Tesla shows the latest Dojo supercomputing: the power consumption can reach two megawatts
- An American company made 0.7nm chips: EUV lithography machines can’t do it
- CVE-2007-4559 Python vulnerability ignored for 15 years puts 350,000 projects at risk of code execution
- RISC-V only takes 12 years to achieve the milestone of 10 billion cores
- 14000 cores + 450W: RTX 4080 graphics card perfectly replaces the RTX 3080
- Big upgrade: The difference between Bluetooth 5.0 and 5.2
- Geeks Disappointed that RTX 4080/4090 doesn’t come with PCIe 5.0
- What are advantages and disadvantages of different load balancing?
Tesla shows the latest Dojo supercomputing: the power consumption can reach two megawatts, tripping the substation
On October 2 at Tesla’s 2022 AI Day , the official showcased the latest achievements of its custom-made Dojo supercomputer .
The power consumption was so strong that the local substation was tripped.
Dojo is Tesla’s own custom supercomputer platform for artificial intelligence machine learning, to help train its vision technology for autonomous driving, and more.
The previous Dojo was equipped with an Nvidia GPU, while the new version uses chips and infrastructure designed by Tesla itself .
Tesla showed off the Dojo supercomputing complete cabinet, claiming it could replace 6 GPUs with a single Dojo unit , which the company claims costs less than one GPU. There are 6 of these units per rack.
The introduction of the Dojo host interface is as follows:
“To support our unprecedented cooling and power density, every aspect of the data center infrastructure had to be re-examined and developed its own high-performance cooling and power systems to power the Dojo cabinets,” said Bill Chang, Tesla Dojo principal systems engineer.
Bill Chang revealed that he tripped the local grid’s substation earlier this year while testing the infrastructure .
“Earlier this year, we started load testing our power and cooling infrastructure and pushed the power above 2 megawatts , then the substation tripped and we got a call from the city.”
Here’s what a full-cluster Dojo Exapod looks like when it’s powered off and on:
Tesla released the main specifications of the Dojo Exapod: 1.1 EFLOP, 1.3 TB SRAM and 13 TB DRAM .
IT House learned that Tesla plans to build seven Dojo Exapod supercomputers in Palo Alto, the first of which is planned to be completed in the first quarter of 2023 .
- DIY a PBX (Phone System) on Raspberry Pi
- How to host multiple websites on Raspberry Pi 3/4?
- A Free Intercom/Paging system with Raspberry pi and old Android phones
- DIY project: How to use Raspberry Pi to build DNS server?
- Raspberry Pi project : How to use Raspberry Pi to build git server?