SoylentNews
SoylentNews is people
https://soylentnews.org/

takyon writes:

Hungry for AI? New supercomputer contains 16 dinner-plate-size chips

On Monday, Cerebras Systems unveiled its 13.5 million core Andromeda AI supercomputer for deep learning, reports Reuters. According Cerebras, Andromeda delivers over one 1 exaflop (1 quintillion operations per second) of AI computational power at 16-bit half precision.

The Andromeda is itself a cluster of 16 Cerebras C-2 computers linked together. Each CS-2 contains one Wafer Scale Engine chip (often called "WSE-2"), which is currently the largest silicon chip ever made, at about 8.5-inches square and packed with 2.6 trillion transistors organized into 850,000 cores.

Cerebras built Andromeda at a data center in Santa Clara, California, for $35 million. It's tuned for applications like large language models and has already been in use for academic and commercial work. "Andromeda delivers near-perfect scaling via simple data parallelism across GPT-class large language models, including GPT-3, GPT-J and GPT-NeoX," writes Cerebras in a press release.

Previously: Cerebras "Wafer Scale Engine" Has 1.2 Trillion Transistors, 400,000 Cores
Cerebras Systems' Wafer Scale Engine Deployed at Argonne National Labs
Cerebras More than Doubles Core and Transistor Count with 2nd-Generation Wafer Scale Engine
The Trillion-Transistor Chip That Just Left a Supercomputer in the Dust

Original Submission

1. "takyon" - https://soylentnews.org/~takyon/
2. "Hungry for AI? New supercomputer contains 16 dinner-plate-size chips" - https://arstechnica.com/information-technology/2022/11/hungry-for-ai-new-supercomputer-contains-16-dinner-plate-size-chips/
3. "reports" - https://www.reuters.com/technology/silicon-valley-chip-startup-cerebras-unveils-ai-supercomputer-2022-11-14/
4. "Cerebras C-2" - https://www.cerebras.net/product-system/
5. "Wafer Scale Engine chip" - https://www.cerebras.net/product-chip/
6. "largest silicon chip" - https://computerhistory.org/blog/the-biggest-chip-in-the-world/
7. "large language models" - https://arstechnica.com/information-technology/2022/09/twitter-pranksters-derail-gpt-3-bot-with-newly-discovered-prompt-injection-hack/
8. "writes" - https://www.cerebras.net/press-release/cerebras-unveils-andromeda-a-13.5-million-core-ai-supercomputer-that-delivers-near-perfect-linear-scaling-for-large-language-models
9. "Cerebras "Wafer Scale Engine" Has 1.2 Trillion Transistors, 400,000 Cores" - https://soylentnews.org/article.pl?sid=19/08/20/115252
10. "Cerebras Systems' Wafer Scale Engine Deployed at Argonne National Labs" - https://soylentnews.org/article.pl?sid=19/11/25/0147213
11. "Cerebras More than Doubles Core and Transistor Count with 2nd-Generation Wafer Scale Engine" - https://soylentnews.org/article.pl?sid=20/08/18/1610208
12. "The Trillion-Transistor Chip That Just Left a Supercomputer in the Dust" - https://soylentnews.org/article.pl?sid=20/11/23/0654212
13. "Original Submission" - https://soylentnews.org/submit.pl?op=viewsub&subid=57543

printed from SoylentNews, Cerebras Packs 16 Wafer-Scale Chips Into Andromeda "AI" Supercomputer on 2024-04-19 16:07:14