First Generation Techyum AI Data Centers With 1800 Exaflops in 6,000 Square Feet

Tachyum is a startup that will make Prodigy processors will enable hyperscale data centers that have 25% of the cost (4X lower cost) and will saving each hyperscale customer billions of dollars per year.

First-generation Prodigy data centres will offer 3.3 EF of FP64, three times the performance of existing supercomputers, and also deliver around 1.8 ZF (Zettaflop) of AI processing in 6,000 square feet at power consumption of only 45 MW.

Prodigy-powered universal servers in hyperscale data centers, during off-peak hours, will deliver 10x more AI Neural Network training/inference resources than currently available.

Tachyum’s Prodigy is the first Universal Processor combining General Purpose Computing, High Performance Computing (HPC), Artificial Intelligence (AI), Deep Machine Learning, Explainable AI, Bio AI, and other AI disciplines within a single chip. It allows for a simple programming model and environment based on a coherent multiprocessor architecture.

The T16192 integrates 192 high-performance, 64-bit cores, 16 DDR5 memory controllers running up to DDR5-7200, and 96 lanes of PCIe 5.0 to address the most demanding applications for Exascale Supercomputing, Big AI, and Big Data.

Condor Galaxy Fastest AI Supercomputer in 2023

Condor Galaxy, a network of nine interconnected AI supercomputers,A made by US-based AI company Cerebras Systems together with G42, UAE-based technology holding group G42, Condor Galaxy 1 (CG-1) is the first deployment of the network.

Located in Santa Clara, California, CG-1 is a 4 exaFLOPs, 54 million core, cloud-based AI supercomputer. Once in full operation, the Condor Galaxy network will boast 36 exaFLOPs of AI computing, significantly reducing the time consumed in AI computing.