Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Video: NVIDIA Announces Turing GPUs and CUDA Toolkit 10

Today at SIGGRPAH, NVIDIA announced its newest GPUs based on the new Turing architecture.

Speaking at the SIGGRAPH professional graphics conference in Vancouver, NVIDIA CEO Jensen Huang unveiled Turing, NVIDIA’s eighth-generation GPU architecture, bringing ray tracing to real-time graphics. He also introduced the first Turing-based GPUsthe NVIDIA Quadro RTX 8000, Quadro RTX 6000 and Quadro RTX 5000. And he detailed the Quadro RTX Server, a reference architecture for the $250 billion visual effects industry.

This fundamentally changes how computer graphics will be done, it’s a step change in realism,” Huang told an audience of more than 1,200 graphics pros gathered at the sleek glass and steel Vancouver Convention Center, which sits across a waterway criss-crossed by cruise ships and seaplanes from the stunning North Shore mountains.

Dell EMC, HP, Inc., Hewlett Packard Enterprise, Lenovo, Fujitsu, Boxx and SuperMicro will be among the system vendors supporting the latest line of Quadro processors, he said. The three new Quadro GPUs will be available starting in the fourth quarter.

NVIDIA also announced CUDA 10, the latest software development platform for building GPU-accelerated applications. This new version of CUDA includes support for Turing GPUs, performance optimized libraries, a new programming model for defining program execution, and enhanced graphics API interoperability.

Release Highlights

  • Turing Support: Build and optimize applications for the next generation of NVIDIA GPUs
  • Performance Optimized Libraries: Strong FFT performance scaling across 16-GPU systems, acceleration of dense linear algebra routines such as
  • Eigensolver and Cholesky factorization, and Turing optimized mixed-precision GEMM performance.
  • nvJPEG: New library for hybrid JPEG processing that provides >2x speedup on single and batched image decoding
  • CUDA Graphs: Programming model constructs for a “define-once-run-repeatedly” execution flow
  • CUDA/Graphics Interop: New interoperability between CUDA and graphics APIs, including Vulkan and DX12
  • New Developer Tools: New Nsight product family of tools for tracing, profiling, and debugging of CUDA applications (Nsight Systems and Nsight Compute)

CUDA 10 also provides all the components needed to build applications for NVIDIA’s most powerful server platforms for AI and high performance computing (HPC) workloads, both on-prem (DGX-2) and in the cloud (HGX-2).

To be notified when CUDA 10 is available for download, join the NVIDIA Developer Program.

Check out our insideHPC Events Calendar

Leave a Comment

*

Resource Links: