An Introduction to the NVIDIA Optical Flow SDK

Artificial Intelligence, Featured, machine learning and AI, motion vectors, NVDEC, NVENC, optical flow, Turing

Nadeem Mohammad, posted Feb 13 2019

NVIDIA’s Turing GPUs  introduced a new hardware functionality for computing optical flow between images with very high performance.

Read more

Turing H.264 Video Encoding Speed and Quality

Accelerated Computing, H.264, NVENC, Tesla T4, Turing, video encoding

Nadeem Mohammad, posted Feb 13 2019

All NVIDIA GPUs starting with Kepler support fully-accelerated hardware video encoding;  GPUs starting with Fermi support fully-accelerated hardware video decoding.

Read more

Using Nsight Compute or Nvprof to Show Mixed Precision Use in Deep Learning Models

Accelerated Computing, Artificial Intelligence, Nsight compute, nvprof, NVVP

Nadeem Mohammad, posted Feb 06 2019

Mixed precision combines different numerical precisions in a computational method. The Volta and Turing generation of GPUs introduced Tensor Cores, which provide significant throughput speedups over single precision math pipelines.

Read more

Massively Scale Your Deep Learning Training with NCCL 2.4

Artificial Intelligence, binary trees, Deep Learning, machine learning and AI, NCCL, NCCL 2.4, Summit

Nadeem Mohammad, posted Feb 04 2019

Imagine using tens of thousands of GPUs to train your neural network.

Read more

Video Series: Mixed-Precision Training Techniques Using Tensor Cores for Deep Learning

Accelerated Computing, Artificial Intelligence, Featured, FP16, machine learning and AI, Mixed Precision, Tensor Cores, Turing, Volta

Nadeem Mohammad, posted Jan 30 2019

Neural networks with thousands of layers and millions of neurons demand high performance and faster training times. The complexity and size of neural networks continue to grow.

Read more