Mixed Precision

NVIDIA Ampere GPU architecture introduced the third generation of Tensor Cores, with the new TensorFloat32 (TF32) mode for accelerating FP32 convolutions and...

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

Double-precision floating point (FP64) has been the de facto standard for doing scientific simulation for several decades. Most numerical methods used in...

Most deep learning frameworks, including PyTorch, train using 32-bit floating point (FP32) arithmetic by default. However, using FP32 for all operations is not...

The success of neural networks thus far has been built on bigger datasets, better theoretical models, and reduced training time. Sequential models, in...

Neural network models have quickly taken advantage of NVIDIA Tensor Cores for deep learning since their introduction in the Tesla V100 GPU last year. For...

Autonomous driving demands safety, and a high-performance computing solution to process sensor data with extreme accuracy. Researchers and developers creating...

[caption id="attachment_7875" align="alignright" width="200"] Tensor cores provide a huge boost to convolutions and matrix operations. Tensor cores are...

Deep Neural Networks (DNNs) have lead to breakthroughs in a number of areas, including image processing and understanding, language modeling, language...

Update, March 25, 2019: The latest Volta and Turing GPUs now incoporate Tensor Cores, which accelerate certain types of FP16 matrix math. This enables faster...