PDF) Performance evaluation of Unified Memory with prefetching and oversubscription for selected parallel CUDA applications on NVIDIA Pascal and Volta GPUs
NVIDIA GPU Architecture: from Pascal to Turing to Ampere - WOLF Advanced Technology
Institute for Advanced Computational Science - NVIDIA Workshops on Deep Learning, Pascal, CUDA and OpenACC
NVIDIA Tensor Core Programming - Lei Mao's Log Book
Pascal (microarchitecture) - Wikipedia
Nvidia TitanXP - Pascal - 3840 Cuda Cores - 12GB GDDR5X - 4K Gaming, Model Name/Number: 900-1G611-2530-