retrieved 15 June 2025.
- ^ Snelgrove, Martin; Wiebe, Darrick (2023-03-28). "Computational memory". US Patent 11614947B2. Retrieved 15 June 2025.
- ^ Beachler, Bob; Snelgrove, Martin (2022). "Untether AI : Boqueria". 2022 IEEE Hot Chips 34 Symposium (HCS). pp. 1–19. doi:10.1109/HCS55958.2022.9895618. ISBN 978-1-6654-6028-6. Retrieved 11 June 2025.
- ^ "Intel-backed Untether AI raises $125 million". betakit.com. 20 July 2021. Retrieved 11 June 2025.
- ^ "New MLPerf Inference v4.1 Benchmark Results". mlcommons.org. 28 August 2024. Retrieved 12 June 2025.
- ^ "AMD and Untether Take On Nvidia in MLPerf Benchmarks". eetimes.com. 28 August 2024. Retrieved 12 June 2025.
- ^ "Untether AI Announces speedAI Accelerator Cards". yahoo.com. 28 August 2024. Retrieved 11 June 2025.
- ^ "Untether AI Ships speedAI 240 Slim". businesswire.com. October 2024. Retrieved 11 June 2025.
- ^ "Untether AI Shuts Down". eetimes.com. June 2025. Retrieved 11 June 2025.