Uploaded November 2020 | Updated September 2026, 2 weeks ago
A100 introduces double-precision Tensor Cores, providing the biggest milestone since the introduction of double-precision computing in GPUs for HPC. This enables researchers to reduce a 10-hour, double-precision simulation running on NVIDIA V100 Tensor Core GPUs to just four hours on A100. HPC applications can also leverage TF32 precision in A100’s Tensor Cores to achieve up to 10X higher throughput for single-precision dense matrix multiply operations.
Scan understands that before making such a large investment, you need to be sure that you are making the right decision for your organisation. This is why we offer the opportunity for you to take part in a Proof-Of-Concept on the DGX A100.
To register your interest in a Proof-Of-Concept on the DGX A100 get in touch with the Scan AI team here - ai@scan.co.uk / 01204 474747 or fill out the form found here - scan.co.uk/business/poc-form
To find out more visit here - scan.co.uk/business/nvidia-dgx-a100-ai-system
Remember to subscribe and follow us on social media:
LinkedIn - https://www.linkedin.com/company/scan...
Facebook - facebook.com/ScanBusiness
Twitter - twitter.com/Scan_Business
A100 introduces double-precision Tensor Cores, providing the biggest milestone since the introduction of double-precision computing in GPUs for HPC. This enables researchers to reduce a 10-hour, double-precision simulation running on NVIDIA V100 Tensor Core GPUs to just four hours on A100. HPC applications can also leverage TF32 precision in A100’s Tensor Cores to achieve up to 10X higher throughput for single-precision dense matrix multiply operations.
Scan understands that before making such a large investment, you need to be sure that you are making the right decision for your organisation. This is why we offer the opportunity for you to take part in a Proof-Of-Concept on the DGX A100.
To register your interest in a Proof-Of-Concept on the DGX A100 get in touch with the Scan AI team here - ai@scan.co.uk / 01204 474747 or fill out the form found here - scan.co.uk/business/poc-form
To find out more visit here - scan.co.uk/business/nvidia-dgx-a100-ai-system
Remember to subscribe and follow us on social media:
LinkedIn - https://www.linkedin.com/company/scan...
Facebook - facebook.com/ScanBusiness
Twitter - twitter.com/Scan_Business
![NVIDIA GTC 2021 - Scan CEO Session [SS33047] - Tune in on Monday 12th April 2021!](https://i.ytimg.com/vi/vRkXEFKXKyg/mqdefault.jpg "NVIDIA GTC 2021 - Scan CEO Session [SS33047] - Tune in on Monday 12th April 2021!
Scan CEO Elan Raja will be presenting at GTC 2021 on the Design and Delivery of a GPU-Accelerated Medical Image Repository for AI-Enhanced Diagnosis and Decision-making. The session ID is [SS33047] - be sure to register if you havent done so already. The session will be available here from 17:00 PM on the 12th April 2021 - https://gtc21.event.nvidia.com/media/1_tvrvz1yo?ncid=ref-spo-47640.
Here is a description of the session:
Scan Computers Deep Learning & AI team worked in collaboration with NVIDIA, Mellanox, and NetApp to deliver a novel AI-powered project for the London Medical Imaging and AI Centre. Understand how a GPU-accelerated hardware stack was designed and deployed to provide patient data insight and enhance medical decision-making within a highly regulated U.K. health-care environment. Learn how the dual objectives of rapid data insight and preservation of patient privacy can be delivered simultaneously, and how the system was conceived to be scalable to handle a daily influx of new data and yet have the capability to learn from this data using specifically tailored machine learning and AI algorithms. Reference architecture details of the hardware and software elements will be presented.
Get in touch with the Scan AI team here - ai@scan.co.uk / 01204 474747
Remember to subscribe and follow us on social media:
LinkedIn - https://www.linkedin.com/company/scan-computers-international-ltd-/
Facebook - https://www.facebook.com/ScanBusiness/
Twitter - https://twitter.com/Scan_Business")
