Hamartia Antidote
ELITE MEMBER
- Joined
- Nov 17, 2013
- Messages
- 35,188
- Reaction score
- 30
- Country
- Location
Tesla Launches New $300M AI Cluster for Advanced Computation
Aug. 29, 2023 ā Tesla is poised to introduce its advanced supercomputer this week, a development highlighted by Tomās Hardware and informed by insights from @SawyerMerritt. Primarily tailored for artificial [ā¦]
www.hpcwire.com
Tesla Launches New $300M AI Cluster for Advanced Computation
Aug. 29, 2023 ā Tesla is poised to introduce its advanced supercomputer this week, a development highlighted by Tomās Hardware and informed by insights from @SawyerMerritt.Primarily tailored for artificial intelligence (AI) processes, the machine will also cater to high-performance computing (HPC) tasks. Based on the Nvidia H100 platform, it is expected to be a noteworthy addition in the industry. The system is equipped with 10,000 Nvidia H100 GPUs, enabling it to potentially reach a peak performance of 340 FP64 PFLOPS for technical computing and 39.58 INT8 ExaFLOPS for AI applications. Teslaās 340 FP64 PFLOPS is higher than 304 FP64 PFLOPS from CINECAās Leonardo supercomputer, the fourth fastest in the world.
A significant feature of this new cluster is its focus on bolstering Teslaās full self-driving (FSD) technology. However, with Nvidia currently facing supply limitations, Teslaās foresight is evident. They have diversified their approach with a strategic investment in a proprietary supercomputer named Dojo, which is anticipated to work in tandem with the Nvidia H100 GPU cluster.
Credit: @SawyerMerritt/Twitter
Beyond mere hardware, the computational infrastructure is set to provide Tesla with an edge in processing vast datasets, critical for real-world AI training scenarios.
Elon Musk has alluded to the companyās long-term strategy, noting Teslaās intent to direct substantial resources towards AI and FSD training in the subsequent years, emphasizing the pivotal role of computing in automotive advancements.
Last edited: