News

Nvidia Launches CUDA 9 at GTC 2017 in China

Nvidia’s CUDA 9 is now available.

Setting a new milestone in the HPC/ AI industries, NVIDIA has recently announced the availability of CUDA 9. The news was shared at GTC 2017 in China, and the release will likely spearhead support for new architectures. It’s worth noting that CUDA 9 has been available in release candidate form for a while now. However, this is the first time that we’ve been able to see the GA mark of the new tooling. Apart from new architectures, libraries optimized for brand new applications might also become available soon. You must be keen to find out about CUDA 9’s main features, though.

CUDA 9 features.

According to the NVIDIA developer site, the main highlights of the new platform are the following:

  • Speed up high-performance computing (HPC) and deep learning apps with new GEMM kernels in cuBLAS.
  • Execute image and signal processing apps faster with performance optimizations across multiple GPU configurations in cuFFT and NVIDIA Performance Primitives.
  • Solve linear and graph analytics problems common in HPC with new algorithms in cuSOLVER and nvGRAPH.
  • Express rich parallel algorithms with threads from sub-tiles to warps, blocks, and grids.
  • Manage and reuse threads efficiently within an application with new API and function primitives.
  • Optimize and pre-fetch memory access by identifying source code causing page faults in unified memory.
  • Inspect unified memory performance bottlenecks with new event filters based on virtual address, migration reason and page fault access type.

Moreover, several Volta and NVLink support items are also included:

  • Replace warp-synchronous programming with robust programming model on Kepler architecture and above.
  • Execute AI applications faster with Tensor Cores performing 5X faster than Pascal GPUs.
  • Scale multi-GPU applications with next-generation NVLink delivering 2X throughput of prior generation.
  • Increase GPU utilization with Volta Multi-Process Service (MPS).
  • Profile PCIe usage by analyzing bandwidth of memory transfers, latency, and comparison with NVLink.

Are you looking forward to Nvidia’s upcoming technologies?

Cernescu Andrei

Candrei is a writer for eTeknix who loves the latest technology news and gaming.

Disqus Comments Loading...

Recent Posts

Nvidia’s GeForce RTX 5090 Possible Price Revealed

According to a new report, the GeForce RTX 5090 GPU will be very expensive. It…

3 hours ago

AMD Krackan Processor with 6 Zen 5 and Zen 5c Cores for Budget AI Laptops Leaked

A new AMD processor in the form of an engineering model has been leaked in…

3 hours ago

SK Hynix Begins Production of First 321-Layer NAND Chips

SK Hynix has claimed to be the first company to mass-produce 321-layer NAND memory chips.…

4 hours ago

Trust Gaming GXT 609 Zoxa 2.0 PC Speakers

SOUNDS GREAT – Full stereo sound (12W peak power) gives your setup a booming audio…

8 hours ago

PowerA Wired Controller for Nintendo Switch

Special Edition Yoshi design Ergonomic controller shape with Nintendo Switch button layout Detachable 10ft (3m)…

8 hours ago

Logitech G Saitek PRO Flight Rudder Pedals

Fluid Motion: These flight rudder pedals are smooth and accurate that enable precise control over…

8 hours ago