Nvidia Tesla
Nvidia's line of GPGPUs for high-performance computing and deep learning.
Nvidia Tesla was a product line from Nvidia built for stream processing and general-purpose graphics processing units (GPGPUs), named after engineer Nikola Tesla. The line started with GPUs from the G80 series and continued alongside each new chip release. These cards were programmable through the CUDA or OpenCL APIs. Tesla competed with AMD's Radeon Instinct and Intel's Xeon Phi lines for deep learning and GPU tasks. Nvidia dropped the Tesla name in May 2020, likely to avoid confusion with the car brand, and now calls its new GPUs Nvidia Data Center GPUs, such as the Ampere-based A100.
Tesla products offered far more computational power than standard microprocessors, targeting the high-performance computing market. They powered some of the world's fastest supercomputers, including Summit at Oak Ridge National Laboratory and Tianhe-1A in Tianjin, China. Unlike Nvidia's GeForce consumer cards or Quadro professional cards, Tesla cards originally could not output images to a display. The last C-class Tesla products, however, included one Dual-Link DVI port.
These products were mainly used for simulations, large-scale calculations (especially floating-point), and high-end image generation in professional and scientific fields. In 2013, defense industry sales made up less than one-sixth of Tesla's total, though Sumit Gupta predicted growth in the geospatial intelligence market.
Quick Facts
- Manufacturer
- Nvidia
- Introduced
- 2007-05-02
- Discontinued
- The Tesla branding was discontinued in 2020 · 05—now branded as Nvidia Data Center GPUs
Facts from the source article.
Lore & Background
Offering computational power much greater than traditional microprocessors, the Tesla products targeted the high-performance computing market. Nvidia Teslas power some of the world's fastest supercomputers, including Summit at Oak Ridge National Laboratory and Tianhe-1A, in Tianjin, China. Unlike Nvidia's consumer GeForce cards and professional Nvidia Quadro cards, Tesla cards were originally unable to output images to a display. However, the last Tesla C-class products included one Dual-Link DVI port.
Tesla products are primarily used in simulations and in large-scale calculations (especially floating-point calculations), and for high-end image generation for professional and scientific fields. In 2013, the defense industry accounted for less than one-sixth of Tesla sales, but Sumit Gupta predicted increasing sales to the geospatial intelligence market. Nvidia DGX servers feature Nvidia GPGPUs.
Reader's Guide
The Nvidia Tesla line established a dedicated hardware platform for general-purpose GPU computing, moving beyond graphics rendering into scientific simulation, deep learning, and large-scale floating-point calculations. Its programmability through CUDA and OpenCL allowed researchers and engineers to harness massive parallel processing power. The brand's retirement in May 2020, reportedly due to confusion with the car manufacturer, marked the transition to Nvidia Data Center GPUs such as the Ampere-based A100. Tesla's legacy includes powering leading supercomputers like Summit and Tianhe-1A, and its competition with AMD's Radeon Instinct and Intel Xeon Phi shaped the market for specialized compute accelerators. The line's evolution from display-less compute cards to the last C-class products with a DVI port reflects its shift toward broader accessibility in high-performance computing.
Did You Know?
- Nvidia Tesla is named after pioneering electrical engineer Nikola Tesla.
- The Tesla brand was retired in May 2020, reportedly because of potential confusion with the brand of cars.
Frequently Asked Questions
What is Nvidia Tesla?
Nvidia Tesla is a product line of graphics processing units designed for stream processing and general-purpose computing tasks such as deep learning. The line began with the G80 series and continued alongside each new chip generation.
Who is the Tesla name on Nvidia GPUs named after?
The line takes its name from the inventor Nikola Tesla, not from the electric-vehicle company. This naming was applied starting with the G80 generation to set these professional computing cards apart from consumer gaming hardware.
How do you program Nvidia Tesla GPUs?
Developers write code for Tesla cards through either the CUDA or OpenCL programming interfaces. Those APIs let programmers exploit the GPU's parallel architecture for workloads far beyond simple graphics rendering.
Why did Nvidia retire the Tesla brand name?
In May 2020 Nvidia stopped using the Tesla label, most likely to cut down on confusion with Tesla, Inc., the car manufacturer. The cards are now sold under the broader "Nvidia Data Center GPUs" umbrella, with the Ampere-based A100 being a current example.
What other GPU lines compete with Nvidia Tesla?
The primary rivals in high-performance computing and deep-learning workloads are AMD's Radeon Instinct series and Intel's Xeon Phi line. All three target the same market of scientific simulation, AI training, and large-scale data processing.
More in Nvidia and AMD Graphics Processors 1-24
Spotted an error? Know more?
Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced