Cerebras and G42 Unveil Condor Galaxy 3, an 8 exaFLOPs AI Supercomputer

Cerebras Systems, the trailblazer in accelerating generative AI, and G42, the important Abu Dhabi-based technology holding group, have launched their latest creation: the Condor Galaxy 3 (CG-3). This marks the third cluster in their constellation of AI supercomputers, following the success of Condor Galaxy 1 and Condor Galaxy 2. With 64 of Cerebras’ CS-3 systems, all powered by the industry’s fastest AI chip, the Wafer-Scale Engine 3 (WSE-3), Condor Galaxy 3 is set to deliver a staggering 8 exaFLOPs of AI performance, boasting a remarkable 58 million AI-optimized cores.

Located in Dallas, Texas, Condor Galaxy 3 brings the total exaFLOP capacity of the Condor Galaxy network to an impressive 16 exaFLOPs. The strategic partnership between Cerebras and G42 has already made significant strides in transforming the landscape of AI compute, with the existing Condor Galaxy network having trained some of the leading open-source models in the industry.

At the core of Condor Galaxy 3 are the 64 Cerebras CS-3 Systems, each equipped with the state-of-the-art WSE-3. Manufactured at TSMC using the 5-nanometer node technology, the WSE-3 offers twice the performance at the same power and price as its predecessor. Designed specifically for training the largest AI models in the industry, the WSE-3 delivers an astounding 125 Petaflops of peak AI performance per chip.

Andrew Feldman, CEO and co-founder of Cerebras, expressed pride in their partnership with G42 and highlighted the significance of Condor Galaxy 3 in advancing AI computing. Together with future supercomputers, this latest addition will provide an unprecedented level of processing power and efficiency, delivering tens of exaflops of AI compute.

The Condor Galaxy network has already witnessed the training of generative AI models, including Jais-30B, Med42, Crystal-Coder-7B, and BTLM-3B-8K. Notably, Jais 13B and Jais30B have been recognized as the top bilingual Arabic models globally and are now available on Azure Cloud. Additionally, BTLM-3B-8K holds the position of the leading 3B model on HuggingFace, offering exceptional performance with its light 3B parameter model for inference. Med42, developed in collaboration with M42 and Core42, has surpassed MedPaLM in terms of performance and accuracy after being trained on Condor Galaxy 1 over a single weekend.

Condor Galaxy 3 is set to be available in the second quarter of 2024. For more information on the Condor Galaxy project, visit their dedicated landing page.

Cerebras Systems is a team of visionary computer architects, scientists, deep learning researchers, and engineers working together to accelerate generative AI. Their flagship product, the CS-3 system, is powered by the world’s largest and fastest AI processor, the Wafer-Scale Engine-3. With the ability to easily cluster CS-3 systems into massive AI supercomputers, Cerebras simplifies the process of placing models on these supercomputers by eliminating the complexities associated with distributed computing. Leading corporations, research institutions, and governments rely on Cerebras solutions to develop proprietary models and train open-source models with millions of downloads. Cerebras solutions are available through the Cerebras Cloud and can also be deployed on-premises.

G42, on the other hand, is a global leader in creating visionary artificial intelligence capabilities for a better future. Operating worldwide from its Abu Dhabi roots, G42 champions AI as a powerful force for positive change. With its team constantly reimagining the possibilities of technology, G42 applies advanced thinking and innovation to accelerate progress and address society’s most pressing challenges. The company collaborates with nations, corporations, and individuals to build the infrastructure for tomorrow’s world, exploring exponential possibilities across various fields, from molecular biology to space exploration. To learn more about G42’s endeavors, visit their website at www.g42.ai.

Background Information

---

About TSMC:

TSMC, or Taiwan Semiconductor Manufacturing Company, is a semiconductor foundry based in Taiwan. Established in 1987, TSMC is a important player in the global semiconductor industry, specializing in the manufacturing of semiconductor wafers for a wide range of clients, including technology companies and chip designers. The company is known for its semiconductor fabrication processes and plays a critical role in advancing semiconductor technology worldwide.

  

Latest Articles about TSMC

Technology Explained

---

Petaflops: Petaflops is a measure of computing speed, specifically one quadrillion floating-point operations per second. This technology is used to measure the performance of supercomputers, which are extremely powerful computers used for complex calculations and simulations. Petaflops technology has revolutionized the computer industry by allowing for faster and more efficient processing of large amounts of data. This has enabled advancements in fields such as weather forecasting, climate modeling, and drug discovery. Petaflops technology has also been utilized in artificial intelligence and machine learning, allowing for more accurate and sophisticated algorithms. In simpler terms, Petaflops is like a race car for computers, allowing them to process information at lightning-fast speeds and tackle complex problems that were previously impossible to solve.

Latest Articles about Petaflops